trevor/chat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

api schema check
All checks were successful
continuous-integration/drone/push Build is passing
Details

Browse Source
This commit is contained in:
Andrew K. Choi
2025-09-26 07:28:07 +09:00
parent e5aa933cf9
commit ed8eb75bac
96 changed files with 24213 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
services/api_gateway/main.py
View File

@@ -247,19 +247,55 @@ async def register_user(user_create: UserCreate, request: Request):
@app.post("/api/v1/auth/login", response_model=Token, tags=["Authentication"], summary="Login user") @app.post("/api/v1/auth/login", response_model=Token, tags=["Authentication"], summary="Login user")
async def login_user(user_login: UserLogin, request: Request): async def login_user(user_login: UserLogin, request: Request):
"""Login user""" """Login user"""
client_ip = get_client_ip(request)
print(f"Login request from {client_ip}: {user_login.model_dump(exclude={'password'})}")
async with httpx.AsyncClient(timeout=30.0) as client: async with httpx.AsyncClient(timeout=30.0) as client:
try: try:
login_data = user_login.model_dump()
print(f"Sending login data to user service: {login_data}")
response = await client.post( response = await client.post(
f"{SERVICES['users']}/api/v1/auth/login", f"{SERVICES['users']}/api/v1/auth/login",
json=user_login.model_dump(), json=login_data,
headers={ headers={
"Content-Type": "application/json", "Content-Type": "application/json",
"Accept": "application/json" "Accept": "application/json"
} }
) )
print(f"User service response: status={response.status_code}")
if response.status_code >= 400:
print(f"Error response body: {response.text}")
if response.status_code == 200: if response.status_code == 200:
return response.json() return response.json()
elif response.status_code == 422:
# Detailed handling for validation errors
try:
error_json = response.json()
print(f"Validation error details: {error_json}")
# Return more detailed validation errors
if "detail" in error_json:
detail = error_json["detail"]
if isinstance(detail, list):
# FastAPI validation errors
formatted_errors = []
for error in detail:
field = error.get("loc", ["unknown"])[-1]
msg = error.get("msg", "Invalid value")
formatted_errors.append(f"{field}: {msg}")
raise HTTPException(
status_code=422,
detail=f"Validation errors: {'; '.join(formatted_errors)}"
)
else:
raise HTTPException(status_code=422, detail=detail)
else:
raise HTTPException(status_code=422, detail="Invalid input data")
except ValueError as ve:
print(f"JSON parse error: {ve}")
raise HTTPException(status_code=422, detail="Invalid request format")
else: else:
error_detail = response.text error_detail = response.text
try: try:
@@ -272,6 +308,7 @@ async def login_user(user_login: UserLogin, request: Request):
except HTTPException: except HTTPException:
raise raise
except Exception as e: except Exception as e:
print(f"Login service error: {str(e)}")
raise HTTPException(status_code=500, detail=f"Login error: {str(e)}") raise HTTPException(status_code=500, detail=f"Login error: {str(e)}")

57
services/user_service/main.py
View File

@@ -134,36 +134,65 @@ async def register_user(user_data: UserCreate, db: AsyncSession = Depends(get_db
@app.post("/api/v1/auth/login", response_model=Token) @app.post("/api/v1/auth/login", response_model=Token)
async def login(user_credentials: UserLogin, db: AsyncSession = Depends(get_db)): async def login(user_credentials: UserLogin, db: AsyncSession = Depends(get_db)):
"""Authenticate user and return token""" """Authenticate user and return token"""
print(f"Login attempt: email={user_credentials.email}, username={user_credentials.username}")
# Проверка валидности входных данных
if not user_credentials.email and not user_credentials.username:
print("Error: Neither email nor username provided")
raise HTTPException(
status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
detail="Either email or username must be provided",
)
if not user_credentials.password:
print("Error: Password not provided")
raise HTTPException(
status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
detail="Password is required",
)
# Определяем, по какому полю ищем пользователя # Определяем, по какому полю ищем пользователя
user = None user = None
if user_credentials.email: try:
result = await db.execute(select(User).filter(User.email == user_credentials.email)) if user_credentials.email:
user = result.scalars().first() print(f"Looking up user by email: {user_credentials.email}")
elif user_credentials.username: result = await db.execute(select(User).filter(User.email == user_credentials.email))
result = await db.execute(select(User).filter(User.username == user_credentials.username)) user = result.scalars().first()
user = result.scalars().first() elif user_credentials.username:
else: print(f"Looking up user by username: {user_credentials.username}")
result = await db.execute(select(User).filter(User.username == user_credentials.username))
user = result.scalars().first()
except Exception as e:
print(f"Database error during user lookup: {str(e)}")
raise HTTPException( raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST, status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail="Either email or username must be provided", detail="Database error during authentication",
) )
# Проверяем наличие пользователя и правильность пароля # Проверяем наличие пользователя и правильность пароля
if not user: if not user:
print(f"User not found: email={user_credentials.email}, username={user_credentials.username}")
raise HTTPException( raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, status_code=status.HTTP_401_UNAUTHORIZED,
detail="Incorrect email or password", detail="Incorrect email or password",
) )
print(f"User found: id={user.id}, email={user.email}")
# Проверка пароля # Проверка пароля
try: try:
if not verify_password(user_credentials.password, str(user.password_hash)): password_valid = verify_password(user_credentials.password, str(user.password_hash))
print(f"Password verification result: {password_valid}")
if not password_valid:
raise HTTPException( raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, status_code=status.HTTP_401_UNAUTHORIZED,
detail="Incorrect email or password", detail="Incorrect email or password",
) )
except Exception: except HTTPException:
raise
except Exception as e:
# Если произошла ошибка при проверке пароля, то считаем, что пароль неверный # Если произошла ошибка при проверке пароля, то считаем, что пароль неверный
print(f"Password verification error: {str(e)}")
raise HTTPException( raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, status_code=status.HTTP_401_UNAUTHORIZED,
detail="Incorrect email or password", detail="Incorrect email or password",
@@ -172,21 +201,25 @@ async def login(user_credentials: UserLogin, db: AsyncSession = Depends(get_db))
# Проверка активности аккаунта # Проверка активности аккаунта
try: try:
is_active = bool(user.is_active) is_active = bool(user.is_active)
print(f"User active status: {is_active}")
if not is_active: if not is_active:
raise HTTPException( raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, status_code=status.HTTP_401_UNAUTHORIZED,
detail="Account is inactive", detail="Account is inactive",
) )
except Exception: except Exception as e:
# Если произошла ошибка при проверке активности, считаем аккаунт активным # Если произошла ошибка при проверке активности, считаем аккаунт активным
print(f"Error checking user active status: {str(e)}")
pass pass
print("Creating access token...")
access_token_expires = timedelta(minutes=settings.ACCESS_TOKEN_EXPIRE_MINUTES) access_token_expires = timedelta(minutes=settings.ACCESS_TOKEN_EXPIRE_MINUTES)
access_token = create_access_token( access_token = create_access_token(
data={"sub": str(user.id), "email": user.email}, data={"sub": str(user.id), "email": user.email},
expires_delta=access_token_expires, expires_delta=access_token_expires,
) )
print("Login successful")
return {"access_token": access_token, "token_type": "bearer"} return {"access_token": access_token, "token_type": "bearer"}

11
services/user_service/schemas.py
View File

@@ -108,11 +108,22 @@ class UserLogin(BaseModel):
@classmethod @classmethod
def validate_password_bytes(cls, v): def validate_password_bytes(cls, v):
"""Ensure password doesn't exceed bcrypt's 72-byte limit.""" """Ensure password doesn't exceed bcrypt's 72-byte limit."""
if not v or len(v.strip()) == 0:
raise ValueError("Password cannot be empty")
password_bytes = v.encode('utf-8') password_bytes = v.encode('utf-8')
if len(password_bytes) > 72: if len(password_bytes) > 72:
raise ValueError("Password is too long when encoded as UTF-8 (max 72 bytes for bcrypt)") raise ValueError("Password is too long when encoded as UTF-8 (max 72 bytes for bcrypt)")
return v return v
@field_validator("username")
@classmethod
def validate_login_fields(cls, v, info):
"""Ensure at least email or username is provided."""
email = info.data.get('email')
if not email and not v:
raise ValueError("Either email or username must be provided")
return v
class Token(BaseModel): class Token(BaseModel):
access_token: str access_token: str

118
test_auth_flow.py Normal file
View File

@@ -0,0 +1,118 @@
#!/usr/bin/env python3
import json
import requests
import time
def test_registration_and_login():
"""Test registration and login flow"""
base_url = "http://localhost:8000"
# Test user data
test_user = {
"email": "testuser@example.com",
"username": "testuser123",
"password": "SecurePass123",
"first_name": "Test",
"last_name": "User"
}
print("🔧 Creating test user")
print("=" * 50)
# Try to register the user
try:
headers = {
"Content-Type": "application/json",
"Accept": "application/json"
}
print(f"Registering user: {test_user['email']}")
registration_response = requests.post(
f"{base_url}/api/v1/auth/register",
json=test_user,
headers=headers,
timeout=10
)
print(f"Registration Status: {registration_response.status_code}")
print(f"Registration Response: {registration_response.text}")
if registration_response.status_code == 200:
print("✅ User registered successfully")
elif registration_response.status_code == 400:
if "already registered" in registration_response.text.lower():
print("ℹ️ User already exists, proceeding with login test")
else:
print(f"❌ Registration failed: {registration_response.text}")
return
else:
print(f"❌ Registration failed with status: {registration_response.status_code}")
return
time.sleep(1)
# Test login scenarios
login_tests = [
{
"name": "Login with email",
"data": {
"email": test_user["email"],
"password": test_user["password"]
}
},
{
"name": "Login with username",
"data": {
"username": test_user["username"],
"password": test_user["password"]
}
},
{
"name": "Login with wrong password",
"data": {
"email": test_user["email"],
"password": "wrongpassword"
}
}
]
for test in login_tests:
print(f"\n🧪 Testing: {test['name']}")
print("=" * 50)
try:
print(f"Login data: {json.dumps(test['data'], indent=2)}")
login_response = requests.post(
f"{base_url}/api/v1/auth/login",
json=test["data"],
headers=headers,
timeout=10
)
print(f"Login Status: {login_response.status_code}")
print(f"Login Response: {login_response.text}")
if login_response.status_code == 200:
try:
token_data = login_response.json()
print(f"✅ Login successful! Token type: {token_data.get('token_type')}")
print(f"Access token (first 20 chars): {token_data.get('access_token', '')[:20]}...")
except:
print("✅ Login successful but response parsing failed")
else:
print(f"❌ Login failed")
except Exception as e:
print(f"Login error: {str(e)}")
time.sleep(1)
except Exception as e:
print(f"Test error: {str(e)}")
if __name__ == "__main__":
print("🔍 Testing registration and login flow")
test_registration_and_login()

83
test_login.py Executable file
View File

@@ -0,0 +1,83 @@
#!/usr/bin/env python3
import json
import requests
import time
# Test login endpoint with detailed logging
def test_login():
"""Test login with various scenarios"""
base_url = "http://localhost:8000"
# Test cases
test_cases = [
{
"name": "Empty request",
"data": {}
},
{
"name": "Only password",
"data": {"password": "testpass123"}
},
{
"name": "Only email",
"data": {"email": "test@example.com"}
},
{
"name": "Valid email and password",
"data": {
"email": "test@example.com",
"password": "testpass123"
}
},
{
"name": "Valid username and password",
"data": {
"username": "testuser",
"password": "testpass123"
}
},
{
"name": "Invalid JSON format",
"data": "invalid json",
"content_type": "text/plain"
}
]
for test_case in test_cases:
print(f"\n🧪 Testing: {test_case['name']}")
print("=" * 50)
try:
headers = {
"Content-Type": test_case.get("content_type", "application/json"),
"Accept": "application/json"
}
if isinstance(test_case["data"], dict):
data = json.dumps(test_case["data"])
print(f"Request data: {data}")
else:
data = test_case["data"]
print(f"Request data (raw): {data}")
response = requests.post(
f"{base_url}/api/v1/auth/login",
data=data,
headers=headers,
timeout=10
)
print(f"Status Code: {response.status_code}")
print(f"Headers: {dict(response.headers)}")
print(f"Response: {response.text}")
except Exception as e:
print(f"Error: {str(e)}")
time.sleep(1) # Wait between requests
if __name__ == "__main__":
print("🔍 Testing login endpoint with detailed logging")
print("Make sure to check the server logs for debugging info")
test_login()

8
venv/bin/normalizer Executable file
View File

@@ -0,0 +1,8 @@
#!/home/trevor/dev/chat/venv/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from charset_normalizer.cli import cli_detect
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(cli_detect())

1
venv/lib/python3.12/site-packages/charset_normalizer-3.4.3.dist-info/INSTALLER Normal file
View File

@@ -0,0 +1 @@
pip

750
venv/lib/python3.12/site-packages/charset_normalizer-3.4.3.dist-info/METADATA Normal file
View File

@@ -0,0 +1,750 @@
Metadata-Version: 2.4
Name: charset-normalizer
Version: 3.4.3
Summary: The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet.
Author-email: "Ahmed R. TAHRI" <tahri.ahmed@proton.me>
Maintainer-email: "Ahmed R. TAHRI" <tahri.ahmed@proton.me>
License: MIT
Project-URL: Changelog, https://github.com/jawah/charset_normalizer/blob/master/CHANGELOG.md
Project-URL: Documentation, https://charset-normalizer.readthedocs.io/
Project-URL: Code, https://github.com/jawah/charset_normalizer
Project-URL: Issue tracker, https://github.com/jawah/charset_normalizer/issues
Keywords: encoding,charset,charset-detector,detector,normalization,unicode,chardet,detect
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Classifier: Topic :: Text Processing :: Linguistic
Classifier: Topic :: Utilities
Classifier: Typing :: Typed
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Provides-Extra: unicode-backport
Dynamic: license-file
<h1 align="center">Charset Detection, for Everyone 👋</h1>
<p align="center">
<sup>The Real First Universal Charset Detector</sup><br>
<a href="https://pypi.org/project/charset-normalizer">
<img src="https://img.shields.io/pypi/pyversions/charset_normalizer.svg?orange=blue" />
</a>
<a href="https://pepy.tech/project/charset-normalizer/">
<img alt="Download Count Total" src="https://static.pepy.tech/badge/charset-normalizer/month" />
</a>
<a href="https://bestpractices.coreinfrastructure.org/projects/7297">
<img src="https://bestpractices.coreinfrastructure.org/projects/7297/badge">
</a>
</p>
<p align="center">
<sup><i>Featured Packages</i></sup><br>
<a href="https://github.com/jawah/niquests">
<img alt="Static Badge" src="https://img.shields.io/badge/Niquests-Most_Advanced_HTTP_Client-cyan">
</a>
<a href="https://github.com/jawah/wassima">
<img alt="Static Badge" src="https://img.shields.io/badge/Wassima-Certifi_Replacement-cyan">
</a>
</p>
<p align="center">
<sup><i>In other language (unofficial port - by the community)</i></sup><br>
<a href="https://github.com/nickspring/charset-normalizer-rs">
<img alt="Static Badge" src="https://img.shields.io/badge/Rust-red">
</a>
</p>
> A library that helps you read text from an unknown charset encoding.<br /> Motivated by `chardet`,
> I'm trying to resolve the issue by taking a new approach.
> All IANA character set names for which the Python core library provides codecs are supported.
<p align="center">
>>>>> <a href="https://charsetnormalizerweb.ousret.now.sh" target="_blank">👉 Try Me Online Now, Then Adopt Me 👈 </a> <<<<<
</p>
This project offers you an alternative to **Universal Charset Encoding Detector**, also known as **Chardet**.
| Feature | [Chardet](https://github.com/chardet/chardet) | Charset Normalizer | [cChardet](https://github.com/PyYoshi/cChardet) |
|--------------------------------------------------|:---------------------------------------------:|:--------------------------------------------------------------------------------------------------:|:-----------------------------------------------:|
| `Fast` | ❌ | ✅ | ✅ |
| `Universal**` | ❌ | ✅ | ❌ |
| `Reliable` **without** distinguishable standards | ❌ | ✅ | ✅ |
| `Reliable` **with** distinguishable standards | ✅ | ✅ | ✅ |
| `License` | LGPL-2.1<br>_restrictive_ | MIT | MPL-1.1<br>_restrictive_ |
| `Native Python` | ✅ | ✅ | ❌ |
| `Detect spoken language` | ❌ | ✅ | N/A |
| `UnicodeDecodeError Safety` | ❌ | ✅ | ❌ |
| `Whl Size (min)` | 193.6 kB | 42 kB | ~200 kB |
| `Supported Encoding` | 33 | 🎉 [99](https://charset-normalizer.readthedocs.io/en/latest/user/support.html#supported-encodings) | 40 |
<p align="center">
<img src="https://i.imgflip.com/373iay.gif" alt="Reading Normalized Text" width="226"/><img src="https://media.tenor.com/images/c0180f70732a18b4965448d33adba3d0/tenor.gif" alt="Cat Reading Text" width="200"/>
</p>
*\*\* : They are clearly using specific code for a specific encoding even if covering most of used one*<br>
## ⚡ Performance
This package offer better performance than its counterpart Chardet. Here are some numbers.
| Package | Accuracy | Mean per file (ms) | File per sec (est) |
|-----------------------------------------------|:--------:|:------------------:|:------------------:|
| [chardet](https://github.com/chardet/chardet) | 86 % | 63 ms | 16 file/sec |
| charset-normalizer | **98 %** | **10 ms** | 100 file/sec |
| Package | 99th percentile | 95th percentile | 50th percentile |
|-----------------------------------------------|:---------------:|:---------------:|:---------------:|
| [chardet](https://github.com/chardet/chardet) | 265 ms | 71 ms | 7 ms |
| charset-normalizer | 100 ms | 50 ms | 5 ms |
_updated as of december 2024 using CPython 3.12_
Chardet's performance on larger file (1MB+) are very poor. Expect huge difference on large payload.
> Stats are generated using 400+ files using default parameters. More details on used files, see GHA workflows.
> And yes, these results might change at any time. The dataset can be updated to include more files.
> The actual delays heavily depends on your CPU capabilities. The factors should remain the same.
> Keep in mind that the stats are generous and that Chardet accuracy vs our is measured using Chardet initial capability
> (e.g. Supported Encoding) Challenge-them if you want.
## ✨ Installation
Using pip:
```sh
pip install charset-normalizer -U
```
## 🚀 Basic Usage
### CLI
This package comes with a CLI.
```
usage: normalizer [-h] [-v] [-a] [-n] [-m] [-r] [-f] [-t THRESHOLD]
file [file ...]
The Real First Universal Charset Detector. Discover originating encoding used
on text file. Normalize text to unicode.
positional arguments:
files File(s) to be analysed
optional arguments:
-h, --help show this help message and exit
-v, --verbose Display complementary information about file if any.
Stdout will contain logs about the detection process.
-a, --with-alternative
Output complementary possibilities if any. Top-level
JSON WILL be a list.
-n, --normalize Permit to normalize input file. If not set, program
does not write anything.
-m, --minimal Only output the charset detected to STDOUT. Disabling
JSON output.
-r, --replace Replace file when trying to normalize it instead of
creating a new one.
-f, --force Replace file without asking if you are sure, use this
flag with caution.
-t THRESHOLD, --threshold THRESHOLD
Define a custom maximum amount of chaos allowed in
decoded content. 0. <= chaos <= 1.
--version Show version information and exit.
```
```bash
normalizer ./data/sample.1.fr.srt
```
or
```bash
python -m charset_normalizer ./data/sample.1.fr.srt
```
🎉 Since version 1.4.0 the CLI produce easily usable stdout result in JSON format.
```json
{
"path": "/home/default/projects/charset_normalizer/data/sample.1.fr.srt",
"encoding": "cp1252",
"encoding_aliases": [
"1252",
"windows_1252"
],
"alternative_encodings": [
"cp1254",
"cp1256",
"cp1258",
"iso8859_14",
"iso8859_15",
"iso8859_16",
"iso8859_3",
"iso8859_9",
"latin_1",
"mbcs"
],
"language": "French",
"alphabets": [
"Basic Latin",
"Latin-1 Supplement"
],
"has_sig_or_bom": false,
"chaos": 0.149,
"coherence": 97.152,
"unicode_path": null,
"is_preferred": true
}
```
### Python
*Just print out normalized text*
```python
from charset_normalizer import from_path
results = from_path('./my_subtitle.srt')
print(str(results.best()))
```
*Upgrade your code without effort*
```python
from charset_normalizer import detect
```
The above code will behave the same as **chardet**. We ensure that we offer the best (reasonable) BC result possible.
See the docs for advanced usage : [readthedocs.io](https://charset-normalizer.readthedocs.io/en/latest/)
## 😇 Why
When I started using Chardet, I noticed that it was not suited to my expectations, and I wanted to propose a
reliable alternative using a completely different method. Also! I never back down on a good challenge!
I **don't care** about the **originating charset** encoding, because **two different tables** can
produce **two identical rendered string.**
What I want is to get readable text, the best I can.
In a way, **I'm brute forcing text decoding.** How cool is that ? 😎
Don't confuse package **ftfy** with charset-normalizer or chardet. ftfy goal is to repair Unicode string whereas charset-normalizer to convert raw file in unknown encoding to unicode.
## 🍰 How
- Discard all charset encoding table that could not fit the binary content.
- Measure noise, or the mess once opened (by chunks) with a corresponding charset encoding.
- Extract matches with the lowest mess detected.
- Additionally, we measure coherence / probe for a language.
**Wait a minute**, what is noise/mess and coherence according to **YOU ?**
*Noise :* I opened hundred of text files, **written by humans**, with the wrong encoding table. **I observed**, then
**I established** some ground rules about **what is obvious** when **it seems like** a mess (aka. defining noise in rendered text).
I know that my interpretation of what is noise is probably incomplete, feel free to contribute in order to
improve or rewrite it.
*Coherence :* For each language there is on earth, we have computed ranked letter appearance occurrences (the best we can). So I thought
that intel is worth something here. So I use those records against decoded text to check if I can detect intelligent design.
## ⚡ Known limitations
- Language detection is unreliable when text contains two or more languages sharing identical letters. (eg. HTML (english tags) + Turkish content (Sharing Latin characters))
- Every charset detector heavily depends on sufficient content. In common cases, do not bother run detection on very tiny content.
## ⚠️ About Python EOLs
**If you are running:**
- Python >=2.7,<3.5: Unsupported
- Python 3.5: charset-normalizer < 2.1
- Python 3.6: charset-normalizer < 3.1
- Python 3.7: charset-normalizer < 4.0
Upgrade your Python interpreter as soon as possible.
## 👤 Contributing
Contributions, issues and feature requests are very much welcome.<br />
Feel free to check [issues page](https://github.com/ousret/charset_normalizer/issues) if you want to contribute.
## 📝 License
Copyright © [Ahmed TAHRI @Ousret](https://github.com/Ousret).<br />
This project is [MIT](https://github.com/Ousret/charset_normalizer/blob/master/LICENSE) licensed.
Characters frequencies used in this project © 2012 [Denny Vrandečić](http://simia.net/letters/)
## 💼 For Enterprise
Professional support for charset-normalizer is available as part of the [Tidelift
Subscription][1]. Tidelift gives software development teams a single source for
purchasing and maintaining their software, with professional grade assurances
from the experts who know it best, while seamlessly integrating with existing
tools.
[1]: https://tidelift.com/subscription/pkg/pypi-charset-normalizer?utm_source=pypi-charset-normalizer&utm_medium=readme
[![OpenSSF Best Practices](https://www.bestpractices.dev/projects/7297/badge)](https://www.bestpractices.dev/projects/7297)
# Changelog
All notable changes to charset-normalizer will be documented in this file. This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
## [3.4.3](https://github.com/Ousret/charset_normalizer/compare/3.4.2...3.4.3) (2025-08-09)
### Changed
- mypy(c) is no longer a required dependency at build time if `CHARSET_NORMALIZER_USE_MYPYC` isn't set to `1`. (#595) (#583)
- automatically lower confidence on small bytes samples that are not Unicode in `detect` output legacy function. (#391)
### Added
- Custom build backend to overcome inability to mark mypy as an optional dependency in the build phase.
- Support for Python 3.14
### Fixed
- sdist archive contained useless directories.
- automatically fallback on valid UTF-16 or UTF-32 even if the md says it's noisy. (#633)
### Misc
- SBOM are automatically published to the relevant GitHub release to comply with regulatory changes.
Each published wheel comes with its SBOM. We choose CycloneDX as the format.
- Prebuilt optimized wheel are no longer distributed by default for CPython 3.7 due to a change in cibuildwheel.
## [3.4.2](https://github.com/Ousret/charset_normalizer/compare/3.4.1...3.4.2) (2025-05-02)
### Fixed
- Addressed the DeprecationWarning in our CLI regarding `argparse.FileType` by backporting the target class into the package. (#591)
- Improved the overall reliability of the detector with CJK Ideographs. (#605) (#587)
### Changed
- Optional mypyc compilation upgraded to version 1.15 for Python >= 3.8
## [3.4.1](https://github.com/Ousret/charset_normalizer/compare/3.4.0...3.4.1) (2024-12-24)
### Changed
- Project metadata are now stored using `pyproject.toml` instead of `setup.cfg` using setuptools as the build backend.
- Enforce annotation delayed loading for a simpler and consistent types in the project.
- Optional mypyc compilation upgraded to version 1.14 for Python >= 3.8
### Added
- pre-commit configuration.
- noxfile.
### Removed
- `build-requirements.txt` as per using `pyproject.toml` native build configuration.
- `bin/integration.py` and `bin/serve.py` in favor of downstream integration test (see noxfile).
- `setup.cfg` in favor of `pyproject.toml` metadata configuration.
- Unused `utils.range_scan` function.
### Fixed
- Converting content to Unicode bytes may insert `utf_8` instead of preferred `utf-8`. (#572)
- Deprecation warning "'count' is passed as positional argument" when converting to Unicode bytes on Python 3.13+
## [3.4.0](https://github.com/Ousret/charset_normalizer/compare/3.3.2...3.4.0) (2024-10-08)
### Added
- Argument `--no-preemptive` in the CLI to prevent the detector to search for hints.
- Support for Python 3.13 (#512)
### Fixed
- Relax the TypeError exception thrown when trying to compare a CharsetMatch with anything else than a CharsetMatch.
- Improved the general reliability of the detector based on user feedbacks. (#520) (#509) (#498) (#407) (#537)
- Declared charset in content (preemptive detection) not changed when converting to utf-8 bytes. (#381)
## [3.3.2](https://github.com/Ousret/charset_normalizer/compare/3.3.1...3.3.2) (2023-10-31)
### Fixed
- Unintentional memory usage regression when using large payload that match several encoding (#376)
- Regression on some detection case showcased in the documentation (#371)
### Added
- Noise (md) probe that identify malformed arabic representation due to the presence of letters in isolated form (credit to my wife)
## [3.3.1](https://github.com/Ousret/charset_normalizer/compare/3.3.0...3.3.1) (2023-10-22)
### Changed
- Optional mypyc compilation upgraded to version 1.6.1 for Python >= 3.8
- Improved the general detection reliability based on reports from the community
## [3.3.0](https://github.com/Ousret/charset_normalizer/compare/3.2.0...3.3.0) (2023-09-30)
### Added
- Allow to execute the CLI (e.g. normalizer) through `python -m charset_normalizer.cli` or `python -m charset_normalizer`
- Support for 9 forgotten encoding that are supported by Python but unlisted in `encoding.aliases` as they have no alias (#323)
### Removed
- (internal) Redundant utils.is_ascii function and unused function is_private_use_only
- (internal) charset_normalizer.assets is moved inside charset_normalizer.constant
### Changed
- (internal) Unicode code blocks in constants are updated using the latest v15.0.0 definition to improve detection
- Optional mypyc compilation upgraded to version 1.5.1 for Python >= 3.8
### Fixed
- Unable to properly sort CharsetMatch when both chaos/noise and coherence were close due to an unreachable condition in \_\_lt\_\_ (#350)
## [3.2.0](https://github.com/Ousret/charset_normalizer/compare/3.1.0...3.2.0) (2023-06-07)
### Changed
- Typehint for function `from_path` no longer enforce `PathLike` as its first argument
- Minor improvement over the global detection reliability
### Added
- Introduce function `is_binary` that relies on main capabilities, and optimized to detect binaries
- Propagate `enable_fallback` argument throughout `from_bytes`, `from_path`, and `from_fp` that allow a deeper control over the detection (default True)
- Explicit support for Python 3.12
### Fixed
- Edge case detection failure where a file would contain 'very-long' camel cased word (Issue #289)
## [3.1.0](https://github.com/Ousret/charset_normalizer/compare/3.0.1...3.1.0) (2023-03-06)
### Added
- Argument `should_rename_legacy` for legacy function `detect` and disregard any new arguments without errors (PR #262)
### Removed
- Support for Python 3.6 (PR #260)
### Changed
- Optional speedup provided by mypy/c 1.0.1
## [3.0.1](https://github.com/Ousret/charset_normalizer/compare/3.0.0...3.0.1) (2022-11-18)
### Fixed
- Multi-bytes cutter/chunk generator did not always cut correctly (PR #233)
### Changed
- Speedup provided by mypy/c 0.990 on Python >= 3.7
## [3.0.0](https://github.com/Ousret/charset_normalizer/compare/2.1.1...3.0.0) (2022-10-20)
### Added
- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
### Changed
- Build with static metadata using 'build' frontend
- Make the language detection stricter
- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
### Fixed
- CLI with opt --normalize fail when using full path for files
- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
- Sphinx warnings when generating the documentation
### Removed
- Coherence detector no longer return 'Simple English' instead return 'English'
- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
- Breaking: Method `first()` and `best()` from CharsetMatch
- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
- Breaking: Top-level function `normalize`
- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
- Support for the backport `unicodedata2`
## [3.0.0rc1](https://github.com/Ousret/charset_normalizer/compare/3.0.0b2...3.0.0rc1) (2022-10-18)
### Added
- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
### Changed
- Build with static metadata using 'build' frontend
- Make the language detection stricter
### Fixed
- CLI with opt --normalize fail when using full path for files
- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
### Removed
- Coherence detector no longer return 'Simple English' instead return 'English'
- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
## [3.0.0b2](https://github.com/Ousret/charset_normalizer/compare/3.0.0b1...3.0.0b2) (2022-08-21)
### Added
- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
### Removed
- Breaking: Method `first()` and `best()` from CharsetMatch
- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
### Fixed
- Sphinx warnings when generating the documentation
## [3.0.0b1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...3.0.0b1) (2022-08-15)
### Changed
- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
### Removed
- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
- Breaking: Top-level function `normalize`
- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
- Support for the backport `unicodedata2`
## [2.1.1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...2.1.1) (2022-08-19)
### Deprecated
- Function `normalize` scheduled for removal in 3.0
### Changed
- Removed useless call to decode in fn is_unprintable (#206)
### Fixed
- Third-party library (i18n xgettext) crashing not recognizing utf_8 (PEP 263) with underscore from [@aleksandernovikov](https://github.com/aleksandernovikov) (#204)
## [2.1.0](https://github.com/Ousret/charset_normalizer/compare/2.0.12...2.1.0) (2022-06-19)
### Added
- Output the Unicode table version when running the CLI with `--version` (PR #194)
### Changed
- Re-use decoded buffer for single byte character sets from [@nijel](https://github.com/nijel) (PR #175)
- Fixing some performance bottlenecks from [@deedy5](https://github.com/deedy5) (PR #183)
### Fixed
- Workaround potential bug in cpython with Zero Width No-Break Space located in Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space (PR #175)
- CLI default threshold aligned with the API threshold from [@oleksandr-kuzmenko](https://github.com/oleksandr-kuzmenko) (PR #181)
### Removed
- Support for Python 3.5 (PR #192)
### Deprecated
- Use of backport unicodedata from `unicodedata2` as Python is quickly catching up, scheduled for removal in 3.0 (PR #194)
## [2.0.12](https://github.com/Ousret/charset_normalizer/compare/2.0.11...2.0.12) (2022-02-12)
### Fixed
- ASCII miss-detection on rare cases (PR #170)
## [2.0.11](https://github.com/Ousret/charset_normalizer/compare/2.0.10...2.0.11) (2022-01-30)
### Added
- Explicit support for Python 3.11 (PR #164)
### Changed
- The logging behavior have been completely reviewed, now using only TRACE and DEBUG levels (PR #163 #165)
## [2.0.10](https://github.com/Ousret/charset_normalizer/compare/2.0.9...2.0.10) (2022-01-04)
### Fixed
- Fallback match entries might lead to UnicodeDecodeError for large bytes sequence (PR #154)
### Changed
- Skipping the language-detection (CD) on ASCII (PR #155)
## [2.0.9](https://github.com/Ousret/charset_normalizer/compare/2.0.8...2.0.9) (2021-12-03)
### Changed
- Moderating the logging impact (since 2.0.8) for specific environments (PR #147)
### Fixed
- Wrong logging level applied when setting kwarg `explain` to True (PR #146)
## [2.0.8](https://github.com/Ousret/charset_normalizer/compare/2.0.7...2.0.8) (2021-11-24)
### Changed
- Improvement over Vietnamese detection (PR #126)
- MD improvement on trailing data and long foreign (non-pure latin) data (PR #124)
- Efficiency improvements in cd/alphabet_languages from [@adbar](https://github.com/adbar) (PR #122)
- call sum() without an intermediary list following PEP 289 recommendations from [@adbar](https://github.com/adbar) (PR #129)
- Code style as refactored by Sourcery-AI (PR #131)
- Minor adjustment on the MD around european words (PR #133)
- Remove and replace SRTs from assets / tests (PR #139)
- Initialize the library logger with a `NullHandler` by default from [@nmaynes](https://github.com/nmaynes) (PR #135)
- Setting kwarg `explain` to True will add provisionally (bounded to function lifespan) a specific stream handler (PR #135)
### Fixed
- Fix large (misleading) sequence giving UnicodeDecodeError (PR #137)
- Avoid using too insignificant chunk (PR #137)
### Added
- Add and expose function `set_logging_handler` to configure a specific StreamHandler from [@nmaynes](https://github.com/nmaynes) (PR #135)
- Add `CHANGELOG.md` entries, format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) (PR #141)
## [2.0.7](https://github.com/Ousret/charset_normalizer/compare/2.0.6...2.0.7) (2021-10-11)
### Added
- Add support for Kazakh (Cyrillic) language detection (PR #109)
### Changed
- Further, improve inferring the language from a given single-byte code page (PR #112)
- Vainly trying to leverage PEP263 when PEP3120 is not supported (PR #116)
- Refactoring for potential performance improvements in loops from [@adbar](https://github.com/adbar) (PR #113)
- Various detection improvement (MD+CD) (PR #117)
### Removed
- Remove redundant logging entry about detected language(s) (PR #115)
### Fixed
- Fix a minor inconsistency between Python 3.5 and other versions regarding language detection (PR #117 #102)
## [2.0.6](https://github.com/Ousret/charset_normalizer/compare/2.0.5...2.0.6) (2021-09-18)
### Fixed
- Unforeseen regression with the loss of the backward-compatibility with some older minor of Python 3.5.x (PR #100)
- Fix CLI crash when using --minimal output in certain cases (PR #103)
### Changed
- Minor improvement to the detection efficiency (less than 1%) (PR #106 #101)
## [2.0.5](https://github.com/Ousret/charset_normalizer/compare/2.0.4...2.0.5) (2021-09-14)
### Changed
- The project now comply with: flake8, mypy, isort and black to ensure a better overall quality (PR #81)
- The BC-support with v1.x was improved, the old staticmethods are restored (PR #82)
- The Unicode detection is slightly improved (PR #93)
- Add syntax sugar \_\_bool\_\_ for results CharsetMatches list-container (PR #91)
### Removed
- The project no longer raise warning on tiny content given for detection, will be simply logged as warning instead (PR #92)
### Fixed
- In some rare case, the chunks extractor could cut in the middle of a multi-byte character and could mislead the mess detection (PR #95)
- Some rare 'space' characters could trip up the UnprintablePlugin/Mess detection (PR #96)
- The MANIFEST.in was not exhaustive (PR #78)
## [2.0.4](https://github.com/Ousret/charset_normalizer/compare/2.0.3...2.0.4) (2021-07-30)
### Fixed
- The CLI no longer raise an unexpected exception when no encoding has been found (PR #70)
- Fix accessing the 'alphabets' property when the payload contains surrogate characters (PR #68)
- The logger could mislead (explain=True) on detected languages and the impact of one MBCS match (PR #72)
- Submatch factoring could be wrong in rare edge cases (PR #72)
- Multiple files given to the CLI were ignored when publishing results to STDOUT. (After the first path) (PR #72)
- Fix line endings from CRLF to LF for certain project files (PR #67)
### Changed
- Adjust the MD to lower the sensitivity, thus improving the global detection reliability (PR #69 #76)
- Allow fallback on specified encoding if any (PR #71)
## [2.0.3](https://github.com/Ousret/charset_normalizer/compare/2.0.2...2.0.3) (2021-07-16)
### Changed
- Part of the detection mechanism has been improved to be less sensitive, resulting in more accurate detection results. Especially ASCII. (PR #63)
- According to the community wishes, the detection will fall back on ASCII or UTF-8 in a last-resort case. (PR #64)
## [2.0.2](https://github.com/Ousret/charset_normalizer/compare/2.0.1...2.0.2) (2021-07-15)
### Fixed
- Empty/Too small JSON payload miss-detection fixed. Report from [@tseaver](https://github.com/tseaver) (PR #59)
### Changed
- Don't inject unicodedata2 into sys.modules from [@akx](https://github.com/akx) (PR #57)
## [2.0.1](https://github.com/Ousret/charset_normalizer/compare/2.0.0...2.0.1) (2021-07-13)
### Fixed
- Make it work where there isn't a filesystem available, dropping assets frequencies.json. Report from [@sethmlarson](https://github.com/sethmlarson). (PR #55)
- Using explain=False permanently disable the verbose output in the current runtime (PR #47)
- One log entry (language target preemptive) was not show in logs when using explain=True (PR #47)
- Fix undesired exception (ValueError) on getitem of instance CharsetMatches (PR #52)
### Changed
- Public function normalize default args values were not aligned with from_bytes (PR #53)
### Added
- You may now use charset aliases in cp_isolation and cp_exclusion arguments (PR #47)
## [2.0.0](https://github.com/Ousret/charset_normalizer/compare/1.4.1...2.0.0) (2021-07-02)
### Changed
- 4x to 5 times faster than the previous 1.4.0 release. At least 2x faster than Chardet.
- Accent has been made on UTF-8 detection, should perform rather instantaneous.
- The backward compatibility with Chardet has been greatly improved. The legacy detect function returns an identical charset name whenever possible.
- The detection mechanism has been slightly improved, now Turkish content is detected correctly (most of the time)
- The program has been rewritten to ease the readability and maintainability. (+Using static typing)+
- utf_7 detection has been reinstated.
### Removed
- This package no longer require anything when used with Python 3.5 (Dropped cached_property)
- Removed support for these languages: Catalan, Esperanto, Kazakh, Baque, Volapük, Azeri, Galician, Nynorsk, Macedonian, and Serbocroatian.
- The exception hook on UnicodeDecodeError has been removed.
### Deprecated
- Methods coherence_non_latin, w_counter, chaos_secondary_pass of the class CharsetMatch are now deprecated and scheduled for removal in v3.0
### Fixed
- The CLI output used the relative path of the file(s). Should be absolute.
## [1.4.1](https://github.com/Ousret/charset_normalizer/compare/1.4.0...1.4.1) (2021-05-28)
### Fixed
- Logger configuration/usage no longer conflict with others (PR #44)
## [1.4.0](https://github.com/Ousret/charset_normalizer/compare/1.3.9...1.4.0) (2021-05-21)
### Removed
- Using standard logging instead of using the package loguru.
- Dropping nose test framework in favor of the maintained pytest.
- Choose to not use dragonmapper package to help with gibberish Chinese/CJK text.
- Require cached_property only for Python 3.5 due to constraint. Dropping for every other interpreter version.
- Stop support for UTF-7 that does not contain a SIG.
- Dropping PrettyTable, replaced with pure JSON output in CLI.
### Fixed
- BOM marker in a CharsetNormalizerMatch instance could be False in rare cases even if obviously present. Due to the sub-match factoring process.
- Not searching properly for the BOM when trying utf32/16 parent codec.
### Changed
- Improving the package final size by compressing frequencies.json.
- Huge improvement over the larges payload.
### Added
- CLI now produces JSON consumable output.
- Return ASCII if given sequences fit. Given reasonable confidence.
## [1.3.9](https://github.com/Ousret/charset_normalizer/compare/1.3.8...1.3.9) (2021-05-13)
### Fixed
- In some very rare cases, you may end up getting encode/decode errors due to a bad bytes payload (PR #40)
## [1.3.8](https://github.com/Ousret/charset_normalizer/compare/1.3.7...1.3.8) (2021-05-12)
### Fixed
- Empty given payload for detection may cause an exception if trying to access the `alphabets` property. (PR #39)
## [1.3.7](https://github.com/Ousret/charset_normalizer/compare/1.3.6...1.3.7) (2021-05-12)
### Fixed
- The legacy detect function should return UTF-8-SIG if sig is present in the payload. (PR #38)
## [1.3.6](https://github.com/Ousret/charset_normalizer/compare/1.3.5...1.3.6) (2021-02-09)
### Changed
- Amend the previous release to allow prettytable 2.0 (PR #35)
## [1.3.5](https://github.com/Ousret/charset_normalizer/compare/1.3.4...1.3.5) (2021-02-08)
### Fixed
- Fix error while using the package with a python pre-release interpreter (PR #33)
### Changed
- Dependencies refactoring, constraints revised.
### Added
- Add python 3.9 and 3.10 to the supported interpreters
MIT License
Copyright (c) 2025 TAHRI Ahmed R.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

35
venv/lib/python3.12/site-packages/charset_normalizer-3.4.3.dist-info/RECORD Normal file
View File

@@ -0,0 +1,35 @@
../../../bin/normalizer,sha256=ezCIXGT5rnoJrfVhJ8DjH9QciCCjdjmtIH6AACYQ5d4,254
charset_normalizer-3.4.3.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
charset_normalizer-3.4.3.dist-info/METADATA,sha256=nBNOskPUtcqHtaSPPaJafjXrlicPcPIgLFzpJQTgvaA,36700
charset_normalizer-3.4.3.dist-info/RECORD,,
charset_normalizer-3.4.3.dist-info/WHEEL,sha256=DxRnWQz-Kp9-4a4hdDHsSv0KUC3H7sN9Nbef3-8RjXU,190
charset_normalizer-3.4.3.dist-info/entry_points.txt,sha256=ADSTKrkXZ3hhdOVFi6DcUEHQRS0xfxDIE_pEz4wLIXA,65
charset_normalizer-3.4.3.dist-info/licenses/LICENSE,sha256=bQ1Bv-FwrGx9wkjJpj4lTQ-0WmDVCoJX0K-SxuJJuIc,1071
charset_normalizer-3.4.3.dist-info/top_level.txt,sha256=7ASyzePr8_xuZWJsnqJjIBtyV8vhEo0wBCv1MPRRi3Q,19
charset_normalizer/__init__.py,sha256=OKRxRv2Zhnqk00tqkN0c1BtJjm165fWXLydE52IKuHc,1590
charset_normalizer/__main__.py,sha256=yzYxMR-IhKRHYwcSlavEv8oGdwxsR89mr2X09qXGdps,109
charset_normalizer/__pycache__/__init__.cpython-312.pyc,,
charset_normalizer/__pycache__/__main__.cpython-312.pyc,,
charset_normalizer/__pycache__/api.cpython-312.pyc,,
charset_normalizer/__pycache__/cd.cpython-312.pyc,,
charset_normalizer/__pycache__/constant.cpython-312.pyc,,
charset_normalizer/__pycache__/legacy.cpython-312.pyc,,
charset_normalizer/__pycache__/md.cpython-312.pyc,,
charset_normalizer/__pycache__/models.cpython-312.pyc,,
charset_normalizer/__pycache__/utils.cpython-312.pyc,,
charset_normalizer/__pycache__/version.cpython-312.pyc,,
charset_normalizer/api.py,sha256=V07i8aVeCD8T2fSia3C-fn0i9t8qQguEBhsqszg32Ns,22668
charset_normalizer/cd.py,sha256=WKTo1HDb-H9HfCDc3Bfwq5jzS25Ziy9SE2a74SgTq88,12522
charset_normalizer/cli/__init__.py,sha256=D8I86lFk2-py45JvqxniTirSj_sFyE6sjaY_0-G1shc,136
charset_normalizer/cli/__main__.py,sha256=dMaXG6IJXRvqq8z2tig7Qb83-BpWTln55ooiku5_uvg,12646
charset_normalizer/cli/__pycache__/__init__.cpython-312.pyc,,
charset_normalizer/cli/__pycache__/__main__.cpython-312.pyc,,
charset_normalizer/constant.py,sha256=7UVY4ldYhmQMHUdgQ_sgZmzcQ0xxYxpBunqSZ-XJZ8U,42713
charset_normalizer/legacy.py,sha256=sYBzSpzsRrg_wF4LP536pG64BItw7Tqtc3SMQAHvFLM,2731
charset_normalizer/md.cpython-312-x86_64-linux-gnu.so,sha256=sZ7umtJLjKfA83NFJ7npkiDyr06zDT8cWtl6uIx2MsM,15912
charset_normalizer/md.py,sha256=-_oN3h3_X99nkFfqamD3yu45DC_wfk5odH0Tr_CQiXs,20145
charset_normalizer/md__mypyc.cpython-312-x86_64-linux-gnu.so,sha256=froFxeWX3QD-u-6lU-1gyOZmEo6pgm3i-HdUWz2J8ro,289536
charset_normalizer/models.py,sha256=lKXhOnIPtiakbK3i__J9wpOfzx3JDTKj7Dn3Rg0VaRI,12394
charset_normalizer/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
charset_normalizer/utils.py,sha256=sTejPgrdlNsKNucZfJCxJ95lMTLA0ShHLLE3n5wpT9Q,12170
charset_normalizer/version.py,sha256=hBN3id1io4HMVPtyDn9IIRVShbBM0kgVs3haVtppZOE,115

7
venv/lib/python3.12/site-packages/charset_normalizer-3.4.3.dist-info/WHEEL Normal file
View File

@@ -0,0 +1,7 @@
Wheel-Version: 1.0
Generator: setuptools (80.9.0)
Root-Is-Purelib: false
Tag: cp312-cp312-manylinux_2_17_x86_64
Tag: cp312-cp312-manylinux2014_x86_64
Tag: cp312-cp312-manylinux_2_28_x86_64

2
venv/lib/python3.12/site-packages/charset_normalizer-3.4.3.dist-info/entry_points.txt Normal file
View File

@@ -0,0 +1,2 @@
[console_scripts]
normalizer = charset_normalizer.cli:cli_detect

21
venv/lib/python3.12/site-packages/charset_normalizer-3.4.3.dist-info/licenses/LICENSE Normal file
View File

@@ -0,0 +1,21 @@
MIT License
Copyright (c) 2025 TAHRI Ahmed R.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

1
venv/lib/python3.12/site-packages/charset_normalizer-3.4.3.dist-info/top_level.txt Normal file
View File

@@ -0,0 +1 @@
charset_normalizer

48
venv/lib/python3.12/site-packages/charset_normalizer/__init__.py Normal file
View File

@@ -0,0 +1,48 @@
"""
Charset-Normalizer
~~~~~~~~~~~~~~
The Real First Universal Charset Detector.
A library that helps you read text from an unknown charset encoding.
Motivated by chardet, This package is trying to resolve the issue by taking a new approach.
All IANA character set names for which the Python core library provides codecs are supported.
Basic usage:
>>> from charset_normalizer import from_bytes
>>> results = from_bytes('Bсеки човек има право на образование. Oбразованието!'.encode('utf_8'))
>>> best_guess = results.best()
>>> str(best_guess)
'Bсеки човек има право на образование. Oбразованието!'
Others methods and usages are available - see the full documentation
at <https://github.com/Ousret/charset_normalizer>.
:copyright: (c) 2021 by Ahmed TAHRI
:license: MIT, see LICENSE for more details.
"""
from __future__ import annotations
import logging
from .api import from_bytes, from_fp, from_path, is_binary
from .legacy import detect
from .models import CharsetMatch, CharsetMatches
from .utils import set_logging_handler
from .version import VERSION, __version__
__all__ = (
"from_fp",
"from_path",
"from_bytes",
"is_binary",
"detect",
"CharsetMatch",
"CharsetMatches",
"__version__",
"VERSION",
"set_logging_handler",
)
# Attach a NullHandler to the top level logger by default
# https://docs.python.org/3.3/howto/logging.html#configuring-logging-for-a-library
logging.getLogger("charset_normalizer").addHandler(logging.NullHandler())

6
venv/lib/python3.12/site-packages/charset_normalizer/__main__.py Normal file
View File

@@ -0,0 +1,6 @@
from __future__ import annotations
from .cli import cli_detect
if __name__ == "__main__":
cli_detect()

669
venv/lib/python3.12/site-packages/charset_normalizer/api.py Normal file
View File

@@ -0,0 +1,669 @@
from __future__ import annotations
import logging
from os import PathLike
from typing import BinaryIO
from .cd import (
coherence_ratio,
encoding_languages,
mb_encoding_languages,
merge_coherence_ratios,
)
from .constant import IANA_SUPPORTED, TOO_BIG_SEQUENCE, TOO_SMALL_SEQUENCE, TRACE
from .md import mess_ratio
from .models import CharsetMatch, CharsetMatches
from .utils import (
any_specified_encoding,
cut_sequence_chunks,
iana_name,
identify_sig_or_bom,
is_cp_similar,
is_multi_byte_encoding,
should_strip_sig_or_bom,
)
logger = logging.getLogger("charset_normalizer")
explain_handler = logging.StreamHandler()
explain_handler.setFormatter(
logging.Formatter("%(asctime)s | %(levelname)s | %(message)s")
)
def from_bytes(
sequences: bytes | bytearray,
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.2,
cp_isolation: list[str] | None = None,
cp_exclusion: list[str] | None = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = True,
) -> CharsetMatches:
"""
Given a raw bytes sequence, return the best possibles charset usable to render str objects.
If there is no results, it is a strong indicator that the source is binary/not text.
By default, the process will extract 5 blocks of 512o each to assess the mess and coherence of a given sequence.
And will give up a particular code page after 20% of measured mess. Those criteria are customizable at will.
The preemptive behavior DOES NOT replace the traditional detection workflow, it prioritize a particular code page
but never take it for granted. Can improve the performance.
You may want to focus your attention to some code page or/and not others, use cp_isolation and cp_exclusion for that
purpose.
This function will strip the SIG in the payload/sequence every time except on UTF-16, UTF-32.
By default the library does not setup any handler other than the NullHandler, if you choose to set the 'explain'
toggle to True it will alter the logger configuration to add a StreamHandler that is suitable for debugging.
Custom logging format and handler can be set manually.
"""
if not isinstance(sequences, (bytearray, bytes)):
raise TypeError(
"Expected object of type bytes or bytearray, got: {}".format(
type(sequences)
)
)
if explain:
previous_logger_level: int = logger.level
logger.addHandler(explain_handler)
logger.setLevel(TRACE)
length: int = len(sequences)
if length == 0:
logger.debug("Encoding detection on empty bytes, assuming utf_8 intention.")
if explain: # Defensive: ensure exit path clean handler
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level or logging.WARNING)
return CharsetMatches([CharsetMatch(sequences, "utf_8", 0.0, False, [], "")])
if cp_isolation is not None:
logger.log(
TRACE,
"cp_isolation is set. use this flag for debugging purpose. "
"limited list of encoding allowed : %s.",
", ".join(cp_isolation),
)
cp_isolation = [iana_name(cp, False) for cp in cp_isolation]
else:
cp_isolation = []
if cp_exclusion is not None:
logger.log(
TRACE,
"cp_exclusion is set. use this flag for debugging purpose. "
"limited list of encoding excluded : %s.",
", ".join(cp_exclusion),
)
cp_exclusion = [iana_name(cp, False) for cp in cp_exclusion]
else:
cp_exclusion = []
if length <= (chunk_size * steps):
logger.log(
TRACE,
"override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.",
steps,
chunk_size,
length,
)
steps = 1
chunk_size = length
if steps > 1 and length / steps < chunk_size:
chunk_size = int(length / steps)
is_too_small_sequence: bool = len(sequences) < TOO_SMALL_SEQUENCE
is_too_large_sequence: bool = len(sequences) >= TOO_BIG_SEQUENCE
if is_too_small_sequence:
logger.log(
TRACE,
"Trying to detect encoding from a tiny portion of ({}) byte(s).".format(
length
),
)
elif is_too_large_sequence:
logger.log(
TRACE,
"Using lazy str decoding because the payload is quite large, ({}) byte(s).".format(
length
),
)
prioritized_encodings: list[str] = []
specified_encoding: str | None = (
any_specified_encoding(sequences) if preemptive_behaviour else None
)
if specified_encoding is not None:
prioritized_encodings.append(specified_encoding)
logger.log(
TRACE,
"Detected declarative mark in sequence. Priority +1 given for %s.",
specified_encoding,
)
tested: set[str] = set()
tested_but_hard_failure: list[str] = []
tested_but_soft_failure: list[str] = []
fallback_ascii: CharsetMatch | None = None
fallback_u8: CharsetMatch | None = None
fallback_specified: CharsetMatch | None = None
results: CharsetMatches = CharsetMatches()
early_stop_results: CharsetMatches = CharsetMatches()
sig_encoding, sig_payload = identify_sig_or_bom(sequences)
if sig_encoding is not None:
prioritized_encodings.append(sig_encoding)
logger.log(
TRACE,
"Detected a SIG or BOM mark on first %i byte(s). Priority +1 given for %s.",
len(sig_payload),
sig_encoding,
)
prioritized_encodings.append("ascii")
if "utf_8" not in prioritized_encodings:
prioritized_encodings.append("utf_8")
for encoding_iana in prioritized_encodings + IANA_SUPPORTED:
if cp_isolation and encoding_iana not in cp_isolation:
continue
if cp_exclusion and encoding_iana in cp_exclusion:
continue
if encoding_iana in tested:
continue
tested.add(encoding_iana)
decoded_payload: str | None = None
bom_or_sig_available: bool = sig_encoding == encoding_iana
strip_sig_or_bom: bool = bom_or_sig_available and should_strip_sig_or_bom(
encoding_iana
)
if encoding_iana in {"utf_16", "utf_32"} and not bom_or_sig_available:
logger.log(
TRACE,
"Encoding %s won't be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.",
encoding_iana,
)
continue
if encoding_iana in {"utf_7"} and not bom_or_sig_available:
logger.log(
TRACE,
"Encoding %s won't be tested as-is because detection is unreliable without BOM/SIG.",
encoding_iana,
)
continue
try:
is_multi_byte_decoder: bool = is_multi_byte_encoding(encoding_iana)
except (ModuleNotFoundError, ImportError):
logger.log(
TRACE,
"Encoding %s does not provide an IncrementalDecoder",
encoding_iana,
)
continue
try:
if is_too_large_sequence and is_multi_byte_decoder is False:
str(
(
sequences[: int(50e4)]
if strip_sig_or_bom is False
else sequences[len(sig_payload) : int(50e4)]
),
encoding=encoding_iana,
)
else:
decoded_payload = str(
(
sequences
if strip_sig_or_bom is False
else sequences[len(sig_payload) :]
),
encoding=encoding_iana,
)
except (UnicodeDecodeError, LookupError) as e:
if not isinstance(e, LookupError):
logger.log(
TRACE,
"Code page %s does not fit given bytes sequence at ALL. %s",
encoding_iana,
str(e),
)
tested_but_hard_failure.append(encoding_iana)
continue
similar_soft_failure_test: bool = False
for encoding_soft_failed in tested_but_soft_failure:
if is_cp_similar(encoding_iana, encoding_soft_failed):
similar_soft_failure_test = True
break
if similar_soft_failure_test:
logger.log(
TRACE,
"%s is deemed too similar to code page %s and was consider unsuited already. Continuing!",
encoding_iana,
encoding_soft_failed,
)
continue
r_ = range(
0 if not bom_or_sig_available else len(sig_payload),
length,
int(length / steps),
)
multi_byte_bonus: bool = (
is_multi_byte_decoder
and decoded_payload is not None
and len(decoded_payload) < length
)
if multi_byte_bonus:
logger.log(
TRACE,
"Code page %s is a multi byte encoding table and it appear that at least one character "
"was encoded using n-bytes.",
encoding_iana,
)
max_chunk_gave_up: int = int(len(r_) / 4)
max_chunk_gave_up = max(max_chunk_gave_up, 2)
early_stop_count: int = 0
lazy_str_hard_failure = False
md_chunks: list[str] = []
md_ratios = []
try:
for chunk in cut_sequence_chunks(
sequences,
encoding_iana,
r_,
chunk_size,
bom_or_sig_available,
strip_sig_or_bom,
sig_payload,
is_multi_byte_decoder,
decoded_payload,
):
md_chunks.append(chunk)
md_ratios.append(
mess_ratio(
chunk,
threshold,
explain is True and 1 <= len(cp_isolation) <= 2,
)
)
if md_ratios[-1] >= threshold:
early_stop_count += 1
if (early_stop_count >= max_chunk_gave_up) or (
bom_or_sig_available and strip_sig_or_bom is False
):
break
except (
UnicodeDecodeError
) as e: # Lazy str loading may have missed something there
logger.log(
TRACE,
"LazyStr Loading: After MD chunk decode, code page %s does not fit given bytes sequence at ALL. %s",
encoding_iana,
str(e),
)
early_stop_count = max_chunk_gave_up
lazy_str_hard_failure = True
# We might want to check the sequence again with the whole content
# Only if initial MD tests passes
if (
not lazy_str_hard_failure
and is_too_large_sequence
and not is_multi_byte_decoder
):
try:
sequences[int(50e3) :].decode(encoding_iana, errors="strict")
except UnicodeDecodeError as e:
logger.log(
TRACE,
"LazyStr Loading: After final lookup, code page %s does not fit given bytes sequence at ALL. %s",
encoding_iana,
str(e),
)
tested_but_hard_failure.append(encoding_iana)
continue
mean_mess_ratio: float = sum(md_ratios) / len(md_ratios) if md_ratios else 0.0
if mean_mess_ratio >= threshold or early_stop_count >= max_chunk_gave_up:
tested_but_soft_failure.append(encoding_iana)
logger.log(
TRACE,
"%s was excluded because of initial chaos probing. Gave up %i time(s). "
"Computed mean chaos is %f %%.",
encoding_iana,
early_stop_count,
round(mean_mess_ratio * 100, ndigits=3),
)
# Preparing those fallbacks in case we got nothing.
if (
enable_fallback
and encoding_iana
in ["ascii", "utf_8", specified_encoding, "utf_16", "utf_32"]
and not lazy_str_hard_failure
):
fallback_entry = CharsetMatch(
sequences,
encoding_iana,
threshold,
bom_or_sig_available,
[],
decoded_payload,
preemptive_declaration=specified_encoding,
)
if encoding_iana == specified_encoding:
fallback_specified = fallback_entry
elif encoding_iana == "ascii":
fallback_ascii = fallback_entry
else:
fallback_u8 = fallback_entry
continue
logger.log(
TRACE,
"%s passed initial chaos probing. Mean measured chaos is %f %%",
encoding_iana,
round(mean_mess_ratio * 100, ndigits=3),
)
if not is_multi_byte_decoder:
target_languages: list[str] = encoding_languages(encoding_iana)
else:
target_languages = mb_encoding_languages(encoding_iana)
if target_languages:
logger.log(
TRACE,
"{} should target any language(s) of {}".format(
encoding_iana, str(target_languages)
),
)
cd_ratios = []
# We shall skip the CD when its about ASCII
# Most of the time its not relevant to run "language-detection" on it.
if encoding_iana != "ascii":
for chunk in md_chunks:
chunk_languages = coherence_ratio(
chunk,
language_threshold,
",".join(target_languages) if target_languages else None,
)
cd_ratios.append(chunk_languages)
cd_ratios_merged = merge_coherence_ratios(cd_ratios)
if cd_ratios_merged:
logger.log(
TRACE,
"We detected language {} using {}".format(
cd_ratios_merged, encoding_iana
),
)
current_match = CharsetMatch(
sequences,
encoding_iana,
mean_mess_ratio,
bom_or_sig_available,
cd_ratios_merged,
(
decoded_payload
if (
is_too_large_sequence is False
or encoding_iana in [specified_encoding, "ascii", "utf_8"]
)
else None
),
preemptive_declaration=specified_encoding,
)
results.append(current_match)
if (
encoding_iana in [specified_encoding, "ascii", "utf_8"]
and mean_mess_ratio < 0.1
):
# If md says nothing to worry about, then... stop immediately!
if mean_mess_ratio == 0.0:
logger.debug(
"Encoding detection: %s is most likely the one.",
current_match.encoding,
)
if explain: # Defensive: ensure exit path clean handler
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([current_match])
early_stop_results.append(current_match)
if (
len(early_stop_results)
and (specified_encoding is None or specified_encoding in tested)
and "ascii" in tested
and "utf_8" in tested
):
probable_result: CharsetMatch = early_stop_results.best() # type: ignore[assignment]
logger.debug(
"Encoding detection: %s is most likely the one.",
probable_result.encoding,
)
if explain: # Defensive: ensure exit path clean handler
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([probable_result])
if encoding_iana == sig_encoding:
logger.debug(
"Encoding detection: %s is most likely the one as we detected a BOM or SIG within "
"the beginning of the sequence.",
encoding_iana,
)
if explain: # Defensive: ensure exit path clean handler
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([results[encoding_iana]])
if len(results) == 0:
if fallback_u8 or fallback_ascii or fallback_specified:
logger.log(
TRACE,
"Nothing got out of the detection process. Using ASCII/UTF-8/Specified fallback.",
)
if fallback_specified:
logger.debug(
"Encoding detection: %s will be used as a fallback match",
fallback_specified.encoding,
)
results.append(fallback_specified)
elif (
(fallback_u8 and fallback_ascii is None)
or (
fallback_u8
and fallback_ascii
and fallback_u8.fingerprint != fallback_ascii.fingerprint
)
or (fallback_u8 is not None)
):
logger.debug("Encoding detection: utf_8 will be used as a fallback match")
results.append(fallback_u8)
elif fallback_ascii:
logger.debug("Encoding detection: ascii will be used as a fallback match")
results.append(fallback_ascii)
if results:
logger.debug(
"Encoding detection: Found %s as plausible (best-candidate) for content. With %i alternatives.",
results.best().encoding, # type: ignore
len(results) - 1,
)
else:
logger.debug("Encoding detection: Unable to determine any suitable charset.")
if explain:
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return results
def from_fp(
fp: BinaryIO,
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: list[str] | None = None,
cp_exclusion: list[str] | None = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = True,
) -> CharsetMatches:
"""
Same thing than the function from_bytes but using a file pointer that is already ready.
Will not close the file pointer.
"""
return from_bytes(
fp.read(),
steps,
chunk_size,
threshold,
cp_isolation,
cp_exclusion,
preemptive_behaviour,
explain,
language_threshold,
enable_fallback,
)
def from_path(
path: str | bytes | PathLike, # type: ignore[type-arg]
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: list[str] | None = None,
cp_exclusion: list[str] | None = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = True,
) -> CharsetMatches:
"""
Same thing than the function from_bytes but with one extra step. Opening and reading given file path in binary mode.
Can raise IOError.
"""
with open(path, "rb") as fp:
return from_fp(
fp,
steps,
chunk_size,
threshold,
cp_isolation,
cp_exclusion,
preemptive_behaviour,
explain,
language_threshold,
enable_fallback,
)
def is_binary(
fp_or_path_or_payload: PathLike | str | BinaryIO | bytes, # type: ignore[type-arg]
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: list[str] | None = None,
cp_exclusion: list[str] | None = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = False,
) -> bool:
"""
Detect if the given input (file, bytes, or path) points to a binary file. aka. not a string.
Based on the same main heuristic algorithms and default kwargs at the sole exception that fallbacks match
are disabled to be stricter around ASCII-compatible but unlikely to be a string.
"""
if isinstance(fp_or_path_or_payload, (str, PathLike)):
guesses = from_path(
fp_or_path_or_payload,
steps=steps,
chunk_size=chunk_size,
threshold=threshold,
cp_isolation=cp_isolation,
cp_exclusion=cp_exclusion,
preemptive_behaviour=preemptive_behaviour,
explain=explain,
language_threshold=language_threshold,
enable_fallback=enable_fallback,
)
elif isinstance(
fp_or_path_or_payload,
(
bytes,
bytearray,
),
):
guesses = from_bytes(
fp_or_path_or_payload,
steps=steps,
chunk_size=chunk_size,
threshold=threshold,
cp_isolation=cp_isolation,
cp_exclusion=cp_exclusion,
preemptive_behaviour=preemptive_behaviour,
explain=explain,
language_threshold=language_threshold,
enable_fallback=enable_fallback,
)
else:
guesses = from_fp(
fp_or_path_or_payload,
steps=steps,
chunk_size=chunk_size,
threshold=threshold,
cp_isolation=cp_isolation,
cp_exclusion=cp_exclusion,
preemptive_behaviour=preemptive_behaviour,
explain=explain,
language_threshold=language_threshold,
enable_fallback=enable_fallback,
)
return not guesses

395
venv/lib/python3.12/site-packages/charset_normalizer/cd.py Normal file
View File

@@ -0,0 +1,395 @@
from __future__ import annotations
import importlib
from codecs import IncrementalDecoder
from collections import Counter
from functools import lru_cache
from typing import Counter as TypeCounter
from .constant import (
FREQUENCIES,
KO_NAMES,
LANGUAGE_SUPPORTED_COUNT,
TOO_SMALL_SEQUENCE,
ZH_NAMES,
)
from .md import is_suspiciously_successive_range
from .models import CoherenceMatches
from .utils import (
is_accentuated,
is_latin,
is_multi_byte_encoding,
is_unicode_range_secondary,
unicode_range,
)
def encoding_unicode_range(iana_name: str) -> list[str]:
"""
Return associated unicode ranges in a single byte code page.
"""
if is_multi_byte_encoding(iana_name):
raise OSError("Function not supported on multi-byte code page")
decoder = importlib.import_module(f"encodings.{iana_name}").IncrementalDecoder
p: IncrementalDecoder = decoder(errors="ignore")
seen_ranges: dict[str, int] = {}
character_count: int = 0
for i in range(0x40, 0xFF):
chunk: str = p.decode(bytes([i]))
if chunk:
character_range: str | None = unicode_range(chunk)
if character_range is None:
continue
if is_unicode_range_secondary(character_range) is False:
if character_range not in seen_ranges:
seen_ranges[character_range] = 0
seen_ranges[character_range] += 1
character_count += 1
return sorted(
[
character_range
for character_range in seen_ranges
if seen_ranges[character_range] / character_count >= 0.15
]
)
def unicode_range_languages(primary_range: str) -> list[str]:
"""
Return inferred languages used with a unicode range.
"""
languages: list[str] = []
for language, characters in FREQUENCIES.items():
for character in characters:
if unicode_range(character) == primary_range:
languages.append(language)
break
return languages
@lru_cache()
def encoding_languages(iana_name: str) -> list[str]:
"""
Single-byte encoding language association. Some code page are heavily linked to particular language(s).
This function does the correspondence.
"""
unicode_ranges: list[str] = encoding_unicode_range(iana_name)
primary_range: str | None = None
for specified_range in unicode_ranges:
if "Latin" not in specified_range:
primary_range = specified_range
break
if primary_range is None:
return ["Latin Based"]
return unicode_range_languages(primary_range)
@lru_cache()
def mb_encoding_languages(iana_name: str) -> list[str]:
"""
Multi-byte encoding language association. Some code page are heavily linked to particular language(s).
This function does the correspondence.
"""
if (
iana_name.startswith("shift_")
or iana_name.startswith("iso2022_jp")
or iana_name.startswith("euc_j")
or iana_name == "cp932"
):
return ["Japanese"]
if iana_name.startswith("gb") or iana_name in ZH_NAMES:
return ["Chinese"]
if iana_name.startswith("iso2022_kr") or iana_name in KO_NAMES:
return ["Korean"]
return []
@lru_cache(maxsize=LANGUAGE_SUPPORTED_COUNT)
def get_target_features(language: str) -> tuple[bool, bool]:
"""
Determine main aspects from a supported language if it contains accents and if is pure Latin.
"""
target_have_accents: bool = False
target_pure_latin: bool = True
for character in FREQUENCIES[language]:
if not target_have_accents and is_accentuated(character):
target_have_accents = True
if target_pure_latin and is_latin(character) is False:
target_pure_latin = False
return target_have_accents, target_pure_latin
def alphabet_languages(
characters: list[str], ignore_non_latin: bool = False
) -> list[str]:
"""
Return associated languages associated to given characters.
"""
languages: list[tuple[str, float]] = []
source_have_accents = any(is_accentuated(character) for character in characters)
for language, language_characters in FREQUENCIES.items():
target_have_accents, target_pure_latin = get_target_features(language)
if ignore_non_latin and target_pure_latin is False:
continue
if target_have_accents is False and source_have_accents:
continue
character_count: int = len(language_characters)
character_match_count: int = len(
[c for c in language_characters if c in characters]
)
ratio: float = character_match_count / character_count
if ratio >= 0.2:
languages.append((language, ratio))
languages = sorted(languages, key=lambda x: x[1], reverse=True)
return [compatible_language[0] for compatible_language in languages]
def characters_popularity_compare(
language: str, ordered_characters: list[str]
) -> float:
"""
Determine if a ordered characters list (by occurrence from most appearance to rarest) match a particular language.
The result is a ratio between 0. (absolutely no correspondence) and 1. (near perfect fit).
Beware that is function is not strict on the match in order to ease the detection. (Meaning close match is 1.)
"""
if language not in FREQUENCIES:
raise ValueError(f"{language} not available")
character_approved_count: int = 0
FREQUENCIES_language_set = set(FREQUENCIES[language])
ordered_characters_count: int = len(ordered_characters)
target_language_characters_count: int = len(FREQUENCIES[language])
large_alphabet: bool = target_language_characters_count > 26
for character, character_rank in zip(
ordered_characters, range(0, ordered_characters_count)
):
if character not in FREQUENCIES_language_set:
continue
character_rank_in_language: int = FREQUENCIES[language].index(character)
expected_projection_ratio: float = (
target_language_characters_count / ordered_characters_count
)
character_rank_projection: int = int(character_rank * expected_projection_ratio)
if (
large_alphabet is False
and abs(character_rank_projection - character_rank_in_language) > 4
):
continue
if (
large_alphabet is True
and abs(character_rank_projection - character_rank_in_language)
< target_language_characters_count / 3
):
character_approved_count += 1
continue
characters_before_source: list[str] = FREQUENCIES[language][
0:character_rank_in_language
]
characters_after_source: list[str] = FREQUENCIES[language][
character_rank_in_language:
]
characters_before: list[str] = ordered_characters[0:character_rank]
characters_after: list[str] = ordered_characters[character_rank:]
before_match_count: int = len(
set(characters_before) & set(characters_before_source)
)
after_match_count: int = len(
set(characters_after) & set(characters_after_source)
)
if len(characters_before_source) == 0 and before_match_count <= 4:
character_approved_count += 1
continue
if len(characters_after_source) == 0 and after_match_count <= 4:
character_approved_count += 1
continue
if (
before_match_count / len(characters_before_source) >= 0.4
or after_match_count / len(characters_after_source) >= 0.4
):
character_approved_count += 1
continue
return character_approved_count / len(ordered_characters)
def alpha_unicode_split(decoded_sequence: str) -> list[str]:
"""
Given a decoded text sequence, return a list of str. Unicode range / alphabet separation.
Ex. a text containing English/Latin with a bit a Hebrew will return two items in the resulting list;
One containing the latin letters and the other hebrew.
"""
layers: dict[str, str] = {}
for character in decoded_sequence:
if character.isalpha() is False:
continue
character_range: str | None = unicode_range(character)
if character_range is None:
continue
layer_target_range: str | None = None
for discovered_range in layers:
if (
is_suspiciously_successive_range(discovered_range, character_range)
is False
):
layer_target_range = discovered_range
break
if layer_target_range is None:
layer_target_range = character_range
if layer_target_range not in layers:
layers[layer_target_range] = character.lower()
continue
layers[layer_target_range] += character.lower()
return list(layers.values())
def merge_coherence_ratios(results: list[CoherenceMatches]) -> CoherenceMatches:
"""
This function merge results previously given by the function coherence_ratio.
The return type is the same as coherence_ratio.
"""
per_language_ratios: dict[str, list[float]] = {}
for result in results:
for sub_result in result:
language, ratio = sub_result
if language not in per_language_ratios:
per_language_ratios[language] = [ratio]
continue
per_language_ratios[language].append(ratio)
merge = [
(
language,
round(
sum(per_language_ratios[language]) / len(per_language_ratios[language]),
4,
),
)
for language in per_language_ratios
]
return sorted(merge, key=lambda x: x[1], reverse=True)
def filter_alt_coherence_matches(results: CoherenceMatches) -> CoherenceMatches:
"""
We shall NOT return "English—" in CoherenceMatches because it is an alternative
of "English". This function only keeps the best match and remove the em-dash in it.
"""
index_results: dict[str, list[float]] = dict()
for result in results:
language, ratio = result
no_em_name: str = language.replace("—", "")
if no_em_name not in index_results:
index_results[no_em_name] = []
index_results[no_em_name].append(ratio)
if any(len(index_results[e]) > 1 for e in index_results):
filtered_results: CoherenceMatches = []
for language in index_results:
filtered_results.append((language, max(index_results[language])))
return filtered_results
return results
@lru_cache(maxsize=2048)
def coherence_ratio(
decoded_sequence: str, threshold: float = 0.1, lg_inclusion: str | None = None
) -> CoherenceMatches:
"""
Detect ANY language that can be identified in given sequence. The sequence will be analysed by layers.
A layer = Character extraction by alphabets/ranges.
"""
results: list[tuple[str, float]] = []
ignore_non_latin: bool = False
sufficient_match_count: int = 0
lg_inclusion_list = lg_inclusion.split(",") if lg_inclusion is not None else []
if "Latin Based" in lg_inclusion_list:
ignore_non_latin = True
lg_inclusion_list.remove("Latin Based")
for layer in alpha_unicode_split(decoded_sequence):
sequence_frequencies: TypeCounter[str] = Counter(layer)
most_common = sequence_frequencies.most_common()
character_count: int = sum(o for c, o in most_common)
if character_count <= TOO_SMALL_SEQUENCE:
continue
popular_character_ordered: list[str] = [c for c, o in most_common]
for language in lg_inclusion_list or alphabet_languages(
popular_character_ordered, ignore_non_latin
):
ratio: float = characters_popularity_compare(
language, popular_character_ordered
)
if ratio < threshold:
continue
elif ratio >= 0.8:
sufficient_match_count += 1
results.append((language, round(ratio, 4)))
if sufficient_match_count >= 3:
break
return sorted(
filter_alt_coherence_matches(results), key=lambda x: x[1], reverse=True
)

8
venv/lib/python3.12/site-packages/charset_normalizer/cli/__init__.py Normal file
View File

@@ -0,0 +1,8 @@
from __future__ import annotations
from .__main__ import cli_detect, query_yes_no
__all__ = (
"cli_detect",
"query_yes_no",
)

381
venv/lib/python3.12/site-packages/charset_normalizer/cli/__main__.py Normal file
View File

@@ -0,0 +1,381 @@
from __future__ import annotations
import argparse
import sys
import typing
from json import dumps
from os.path import abspath, basename, dirname, join, realpath
from platform import python_version
from unicodedata import unidata_version
import charset_normalizer.md as md_module
from charset_normalizer import from_fp
from charset_normalizer.models import CliDetectionResult
from charset_normalizer.version import __version__
def query_yes_no(question: str, default: str = "yes") -> bool:
"""Ask a yes/no question via input() and return their answer.
"question" is a string that is presented to the user.
"default" is the presumed answer if the user just hits <Enter>.
It must be "yes" (the default), "no" or None (meaning
an answer is required of the user).
The "answer" return value is True for "yes" or False for "no".
Credit goes to (c) https://stackoverflow.com/questions/3041986/apt-command-line-interface-like-yes-no-input
"""
valid = {"yes": True, "y": True, "ye": True, "no": False, "n": False}
if default is None:
prompt = " [y/n] "
elif default == "yes":
prompt = " [Y/n] "
elif default == "no":
prompt = " [y/N] "
else:
raise ValueError("invalid default answer: '%s'" % default)
while True:
sys.stdout.write(question + prompt)
choice = input().lower()
if default is not None and choice == "":
return valid[default]
elif choice in valid:
return valid[choice]
else:
sys.stdout.write("Please respond with 'yes' or 'no' (or 'y' or 'n').\n")
class FileType:
"""Factory for creating file object types
Instances of FileType are typically passed as type= arguments to the
ArgumentParser add_argument() method.
Keyword Arguments:
- mode -- A string indicating how the file is to be opened. Accepts the
same values as the builtin open() function.
- bufsize -- The file's desired buffer size. Accepts the same values as
the builtin open() function.
- encoding -- The file's encoding. Accepts the same values as the
builtin open() function.
- errors -- A string indicating how encoding and decoding errors are to
be handled. Accepts the same value as the builtin open() function.
Backported from CPython 3.12
"""
def __init__(
self,
mode: str = "r",
bufsize: int = -1,
encoding: str | None = None,
errors: str | None = None,
):
self._mode = mode
self._bufsize = bufsize
self._encoding = encoding
self._errors = errors
def __call__(self, string: str) -> typing.IO: # type: ignore[type-arg]
# the special argument "-" means sys.std{in,out}
if string == "-":
if "r" in self._mode:
return sys.stdin.buffer if "b" in self._mode else sys.stdin
elif any(c in self._mode for c in "wax"):
return sys.stdout.buffer if "b" in self._mode else sys.stdout
else:
msg = f'argument "-" with mode {self._mode}'
raise ValueError(msg)
# all other arguments are used as file names
try:
return open(string, self._mode, self._bufsize, self._encoding, self._errors)
except OSError as e:
message = f"can't open '{string}': {e}"
raise argparse.ArgumentTypeError(message)
def __repr__(self) -> str:
args = self._mode, self._bufsize
kwargs = [("encoding", self._encoding), ("errors", self._errors)]
args_str = ", ".join(
[repr(arg) for arg in args if arg != -1]
+ [f"{kw}={arg!r}" for kw, arg in kwargs if arg is not None]
)
return f"{type(self).__name__}({args_str})"
def cli_detect(argv: list[str] | None = None) -> int:
"""
CLI assistant using ARGV and ArgumentParser
:param argv:
:return: 0 if everything is fine, anything else equal trouble
"""
parser = argparse.ArgumentParser(
description="The Real First Universal Charset Detector. "
"Discover originating encoding used on text file. "
"Normalize text to unicode."
)
parser.add_argument(
"files", type=FileType("rb"), nargs="+", help="File(s) to be analysed"
)
parser.add_argument(
"-v",
"--verbose",
action="store_true",
default=False,
dest="verbose",
help="Display complementary information about file if any. "
"Stdout will contain logs about the detection process.",
)
parser.add_argument(
"-a",
"--with-alternative",
action="store_true",
default=False,
dest="alternatives",
help="Output complementary possibilities if any. Top-level JSON WILL be a list.",
)
parser.add_argument(
"-n",
"--normalize",
action="store_true",
default=False,
dest="normalize",
help="Permit to normalize input file. If not set, program does not write anything.",
)
parser.add_argument(
"-m",
"--minimal",
action="store_true",
default=False,
dest="minimal",
help="Only output the charset detected to STDOUT. Disabling JSON output.",
)
parser.add_argument(
"-r",
"--replace",
action="store_true",
default=False,
dest="replace",
help="Replace file when trying to normalize it instead of creating a new one.",
)
parser.add_argument(
"-f",
"--force",
action="store_true",
default=False,
dest="force",
help="Replace file without asking if you are sure, use this flag with caution.",
)
parser.add_argument(
"-i",
"--no-preemptive",
action="store_true",
default=False,
dest="no_preemptive",
help="Disable looking at a charset declaration to hint the detector.",
)
parser.add_argument(
"-t",
"--threshold",
action="store",
default=0.2,
type=float,
dest="threshold",
help="Define a custom maximum amount of noise allowed in decoded content. 0. <= noise <= 1.",
)
parser.add_argument(
"--version",
action="version",
version="Charset-Normalizer {} - Python {} - Unicode {} - SpeedUp {}".format(
__version__,
python_version(),
unidata_version,
"OFF" if md_module.__file__.lower().endswith(".py") else "ON",
),
help="Show version information and exit.",
)
args = parser.parse_args(argv)
if args.replace is True and args.normalize is False:
if args.files:
for my_file in args.files:
my_file.close()
print("Use --replace in addition of --normalize only.", file=sys.stderr)
return 1
if args.force is True and args.replace is False:
if args.files:
for my_file in args.files:
my_file.close()
print("Use --force in addition of --replace only.", file=sys.stderr)
return 1
if args.threshold < 0.0 or args.threshold > 1.0:
if args.files:
for my_file in args.files:
my_file.close()
print("--threshold VALUE should be between 0. AND 1.", file=sys.stderr)
return 1
x_ = []
for my_file in args.files:
matches = from_fp(
my_file,
threshold=args.threshold,
explain=args.verbose,
preemptive_behaviour=args.no_preemptive is False,
)
best_guess = matches.best()
if best_guess is None:
print(
'Unable to identify originating encoding for "{}". {}'.format(
my_file.name,
(
"Maybe try increasing maximum amount of chaos."
if args.threshold < 1.0
else ""
),
),
file=sys.stderr,
)
x_.append(
CliDetectionResult(
abspath(my_file.name),
None,
[],
[],
"Unknown",
[],
False,
1.0,
0.0,
None,
True,
)
)
else:
x_.append(
CliDetectionResult(
abspath(my_file.name),
best_guess.encoding,
best_guess.encoding_aliases,
[
cp
for cp in best_guess.could_be_from_charset
if cp != best_guess.encoding
],
best_guess.language,
best_guess.alphabets,
best_guess.bom,
best_guess.percent_chaos,
best_guess.percent_coherence,
None,
True,
)
)
if len(matches) > 1 and args.alternatives:
for el in matches:
if el != best_guess:
x_.append(
CliDetectionResult(
abspath(my_file.name),
el.encoding,
el.encoding_aliases,
[
cp
for cp in el.could_be_from_charset
if cp != el.encoding
],
el.language,
el.alphabets,
el.bom,
el.percent_chaos,
el.percent_coherence,
None,
False,
)
)
if args.normalize is True:
if best_guess.encoding.startswith("utf") is True:
print(
'"{}" file does not need to be normalized, as it already came from unicode.'.format(
my_file.name
),
file=sys.stderr,
)
if my_file.closed is False:
my_file.close()
continue
dir_path = dirname(realpath(my_file.name))
file_name = basename(realpath(my_file.name))
o_: list[str] = file_name.split(".")
if args.replace is False:
o_.insert(-1, best_guess.encoding)
if my_file.closed is False:
my_file.close()
elif (
args.force is False
and query_yes_no(
'Are you sure to normalize "{}" by replacing it ?'.format(
my_file.name
),
"no",
)
is False
):
if my_file.closed is False:
my_file.close()
continue
try:
x_[0].unicode_path = join(dir_path, ".".join(o_))
with open(x_[0].unicode_path, "wb") as fp:
fp.write(best_guess.output())
except OSError as e:
print(str(e), file=sys.stderr)
if my_file.closed is False:
my_file.close()
return 2
if my_file.closed is False:
my_file.close()
if args.minimal is False:
print(
dumps(
[el.__dict__ for el in x_] if len(x_) > 1 else x_[0].__dict__,
ensure_ascii=True,
indent=4,
)
)
else:
for my_file in args.files:
print(
", ".join(
[
el.encoding or "undefined"
for el in x_
if el.path == abspath(my_file.name)
]
)
)
return 0
if __name__ == "__main__":
cli_detect()

2015
venv/lib/python3.12/site-packages/charset_normalizer/constant.py Normal file
View File

File diff suppressed because it is too large Load Diff

80
venv/lib/python3.12/site-packages/charset_normalizer/legacy.py Normal file
View File

@@ -0,0 +1,80 @@
from __future__ import annotations
from typing import TYPE_CHECKING, Any
from warnings import warn
from .api import from_bytes
from .constant import CHARDET_CORRESPONDENCE, TOO_SMALL_SEQUENCE
# TODO: remove this check when dropping Python 3.7 support
if TYPE_CHECKING:
from typing_extensions import TypedDict
class ResultDict(TypedDict):
encoding: str | None
language: str
confidence: float | None
def detect(
byte_str: bytes, should_rename_legacy: bool = False, **kwargs: Any
) -> ResultDict:
"""
chardet legacy method
Detect the encoding of the given byte string. It should be mostly backward-compatible.
Encoding name will match Chardet own writing whenever possible. (Not on encoding name unsupported by it)
This function is deprecated and should be used to migrate your project easily, consult the documentation for
further information. Not planned for removal.
:param byte_str: The byte sequence to examine.
:param should_rename_legacy: Should we rename legacy encodings
to their more modern equivalents?
"""
if len(kwargs):
warn(
f"charset-normalizer disregard arguments '{','.join(list(kwargs.keys()))}' in legacy function detect()"
)
if not isinstance(byte_str, (bytearray, bytes)):
raise TypeError( # pragma: nocover
f"Expected object of type bytes or bytearray, got: {type(byte_str)}"
)
if isinstance(byte_str, bytearray):
byte_str = bytes(byte_str)
r = from_bytes(byte_str).best()
encoding = r.encoding if r is not None else None
language = r.language if r is not None and r.language != "Unknown" else ""
confidence = 1.0 - r.chaos if r is not None else None
# automatically lower confidence
# on small bytes samples.
# https://github.com/jawah/charset_normalizer/issues/391
if (
confidence is not None
and confidence >= 0.9
and encoding
not in {
"utf_8",
"ascii",
}
and r.bom is False # type: ignore[union-attr]
and len(byte_str) < TOO_SMALL_SEQUENCE
):
confidence -= 0.2
# Note: CharsetNormalizer does not return 'UTF-8-SIG' as the sig get stripped in the detection/normalization process
# but chardet does return 'utf-8-sig' and it is a valid codec name.
if r is not None and encoding == "utf_8" and r.bom:
encoding += "_sig"
if should_rename_legacy is False and encoding in CHARDET_CORRESPONDENCE:
encoding = CHARDET_CORRESPONDENCE[encoding]
return {
"encoding": encoding,
"language": language,
"confidence": confidence,
}

BIN
venv/lib/python3.12/site-packages/charset_normalizer/md.cpython-312-x86_64-linux-gnu.so Executable file
View File

Binary file not shown.

635
venv/lib/python3.12/site-packages/charset_normalizer/md.py Normal file
View File

@@ -0,0 +1,635 @@
from __future__ import annotations
from functools import lru_cache
from logging import getLogger
from .constant import (
COMMON_SAFE_ASCII_CHARACTERS,
TRACE,
UNICODE_SECONDARY_RANGE_KEYWORD,
)
from .utils import (
is_accentuated,
is_arabic,
is_arabic_isolated_form,
is_case_variable,
is_cjk,
is_emoticon,
is_hangul,
is_hiragana,
is_katakana,
is_latin,
is_punctuation,
is_separator,
is_symbol,
is_thai,
is_unprintable,
remove_accent,
unicode_range,
is_cjk_uncommon,
)
class MessDetectorPlugin:
"""
Base abstract class used for mess detection plugins.
All detectors MUST extend and implement given methods.
"""
def eligible(self, character: str) -> bool:
"""
Determine if given character should be fed in.
"""
raise NotImplementedError # pragma: nocover
def feed(self, character: str) -> None:
"""
The main routine to be executed upon character.
Insert the logic in witch the text would be considered chaotic.
"""
raise NotImplementedError # pragma: nocover
def reset(self) -> None: # pragma: no cover
"""
Permit to reset the plugin to the initial state.
"""
raise NotImplementedError
@property
def ratio(self) -> float:
"""
Compute the chaos ratio based on what your feed() has seen.
Must NOT be lower than 0.; No restriction gt 0.
"""
raise NotImplementedError # pragma: nocover
class TooManySymbolOrPunctuationPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._punctuation_count: int = 0
self._symbol_count: int = 0
self._character_count: int = 0
self._last_printable_char: str | None = None
self._frenzy_symbol_in_word: bool = False
def eligible(self, character: str) -> bool:
return character.isprintable()
def feed(self, character: str) -> None:
self._character_count += 1
if (
character != self._last_printable_char
and character not in COMMON_SAFE_ASCII_CHARACTERS
):
if is_punctuation(character):
self._punctuation_count += 1
elif (
character.isdigit() is False
and is_symbol(character)
and is_emoticon(character) is False
):
self._symbol_count += 2
self._last_printable_char = character
def reset(self) -> None: # Abstract
self._punctuation_count = 0
self._character_count = 0
self._symbol_count = 0
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
ratio_of_punctuation: float = (
self._punctuation_count + self._symbol_count
) / self._character_count
return ratio_of_punctuation if ratio_of_punctuation >= 0.3 else 0.0
class TooManyAccentuatedPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._character_count: int = 0
self._accentuated_count: int = 0
def eligible(self, character: str) -> bool:
return character.isalpha()
def feed(self, character: str) -> None:
self._character_count += 1
if is_accentuated(character):
self._accentuated_count += 1
def reset(self) -> None: # Abstract
self._character_count = 0
self._accentuated_count = 0
@property
def ratio(self) -> float:
if self._character_count < 8:
return 0.0
ratio_of_accentuation: float = self._accentuated_count / self._character_count
return ratio_of_accentuation if ratio_of_accentuation >= 0.35 else 0.0
class UnprintablePlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._unprintable_count: int = 0
self._character_count: int = 0
def eligible(self, character: str) -> bool:
return True
def feed(self, character: str) -> None:
if is_unprintable(character):
self._unprintable_count += 1
self._character_count += 1
def reset(self) -> None: # Abstract
self._unprintable_count = 0
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
return (self._unprintable_count * 8) / self._character_count
class SuspiciousDuplicateAccentPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._successive_count: int = 0
self._character_count: int = 0
self._last_latin_character: str | None = None
def eligible(self, character: str) -> bool:
return character.isalpha() and is_latin(character)
def feed(self, character: str) -> None:
self._character_count += 1
if (
self._last_latin_character is not None
and is_accentuated(character)
and is_accentuated(self._last_latin_character)
):
if character.isupper() and self._last_latin_character.isupper():
self._successive_count += 1
# Worse if its the same char duplicated with different accent.
if remove_accent(character) == remove_accent(self._last_latin_character):
self._successive_count += 1
self._last_latin_character = character
def reset(self) -> None: # Abstract
self._successive_count = 0
self._character_count = 0
self._last_latin_character = None
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
return (self._successive_count * 2) / self._character_count
class SuspiciousRange(MessDetectorPlugin):
def __init__(self) -> None:
self._suspicious_successive_range_count: int = 0
self._character_count: int = 0
self._last_printable_seen: str | None = None
def eligible(self, character: str) -> bool:
return character.isprintable()
def feed(self, character: str) -> None:
self._character_count += 1
if (
character.isspace()
or is_punctuation(character)
or character in COMMON_SAFE_ASCII_CHARACTERS
):
self._last_printable_seen = None
return
if self._last_printable_seen is None:
self._last_printable_seen = character
return
unicode_range_a: str | None = unicode_range(self._last_printable_seen)
unicode_range_b: str | None = unicode_range(character)
if is_suspiciously_successive_range(unicode_range_a, unicode_range_b):
self._suspicious_successive_range_count += 1
self._last_printable_seen = character
def reset(self) -> None: # Abstract
self._character_count = 0
self._suspicious_successive_range_count = 0
self._last_printable_seen = None
@property
def ratio(self) -> float:
if self._character_count <= 13:
return 0.0
ratio_of_suspicious_range_usage: float = (
self._suspicious_successive_range_count * 2
) / self._character_count
return ratio_of_suspicious_range_usage
class SuperWeirdWordPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._word_count: int = 0
self._bad_word_count: int = 0
self._foreign_long_count: int = 0
self._is_current_word_bad: bool = False
self._foreign_long_watch: bool = False
self._character_count: int = 0
self._bad_character_count: int = 0
self._buffer: str = ""
self._buffer_accent_count: int = 0
self._buffer_glyph_count: int = 0
def eligible(self, character: str) -> bool:
return True
def feed(self, character: str) -> None:
if character.isalpha():
self._buffer += character
if is_accentuated(character):
self._buffer_accent_count += 1
if (
self._foreign_long_watch is False
and (is_latin(character) is False or is_accentuated(character))
and is_cjk(character) is False
and is_hangul(character) is False
and is_katakana(character) is False
and is_hiragana(character) is False
and is_thai(character) is False
):
self._foreign_long_watch = True
if (
is_cjk(character)
or is_hangul(character)
or is_katakana(character)
or is_hiragana(character)
or is_thai(character)
):
self._buffer_glyph_count += 1
return
if not self._buffer:
return
if (
character.isspace() or is_punctuation(character) or is_separator(character)
) and self._buffer:
self._word_count += 1
buffer_length: int = len(self._buffer)
self._character_count += buffer_length
if buffer_length >= 4:
if self._buffer_accent_count / buffer_length >= 0.5:
self._is_current_word_bad = True
# Word/Buffer ending with an upper case accentuated letter are so rare,
# that we will consider them all as suspicious. Same weight as foreign_long suspicious.
elif (
is_accentuated(self._buffer[-1])
and self._buffer[-1].isupper()
and all(_.isupper() for _ in self._buffer) is False
):
self._foreign_long_count += 1
self._is_current_word_bad = True
elif self._buffer_glyph_count == 1:
self._is_current_word_bad = True
self._foreign_long_count += 1
if buffer_length >= 24 and self._foreign_long_watch:
camel_case_dst = [
i
for c, i in zip(self._buffer, range(0, buffer_length))
if c.isupper()
]
probable_camel_cased: bool = False
if camel_case_dst and (len(camel_case_dst) / buffer_length <= 0.3):
probable_camel_cased = True
if not probable_camel_cased:
self._foreign_long_count += 1
self._is_current_word_bad = True
if self._is_current_word_bad:
self._bad_word_count += 1
self._bad_character_count += len(self._buffer)
self._is_current_word_bad = False
self._foreign_long_watch = False
self._buffer = ""
self._buffer_accent_count = 0
self._buffer_glyph_count = 0
elif (
character not in {"<", ">", "-", "=", "~", "|", "_"}
and character.isdigit() is False
and is_symbol(character)
):
self._is_current_word_bad = True
self._buffer += character
def reset(self) -> None: # Abstract
self._buffer = ""
self._is_current_word_bad = False
self._foreign_long_watch = False
self._bad_word_count = 0
self._word_count = 0
self._character_count = 0
self._bad_character_count = 0
self._foreign_long_count = 0
@property
def ratio(self) -> float:
if self._word_count <= 10 and self._foreign_long_count == 0:
return 0.0
return self._bad_character_count / self._character_count
class CjkUncommonPlugin(MessDetectorPlugin):
"""
Detect messy CJK text that probably means nothing.
"""
def __init__(self) -> None:
self._character_count: int = 0
self._uncommon_count: int = 0
def eligible(self, character: str) -> bool:
return is_cjk(character)
def feed(self, character: str) -> None:
self._character_count += 1
if is_cjk_uncommon(character):
self._uncommon_count += 1
return
def reset(self) -> None: # Abstract
self._character_count = 0
self._uncommon_count = 0
@property
def ratio(self) -> float:
if self._character_count < 8:
return 0.0
uncommon_form_usage: float = self._uncommon_count / self._character_count
# we can be pretty sure it's garbage when uncommon characters are widely
# used. otherwise it could just be traditional chinese for example.
return uncommon_form_usage / 10 if uncommon_form_usage > 0.5 else 0.0
class ArchaicUpperLowerPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._buf: bool = False
self._character_count_since_last_sep: int = 0
self._successive_upper_lower_count: int = 0
self._successive_upper_lower_count_final: int = 0
self._character_count: int = 0
self._last_alpha_seen: str | None = None
self._current_ascii_only: bool = True
def eligible(self, character: str) -> bool:
return True
def feed(self, character: str) -> None:
is_concerned = character.isalpha() and is_case_variable(character)
chunk_sep = is_concerned is False
if chunk_sep and self._character_count_since_last_sep > 0:
if (
self._character_count_since_last_sep <= 64
and character.isdigit() is False
and self._current_ascii_only is False
):
self._successive_upper_lower_count_final += (
self._successive_upper_lower_count
)
self._successive_upper_lower_count = 0
self._character_count_since_last_sep = 0
self._last_alpha_seen = None
self._buf = False
self._character_count += 1
self._current_ascii_only = True
return
if self._current_ascii_only is True and character.isascii() is False:
self._current_ascii_only = False
if self._last_alpha_seen is not None:
if (character.isupper() and self._last_alpha_seen.islower()) or (
character.islower() and self._last_alpha_seen.isupper()
):
if self._buf is True:
self._successive_upper_lower_count += 2
self._buf = False
else:
self._buf = True
else:
self._buf = False
self._character_count += 1
self._character_count_since_last_sep += 1
self._last_alpha_seen = character
def reset(self) -> None: # Abstract
self._character_count = 0
self._character_count_since_last_sep = 0
self._successive_upper_lower_count = 0
self._successive_upper_lower_count_final = 0
self._last_alpha_seen = None
self._buf = False
self._current_ascii_only = True
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
return self._successive_upper_lower_count_final / self._character_count
class ArabicIsolatedFormPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._character_count: int = 0
self._isolated_form_count: int = 0
def reset(self) -> None: # Abstract
self._character_count = 0
self._isolated_form_count = 0
def eligible(self, character: str) -> bool:
return is_arabic(character)
def feed(self, character: str) -> None:
self._character_count += 1
if is_arabic_isolated_form(character):
self._isolated_form_count += 1
@property
def ratio(self) -> float:
if self._character_count < 8:
return 0.0
isolated_form_usage: float = self._isolated_form_count / self._character_count
return isolated_form_usage
@lru_cache(maxsize=1024)
def is_suspiciously_successive_range(
unicode_range_a: str | None, unicode_range_b: str | None
) -> bool:
"""
Determine if two Unicode range seen next to each other can be considered as suspicious.
"""
if unicode_range_a is None or unicode_range_b is None:
return True
if unicode_range_a == unicode_range_b:
return False
if "Latin" in unicode_range_a and "Latin" in unicode_range_b:
return False
if "Emoticons" in unicode_range_a or "Emoticons" in unicode_range_b:
return False
# Latin characters can be accompanied with a combining diacritical mark
# eg. Vietnamese.
if ("Latin" in unicode_range_a or "Latin" in unicode_range_b) and (
"Combining" in unicode_range_a or "Combining" in unicode_range_b
):
return False
keywords_range_a, keywords_range_b = (
unicode_range_a.split(" "),
unicode_range_b.split(" "),
)
for el in keywords_range_a:
if el in UNICODE_SECONDARY_RANGE_KEYWORD:
continue
if el in keywords_range_b:
return False
# Japanese Exception
range_a_jp_chars, range_b_jp_chars = (
unicode_range_a
in (
"Hiragana",
"Katakana",
),
unicode_range_b in ("Hiragana", "Katakana"),
)
if (range_a_jp_chars or range_b_jp_chars) and (
"CJK" in unicode_range_a or "CJK" in unicode_range_b
):
return False
if range_a_jp_chars and range_b_jp_chars:
return False
if "Hangul" in unicode_range_a or "Hangul" in unicode_range_b:
if "CJK" in unicode_range_a or "CJK" in unicode_range_b:
return False
if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin":
return False
# Chinese/Japanese use dedicated range for punctuation and/or separators.
if ("CJK" in unicode_range_a or "CJK" in unicode_range_b) or (
unicode_range_a in ["Katakana", "Hiragana"]
and unicode_range_b in ["Katakana", "Hiragana"]
):
if "Punctuation" in unicode_range_a or "Punctuation" in unicode_range_b:
return False
if "Forms" in unicode_range_a or "Forms" in unicode_range_b:
return False
if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin":
return False
return True
@lru_cache(maxsize=2048)
def mess_ratio(
decoded_sequence: str, maximum_threshold: float = 0.2, debug: bool = False
) -> float:
"""
Compute a mess ratio given a decoded bytes sequence. The maximum threshold does stop the computation earlier.
"""
detectors: list[MessDetectorPlugin] = [
md_class() for md_class in MessDetectorPlugin.__subclasses__()
]
length: int = len(decoded_sequence) + 1
mean_mess_ratio: float = 0.0
if length < 512:
intermediary_mean_mess_ratio_calc: int = 32
elif length <= 1024:
intermediary_mean_mess_ratio_calc = 64
else:
intermediary_mean_mess_ratio_calc = 128
for character, index in zip(decoded_sequence + "\n", range(length)):
for detector in detectors:
if detector.eligible(character):
detector.feed(character)
if (
index > 0 and index % intermediary_mean_mess_ratio_calc == 0
) or index == length - 1:
mean_mess_ratio = sum(dt.ratio for dt in detectors)
if mean_mess_ratio >= maximum_threshold:
break
if debug:
logger = getLogger("charset_normalizer")
logger.log(
TRACE,
"Mess-detector extended-analysis start. "
f"intermediary_mean_mess_ratio_calc={intermediary_mean_mess_ratio_calc} mean_mess_ratio={mean_mess_ratio} "
f"maximum_threshold={maximum_threshold}",
)
if len(decoded_sequence) > 16:
logger.log(TRACE, f"Starting with: {decoded_sequence[:16]}")
logger.log(TRACE, f"Ending with: {decoded_sequence[-16::]}")
for dt in detectors:
logger.log(TRACE, f"{dt.__class__}: {dt.ratio}")
return round(mean_mess_ratio, 3)

BIN
venv/lib/python3.12/site-packages/charset_normalizer/md__mypyc.cpython-312-x86_64-linux-gnu.so Executable file
View File

Binary file not shown.

360
venv/lib/python3.12/site-packages/charset_normalizer/models.py Normal file
View File

@@ -0,0 +1,360 @@
from __future__ import annotations
from encodings.aliases import aliases
from hashlib import sha256
from json import dumps
from re import sub
from typing import Any, Iterator, List, Tuple
from .constant import RE_POSSIBLE_ENCODING_INDICATION, TOO_BIG_SEQUENCE
from .utils import iana_name, is_multi_byte_encoding, unicode_range
class CharsetMatch:
def __init__(
self,
payload: bytes,
guessed_encoding: str,
mean_mess_ratio: float,
has_sig_or_bom: bool,
languages: CoherenceMatches,
decoded_payload: str | None = None,
preemptive_declaration: str | None = None,
):
self._payload: bytes = payload
self._encoding: str = guessed_encoding
self._mean_mess_ratio: float = mean_mess_ratio
self._languages: CoherenceMatches = languages
self._has_sig_or_bom: bool = has_sig_or_bom
self._unicode_ranges: list[str] | None = None
self._leaves: list[CharsetMatch] = []
self._mean_coherence_ratio: float = 0.0
self._output_payload: bytes | None = None
self._output_encoding: str | None = None
self._string: str | None = decoded_payload
self._preemptive_declaration: str | None = preemptive_declaration
def __eq__(self, other: object) -> bool:
if not isinstance(other, CharsetMatch):
if isinstance(other, str):
return iana_name(other) == self.encoding
return False
return self.encoding == other.encoding and self.fingerprint == other.fingerprint
def __lt__(self, other: object) -> bool:
"""
Implemented to make sorted available upon CharsetMatches items.
"""
if not isinstance(other, CharsetMatch):
raise ValueError
chaos_difference: float = abs(self.chaos - other.chaos)
coherence_difference: float = abs(self.coherence - other.coherence)
# Below 1% difference --> Use Coherence
if chaos_difference < 0.01 and coherence_difference > 0.02:
return self.coherence > other.coherence
elif chaos_difference < 0.01 and coherence_difference <= 0.02:
# When having a difficult decision, use the result that decoded as many multi-byte as possible.
# preserve RAM usage!
if len(self._payload) >= TOO_BIG_SEQUENCE:
return self.chaos < other.chaos
return self.multi_byte_usage > other.multi_byte_usage
return self.chaos < other.chaos
@property
def multi_byte_usage(self) -> float:
return 1.0 - (len(str(self)) / len(self.raw))
def __str__(self) -> str:
# Lazy Str Loading
if self._string is None:
self._string = str(self._payload, self._encoding, "strict")
return self._string
def __repr__(self) -> str:
return f"<CharsetMatch '{self.encoding}' bytes({self.fingerprint})>"
def add_submatch(self, other: CharsetMatch) -> None:
if not isinstance(other, CharsetMatch) or other == self:
raise ValueError(
"Unable to add instance <{}> as a submatch of a CharsetMatch".format(
other.__class__
)
)
other._string = None # Unload RAM usage; dirty trick.
self._leaves.append(other)
@property
def encoding(self) -> str:
return self._encoding
@property
def encoding_aliases(self) -> list[str]:
"""
Encoding name are known by many name, using this could help when searching for IBM855 when it's listed as CP855.
"""
also_known_as: list[str] = []
for u, p in aliases.items():
if self.encoding == u:
also_known_as.append(p)
elif self.encoding == p:
also_known_as.append(u)
return also_known_as
@property
def bom(self) -> bool:
return self._has_sig_or_bom
@property
def byte_order_mark(self) -> bool:
return self._has_sig_or_bom
@property
def languages(self) -> list[str]:
"""
Return the complete list of possible languages found in decoded sequence.
Usually not really useful. Returned list may be empty even if 'language' property return something != 'Unknown'.
"""
return [e[0] for e in self._languages]
@property
def language(self) -> str:
"""
Most probable language found in decoded sequence. If none were detected or inferred, the property will return
"Unknown".
"""
if not self._languages:
# Trying to infer the language based on the given encoding
# Its either English or we should not pronounce ourselves in certain cases.
if "ascii" in self.could_be_from_charset:
return "English"
# doing it there to avoid circular import
from charset_normalizer.cd import encoding_languages, mb_encoding_languages
languages = (
mb_encoding_languages(self.encoding)
if is_multi_byte_encoding(self.encoding)
else encoding_languages(self.encoding)
)
if len(languages) == 0 or "Latin Based" in languages:
return "Unknown"
return languages[0]
return self._languages[0][0]
@property
def chaos(self) -> float:
return self._mean_mess_ratio
@property
def coherence(self) -> float:
if not self._languages:
return 0.0
return self._languages[0][1]
@property
def percent_chaos(self) -> float:
return round(self.chaos * 100, ndigits=3)
@property
def percent_coherence(self) -> float:
return round(self.coherence * 100, ndigits=3)
@property
def raw(self) -> bytes:
"""
Original untouched bytes.
"""
return self._payload
@property
def submatch(self) -> list[CharsetMatch]:
return self._leaves
@property
def has_submatch(self) -> bool:
return len(self._leaves) > 0
@property
def alphabets(self) -> list[str]:
if self._unicode_ranges is not None:
return self._unicode_ranges
# list detected ranges
detected_ranges: list[str | None] = [unicode_range(char) for char in str(self)]
# filter and sort
self._unicode_ranges = sorted(list({r for r in detected_ranges if r}))
return self._unicode_ranges
@property
def could_be_from_charset(self) -> list[str]:
"""
The complete list of encoding that output the exact SAME str result and therefore could be the originating
encoding.
This list does include the encoding available in property 'encoding'.
"""
return [self._encoding] + [m.encoding for m in self._leaves]
def output(self, encoding: str = "utf_8") -> bytes:
"""
Method to get re-encoded bytes payload using given target encoding. Default to UTF-8.
Any errors will be simply ignored by the encoder NOT replaced.
"""
if self._output_encoding is None or self._output_encoding != encoding:
self._output_encoding = encoding
decoded_string = str(self)
if (
self._preemptive_declaration is not None
and self._preemptive_declaration.lower()
not in ["utf-8", "utf8", "utf_8"]
):
patched_header = sub(
RE_POSSIBLE_ENCODING_INDICATION,
lambda m: m.string[m.span()[0] : m.span()[1]].replace(
m.groups()[0],
iana_name(self._output_encoding).replace("_", "-"), # type: ignore[arg-type]
),
decoded_string[:8192],
count=1,
)
decoded_string = patched_header + decoded_string[8192:]
self._output_payload = decoded_string.encode(encoding, "replace")
return self._output_payload # type: ignore
@property
def fingerprint(self) -> str:
"""
Retrieve the unique SHA256 computed using the transformed (re-encoded) payload. Not the original one.
"""
return sha256(self.output()).hexdigest()
class CharsetMatches:
"""
Container with every CharsetMatch items ordered by default from most probable to the less one.
Act like a list(iterable) but does not implements all related methods.
"""
def __init__(self, results: list[CharsetMatch] | None = None):
self._results: list[CharsetMatch] = sorted(results) if results else []
def __iter__(self) -> Iterator[CharsetMatch]:
yield from self._results
def __getitem__(self, item: int | str) -> CharsetMatch:
"""
Retrieve a single item either by its position or encoding name (alias may be used here).
Raise KeyError upon invalid index or encoding not present in results.
"""
if isinstance(item, int):
return self._results[item]
if isinstance(item, str):
item = iana_name(item, False)
for result in self._results:
if item in result.could_be_from_charset:
return result
raise KeyError
def __len__(self) -> int:
return len(self._results)
def __bool__(self) -> bool:
return len(self._results) > 0
def append(self, item: CharsetMatch) -> None:
"""
Insert a single match. Will be inserted accordingly to preserve sort.
Can be inserted as a submatch.
"""
if not isinstance(item, CharsetMatch):
raise ValueError(
"Cannot append instance '{}' to CharsetMatches".format(
str(item.__class__)
)
)
# We should disable the submatch factoring when the input file is too heavy (conserve RAM usage)
if len(item.raw) < TOO_BIG_SEQUENCE:
for match in self._results:
if match.fingerprint == item.fingerprint and match.chaos == item.chaos:
match.add_submatch(item)
return
self._results.append(item)
self._results = sorted(self._results)
def best(self) -> CharsetMatch | None:
"""
Simply return the first match. Strict equivalent to matches[0].
"""
if not self._results:
return None
return self._results[0]
def first(self) -> CharsetMatch | None:
"""
Redundant method, call the method best(). Kept for BC reasons.
"""
return self.best()
CoherenceMatch = Tuple[str, float]
CoherenceMatches = List[CoherenceMatch]
class CliDetectionResult:
def __init__(
self,
path: str,
encoding: str | None,
encoding_aliases: list[str],
alternative_encodings: list[str],
language: str,
alphabets: list[str],
has_sig_or_bom: bool,
chaos: float,
coherence: float,
unicode_path: str | None,
is_preferred: bool,
):
self.path: str = path
self.unicode_path: str | None = unicode_path
self.encoding: str | None = encoding
self.encoding_aliases: list[str] = encoding_aliases
self.alternative_encodings: list[str] = alternative_encodings
self.language: str = language
self.alphabets: list[str] = alphabets
self.has_sig_or_bom: bool = has_sig_or_bom
self.chaos: float = chaos
self.coherence: float = coherence
self.is_preferred: bool = is_preferred
@property
def __dict__(self) -> dict[str, Any]: # type: ignore
return {
"path": self.path,
"encoding": self.encoding,
"encoding_aliases": self.encoding_aliases,
"alternative_encodings": self.alternative_encodings,
"language": self.language,
"alphabets": self.alphabets,
"has_sig_or_bom": self.has_sig_or_bom,
"chaos": self.chaos,
"coherence": self.coherence,
"unicode_path": self.unicode_path,
"is_preferred": self.is_preferred,
}
def to_json(self) -> str:
return dumps(self.__dict__, ensure_ascii=True, indent=4)

0
venv/lib/python3.12/site-packages/charset_normalizer/py.typed Normal file
View File

414
venv/lib/python3.12/site-packages/charset_normalizer/utils.py Normal file
View File

@@ -0,0 +1,414 @@
from __future__ import annotations
import importlib
import logging
import unicodedata
from codecs import IncrementalDecoder
from encodings.aliases import aliases
from functools import lru_cache
from re import findall
from typing import Generator
from _multibytecodec import ( # type: ignore[import-not-found,import]
MultibyteIncrementalDecoder,
)
from .constant import (
ENCODING_MARKS,
IANA_SUPPORTED_SIMILAR,
RE_POSSIBLE_ENCODING_INDICATION,
UNICODE_RANGES_COMBINED,
UNICODE_SECONDARY_RANGE_KEYWORD,
UTF8_MAXIMAL_ALLOCATION,
COMMON_CJK_CHARACTERS,
)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_accentuated(character: str) -> bool:
try:
description: str = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return (
"WITH GRAVE" in description
or "WITH ACUTE" in description
or "WITH CEDILLA" in description
or "WITH DIAERESIS" in description
or "WITH CIRCUMFLEX" in description
or "WITH TILDE" in description
or "WITH MACRON" in description
or "WITH RING ABOVE" in description
)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def remove_accent(character: str) -> str:
decomposed: str = unicodedata.decomposition(character)
if not decomposed:
return character
codes: list[str] = decomposed.split(" ")
return chr(int(codes[0], 16))
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def unicode_range(character: str) -> str | None:
"""
Retrieve the Unicode range official name from a single character.
"""
character_ord: int = ord(character)
for range_name, ord_range in UNICODE_RANGES_COMBINED.items():
if character_ord in ord_range:
return range_name
return None
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_latin(character: str) -> bool:
try:
description: str = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "LATIN" in description
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_punctuation(character: str) -> bool:
character_category: str = unicodedata.category(character)
if "P" in character_category:
return True
character_range: str | None = unicode_range(character)
if character_range is None:
return False
return "Punctuation" in character_range
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_symbol(character: str) -> bool:
character_category: str = unicodedata.category(character)
if "S" in character_category or "N" in character_category:
return True
character_range: str | None = unicode_range(character)
if character_range is None:
return False
return "Forms" in character_range and character_category != "Lo"
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_emoticon(character: str) -> bool:
character_range: str | None = unicode_range(character)
if character_range is None:
return False
return "Emoticons" in character_range or "Pictographs" in character_range
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_separator(character: str) -> bool:
if character.isspace() or character in {"｜", "+", "<", ">"}:
return True
character_category: str = unicodedata.category(character)
return "Z" in character_category or character_category in {"Po", "Pd", "Pc"}
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_case_variable(character: str) -> bool:
return character.islower() != character.isupper()
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_cjk(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "CJK" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_hiragana(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "HIRAGANA" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_katakana(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "KATAKANA" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_hangul(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "HANGUL" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_thai(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "THAI" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_arabic(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "ARABIC" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_arabic_isolated_form(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "ARABIC" in character_name and "ISOLATED FORM" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_cjk_uncommon(character: str) -> bool:
return character not in COMMON_CJK_CHARACTERS
@lru_cache(maxsize=len(UNICODE_RANGES_COMBINED))
def is_unicode_range_secondary(range_name: str) -> bool:
return any(keyword in range_name for keyword in UNICODE_SECONDARY_RANGE_KEYWORD)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_unprintable(character: str) -> bool:
return (
character.isspace() is False # includes \n \t \r \v
and character.isprintable() is False
and character != "\x1a" # Why? Its the ASCII substitute character.
and character != "\ufeff" # bug discovered in Python,
# Zero Width No-Break Space located in Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space.
)
def any_specified_encoding(sequence: bytes, search_zone: int = 8192) -> str | None:
"""
Extract using ASCII-only decoder any specified encoding in the first n-bytes.
"""
if not isinstance(sequence, bytes):
raise TypeError
seq_len: int = len(sequence)
results: list[str] = findall(
RE_POSSIBLE_ENCODING_INDICATION,
sequence[: min(seq_len, search_zone)].decode("ascii", errors="ignore"),
)
if len(results) == 0:
return None
for specified_encoding in results:
specified_encoding = specified_encoding.lower().replace("-", "_")
encoding_alias: str
encoding_iana: str
for encoding_alias, encoding_iana in aliases.items():
if encoding_alias == specified_encoding:
return encoding_iana
if encoding_iana == specified_encoding:
return encoding_iana
return None
@lru_cache(maxsize=128)
def is_multi_byte_encoding(name: str) -> bool:
"""
Verify is a specific encoding is a multi byte one based on it IANA name
"""
return name in {
"utf_8",
"utf_8_sig",
"utf_16",
"utf_16_be",
"utf_16_le",
"utf_32",
"utf_32_le",
"utf_32_be",
"utf_7",
} or issubclass(
importlib.import_module(f"encodings.{name}").IncrementalDecoder,
MultibyteIncrementalDecoder,
)
def identify_sig_or_bom(sequence: bytes) -> tuple[str | None, bytes]:
"""
Identify and extract SIG/BOM in given sequence.
"""
for iana_encoding in ENCODING_MARKS:
marks: bytes | list[bytes] = ENCODING_MARKS[iana_encoding]
if isinstance(marks, bytes):
marks = [marks]
for mark in marks:
if sequence.startswith(mark):
return iana_encoding, mark
return None, b""
def should_strip_sig_or_bom(iana_encoding: str) -> bool:
return iana_encoding not in {"utf_16", "utf_32"}
def iana_name(cp_name: str, strict: bool = True) -> str:
"""Returns the Python normalized encoding name (Not the IANA official name)."""
cp_name = cp_name.lower().replace("-", "_")
encoding_alias: str
encoding_iana: str
for encoding_alias, encoding_iana in aliases.items():
if cp_name in [encoding_alias, encoding_iana]:
return encoding_iana
if strict:
raise ValueError(f"Unable to retrieve IANA for '{cp_name}'")
return cp_name
def cp_similarity(iana_name_a: str, iana_name_b: str) -> float:
if is_multi_byte_encoding(iana_name_a) or is_multi_byte_encoding(iana_name_b):
return 0.0
decoder_a = importlib.import_module(f"encodings.{iana_name_a}").IncrementalDecoder
decoder_b = importlib.import_module(f"encodings.{iana_name_b}").IncrementalDecoder
id_a: IncrementalDecoder = decoder_a(errors="ignore")
id_b: IncrementalDecoder = decoder_b(errors="ignore")
character_match_count: int = 0
for i in range(255):
to_be_decoded: bytes = bytes([i])
if id_a.decode(to_be_decoded) == id_b.decode(to_be_decoded):
character_match_count += 1
return character_match_count / 254
def is_cp_similar(iana_name_a: str, iana_name_b: str) -> bool:
"""
Determine if two code page are at least 80% similar. IANA_SUPPORTED_SIMILAR dict was generated using
the function cp_similarity.
"""
return (
iana_name_a in IANA_SUPPORTED_SIMILAR
and iana_name_b in IANA_SUPPORTED_SIMILAR[iana_name_a]
)
def set_logging_handler(
name: str = "charset_normalizer",
level: int = logging.INFO,
format_string: str = "%(asctime)s | %(levelname)s | %(message)s",
) -> None:
logger = logging.getLogger(name)
logger.setLevel(level)
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter(format_string))
logger.addHandler(handler)
def cut_sequence_chunks(
sequences: bytes,
encoding_iana: str,
offsets: range,
chunk_size: int,
bom_or_sig_available: bool,
strip_sig_or_bom: bool,
sig_payload: bytes,
is_multi_byte_decoder: bool,
decoded_payload: str | None = None,
) -> Generator[str, None, None]:
if decoded_payload and is_multi_byte_decoder is False:
for i in offsets:
chunk = decoded_payload[i : i + chunk_size]
if not chunk:
break
yield chunk
else:
for i in offsets:
chunk_end = i + chunk_size
if chunk_end > len(sequences) + 8:
continue
cut_sequence = sequences[i : i + chunk_size]
if bom_or_sig_available and strip_sig_or_bom is False:
cut_sequence = sig_payload + cut_sequence
chunk = cut_sequence.decode(
encoding_iana,
errors="ignore" if is_multi_byte_decoder else "strict",
)
# multi-byte bad cutting detector and adjustment
# not the cleanest way to perform that fix but clever enough for now.
if is_multi_byte_decoder and i > 0:
chunk_partial_size_chk: int = min(chunk_size, 16)
if (
decoded_payload
and chunk[:chunk_partial_size_chk] not in decoded_payload
):
for j in range(i, i - 4, -1):
cut_sequence = sequences[j:chunk_end]
if bom_or_sig_available and strip_sig_or_bom is False:
cut_sequence = sig_payload + cut_sequence
chunk = cut_sequence.decode(encoding_iana, errors="ignore")
if chunk[:chunk_partial_size_chk] in decoded_payload:
break
yield chunk

8
venv/lib/python3.12/site-packages/charset_normalizer/version.py Normal file
View File

@@ -0,0 +1,8 @@
"""
Expose version
"""
from __future__ import annotations
__version__ = "3.4.3"
VERSION = __version__.split(".")

1
venv/lib/python3.12/site-packages/requests-2.32.5.dist-info/INSTALLER Normal file
View File

@@ -0,0 +1 @@
pip

133
venv/lib/python3.12/site-packages/requests-2.32.5.dist-info/METADATA Normal file
View File

@@ -0,0 +1,133 @@
Metadata-Version: 2.4
Name: requests
Version: 2.32.5
Summary: Python HTTP for Humans.
Home-page: https://requests.readthedocs.io
Author: Kenneth Reitz
Author-email: me@kennethreitz.org
License: Apache-2.0
Project-URL: Documentation, https://requests.readthedocs.io
Project-URL: Source, https://github.com/psf/requests
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: Web Environment
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Classifier: Topic :: Internet :: WWW/HTTP
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: charset_normalizer<4,>=2
Requires-Dist: idna<4,>=2.5
Requires-Dist: urllib3<3,>=1.21.1
Requires-Dist: certifi>=2017.4.17
Provides-Extra: security
Provides-Extra: socks
Requires-Dist: PySocks!=1.5.7,>=1.5.6; extra == "socks"
Provides-Extra: use-chardet-on-py3
Requires-Dist: chardet<6,>=3.0.2; extra == "use-chardet-on-py3"
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: license-file
Dynamic: project-url
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary
# Requests
**Requests** is a simple, yet elegant, HTTP library.
```python
>>> import requests
>>> r = requests.get('https://httpbin.org/basic-auth/user/pass', auth=('user', 'pass'))
>>> r.status_code
200
>>> r.headers['content-type']
'application/json; charset=utf8'
>>> r.encoding
'utf-8'
>>> r.text
'{"authenticated": true, ...'
>>> r.json()
{'authenticated': True, ...}
```
Requests allows you to send HTTP/1.1 requests extremely easily. There’s no need to manually add query strings to your URLs, or to form-encode your `PUT` & `POST` data — but nowadays, just use the `json` method!
Requests is one of the most downloaded Python packages today, pulling in around `30M downloads / week`— according to GitHub, Requests is currently [depended upon](https://github.com/psf/requests/network/dependents?package_id=UGFja2FnZS01NzA4OTExNg%3D%3D) by `1,000,000+` repositories. You may certainly put your trust in this code.
[![Downloads](https://static.pepy.tech/badge/requests/month)](https://pepy.tech/project/requests)
[![Supported Versions](https://img.shields.io/pypi/pyversions/requests.svg)](https://pypi.org/project/requests)
[![Contributors](https://img.shields.io/github/contributors/psf/requests.svg)](https://github.com/psf/requests/graphs/contributors)
## Installing Requests and Supported Versions
Requests is available on PyPI:
```console
$ python -m pip install requests
```
Requests officially supports Python 3.9+.
## Supported Features & Best–Practices
Requests is ready for the demands of building robust and reliable HTTP–speaking applications, for the needs of today.
- Keep-Alive & Connection Pooling
- International Domains and URLs
- Sessions with Cookie Persistence
- Browser-style TLS/SSL Verification
- Basic & Digest Authentication
- Familiar `dict`–like Cookies
- Automatic Content Decompression and Decoding
- Multi-part File Uploads
- SOCKS Proxy Support
- Connection Timeouts
- Streaming Downloads
- Automatic honoring of `.netrc`
- Chunked HTTP Requests
## API Reference and User Guide available on [Read the Docs](https://requests.readthedocs.io)
[![Read the Docs](https://raw.githubusercontent.com/psf/requests/main/ext/ss.png)](https://requests.readthedocs.io)
## Cloning the repository
When cloning the Requests repository, you may need to add the `-c
fetch.fsck.badTimezone=ignore` flag to avoid an error about a bad commit timestamp (see
[this issue](https://github.com/psf/requests/issues/2690) for more background):
```shell
git clone -c fetch.fsck.badTimezone=ignore https://github.com/psf/requests.git
```
You can also apply this setting to your global Git config:
```shell
git config --global fetch.fsck.badTimezone ignore
```
---
[![Kenneth Reitz](https://raw.githubusercontent.com/psf/requests/main/ext/kr.png)](https://kennethreitz.org) [![Python Software Foundation](https://raw.githubusercontent.com/psf/requests/main/ext/psf.png)](https://www.python.org/psf)

43
venv/lib/python3.12/site-packages/requests-2.32.5.dist-info/RECORD Normal file
View File

@@ -0,0 +1,43 @@
requests-2.32.5.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
requests-2.32.5.dist-info/METADATA,sha256=ZbWgjagfSRVRPnYJZf8Ut1GPZbe7Pv4NqzZLvMTUDLA,4945
requests-2.32.5.dist-info/RECORD,,
requests-2.32.5.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
requests-2.32.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
requests-2.32.5.dist-info/licenses/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
requests-2.32.5.dist-info/top_level.txt,sha256=fMSVmHfb5rbGOo6xv-O_tUX6j-WyixssE-SnwcDRxNQ,9
requests/__init__.py,sha256=4xaAERmPDIBPsa2PsjpU9r06yooK-2mZKHTZAhWRWts,5072
requests/__pycache__/__init__.cpython-312.pyc,,
requests/__pycache__/__version__.cpython-312.pyc,,
requests/__pycache__/_internal_utils.cpython-312.pyc,,
requests/__pycache__/adapters.cpython-312.pyc,,
requests/__pycache__/api.cpython-312.pyc,,
requests/__pycache__/auth.cpython-312.pyc,,
requests/__pycache__/certs.cpython-312.pyc,,
requests/__pycache__/compat.cpython-312.pyc,,
requests/__pycache__/cookies.cpython-312.pyc,,
requests/__pycache__/exceptions.cpython-312.pyc,,
requests/__pycache__/help.cpython-312.pyc,,
requests/__pycache__/hooks.cpython-312.pyc,,
requests/__pycache__/models.cpython-312.pyc,,
requests/__pycache__/packages.cpython-312.pyc,,
requests/__pycache__/sessions.cpython-312.pyc,,
requests/__pycache__/status_codes.cpython-312.pyc,,
requests/__pycache__/structures.cpython-312.pyc,,
requests/__pycache__/utils.cpython-312.pyc,,
requests/__version__.py,sha256=QKDceK8K_ujqwDDc3oYrR0odOBYgKVOQQ5vFap_G_cg,435
requests/_internal_utils.py,sha256=nMQymr4hs32TqVo5AbCrmcJEhvPUh7xXlluyqwslLiQ,1495
requests/adapters.py,sha256=8nX113gbb123aUtx2ETkAN_6IsYX-M2fRoLGluTEcRk,26285
requests/api.py,sha256=_Zb9Oa7tzVIizTKwFrPjDEY9ejtm_OnSRERnADxGsQs,6449
requests/auth.py,sha256=kF75tqnLctZ9Mf_hm9TZIj4cQWnN5uxRz8oWsx5wmR0,10186
requests/certs.py,sha256=Z9Sb410Anv6jUFTyss0jFFhU6xst8ctELqfy8Ev23gw,429
requests/compat.py,sha256=J7sIjR6XoDGp5JTVzOxkK5fSoUVUa_Pjc7iRZhAWGmI,2142
requests/cookies.py,sha256=bNi-iqEj4NPZ00-ob-rHvzkvObzN3lEpgw3g6paS3Xw,18590
requests/exceptions.py,sha256=jJPS1UWATs86ShVUaLorTiJb1SaGuoNEWgICJep-VkY,4260
requests/help.py,sha256=gPX5d_H7Xd88aDABejhqGgl9B1VFRTt5BmiYvL3PzIQ,3875
requests/hooks.py,sha256=CiuysiHA39V5UfcCBXFIx83IrDpuwfN9RcTUgv28ftQ,733
requests/models.py,sha256=MjZdZ4k7tnw-1nz5PKShjmPmqyk0L6DciwnFngb_Vk4,35510
requests/packages.py,sha256=_g0gZ681UyAlKHRjH6kanbaoxx2eAb6qzcXiODyTIoc,904
requests/sessions.py,sha256=Cl1dpEnOfwrzzPbku-emepNeN4Rt_0_58Iy2x-JGTm8,30503
requests/status_codes.py,sha256=iJUAeA25baTdw-6PfD0eF4qhpINDJRJI-yaMqxs4LEI,4322
requests/structures.py,sha256=-IbmhVz06S-5aPSZuUthZ6-6D9XOjRuTXHOabY041XM,2912
requests/utils.py,sha256=WqU86rZ3wvhC-tQjWcjtH_HEKZwWB3iWCZV6SW5DEdQ,33213

0
venv/lib/python3.12/site-packages/requests-2.32.5.dist-info/REQUESTED Normal file
View File

5
venv/lib/python3.12/site-packages/requests-2.32.5.dist-info/WHEEL Normal file
View File

@@ -0,0 +1,5 @@
Wheel-Version: 1.0
Generator: setuptools (80.9.0)
Root-Is-Purelib: true
Tag: py3-none-any

175
venv/lib/python3.12/site-packages/requests-2.32.5.dist-info/licenses/LICENSE Normal file
View File

@@ -0,0 +1,175 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.

1
venv/lib/python3.12/site-packages/requests-2.32.5.dist-info/top_level.txt Normal file
View File

@@ -0,0 +1 @@
requests

184
venv/lib/python3.12/site-packages/requests/__init__.py Normal file
View File

@@ -0,0 +1,184 @@
# __
# /__) _ _ _ _ _/ _
# / ( (- (/ (/ (- _) / _)
# /
"""
Requests HTTP Library
~~~~~~~~~~~~~~~~~~~~~
Requests is an HTTP library, written in Python, for human beings.
Basic GET usage:
>>> import requests
>>> r = requests.get('https://www.python.org')
>>> r.status_code
200
>>> b'Python is a programming language' in r.content
True
... or POST:
>>> payload = dict(key1='value1', key2='value2')
>>> r = requests.post('https://httpbin.org/post', data=payload)
>>> print(r.text)
{
...
"form": {
"key1": "value1",
"key2": "value2"
},
...
}
The other HTTP methods are supported - see `requests.api`. Full documentation
is at <https://requests.readthedocs.io>.
:copyright: (c) 2017 by Kenneth Reitz.
:license: Apache 2.0, see LICENSE for more details.
"""
import warnings
import urllib3
from .exceptions import RequestsDependencyWarning
try:
from charset_normalizer import __version__ as charset_normalizer_version
except ImportError:
charset_normalizer_version = None
try:
from chardet import __version__ as chardet_version
except ImportError:
chardet_version = None
def check_compatibility(urllib3_version, chardet_version, charset_normalizer_version):
urllib3_version = urllib3_version.split(".")
assert urllib3_version != ["dev"] # Verify urllib3 isn't installed from git.
# Sometimes, urllib3 only reports its version as 16.1.
if len(urllib3_version) == 2:
urllib3_version.append("0")
# Check urllib3 for compatibility.
major, minor, patch = urllib3_version # noqa: F811
major, minor, patch = int(major), int(minor), int(patch)
# urllib3 >= 1.21.1
assert major >= 1
if major == 1:
assert minor >= 21
# Check charset_normalizer for compatibility.
if chardet_version:
major, minor, patch = chardet_version.split(".")[:3]
major, minor, patch = int(major), int(minor), int(patch)
# chardet_version >= 3.0.2, < 6.0.0
assert (3, 0, 2) <= (major, minor, patch) < (6, 0, 0)
elif charset_normalizer_version:
major, minor, patch = charset_normalizer_version.split(".")[:3]
major, minor, patch = int(major), int(minor), int(patch)
# charset_normalizer >= 2.0.0 < 4.0.0
assert (2, 0, 0) <= (major, minor, patch) < (4, 0, 0)
else:
warnings.warn(
"Unable to find acceptable character detection dependency "
"(chardet or charset_normalizer).",
RequestsDependencyWarning,
)
def _check_cryptography(cryptography_version):
# cryptography < 1.3.4
try:
cryptography_version = list(map(int, cryptography_version.split(".")))
except ValueError:
return
if cryptography_version < [1, 3, 4]:
warning = "Old version of cryptography ({}) may cause slowdown.".format(
cryptography_version
)
warnings.warn(warning, RequestsDependencyWarning)
# Check imported dependencies for compatibility.
try:
check_compatibility(
urllib3.__version__, chardet_version, charset_normalizer_version
)
except (AssertionError, ValueError):
warnings.warn(
"urllib3 ({}) or chardet ({})/charset_normalizer ({}) doesn't match a supported "
"version!".format(
urllib3.__version__, chardet_version, charset_normalizer_version
),
RequestsDependencyWarning,
)
# Attempt to enable urllib3's fallback for SNI support
# if the standard library doesn't support SNI or the
# 'ssl' library isn't available.
try:
try:
import ssl
except ImportError:
ssl = None
if not getattr(ssl, "HAS_SNI", False):
from urllib3.contrib import pyopenssl
pyopenssl.inject_into_urllib3()
# Check cryptography version
from cryptography import __version__ as cryptography_version
_check_cryptography(cryptography_version)
except ImportError:
pass
# urllib3's DependencyWarnings should be silenced.
from urllib3.exceptions import DependencyWarning
warnings.simplefilter("ignore", DependencyWarning)
# Set default logging handler to avoid "No handler found" warnings.
import logging
from logging import NullHandler
from . import packages, utils
from .__version__ import (
__author__,
__author_email__,
__build__,
__cake__,
__copyright__,
__description__,
__license__,
__title__,
__url__,
__version__,
)
from .api import delete, get, head, options, patch, post, put, request
from .exceptions import (
ConnectionError,
ConnectTimeout,
FileModeWarning,
HTTPError,
JSONDecodeError,
ReadTimeout,
RequestException,
Timeout,
TooManyRedirects,
URLRequired,
)
from .models import PreparedRequest, Request, Response
from .sessions import Session, session
from .status_codes import codes
logging.getLogger(__name__).addHandler(NullHandler())
# FileModeWarnings go off per the default.
warnings.simplefilter("default", FileModeWarning, append=True)

14
venv/lib/python3.12/site-packages/requests/__version__.py Normal file
View File

@@ -0,0 +1,14 @@
# .-. .-. .-. . . .-. .-. .-. .-.
# |( |- |.| | | |- `-. | `-.
# ' ' `-' `-`.`-' `-' `-' ' `-'
__title__ = "requests"
__description__ = "Python HTTP for Humans."
__url__ = "https://requests.readthedocs.io"
__version__ = "2.32.5"
__build__ = 0x023205
__author__ = "Kenneth Reitz"
__author_email__ = "me@kennethreitz.org"
__license__ = "Apache-2.0"
__copyright__ = "Copyright Kenneth Reitz"
__cake__ = "\u2728 \U0001f370 \u2728"

50
venv/lib/python3.12/site-packages/requests/_internal_utils.py Normal file
View File

@@ -0,0 +1,50 @@
"""
requests._internal_utils
~~~~~~~~~~~~~~
Provides utility functions that are consumed internally by Requests
which depend on extremely few external helpers (such as compat)
"""
import re
from .compat import builtin_str
_VALID_HEADER_NAME_RE_BYTE = re.compile(rb"^[^:\s][^:\r\n]*$")
_VALID_HEADER_NAME_RE_STR = re.compile(r"^[^:\s][^:\r\n]*$")
_VALID_HEADER_VALUE_RE_BYTE = re.compile(rb"^\S[^\r\n]*$|^$")
_VALID_HEADER_VALUE_RE_STR = re.compile(r"^\S[^\r\n]*$|^$")
_HEADER_VALIDATORS_STR = (_VALID_HEADER_NAME_RE_STR, _VALID_HEADER_VALUE_RE_STR)
_HEADER_VALIDATORS_BYTE = (_VALID_HEADER_NAME_RE_BYTE, _VALID_HEADER_VALUE_RE_BYTE)
HEADER_VALIDATORS = {
bytes: _HEADER_VALIDATORS_BYTE,
str: _HEADER_VALIDATORS_STR,
}
def to_native_string(string, encoding="ascii"):
"""Given a string object, regardless of type, returns a representation of
that string in the native string type, encoding and decoding where
necessary. This assumes ASCII unless told otherwise.
"""
if isinstance(string, builtin_str):
out = string
else:
out = string.decode(encoding)
return out
def unicode_is_ascii(u_string):
"""Determine if unicode string only contains ASCII characters.
:param str u_string: unicode string to check. Must be unicode
and not Python 2 `str`.
:rtype: bool
"""
assert isinstance(u_string, str)
try:
u_string.encode("ascii")
return True
except UnicodeEncodeError:
return False

696
venv/lib/python3.12/site-packages/requests/adapters.py Normal file
View File

@@ -0,0 +1,696 @@
"""
requests.adapters
~~~~~~~~~~~~~~~~~
This module contains the transport adapters that Requests uses to define
and maintain connections.
"""
import os.path
import socket # noqa: F401
import typing
import warnings
from urllib3.exceptions import ClosedPoolError, ConnectTimeoutError
from urllib3.exceptions import HTTPError as _HTTPError
from urllib3.exceptions import InvalidHeader as _InvalidHeader
from urllib3.exceptions import (
LocationValueError,
MaxRetryError,
NewConnectionError,
ProtocolError,
)
from urllib3.exceptions import ProxyError as _ProxyError
from urllib3.exceptions import ReadTimeoutError, ResponseError
from urllib3.exceptions import SSLError as _SSLError
from urllib3.poolmanager import PoolManager, proxy_from_url
from urllib3.util import Timeout as TimeoutSauce
from urllib3.util import parse_url
from urllib3.util.retry import Retry
from .auth import _basic_auth_str
from .compat import basestring, urlparse
from .cookies import extract_cookies_to_jar
from .exceptions import (
ConnectionError,
ConnectTimeout,
InvalidHeader,
InvalidProxyURL,
InvalidSchema,
InvalidURL,
ProxyError,
ReadTimeout,
RetryError,
SSLError,
)
from .models import Response
from .structures import CaseInsensitiveDict
from .utils import (
DEFAULT_CA_BUNDLE_PATH,
extract_zipped_paths,
get_auth_from_url,
get_encoding_from_headers,
prepend_scheme_if_needed,
select_proxy,
urldefragauth,
)
try:
from urllib3.contrib.socks import SOCKSProxyManager
except ImportError:
def SOCKSProxyManager(*args, **kwargs):
raise InvalidSchema("Missing dependencies for SOCKS support.")
if typing.TYPE_CHECKING:
from .models import PreparedRequest
DEFAULT_POOLBLOCK = False
DEFAULT_POOLSIZE = 10
DEFAULT_RETRIES = 0
DEFAULT_POOL_TIMEOUT = None
def _urllib3_request_context(
request: "PreparedRequest",
verify: "bool | str | None",
client_cert: "typing.Tuple[str, str] | str | None",
poolmanager: "PoolManager",
) -> "(typing.Dict[str, typing.Any], typing.Dict[str, typing.Any])":
host_params = {}
pool_kwargs = {}
parsed_request_url = urlparse(request.url)
scheme = parsed_request_url.scheme.lower()
port = parsed_request_url.port
cert_reqs = "CERT_REQUIRED"
if verify is False:
cert_reqs = "CERT_NONE"
elif isinstance(verify, str):
if not os.path.isdir(verify):
pool_kwargs["ca_certs"] = verify
else:
pool_kwargs["ca_cert_dir"] = verify
pool_kwargs["cert_reqs"] = cert_reqs
if client_cert is not None:
if isinstance(client_cert, tuple) and len(client_cert) == 2:
pool_kwargs["cert_file"] = client_cert[0]
pool_kwargs["key_file"] = client_cert[1]
else:
# According to our docs, we allow users to specify just the client
# cert path
pool_kwargs["cert_file"] = client_cert
host_params = {
"scheme": scheme,
"host": parsed_request_url.hostname,
"port": port,
}
return host_params, pool_kwargs
class BaseAdapter:
"""The Base Transport Adapter"""
def __init__(self):
super().__init__()
def send(
self, request, stream=False, timeout=None, verify=True, cert=None, proxies=None
):
"""Sends PreparedRequest object. Returns Response object.
:param request: The :class:`PreparedRequest <PreparedRequest>` being sent.
:param stream: (optional) Whether to stream the request content.
:param timeout: (optional) How long to wait for the server to send
data before giving up, as a float, or a :ref:`(connect timeout,
read timeout) <timeouts>` tuple.
:type timeout: float or tuple
:param verify: (optional) Either a boolean, in which case it controls whether we verify
the server's TLS certificate, or a string, in which case it must be a path
to a CA bundle to use
:param cert: (optional) Any user-provided SSL certificate to be trusted.
:param proxies: (optional) The proxies dictionary to apply to the request.
"""
raise NotImplementedError
def close(self):
"""Cleans up adapter specific items."""
raise NotImplementedError
class HTTPAdapter(BaseAdapter):
"""The built-in HTTP Adapter for urllib3.
Provides a general-case interface for Requests sessions to contact HTTP and
HTTPS urls by implementing the Transport Adapter interface. This class will
usually be created by the :class:`Session <Session>` class under the
covers.
:param pool_connections: The number of urllib3 connection pools to cache.
:param pool_maxsize: The maximum number of connections to save in the pool.
:param max_retries: The maximum number of retries each connection
should attempt. Note, this applies only to failed DNS lookups, socket
connections and connection timeouts, never to requests where data has
made it to the server. By default, Requests does not retry failed
connections. If you need granular control over the conditions under
which we retry a request, import urllib3's ``Retry`` class and pass
that instead.
:param pool_block: Whether the connection pool should block for connections.
Usage::
>>> import requests
>>> s = requests.Session()
>>> a = requests.adapters.HTTPAdapter(max_retries=3)
>>> s.mount('http://', a)
"""
__attrs__ = [
"max_retries",
"config",
"_pool_connections",
"_pool_maxsize",
"_pool_block",
]
def __init__(
self,
pool_connections=DEFAULT_POOLSIZE,
pool_maxsize=DEFAULT_POOLSIZE,
max_retries=DEFAULT_RETRIES,
pool_block=DEFAULT_POOLBLOCK,
):
if max_retries == DEFAULT_RETRIES:
self.max_retries = Retry(0, read=False)
else:
self.max_retries = Retry.from_int(max_retries)
self.config = {}
self.proxy_manager = {}
super().__init__()
self._pool_connections = pool_connections
self._pool_maxsize = pool_maxsize
self._pool_block = pool_block
self.init_poolmanager(pool_connections, pool_maxsize, block=pool_block)
def __getstate__(self):
return {attr: getattr(self, attr, None) for attr in self.__attrs__}
def __setstate__(self, state):
# Can't handle by adding 'proxy_manager' to self.__attrs__ because
# self.poolmanager uses a lambda function, which isn't pickleable.
self.proxy_manager = {}
self.config = {}
for attr, value in state.items():
setattr(self, attr, value)
self.init_poolmanager(
self._pool_connections, self._pool_maxsize, block=self._pool_block
)
def init_poolmanager(
self, connections, maxsize, block=DEFAULT_POOLBLOCK, **pool_kwargs
):
"""Initializes a urllib3 PoolManager.
This method should not be called from user code, and is only
exposed for use when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param connections: The number of urllib3 connection pools to cache.
:param maxsize: The maximum number of connections to save in the pool.
:param block: Block when no free connections are available.
:param pool_kwargs: Extra keyword arguments used to initialize the Pool Manager.
"""
# save these values for pickling
self._pool_connections = connections
self._pool_maxsize = maxsize
self._pool_block = block
self.poolmanager = PoolManager(
num_pools=connections,
maxsize=maxsize,
block=block,
**pool_kwargs,
)
def proxy_manager_for(self, proxy, **proxy_kwargs):
"""Return urllib3 ProxyManager for the given proxy.
This method should not be called from user code, and is only
exposed for use when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param proxy: The proxy to return a urllib3 ProxyManager for.
:param proxy_kwargs: Extra keyword arguments used to configure the Proxy Manager.
:returns: ProxyManager
:rtype: urllib3.ProxyManager
"""
if proxy in self.proxy_manager:
manager = self.proxy_manager[proxy]
elif proxy.lower().startswith("socks"):
username, password = get_auth_from_url(proxy)
manager = self.proxy_manager[proxy] = SOCKSProxyManager(
proxy,
username=username,
password=password,
num_pools=self._pool_connections,
maxsize=self._pool_maxsize,
block=self._pool_block,
**proxy_kwargs,
)
else:
proxy_headers = self.proxy_headers(proxy)
manager = self.proxy_manager[proxy] = proxy_from_url(
proxy,
proxy_headers=proxy_headers,
num_pools=self._pool_connections,
maxsize=self._pool_maxsize,
block=self._pool_block,
**proxy_kwargs,
)
return manager
def cert_verify(self, conn, url, verify, cert):
"""Verify a SSL certificate. This method should not be called from user
code, and is only exposed for use when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param conn: The urllib3 connection object associated with the cert.
:param url: The requested URL.
:param verify: Either a boolean, in which case it controls whether we verify
the server's TLS certificate, or a string, in which case it must be a path
to a CA bundle to use
:param cert: The SSL certificate to verify.
"""
if url.lower().startswith("https") and verify:
cert_loc = None
# Allow self-specified cert location.
if verify is not True:
cert_loc = verify
if not cert_loc:
cert_loc = extract_zipped_paths(DEFAULT_CA_BUNDLE_PATH)
if not cert_loc or not os.path.exists(cert_loc):
raise OSError(
f"Could not find a suitable TLS CA certificate bundle, "
f"invalid path: {cert_loc}"
)
conn.cert_reqs = "CERT_REQUIRED"
if not os.path.isdir(cert_loc):
conn.ca_certs = cert_loc
else:
conn.ca_cert_dir = cert_loc
else:
conn.cert_reqs = "CERT_NONE"
conn.ca_certs = None
conn.ca_cert_dir = None
if cert:
if not isinstance(cert, basestring):
conn.cert_file = cert[0]
conn.key_file = cert[1]
else:
conn.cert_file = cert
conn.key_file = None
if conn.cert_file and not os.path.exists(conn.cert_file):
raise OSError(
f"Could not find the TLS certificate file, "
f"invalid path: {conn.cert_file}"
)
if conn.key_file and not os.path.exists(conn.key_file):
raise OSError(
f"Could not find the TLS key file, invalid path: {conn.key_file}"
)
def build_response(self, req, resp):
"""Builds a :class:`Response <requests.Response>` object from a urllib3
response. This should not be called from user code, and is only exposed
for use when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`
:param req: The :class:`PreparedRequest <PreparedRequest>` used to generate the response.
:param resp: The urllib3 response object.
:rtype: requests.Response
"""
response = Response()
# Fallback to None if there's no status_code, for whatever reason.
response.status_code = getattr(resp, "status", None)
# Make headers case-insensitive.
response.headers = CaseInsensitiveDict(getattr(resp, "headers", {}))
# Set encoding.
response.encoding = get_encoding_from_headers(response.headers)
response.raw = resp
response.reason = response.raw.reason
if isinstance(req.url, bytes):
response.url = req.url.decode("utf-8")
else:
response.url = req.url
# Add new cookies from the server.
extract_cookies_to_jar(response.cookies, req, resp)
# Give the Response some context.
response.request = req
response.connection = self
return response
def build_connection_pool_key_attributes(self, request, verify, cert=None):
"""Build the PoolKey attributes used by urllib3 to return a connection.
This looks at the PreparedRequest, the user-specified verify value,
and the value of the cert parameter to determine what PoolKey values
to use to select a connection from a given urllib3 Connection Pool.
The SSL related pool key arguments are not consistently set. As of
this writing, use the following to determine what keys may be in that
dictionary:
* If ``verify`` is ``True``, ``"ssl_context"`` will be set and will be the
default Requests SSL Context
* If ``verify`` is ``False``, ``"ssl_context"`` will not be set but
``"cert_reqs"`` will be set
* If ``verify`` is a string, (i.e., it is a user-specified trust bundle)
``"ca_certs"`` will be set if the string is not a directory recognized
by :py:func:`os.path.isdir`, otherwise ``"ca_cert_dir"`` will be
set.
* If ``"cert"`` is specified, ``"cert_file"`` will always be set. If
``"cert"`` is a tuple with a second item, ``"key_file"`` will also
be present
To override these settings, one may subclass this class, call this
method and use the above logic to change parameters as desired. For
example, if one wishes to use a custom :py:class:`ssl.SSLContext` one
must both set ``"ssl_context"`` and based on what else they require,
alter the other keys to ensure the desired behaviour.
:param request:
The PreparedReqest being sent over the connection.
:type request:
:class:`~requests.models.PreparedRequest`
:param verify:
Either a boolean, in which case it controls whether
we verify the server's TLS certificate, or a string, in which case it
must be a path to a CA bundle to use.
:param cert:
(optional) Any user-provided SSL certificate for client
authentication (a.k.a., mTLS). This may be a string (i.e., just
the path to a file which holds both certificate and key) or a
tuple of length 2 with the certificate file path and key file
path.
:returns:
A tuple of two dictionaries. The first is the "host parameters"
portion of the Pool Key including scheme, hostname, and port. The
second is a dictionary of SSLContext related parameters.
"""
return _urllib3_request_context(request, verify, cert, self.poolmanager)
def get_connection_with_tls_context(self, request, verify, proxies=None, cert=None):
"""Returns a urllib3 connection for the given request and TLS settings.
This should not be called from user code, and is only exposed for use
when subclassing the :class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param request:
The :class:`PreparedRequest <PreparedRequest>` object to be sent
over the connection.
:param verify:
Either a boolean, in which case it controls whether we verify the
server's TLS certificate, or a string, in which case it must be a
path to a CA bundle to use.
:param proxies:
(optional) The proxies dictionary to apply to the request.
:param cert:
(optional) Any user-provided SSL certificate to be used for client
authentication (a.k.a., mTLS).
:rtype:
urllib3.ConnectionPool
"""
proxy = select_proxy(request.url, proxies)
try:
host_params, pool_kwargs = self.build_connection_pool_key_attributes(
request,
verify,
cert,
)
except ValueError as e:
raise InvalidURL(e, request=request)
if proxy:
proxy = prepend_scheme_if_needed(proxy, "http")
proxy_url = parse_url(proxy)
if not proxy_url.host:
raise InvalidProxyURL(
"Please check proxy URL. It is malformed "
"and could be missing the host."
)
proxy_manager = self.proxy_manager_for(proxy)
conn = proxy_manager.connection_from_host(
**host_params, pool_kwargs=pool_kwargs
)
else:
# Only scheme should be lower case
conn = self.poolmanager.connection_from_host(
**host_params, pool_kwargs=pool_kwargs
)
return conn
def get_connection(self, url, proxies=None):
"""DEPRECATED: Users should move to `get_connection_with_tls_context`
for all subclasses of HTTPAdapter using Requests>=2.32.2.
Returns a urllib3 connection for the given URL. This should not be
called from user code, and is only exposed for use when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param url: The URL to connect to.
:param proxies: (optional) A Requests-style dictionary of proxies used on this request.
:rtype: urllib3.ConnectionPool
"""
warnings.warn(
(
"`get_connection` has been deprecated in favor of "
"`get_connection_with_tls_context`. Custom HTTPAdapter subclasses "
"will need to migrate for Requests>=2.32.2. Please see "
"https://github.com/psf/requests/pull/6710 for more details."
),
DeprecationWarning,
)
proxy = select_proxy(url, proxies)
if proxy:
proxy = prepend_scheme_if_needed(proxy, "http")
proxy_url = parse_url(proxy)
if not proxy_url.host:
raise InvalidProxyURL(
"Please check proxy URL. It is malformed "
"and could be missing the host."
)
proxy_manager = self.proxy_manager_for(proxy)
conn = proxy_manager.connection_from_url(url)
else:
# Only scheme should be lower case
parsed = urlparse(url)
url = parsed.geturl()
conn = self.poolmanager.connection_from_url(url)
return conn
def close(self):
"""Disposes of any internal state.
Currently, this closes the PoolManager and any active ProxyManager,
which closes any pooled connections.
"""
self.poolmanager.clear()
for proxy in self.proxy_manager.values():
proxy.clear()
def request_url(self, request, proxies):
"""Obtain the url to use when making the final request.
If the message is being sent through a HTTP proxy, the full URL has to
be used. Otherwise, we should only use the path portion of the URL.
This should not be called from user code, and is only exposed for use
when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param request: The :class:`PreparedRequest <PreparedRequest>` being sent.
:param proxies: A dictionary of schemes or schemes and hosts to proxy URLs.
:rtype: str
"""
proxy = select_proxy(request.url, proxies)
scheme = urlparse(request.url).scheme
is_proxied_http_request = proxy and scheme != "https"
using_socks_proxy = False
if proxy:
proxy_scheme = urlparse(proxy).scheme.lower()
using_socks_proxy = proxy_scheme.startswith("socks")
url = request.path_url
if url.startswith("//"): # Don't confuse urllib3
url = f"/{url.lstrip('/')}"
if is_proxied_http_request and not using_socks_proxy:
url = urldefragauth(request.url)
return url
def add_headers(self, request, **kwargs):
"""Add any headers needed by the connection. As of v2.0 this does
nothing by default, but is left for overriding by users that subclass
the :class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
This should not be called from user code, and is only exposed for use
when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param request: The :class:`PreparedRequest <PreparedRequest>` to add headers to.
:param kwargs: The keyword arguments from the call to send().
"""
pass
def proxy_headers(self, proxy):
"""Returns a dictionary of the headers to add to any request sent
through a proxy. This works with urllib3 magic to ensure that they are
correctly sent to the proxy, rather than in a tunnelled request if
CONNECT is being used.
This should not be called from user code, and is only exposed for use
when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param proxy: The url of the proxy being used for this request.
:rtype: dict
"""
headers = {}
username, password = get_auth_from_url(proxy)
if username:
headers["Proxy-Authorization"] = _basic_auth_str(username, password)
return headers
def send(
self, request, stream=False, timeout=None, verify=True, cert=None, proxies=None
):
"""Sends PreparedRequest object. Returns Response object.
:param request: The :class:`PreparedRequest <PreparedRequest>` being sent.
:param stream: (optional) Whether to stream the request content.
:param timeout: (optional) How long to wait for the server to send
data before giving up, as a float, or a :ref:`(connect timeout,
read timeout) <timeouts>` tuple.
:type timeout: float or tuple or urllib3 Timeout object
:param verify: (optional) Either a boolean, in which case it controls whether
we verify the server's TLS certificate, or a string, in which case it
must be a path to a CA bundle to use
:param cert: (optional) Any user-provided SSL certificate to be trusted.
:param proxies: (optional) The proxies dictionary to apply to the request.
:rtype: requests.Response
"""
try:
conn = self.get_connection_with_tls_context(
request, verify, proxies=proxies, cert=cert
)
except LocationValueError as e:
raise InvalidURL(e, request=request)
self.cert_verify(conn, request.url, verify, cert)
url = self.request_url(request, proxies)
self.add_headers(
request,
stream=stream,
timeout=timeout,
verify=verify,
cert=cert,
proxies=proxies,
)
chunked = not (request.body is None or "Content-Length" in request.headers)
if isinstance(timeout, tuple):
try:
connect, read = timeout
timeout = TimeoutSauce(connect=connect, read=read)
except ValueError:
raise ValueError(
f"Invalid timeout {timeout}. Pass a (connect, read) timeout tuple, "
f"or a single float to set both timeouts to the same value."
)
elif isinstance(timeout, TimeoutSauce):
pass
else:
timeout = TimeoutSauce(connect=timeout, read=timeout)
try:
resp = conn.urlopen(
method=request.method,
url=url,
body=request.body,
headers=request.headers,
redirect=False,
assert_same_host=False,
preload_content=False,
decode_content=False,
retries=self.max_retries,
timeout=timeout,
chunked=chunked,
)
except (ProtocolError, OSError) as err:
raise ConnectionError(err, request=request)
except MaxRetryError as e:
if isinstance(e.reason, ConnectTimeoutError):
# TODO: Remove this in 3.0.0: see #2811
if not isinstance(e.reason, NewConnectionError):
raise ConnectTimeout(e, request=request)
if isinstance(e.reason, ResponseError):
raise RetryError(e, request=request)
if isinstance(e.reason, _ProxyError):
raise ProxyError(e, request=request)
if isinstance(e.reason, _SSLError):
# This branch is for urllib3 v1.22 and later.
raise SSLError(e, request=request)
raise ConnectionError(e, request=request)
except ClosedPoolError as e:
raise ConnectionError(e, request=request)
except _ProxyError as e:
raise ProxyError(e)
except (_SSLError, _HTTPError) as e:
if isinstance(e, _SSLError):
# This branch is for urllib3 versions earlier than v1.22
raise SSLError(e, request=request)
elif isinstance(e, ReadTimeoutError):
raise ReadTimeout(e, request=request)
elif isinstance(e, _InvalidHeader):
raise InvalidHeader(e, request=request)
else:
raise
return self.build_response(request, resp)

157
venv/lib/python3.12/site-packages/requests/api.py Normal file
View File

@@ -0,0 +1,157 @@
"""
requests.api
~~~~~~~~~~~~
This module implements the Requests API.
:copyright: (c) 2012 by Kenneth Reitz.
:license: Apache2, see LICENSE for more details.
"""
from . import sessions
def request(method, url, **kwargs):
"""Constructs and sends a :class:`Request <Request>`.
:param method: method for the new :class:`Request` object: ``GET``, ``OPTIONS``, ``HEAD``, ``POST``, ``PUT``, ``PATCH``, or ``DELETE``.
:param url: URL for the new :class:`Request` object.
:param params: (optional) Dictionary, list of tuples or bytes to send
in the query string for the :class:`Request`.
:param data: (optional) Dictionary, list of tuples, bytes, or file-like
object to send in the body of the :class:`Request`.
:param json: (optional) A JSON serializable Python object to send in the body of the :class:`Request`.
:param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`.
:param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`.
:param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': file-tuple}``) for multipart encoding upload.
``file-tuple`` can be a 2-tuple ``('filename', fileobj)``, 3-tuple ``('filename', fileobj, 'content_type')``
or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content_type'`` is a string
defining the content type of the given file and ``custom_headers`` a dict-like object containing additional headers
to add for the file.
:param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth.
:param timeout: (optional) How many seconds to wait for the server to send data
before giving up, as a float, or a :ref:`(connect timeout, read
timeout) <timeouts>` tuple.
:type timeout: float or tuple
:param allow_redirects: (optional) Boolean. Enable/disable GET/OPTIONS/POST/PUT/PATCH/DELETE/HEAD redirection. Defaults to ``True``.
:type allow_redirects: bool
:param proxies: (optional) Dictionary mapping protocol to the URL of the proxy.
:param verify: (optional) Either a boolean, in which case it controls whether we verify
the server's TLS certificate, or a string, in which case it must be a path
to a CA bundle to use. Defaults to ``True``.
:param stream: (optional) if ``False``, the response content will be immediately downloaded.
:param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair.
:return: :class:`Response <Response>` object
:rtype: requests.Response
Usage::
>>> import requests
>>> req = requests.request('GET', 'https://httpbin.org/get')
>>> req
<Response [200]>
"""
# By using the 'with' statement we are sure the session is closed, thus we
# avoid leaving sockets open which can trigger a ResourceWarning in some
# cases, and look like a memory leak in others.
with sessions.Session() as session:
return session.request(method=method, url=url, **kwargs)
def get(url, params=None, **kwargs):
r"""Sends a GET request.
:param url: URL for the new :class:`Request` object.
:param params: (optional) Dictionary, list of tuples or bytes to send
in the query string for the :class:`Request`.
:param \*\*kwargs: Optional arguments that ``request`` takes.
:return: :class:`Response <Response>` object
:rtype: requests.Response
"""
return request("get", url, params=params, **kwargs)
def options(url, **kwargs):
r"""Sends an OPTIONS request.
:param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes.
:return: :class:`Response <Response>` object
:rtype: requests.Response
"""
return request("options", url, **kwargs)
def head(url, **kwargs):
r"""Sends a HEAD request.
:param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes. If
`allow_redirects` is not provided, it will be set to `False` (as
opposed to the default :meth:`request` behavior).
:return: :class:`Response <Response>` object
:rtype: requests.Response
"""
kwargs.setdefault("allow_redirects", False)
return request("head", url, **kwargs)
def post(url, data=None, json=None, **kwargs):
r"""Sends a POST request.
:param url: URL for the new :class:`Request` object.
:param data: (optional) Dictionary, list of tuples, bytes, or file-like
object to send in the body of the :class:`Request`.
:param json: (optional) A JSON serializable Python object to send in the body of the :class:`Request`.
:param \*\*kwargs: Optional arguments that ``request`` takes.
:return: :class:`Response <Response>` object
:rtype: requests.Response
"""
return request("post", url, data=data, json=json, **kwargs)
def put(url, data=None, **kwargs):
r"""Sends a PUT request.
:param url: URL for the new :class:`Request` object.
:param data: (optional) Dictionary, list of tuples, bytes, or file-like
object to send in the body of the :class:`Request`.
:param json: (optional) A JSON serializable Python object to send in the body of the :class:`Request`.
:param \*\*kwargs: Optional arguments that ``request`` takes.
:return: :class:`Response <Response>` object
:rtype: requests.Response
"""
return request("put", url, data=data, **kwargs)
def patch(url, data=None, **kwargs):
r"""Sends a PATCH request.
:param url: URL for the new :class:`Request` object.
:param data: (optional) Dictionary, list of tuples, bytes, or file-like
object to send in the body of the :class:`Request`.
:param json: (optional) A JSON serializable Python object to send in the body of the :class:`Request`.
:param \*\*kwargs: Optional arguments that ``request`` takes.
:return: :class:`Response <Response>` object
:rtype: requests.Response
"""
return request("patch", url, data=data, **kwargs)
def delete(url, **kwargs):
r"""Sends a DELETE request.
:param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes.
:return: :class:`Response <Response>` object
:rtype: requests.Response
"""
return request("delete", url, **kwargs)

314
venv/lib/python3.12/site-packages/requests/auth.py Normal file
View File

@@ -0,0 +1,314 @@
"""
requests.auth
~~~~~~~~~~~~~
This module contains the authentication handlers for Requests.
"""
import hashlib
import os
import re
import threading
import time
import warnings
from base64 import b64encode
from ._internal_utils import to_native_string
from .compat import basestring, str, urlparse
from .cookies import extract_cookies_to_jar
from .utils import parse_dict_header
CONTENT_TYPE_FORM_URLENCODED = "application/x-www-form-urlencoded"
CONTENT_TYPE_MULTI_PART = "multipart/form-data"
def _basic_auth_str(username, password):
"""Returns a Basic Auth string."""
# "I want us to put a big-ol' comment on top of it that
# says that this behaviour is dumb but we need to preserve
# it because people are relying on it."
# - Lukasa
#
# These are here solely to maintain backwards compatibility
# for things like ints. This will be removed in 3.0.0.
if not isinstance(username, basestring):
warnings.warn(
"Non-string usernames will no longer be supported in Requests "
"3.0.0. Please convert the object you've passed in ({!r}) to "
"a string or bytes object in the near future to avoid "
"problems.".format(username),
category=DeprecationWarning,
)
username = str(username)
if not isinstance(password, basestring):
warnings.warn(
"Non-string passwords will no longer be supported in Requests "
"3.0.0. Please convert the object you've passed in ({!r}) to "
"a string or bytes object in the near future to avoid "
"problems.".format(type(password)),
category=DeprecationWarning,
)
password = str(password)
# -- End Removal --
if isinstance(username, str):
username = username.encode("latin1")
if isinstance(password, str):
password = password.encode("latin1")
authstr = "Basic " + to_native_string(
b64encode(b":".join((username, password))).strip()
)
return authstr
class AuthBase:
"""Base class that all auth implementations derive from"""
def __call__(self, r):
raise NotImplementedError("Auth hooks must be callable.")
class HTTPBasicAuth(AuthBase):
"""Attaches HTTP Basic Authentication to the given Request object."""
def __init__(self, username, password):
self.username = username
self.password = password
def __eq__(self, other):
return all(
[
self.username == getattr(other, "username", None),
self.password == getattr(other, "password", None),
]
)
def __ne__(self, other):
return not self == other
def __call__(self, r):
r.headers["Authorization"] = _basic_auth_str(self.username, self.password)
return r
class HTTPProxyAuth(HTTPBasicAuth):
"""Attaches HTTP Proxy Authentication to a given Request object."""
def __call__(self, r):
r.headers["Proxy-Authorization"] = _basic_auth_str(self.username, self.password)
return r
class HTTPDigestAuth(AuthBase):
"""Attaches HTTP Digest Authentication to the given Request object."""
def __init__(self, username, password):
self.username = username
self.password = password
# Keep state in per-thread local storage
self._thread_local = threading.local()
def init_per_thread_state(self):
# Ensure state is initialized just once per-thread
if not hasattr(self._thread_local, "init"):
self._thread_local.init = True
self._thread_local.last_nonce = ""
self._thread_local.nonce_count = 0
self._thread_local.chal = {}
self._thread_local.pos = None
self._thread_local.num_401_calls = None
def build_digest_header(self, method, url):
"""
:rtype: str
"""
realm = self._thread_local.chal["realm"]
nonce = self._thread_local.chal["nonce"]
qop = self._thread_local.chal.get("qop")
algorithm = self._thread_local.chal.get("algorithm")
opaque = self._thread_local.chal.get("opaque")
hash_utf8 = None
if algorithm is None:
_algorithm = "MD5"
else:
_algorithm = algorithm.upper()
# lambdas assume digest modules are imported at the top level
if _algorithm == "MD5" or _algorithm == "MD5-SESS":
def md5_utf8(x):
if isinstance(x, str):
x = x.encode("utf-8")
return hashlib.md5(x).hexdigest()
hash_utf8 = md5_utf8
elif _algorithm == "SHA":
def sha_utf8(x):
if isinstance(x, str):
x = x.encode("utf-8")
return hashlib.sha1(x).hexdigest()
hash_utf8 = sha_utf8
elif _algorithm == "SHA-256":
def sha256_utf8(x):
if isinstance(x, str):
x = x.encode("utf-8")
return hashlib.sha256(x).hexdigest()
hash_utf8 = sha256_utf8
elif _algorithm == "SHA-512":
def sha512_utf8(x):
if isinstance(x, str):
x = x.encode("utf-8")
return hashlib.sha512(x).hexdigest()
hash_utf8 = sha512_utf8
KD = lambda s, d: hash_utf8(f"{s}:{d}") # noqa:E731
if hash_utf8 is None:
return None
# XXX not implemented yet
entdig = None
p_parsed = urlparse(url)
#: path is request-uri defined in RFC 2616 which should not be empty
path = p_parsed.path or "/"
if p_parsed.query:
path += f"?{p_parsed.query}"
A1 = f"{self.username}:{realm}:{self.password}"
A2 = f"{method}:{path}"
HA1 = hash_utf8(A1)
HA2 = hash_utf8(A2)
if nonce == self._thread_local.last_nonce:
self._thread_local.nonce_count += 1
else:
self._thread_local.nonce_count = 1
ncvalue = f"{self._thread_local.nonce_count:08x}"
s = str(self._thread_local.nonce_count).encode("utf-8")
s += nonce.encode("utf-8")
s += time.ctime().encode("utf-8")
s += os.urandom(8)
cnonce = hashlib.sha1(s).hexdigest()[:16]
if _algorithm == "MD5-SESS":
HA1 = hash_utf8(f"{HA1}:{nonce}:{cnonce}")
if not qop:
respdig = KD(HA1, f"{nonce}:{HA2}")
elif qop == "auth" or "auth" in qop.split(","):
noncebit = f"{nonce}:{ncvalue}:{cnonce}:auth:{HA2}"
respdig = KD(HA1, noncebit)
else:
# XXX handle auth-int.
return None
self._thread_local.last_nonce = nonce
# XXX should the partial digests be encoded too?
base = (
f'username="{self.username}", realm="{realm}", nonce="{nonce}", '
f'uri="{path}", response="{respdig}"'
)
if opaque:
base += f', opaque="{opaque}"'
if algorithm:
base += f', algorithm="{algorithm}"'
if entdig:
base += f', digest="{entdig}"'
if qop:
base += f', qop="auth", nc={ncvalue}, cnonce="{cnonce}"'
return f"Digest {base}"
def handle_redirect(self, r, **kwargs):
"""Reset num_401_calls counter on redirects."""
if r.is_redirect:
self._thread_local.num_401_calls = 1
def handle_401(self, r, **kwargs):
"""
Takes the given response and tries digest-auth, if needed.
:rtype: requests.Response
"""
# If response is not 4xx, do not auth
# See https://github.com/psf/requests/issues/3772
if not 400 <= r.status_code < 500:
self._thread_local.num_401_calls = 1
return r
if self._thread_local.pos is not None:
# Rewind the file position indicator of the body to where
# it was to resend the request.
r.request.body.seek(self._thread_local.pos)
s_auth = r.headers.get("www-authenticate", "")
if "digest" in s_auth.lower() and self._thread_local.num_401_calls < 2:
self._thread_local.num_401_calls += 1
pat = re.compile(r"digest ", flags=re.IGNORECASE)
self._thread_local.chal = parse_dict_header(pat.sub("", s_auth, count=1))
# Consume content and release the original connection
# to allow our new request to reuse the same one.
r.content
r.close()
prep = r.request.copy()
extract_cookies_to_jar(prep._cookies, r.request, r.raw)
prep.prepare_cookies(prep._cookies)
prep.headers["Authorization"] = self.build_digest_header(
prep.method, prep.url
)
_r = r.connection.send(prep, **kwargs)
_r.history.append(r)
_r.request = prep
return _r
self._thread_local.num_401_calls = 1
return r
def __call__(self, r):
# Initialize per-thread state, if needed
self.init_per_thread_state()
# If we have a saved nonce, skip the 401
if self._thread_local.last_nonce:
r.headers["Authorization"] = self.build_digest_header(r.method, r.url)
try:
self._thread_local.pos = r.body.tell()
except AttributeError:
# In the case of HTTPDigestAuth being reused and the body of
# the previous request was a file-like object, pos has the
# file position of the previous body. Ensure it's set to
# None.
self._thread_local.pos = None
r.register_hook("response", self.handle_401)
r.register_hook("response", self.handle_redirect)
self._thread_local.num_401_calls = 1
return r
def __eq__(self, other):
return all(
[
self.username == getattr(other, "username", None),
self.password == getattr(other, "password", None),
]
)
def __ne__(self, other):
return not self == other

17
venv/lib/python3.12/site-packages/requests/certs.py Normal file
View File

@@ -0,0 +1,17 @@
#!/usr/bin/env python
"""
requests.certs
~~~~~~~~~~~~~~
This module returns the preferred default CA certificate bundle. There is
only one — the one from the certifi package.
If you are packaging Requests, e.g., for a Linux distribution or a managed
environment, you can change the definition of where() to return a separately
packaged CA bundle.
"""
from certifi import where
if __name__ == "__main__":
print(where())

106
venv/lib/python3.12/site-packages/requests/compat.py Normal file
View File

@@ -0,0 +1,106 @@
"""
requests.compat
~~~~~~~~~~~~~~~
This module previously handled import compatibility issues
between Python 2 and Python 3. It remains for backwards
compatibility until the next major version.
"""
import importlib
import sys
# -------
# urllib3
# -------
from urllib3 import __version__ as urllib3_version
# Detect which major version of urllib3 is being used.
try:
is_urllib3_1 = int(urllib3_version.split(".")[0]) == 1
except (TypeError, AttributeError):
# If we can't discern a version, prefer old functionality.
is_urllib3_1 = True
# -------------------
# Character Detection
# -------------------
def _resolve_char_detection():
"""Find supported character detection libraries."""
chardet = None
for lib in ("chardet", "charset_normalizer"):
if chardet is None:
try:
chardet = importlib.import_module(lib)
except ImportError:
pass
return chardet
chardet = _resolve_char_detection()
# -------
# Pythons
# -------
# Syntax sugar.
_ver = sys.version_info
#: Python 2.x?
is_py2 = _ver[0] == 2
#: Python 3.x?
is_py3 = _ver[0] == 3
# json/simplejson module import resolution
has_simplejson = False
try:
import simplejson as json
has_simplejson = True
except ImportError:
import json
if has_simplejson:
from simplejson import JSONDecodeError
else:
from json import JSONDecodeError
# Keep OrderedDict for backwards compatibility.
from collections import OrderedDict
from collections.abc import Callable, Mapping, MutableMapping
from http import cookiejar as cookielib
from http.cookies import Morsel
from io import StringIO
# --------------
# Legacy Imports
# --------------
from urllib.parse import (
quote,
quote_plus,
unquote,
unquote_plus,
urldefrag,
urlencode,
urljoin,
urlparse,
urlsplit,
urlunparse,
)
from urllib.request import (
getproxies,
getproxies_environment,
parse_http_list,
proxy_bypass,
proxy_bypass_environment,
)
builtin_str = str
str = str
bytes = bytes
basestring = (str, bytes)
numeric_types = (int, float)
integer_types = (int,)

561
venv/lib/python3.12/site-packages/requests/cookies.py Normal file
View File

@@ -0,0 +1,561 @@
"""
requests.cookies
~~~~~~~~~~~~~~~~
Compatibility code to be able to use `http.cookiejar.CookieJar` with requests.
requests.utils imports from here, so be careful with imports.
"""
import calendar
import copy
import time
from ._internal_utils import to_native_string
from .compat import Morsel, MutableMapping, cookielib, urlparse, urlunparse
try:
import threading
except ImportError:
import dummy_threading as threading
class MockRequest:
"""Wraps a `requests.Request` to mimic a `urllib2.Request`.
The code in `http.cookiejar.CookieJar` expects this interface in order to correctly
manage cookie policies, i.e., determine whether a cookie can be set, given the
domains of the request and the cookie.
The original request object is read-only. The client is responsible for collecting
the new headers via `get_new_headers()` and interpreting them appropriately. You
probably want `get_cookie_header`, defined below.
"""
def __init__(self, request):
self._r = request
self._new_headers = {}
self.type = urlparse(self._r.url).scheme
def get_type(self):
return self.type
def get_host(self):
return urlparse(self._r.url).netloc
def get_origin_req_host(self):
return self.get_host()
def get_full_url(self):
# Only return the response's URL if the user hadn't set the Host
# header
if not self._r.headers.get("Host"):
return self._r.url
# If they did set it, retrieve it and reconstruct the expected domain
host = to_native_string(self._r.headers["Host"], encoding="utf-8")
parsed = urlparse(self._r.url)
# Reconstruct the URL as we expect it
return urlunparse(
[
parsed.scheme,
host,
parsed.path,
parsed.params,
parsed.query,
parsed.fragment,
]
)
def is_unverifiable(self):
return True
def has_header(self, name):
return name in self._r.headers or name in self._new_headers
def get_header(self, name, default=None):
return self._r.headers.get(name, self._new_headers.get(name, default))
def add_header(self, key, val):
"""cookiejar has no legitimate use for this method; add it back if you find one."""
raise NotImplementedError(
"Cookie headers should be added with add_unredirected_header()"
)
def add_unredirected_header(self, name, value):
self._new_headers[name] = value
def get_new_headers(self):
return self._new_headers
@property
def unverifiable(self):
return self.is_unverifiable()
@property
def origin_req_host(self):
return self.get_origin_req_host()
@property
def host(self):
return self.get_host()
class MockResponse:
"""Wraps a `httplib.HTTPMessage` to mimic a `urllib.addinfourl`.
...what? Basically, expose the parsed HTTP headers from the server response
the way `http.cookiejar` expects to see them.
"""
def __init__(self, headers):
"""Make a MockResponse for `cookiejar` to read.
:param headers: a httplib.HTTPMessage or analogous carrying the headers
"""
self._headers = headers
def info(self):
return self._headers
def getheaders(self, name):
self._headers.getheaders(name)
def extract_cookies_to_jar(jar, request, response):
"""Extract the cookies from the response into a CookieJar.
:param jar: http.cookiejar.CookieJar (not necessarily a RequestsCookieJar)
:param request: our own requests.Request object
:param response: urllib3.HTTPResponse object
"""
if not (hasattr(response, "_original_response") and response._original_response):
return
# the _original_response field is the wrapped httplib.HTTPResponse object,
req = MockRequest(request)
# pull out the HTTPMessage with the headers and put it in the mock:
res = MockResponse(response._original_response.msg)
jar.extract_cookies(res, req)
def get_cookie_header(jar, request):
"""
Produce an appropriate Cookie header string to be sent with `request`, or None.
:rtype: str
"""
r = MockRequest(request)
jar.add_cookie_header(r)
return r.get_new_headers().get("Cookie")
def remove_cookie_by_name(cookiejar, name, domain=None, path=None):
"""Unsets a cookie by name, by default over all domains and paths.
Wraps CookieJar.clear(), is O(n).
"""
clearables = []
for cookie in cookiejar:
if cookie.name != name:
continue
if domain is not None and domain != cookie.domain:
continue
if path is not None and path != cookie.path:
continue
clearables.append((cookie.domain, cookie.path, cookie.name))
for domain, path, name in clearables:
cookiejar.clear(domain, path, name)
class CookieConflictError(RuntimeError):
"""There are two cookies that meet the criteria specified in the cookie jar.
Use .get and .set and include domain and path args in order to be more specific.
"""
class RequestsCookieJar(cookielib.CookieJar, MutableMapping):
"""Compatibility class; is a http.cookiejar.CookieJar, but exposes a dict
interface.
This is the CookieJar we create by default for requests and sessions that
don't specify one, since some clients may expect response.cookies and
session.cookies to support dict operations.
Requests does not use the dict interface internally; it's just for
compatibility with external client code. All requests code should work
out of the box with externally provided instances of ``CookieJar``, e.g.
``LWPCookieJar`` and ``FileCookieJar``.
Unlike a regular CookieJar, this class is pickleable.
.. warning:: dictionary operations that are normally O(1) may be O(n).
"""
def get(self, name, default=None, domain=None, path=None):
"""Dict-like get() that also supports optional domain and path args in
order to resolve naming collisions from using one cookie jar over
multiple domains.
.. warning:: operation is O(n), not O(1).
"""
try:
return self._find_no_duplicates(name, domain, path)
except KeyError:
return default
def set(self, name, value, **kwargs):
"""Dict-like set() that also supports optional domain and path args in
order to resolve naming collisions from using one cookie jar over
multiple domains.
"""
# support client code that unsets cookies by assignment of a None value:
if value is None:
remove_cookie_by_name(
self, name, domain=kwargs.get("domain"), path=kwargs.get("path")
)
return
if isinstance(value, Morsel):
c = morsel_to_cookie(value)
else:
c = create_cookie(name, value, **kwargs)
self.set_cookie(c)
return c
def iterkeys(self):
"""Dict-like iterkeys() that returns an iterator of names of cookies
from the jar.
.. seealso:: itervalues() and iteritems().
"""
for cookie in iter(self):
yield cookie.name
def keys(self):
"""Dict-like keys() that returns a list of names of cookies from the
jar.
.. seealso:: values() and items().
"""
return list(self.iterkeys())
def itervalues(self):
"""Dict-like itervalues() that returns an iterator of values of cookies
from the jar.
.. seealso:: iterkeys() and iteritems().
"""
for cookie in iter(self):
yield cookie.value
def values(self):
"""Dict-like values() that returns a list of values of cookies from the
jar.
.. seealso:: keys() and items().
"""
return list(self.itervalues())
def iteritems(self):
"""Dict-like iteritems() that returns an iterator of name-value tuples
from the jar.
.. seealso:: iterkeys() and itervalues().
"""
for cookie in iter(self):
yield cookie.name, cookie.value
def items(self):
"""Dict-like items() that returns a list of name-value tuples from the
jar. Allows client-code to call ``dict(RequestsCookieJar)`` and get a
vanilla python dict of key value pairs.
.. seealso:: keys() and values().
"""
return list(self.iteritems())
def list_domains(self):
"""Utility method to list all the domains in the jar."""
domains = []
for cookie in iter(self):
if cookie.domain not in domains:
domains.append(cookie.domain)
return domains
def list_paths(self):
"""Utility method to list all the paths in the jar."""
paths = []
for cookie in iter(self):
if cookie.path not in paths:
paths.append(cookie.path)
return paths
def multiple_domains(self):
"""Returns True if there are multiple domains in the jar.
Returns False otherwise.
:rtype: bool
"""
domains = []
for cookie in iter(self):
if cookie.domain is not None and cookie.domain in domains:
return True
domains.append(cookie.domain)
return False # there is only one domain in jar
def get_dict(self, domain=None, path=None):
"""Takes as an argument an optional domain and path and returns a plain
old Python dict of name-value pairs of cookies that meet the
requirements.
:rtype: dict
"""
dictionary = {}
for cookie in iter(self):
if (domain is None or cookie.domain == domain) and (
path is None or cookie.path == path
):
dictionary[cookie.name] = cookie.value
return dictionary
def __contains__(self, name):
try:
return super().__contains__(name)
except CookieConflictError:
return True
def __getitem__(self, name):
"""Dict-like __getitem__() for compatibility with client code. Throws
exception if there are more than one cookie with name. In that case,
use the more explicit get() method instead.
.. warning:: operation is O(n), not O(1).
"""
return self._find_no_duplicates(name)
def __setitem__(self, name, value):
"""Dict-like __setitem__ for compatibility with client code. Throws
exception if there is already a cookie of that name in the jar. In that
case, use the more explicit set() method instead.
"""
self.set(name, value)
def __delitem__(self, name):
"""Deletes a cookie given a name. Wraps ``http.cookiejar.CookieJar``'s
``remove_cookie_by_name()``.
"""
remove_cookie_by_name(self, name)
def set_cookie(self, cookie, *args, **kwargs):
if (
hasattr(cookie.value, "startswith")
and cookie.value.startswith('"')
and cookie.value.endswith('"')
):
cookie.value = cookie.value.replace('\\"', "")
return super().set_cookie(cookie, *args, **kwargs)
def update(self, other):
"""Updates this jar with cookies from another CookieJar or dict-like"""
if isinstance(other, cookielib.CookieJar):
for cookie in other:
self.set_cookie(copy.copy(cookie))
else:
super().update(other)
def _find(self, name, domain=None, path=None):
"""Requests uses this method internally to get cookie values.
If there are conflicting cookies, _find arbitrarily chooses one.
See _find_no_duplicates if you want an exception thrown if there are
conflicting cookies.
:param name: a string containing name of cookie
:param domain: (optional) string containing domain of cookie
:param path: (optional) string containing path of cookie
:return: cookie.value
"""
for cookie in iter(self):
if cookie.name == name:
if domain is None or cookie.domain == domain:
if path is None or cookie.path == path:
return cookie.value
raise KeyError(f"name={name!r}, domain={domain!r}, path={path!r}")
def _find_no_duplicates(self, name, domain=None, path=None):
"""Both ``__get_item__`` and ``get`` call this function: it's never
used elsewhere in Requests.
:param name: a string containing name of cookie
:param domain: (optional) string containing domain of cookie
:param path: (optional) string containing path of cookie
:raises KeyError: if cookie is not found
:raises CookieConflictError: if there are multiple cookies
that match name and optionally domain and path
:return: cookie.value
"""
toReturn = None
for cookie in iter(self):
if cookie.name == name:
if domain is None or cookie.domain == domain:
if path is None or cookie.path == path:
if toReturn is not None:
# if there are multiple cookies that meet passed in criteria
raise CookieConflictError(
f"There are multiple cookies with name, {name!r}"
)
# we will eventually return this as long as no cookie conflict
toReturn = cookie.value
if toReturn:
return toReturn
raise KeyError(f"name={name!r}, domain={domain!r}, path={path!r}")
def __getstate__(self):
"""Unlike a normal CookieJar, this class is pickleable."""
state = self.__dict__.copy()
# remove the unpickleable RLock object
state.pop("_cookies_lock")
return state
def __setstate__(self, state):
"""Unlike a normal CookieJar, this class is pickleable."""
self.__dict__.update(state)
if "_cookies_lock" not in self.__dict__:
self._cookies_lock = threading.RLock()
def copy(self):
"""Return a copy of this RequestsCookieJar."""
new_cj = RequestsCookieJar()
new_cj.set_policy(self.get_policy())
new_cj.update(self)
return new_cj
def get_policy(self):
"""Return the CookiePolicy instance used."""
return self._policy
def _copy_cookie_jar(jar):
if jar is None:
return None
if hasattr(jar, "copy"):
# We're dealing with an instance of RequestsCookieJar
return jar.copy()
# We're dealing with a generic CookieJar instance
new_jar = copy.copy(jar)
new_jar.clear()
for cookie in jar:
new_jar.set_cookie(copy.copy(cookie))
return new_jar
def create_cookie(name, value, **kwargs):
"""Make a cookie from underspecified parameters.
By default, the pair of `name` and `value` will be set for the domain ''
and sent on every request (this is sometimes called a "supercookie").
"""
result = {
"version": 0,
"name": name,
"value": value,
"port": None,
"domain": "",
"path": "/",
"secure": False,
"expires": None,
"discard": True,
"comment": None,
"comment_url": None,
"rest": {"HttpOnly": None},
"rfc2109": False,
}
badargs = set(kwargs) - set(result)
if badargs:
raise TypeError(
f"create_cookie() got unexpected keyword arguments: {list(badargs)}"
)
result.update(kwargs)
result["port_specified"] = bool(result["port"])
result["domain_specified"] = bool(result["domain"])
result["domain_initial_dot"] = result["domain"].startswith(".")
result["path_specified"] = bool(result["path"])
return cookielib.Cookie(**result)
def morsel_to_cookie(morsel):
"""Convert a Morsel object into a Cookie containing the one k/v pair."""
expires = None
if morsel["max-age"]:
try:
expires = int(time.time() + int(morsel["max-age"]))
except ValueError:
raise TypeError(f"max-age: {morsel['max-age']} must be integer")
elif morsel["expires"]:
time_template = "%a, %d-%b-%Y %H:%M:%S GMT"
expires = calendar.timegm(time.strptime(morsel["expires"], time_template))
return create_cookie(
comment=morsel["comment"],
comment_url=bool(morsel["comment"]),
discard=False,
domain=morsel["domain"],
expires=expires,
name=morsel.key,
path=morsel["path"],
port=None,
rest={"HttpOnly": morsel["httponly"]},
rfc2109=False,
secure=bool(morsel["secure"]),
value=morsel.value,
version=morsel["version"] or 0,
)
def cookiejar_from_dict(cookie_dict, cookiejar=None, overwrite=True):
"""Returns a CookieJar from a key/value dictionary.
:param cookie_dict: Dict of key/values to insert into CookieJar.
:param cookiejar: (optional) A cookiejar to add the cookies to.
:param overwrite: (optional) If False, will not replace cookies
already in the jar with new ones.
:rtype: CookieJar
"""
if cookiejar is None:
cookiejar = RequestsCookieJar()
if cookie_dict is not None:
names_from_jar = [cookie.name for cookie in cookiejar]
for name in cookie_dict:
if overwrite or (name not in names_from_jar):
cookiejar.set_cookie(create_cookie(name, cookie_dict[name]))
return cookiejar
def merge_cookies(cookiejar, cookies):
"""Add cookies to cookiejar and returns a merged CookieJar.
:param cookiejar: CookieJar object to add the cookies to.
:param cookies: Dictionary or CookieJar object to be added.
:rtype: CookieJar
"""
if not isinstance(cookiejar, cookielib.CookieJar):
raise ValueError("You can only merge into CookieJar")
if isinstance(cookies, dict):
cookiejar = cookiejar_from_dict(cookies, cookiejar=cookiejar, overwrite=False)
elif isinstance(cookies, cookielib.CookieJar):
try:
cookiejar.update(cookies)
except AttributeError:
for cookie_in_jar in cookies:
cookiejar.set_cookie(cookie_in_jar)
return cookiejar

151
venv/lib/python3.12/site-packages/requests/exceptions.py Normal file
View File

@@ -0,0 +1,151 @@
"""
requests.exceptions
~~~~~~~~~~~~~~~~~~~
This module contains the set of Requests' exceptions.
"""
from urllib3.exceptions import HTTPError as BaseHTTPError
from .compat import JSONDecodeError as CompatJSONDecodeError
class RequestException(IOError):
"""There was an ambiguous exception that occurred while handling your
request.
"""
def __init__(self, *args, **kwargs):
"""Initialize RequestException with `request` and `response` objects."""
response = kwargs.pop("response", None)
self.response = response
self.request = kwargs.pop("request", None)
if response is not None and not self.request and hasattr(response, "request"):
self.request = self.response.request
super().__init__(*args, **kwargs)
class InvalidJSONError(RequestException):
"""A JSON error occurred."""
class JSONDecodeError(InvalidJSONError, CompatJSONDecodeError):
"""Couldn't decode the text into json"""
def __init__(self, *args, **kwargs):
"""
Construct the JSONDecodeError instance first with all
args. Then use it's args to construct the IOError so that
the json specific args aren't used as IOError specific args
and the error message from JSONDecodeError is preserved.
"""
CompatJSONDecodeError.__init__(self, *args)
InvalidJSONError.__init__(self, *self.args, **kwargs)
def __reduce__(self):
"""
The __reduce__ method called when pickling the object must
be the one from the JSONDecodeError (be it json/simplejson)
as it expects all the arguments for instantiation, not just
one like the IOError, and the MRO would by default call the
__reduce__ method from the IOError due to the inheritance order.
"""
return CompatJSONDecodeError.__reduce__(self)
class HTTPError(RequestException):
"""An HTTP error occurred."""
class ConnectionError(RequestException):
"""A Connection error occurred."""
class ProxyError(ConnectionError):
"""A proxy error occurred."""
class SSLError(ConnectionError):
"""An SSL error occurred."""
class Timeout(RequestException):
"""The request timed out.
Catching this error will catch both
:exc:`~requests.exceptions.ConnectTimeout` and
:exc:`~requests.exceptions.ReadTimeout` errors.
"""
class ConnectTimeout(ConnectionError, Timeout):
"""The request timed out while trying to connect to the remote server.
Requests that produced this error are safe to retry.
"""
class ReadTimeout(Timeout):
"""The server did not send any data in the allotted amount of time."""
class URLRequired(RequestException):
"""A valid URL is required to make a request."""
class TooManyRedirects(RequestException):
"""Too many redirects."""
class MissingSchema(RequestException, ValueError):
"""The URL scheme (e.g. http or https) is missing."""
class InvalidSchema(RequestException, ValueError):
"""The URL scheme provided is either invalid or unsupported."""
class InvalidURL(RequestException, ValueError):
"""The URL provided was somehow invalid."""
class InvalidHeader(RequestException, ValueError):
"""The header value provided was somehow invalid."""
class InvalidProxyURL(InvalidURL):
"""The proxy URL provided is invalid."""
class ChunkedEncodingError(RequestException):
"""The server declared chunked encoding but sent an invalid chunk."""
class ContentDecodingError(RequestException, BaseHTTPError):
"""Failed to decode response content."""
class StreamConsumedError(RequestException, TypeError):
"""The content for this response was already consumed."""
class RetryError(RequestException):
"""Custom retries logic failed"""
class UnrewindableBodyError(RequestException):
"""Requests encountered an error when trying to rewind a body."""
# Warnings
class RequestsWarning(Warning):
"""Base warning for Requests."""
class FileModeWarning(RequestsWarning, DeprecationWarning):
"""A file was opened in text mode, but Requests determined its binary length."""
class RequestsDependencyWarning(RequestsWarning):
"""An imported dependency doesn't match the expected version range."""

134
venv/lib/python3.12/site-packages/requests/help.py Normal file
View File

@@ -0,0 +1,134 @@
"""Module containing bug report helper(s)."""
import json
import platform
import ssl
import sys
import idna
import urllib3
from . import __version__ as requests_version
try:
import charset_normalizer
except ImportError:
charset_normalizer = None
try:
import chardet
except ImportError:
chardet = None
try:
from urllib3.contrib import pyopenssl
except ImportError:
pyopenssl = None
OpenSSL = None
cryptography = None
else:
import cryptography
import OpenSSL
def _implementation():
"""Return a dict with the Python implementation and version.
Provide both the name and the version of the Python implementation
currently running. For example, on CPython 3.10.3 it will return
{'name': 'CPython', 'version': '3.10.3'}.
This function works best on CPython and PyPy: in particular, it probably
doesn't work for Jython or IronPython. Future investigation should be done
to work out the correct shape of the code for those platforms.
"""
implementation = platform.python_implementation()
if implementation == "CPython":
implementation_version = platform.python_version()
elif implementation == "PyPy":
implementation_version = "{}.{}.{}".format(
sys.pypy_version_info.major,
sys.pypy_version_info.minor,
sys.pypy_version_info.micro,
)
if sys.pypy_version_info.releaselevel != "final":
implementation_version = "".join(
[implementation_version, sys.pypy_version_info.releaselevel]
)
elif implementation == "Jython":
implementation_version = platform.python_version() # Complete Guess
elif implementation == "IronPython":
implementation_version = platform.python_version() # Complete Guess
else:
implementation_version = "Unknown"
return {"name": implementation, "version": implementation_version}
def info():
"""Generate information for a bug report."""
try:
platform_info = {
"system": platform.system(),
"release": platform.release(),
}
except OSError:
platform_info = {
"system": "Unknown",
"release": "Unknown",
}
implementation_info = _implementation()
urllib3_info = {"version": urllib3.__version__}
charset_normalizer_info = {"version": None}
chardet_info = {"version": None}
if charset_normalizer:
charset_normalizer_info = {"version": charset_normalizer.__version__}
if chardet:
chardet_info = {"version": chardet.__version__}
pyopenssl_info = {
"version": None,
"openssl_version": "",
}
if OpenSSL:
pyopenssl_info = {
"version": OpenSSL.__version__,
"openssl_version": f"{OpenSSL.SSL.OPENSSL_VERSION_NUMBER:x}",
}
cryptography_info = {
"version": getattr(cryptography, "__version__", ""),
}
idna_info = {
"version": getattr(idna, "__version__", ""),
}
system_ssl = ssl.OPENSSL_VERSION_NUMBER
system_ssl_info = {"version": f"{system_ssl:x}" if system_ssl is not None else ""}
return {
"platform": platform_info,
"implementation": implementation_info,
"system_ssl": system_ssl_info,
"using_pyopenssl": pyopenssl is not None,
"using_charset_normalizer": chardet is None,
"pyOpenSSL": pyopenssl_info,
"urllib3": urllib3_info,
"chardet": chardet_info,
"charset_normalizer": charset_normalizer_info,
"cryptography": cryptography_info,
"idna": idna_info,
"requests": {
"version": requests_version,
},
}
def main():
"""Pretty-print the bug information as JSON."""
print(json.dumps(info(), sort_keys=True, indent=2))
if __name__ == "__main__":
main()

33
venv/lib/python3.12/site-packages/requests/hooks.py Normal file
View File

@@ -0,0 +1,33 @@
"""
requests.hooks
~~~~~~~~~~~~~~
This module provides the capabilities for the Requests hooks system.
Available hooks:
``response``:
The response generated from a Request.
"""
HOOKS = ["response"]
def default_hooks():
return {event: [] for event in HOOKS}
# TODO: response is the only one
def dispatch_hook(key, hooks, hook_data, **kwargs):
"""Dispatches a hook dictionary on a given piece of data."""
hooks = hooks or {}
hooks = hooks.get(key)
if hooks:
if hasattr(hooks, "__call__"):
hooks = [hooks]
for hook in hooks:
_hook_data = hook(hook_data, **kwargs)
if _hook_data is not None:
hook_data = _hook_data
return hook_data

1039
venv/lib/python3.12/site-packages/requests/models.py Normal file
View File

File diff suppressed because it is too large Load Diff

23
venv/lib/python3.12/site-packages/requests/packages.py Normal file
View File

@@ -0,0 +1,23 @@
import sys
from .compat import chardet
# This code exists for backwards compatibility reasons.
# I don't like it either. Just look the other way. :)
for package in ("urllib3", "idna"):
locals()[package] = __import__(package)
# This traversal is apparently necessary such that the identities are
# preserved (requests.packages.urllib3.* is urllib3.*)
for mod in list(sys.modules):
if mod == package or mod.startswith(f"{package}."):
sys.modules[f"requests.packages.{mod}"] = sys.modules[mod]
if chardet is not None:
target = chardet.__name__
for mod in list(sys.modules):
if mod == target or mod.startswith(f"{target}."):
imported_mod = sys.modules[mod]
sys.modules[f"requests.packages.{mod}"] = imported_mod
mod = mod.replace(target, "chardet")
sys.modules[f"requests.packages.{mod}"] = imported_mod

831
venv/lib/python3.12/site-packages/requests/sessions.py Normal file
View File

@@ -0,0 +1,831 @@
"""
requests.sessions
~~~~~~~~~~~~~~~~~
This module provides a Session object to manage and persist settings across
requests (cookies, auth, proxies).
"""
import os
import sys
import time
from collections import OrderedDict
from datetime import timedelta
from ._internal_utils import to_native_string
from .adapters import HTTPAdapter
from .auth import _basic_auth_str
from .compat import Mapping, cookielib, urljoin, urlparse
from .cookies import (
RequestsCookieJar,
cookiejar_from_dict,
extract_cookies_to_jar,
merge_cookies,
)
from .exceptions import (
ChunkedEncodingError,
ContentDecodingError,
InvalidSchema,
TooManyRedirects,
)
from .hooks import default_hooks, dispatch_hook
# formerly defined here, reexposed here for backward compatibility
from .models import ( # noqa: F401
DEFAULT_REDIRECT_LIMIT,
REDIRECT_STATI,
PreparedRequest,
Request,
)
from .status_codes import codes
from .structures import CaseInsensitiveDict
from .utils import ( # noqa: F401
DEFAULT_PORTS,
default_headers,
get_auth_from_url,
get_environ_proxies,
get_netrc_auth,
requote_uri,
resolve_proxies,
rewind_body,
should_bypass_proxies,
to_key_val_list,
)
# Preferred clock, based on which one is more accurate on a given system.
if sys.platform == "win32":
preferred_clock = time.perf_counter
else:
preferred_clock = time.time
def merge_setting(request_setting, session_setting, dict_class=OrderedDict):
"""Determines appropriate setting for a given request, taking into account
the explicit setting on that request, and the setting in the session. If a
setting is a dictionary, they will be merged together using `dict_class`
"""
if session_setting is None:
return request_setting
if request_setting is None:
return session_setting
# Bypass if not a dictionary (e.g. verify)
if not (
isinstance(session_setting, Mapping) and isinstance(request_setting, Mapping)
):
return request_setting
merged_setting = dict_class(to_key_val_list(session_setting))
merged_setting.update(to_key_val_list(request_setting))
# Remove keys that are set to None. Extract keys first to avoid altering
# the dictionary during iteration.
none_keys = [k for (k, v) in merged_setting.items() if v is None]
for key in none_keys:
del merged_setting[key]
return merged_setting
def merge_hooks(request_hooks, session_hooks, dict_class=OrderedDict):
"""Properly merges both requests and session hooks.
This is necessary because when request_hooks == {'response': []}, the
merge breaks Session hooks entirely.
"""
if session_hooks is None or session_hooks.get("response") == []:
return request_hooks
if request_hooks is None or request_hooks.get("response") == []:
return session_hooks
return merge_setting(request_hooks, session_hooks, dict_class)
class SessionRedirectMixin:
def get_redirect_target(self, resp):
"""Receives a Response. Returns a redirect URI or ``None``"""
# Due to the nature of how requests processes redirects this method will
# be called at least once upon the original response and at least twice
# on each subsequent redirect response (if any).
# If a custom mixin is used to handle this logic, it may be advantageous
# to cache the redirect location onto the response object as a private
# attribute.
if resp.is_redirect:
location = resp.headers["location"]
# Currently the underlying http module on py3 decode headers
# in latin1, but empirical evidence suggests that latin1 is very
# rarely used with non-ASCII characters in HTTP headers.
# It is more likely to get UTF8 header rather than latin1.
# This causes incorrect handling of UTF8 encoded location headers.
# To solve this, we re-encode the location in latin1.
location = location.encode("latin1")
return to_native_string(location, "utf8")
return None
def should_strip_auth(self, old_url, new_url):
"""Decide whether Authorization header should be removed when redirecting"""
old_parsed = urlparse(old_url)
new_parsed = urlparse(new_url)
if old_parsed.hostname != new_parsed.hostname:
return True
# Special case: allow http -> https redirect when using the standard
# ports. This isn't specified by RFC 7235, but is kept to avoid
# breaking backwards compatibility with older versions of requests
# that allowed any redirects on the same host.
if (
old_parsed.scheme == "http"
and old_parsed.port in (80, None)
and new_parsed.scheme == "https"
and new_parsed.port in (443, None)
):
return False
# Handle default port usage corresponding to scheme.
changed_port = old_parsed.port != new_parsed.port
changed_scheme = old_parsed.scheme != new_parsed.scheme
default_port = (DEFAULT_PORTS.get(old_parsed.scheme, None), None)
if (
not changed_scheme
and old_parsed.port in default_port
and new_parsed.port in default_port
):
return False
# Standard case: root URI must match
return changed_port or changed_scheme
def resolve_redirects(
self,
resp,
req,
stream=False,
timeout=None,
verify=True,
cert=None,
proxies=None,
yield_requests=False,
**adapter_kwargs,
):
"""Receives a Response. Returns a generator of Responses or Requests."""
hist = [] # keep track of history
url = self.get_redirect_target(resp)
previous_fragment = urlparse(req.url).fragment
while url:
prepared_request = req.copy()
# Update history and keep track of redirects.
# resp.history must ignore the original request in this loop
hist.append(resp)
resp.history = hist[1:]
try:
resp.content # Consume socket so it can be released
except (ChunkedEncodingError, ContentDecodingError, RuntimeError):
resp.raw.read(decode_content=False)
if len(resp.history) >= self.max_redirects:
raise TooManyRedirects(
f"Exceeded {self.max_redirects} redirects.", response=resp
)
# Release the connection back into the pool.
resp.close()
# Handle redirection without scheme (see: RFC 1808 Section 4)
if url.startswith("//"):
parsed_rurl = urlparse(resp.url)
url = ":".join([to_native_string(parsed_rurl.scheme), url])
# Normalize url case and attach previous fragment if needed (RFC 7231 7.1.2)
parsed = urlparse(url)
if parsed.fragment == "" and previous_fragment:
parsed = parsed._replace(fragment=previous_fragment)
elif parsed.fragment:
previous_fragment = parsed.fragment
url = parsed.geturl()
# Facilitate relative 'location' headers, as allowed by RFC 7231.
# (e.g. '/path/to/resource' instead of 'http://domain.tld/path/to/resource')
# Compliant with RFC3986, we percent encode the url.
if not parsed.netloc:
url = urljoin(resp.url, requote_uri(url))
else:
url = requote_uri(url)
prepared_request.url = to_native_string(url)
self.rebuild_method(prepared_request, resp)
# https://github.com/psf/requests/issues/1084
if resp.status_code not in (
codes.temporary_redirect,
codes.permanent_redirect,
):
# https://github.com/psf/requests/issues/3490
purged_headers = ("Content-Length", "Content-Type", "Transfer-Encoding")
for header in purged_headers:
prepared_request.headers.pop(header, None)
prepared_request.body = None
headers = prepared_request.headers
headers.pop("Cookie", None)
# Extract any cookies sent on the response to the cookiejar
# in the new request. Because we've mutated our copied prepared
# request, use the old one that we haven't yet touched.
extract_cookies_to_jar(prepared_request._cookies, req, resp.raw)
merge_cookies(prepared_request._cookies, self.cookies)
prepared_request.prepare_cookies(prepared_request._cookies)
# Rebuild auth and proxy information.
proxies = self.rebuild_proxies(prepared_request, proxies)
self.rebuild_auth(prepared_request, resp)
# A failed tell() sets `_body_position` to `object()`. This non-None
# value ensures `rewindable` will be True, allowing us to raise an
# UnrewindableBodyError, instead of hanging the connection.
rewindable = prepared_request._body_position is not None and (
"Content-Length" in headers or "Transfer-Encoding" in headers
)
# Attempt to rewind consumed file-like object.
if rewindable:
rewind_body(prepared_request)
# Override the original request.
req = prepared_request
if yield_requests:
yield req
else:
resp = self.send(
req,
stream=stream,
timeout=timeout,
verify=verify,
cert=cert,
proxies=proxies,
allow_redirects=False,
**adapter_kwargs,
)
extract_cookies_to_jar(self.cookies, prepared_request, resp.raw)
# extract redirect url, if any, for the next loop
url = self.get_redirect_target(resp)
yield resp
def rebuild_auth(self, prepared_request, response):
"""When being redirected we may want to strip authentication from the
request to avoid leaking credentials. This method intelligently removes
and reapplies authentication where possible to avoid credential loss.
"""
headers = prepared_request.headers
url = prepared_request.url
if "Authorization" in headers and self.should_strip_auth(
response.request.url, url
):
# If we get redirected to a new host, we should strip out any
# authentication headers.
del headers["Authorization"]
# .netrc might have more auth for us on our new host.
new_auth = get_netrc_auth(url) if self.trust_env else None
if new_auth is not None:
prepared_request.prepare_auth(new_auth)
def rebuild_proxies(self, prepared_request, proxies):
"""This method re-evaluates the proxy configuration by considering the
environment variables. If we are redirected to a URL covered by
NO_PROXY, we strip the proxy configuration. Otherwise, we set missing
proxy keys for this URL (in case they were stripped by a previous
redirect).
This method also replaces the Proxy-Authorization header where
necessary.
:rtype: dict
"""
headers = prepared_request.headers
scheme = urlparse(prepared_request.url).scheme
new_proxies = resolve_proxies(prepared_request, proxies, self.trust_env)
if "Proxy-Authorization" in headers:
del headers["Proxy-Authorization"]
try:
username, password = get_auth_from_url(new_proxies[scheme])
except KeyError:
username, password = None, None
# urllib3 handles proxy authorization for us in the standard adapter.
# Avoid appending this to TLS tunneled requests where it may be leaked.
if not scheme.startswith("https") and username and password:
headers["Proxy-Authorization"] = _basic_auth_str(username, password)
return new_proxies
def rebuild_method(self, prepared_request, response):
"""When being redirected we may want to change the method of the request
based on certain specs or browser behavior.
"""
method = prepared_request.method
# https://tools.ietf.org/html/rfc7231#section-6.4.4
if response.status_code == codes.see_other and method != "HEAD":
method = "GET"
# Do what the browsers do, despite standards...
# First, turn 302s into GETs.
if response.status_code == codes.found and method != "HEAD":
method = "GET"
# Second, if a POST is responded to with a 301, turn it into a GET.
# This bizarre behaviour is explained in Issue 1704.
if response.status_code == codes.moved and method == "POST":
method = "GET"
prepared_request.method = method
class Session(SessionRedirectMixin):
"""A Requests session.
Provides cookie persistence, connection-pooling, and configuration.
Basic Usage::
>>> import requests
>>> s = requests.Session()
>>> s.get('https://httpbin.org/get')
<Response [200]>
Or as a context manager::
>>> with requests.Session() as s:
... s.get('https://httpbin.org/get')
<Response [200]>
"""
__attrs__ = [
"headers",
"cookies",
"auth",
"proxies",
"hooks",
"params",
"verify",
"cert",
"adapters",
"stream",
"trust_env",
"max_redirects",
]
def __init__(self):
#: A case-insensitive dictionary of headers to be sent on each
#: :class:`Request <Request>` sent from this
#: :class:`Session <Session>`.
self.headers = default_headers()
#: Default Authentication tuple or object to attach to
#: :class:`Request <Request>`.
self.auth = None
#: Dictionary mapping protocol or protocol and host to the URL of the proxy
#: (e.g. {'http': 'foo.bar:3128', 'http://host.name': 'foo.bar:4012'}) to
#: be used on each :class:`Request <Request>`.
self.proxies = {}
#: Event-handling hooks.
self.hooks = default_hooks()
#: Dictionary of querystring data to attach to each
#: :class:`Request <Request>`. The dictionary values may be lists for
#: representing multivalued query parameters.
self.params = {}
#: Stream response content default.
self.stream = False
#: SSL Verification default.
#: Defaults to `True`, requiring requests to verify the TLS certificate at the
#: remote end.
#: If verify is set to `False`, requests will accept any TLS certificate
#: presented by the server, and will ignore hostname mismatches and/or
#: expired certificates, which will make your application vulnerable to
#: man-in-the-middle (MitM) attacks.
#: Only set this to `False` for testing.
self.verify = True
#: SSL client certificate default, if String, path to ssl client
#: cert file (.pem). If Tuple, ('cert', 'key') pair.
self.cert = None
#: Maximum number of redirects allowed. If the request exceeds this
#: limit, a :class:`TooManyRedirects` exception is raised.
#: This defaults to requests.models.DEFAULT_REDIRECT_LIMIT, which is
#: 30.
self.max_redirects = DEFAULT_REDIRECT_LIMIT
#: Trust environment settings for proxy configuration, default
#: authentication and similar.
self.trust_env = True
#: A CookieJar containing all currently outstanding cookies set on this
#: session. By default it is a
#: :class:`RequestsCookieJar <requests.cookies.RequestsCookieJar>`, but
#: may be any other ``cookielib.CookieJar`` compatible object.
self.cookies = cookiejar_from_dict({})
# Default connection adapters.
self.adapters = OrderedDict()
self.mount("https://", HTTPAdapter())
self.mount("http://", HTTPAdapter())
def __enter__(self):
return self
def __exit__(self, *args):
self.close()
def prepare_request(self, request):
"""Constructs a :class:`PreparedRequest <PreparedRequest>` for
transmission and returns it. The :class:`PreparedRequest` has settings
merged from the :class:`Request <Request>` instance and those of the
:class:`Session`.
:param request: :class:`Request` instance to prepare with this
session's settings.
:rtype: requests.PreparedRequest
"""
cookies = request.cookies or {}
# Bootstrap CookieJar.
if not isinstance(cookies, cookielib.CookieJar):
cookies = cookiejar_from_dict(cookies)
# Merge with session cookies
merged_cookies = merge_cookies(
merge_cookies(RequestsCookieJar(), self.cookies), cookies
)
# Set environment's basic authentication if not explicitly set.
auth = request.auth
if self.trust_env and not auth and not self.auth:
auth = get_netrc_auth(request.url)
p = PreparedRequest()
p.prepare(
method=request.method.upper(),
url=request.url,
files=request.files,
data=request.data,
json=request.json,
headers=merge_setting(
request.headers, self.headers, dict_class=CaseInsensitiveDict
),
params=merge_setting(request.params, self.params),
auth=merge_setting(auth, self.auth),
cookies=merged_cookies,
hooks=merge_hooks(request.hooks, self.hooks),
)
return p
def request(
self,
method,
url,
params=None,
data=None,
headers=None,
cookies=None,
files=None,
auth=None,
timeout=None,
allow_redirects=True,
proxies=None,
hooks=None,
stream=None,
verify=None,
cert=None,
json=None,
):
"""Constructs a :class:`Request <Request>`, prepares it and sends it.
Returns :class:`Response <Response>` object.
:param method: method for the new :class:`Request` object.
:param url: URL for the new :class:`Request` object.
:param params: (optional) Dictionary or bytes to be sent in the query
string for the :class:`Request`.
:param data: (optional) Dictionary, list of tuples, bytes, or file-like
object to send in the body of the :class:`Request`.
:param json: (optional) json to send in the body of the
:class:`Request`.
:param headers: (optional) Dictionary of HTTP Headers to send with the
:class:`Request`.
:param cookies: (optional) Dict or CookieJar object to send with the
:class:`Request`.
:param files: (optional) Dictionary of ``'filename': file-like-objects``
for multipart encoding upload.
:param auth: (optional) Auth tuple or callable to enable
Basic/Digest/Custom HTTP Auth.
:param timeout: (optional) How many seconds to wait for the server to send
data before giving up, as a float, or a :ref:`(connect timeout,
read timeout) <timeouts>` tuple.
:type timeout: float or tuple
:param allow_redirects: (optional) Set to True by default.
:type allow_redirects: bool
:param proxies: (optional) Dictionary mapping protocol or protocol and
hostname to the URL of the proxy.
:param hooks: (optional) Dictionary mapping hook name to one event or
list of events, event must be callable.
:param stream: (optional) whether to immediately download the response
content. Defaults to ``False``.
:param verify: (optional) Either a boolean, in which case it controls whether we verify
the server's TLS certificate, or a string, in which case it must be a path
to a CA bundle to use. Defaults to ``True``. When set to
``False``, requests will accept any TLS certificate presented by
the server, and will ignore hostname mismatches and/or expired
certificates, which will make your application vulnerable to
man-in-the-middle (MitM) attacks. Setting verify to ``False``
may be useful during local development or testing.
:param cert: (optional) if String, path to ssl client cert file (.pem).
If Tuple, ('cert', 'key') pair.
:rtype: requests.Response
"""
# Create the Request.
req = Request(
method=method.upper(),
url=url,
headers=headers,
files=files,
data=data or {},
json=json,
params=params or {},
auth=auth,
cookies=cookies,
hooks=hooks,
)
prep = self.prepare_request(req)
proxies = proxies or {}
settings = self.merge_environment_settings(
prep.url, proxies, stream, verify, cert
)
# Send the request.
send_kwargs = {
"timeout": timeout,
"allow_redirects": allow_redirects,
}
send_kwargs.update(settings)
resp = self.send(prep, **send_kwargs)
return resp
def get(self, url, **kwargs):
r"""Sends a GET request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes.
:rtype: requests.Response
"""
kwargs.setdefault("allow_redirects", True)
return self.request("GET", url, **kwargs)
def options(self, url, **kwargs):
r"""Sends a OPTIONS request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes.
:rtype: requests.Response
"""
kwargs.setdefault("allow_redirects", True)
return self.request("OPTIONS", url, **kwargs)
def head(self, url, **kwargs):
r"""Sends a HEAD request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes.
:rtype: requests.Response
"""
kwargs.setdefault("allow_redirects", False)
return self.request("HEAD", url, **kwargs)
def post(self, url, data=None, json=None, **kwargs):
r"""Sends a POST request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param data: (optional) Dictionary, list of tuples, bytes, or file-like
object to send in the body of the :class:`Request`.
:param json: (optional) json to send in the body of the :class:`Request`.
:param \*\*kwargs: Optional arguments that ``request`` takes.
:rtype: requests.Response
"""
return self.request("POST", url, data=data, json=json, **kwargs)
def put(self, url, data=None, **kwargs):
r"""Sends a PUT request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param data: (optional) Dictionary, list of tuples, bytes, or file-like
object to send in the body of the :class:`Request`.
:param \*\*kwargs: Optional arguments that ``request`` takes.
:rtype: requests.Response
"""
return self.request("PUT", url, data=data, **kwargs)
def patch(self, url, data=None, **kwargs):
r"""Sends a PATCH request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param data: (optional) Dictionary, list of tuples, bytes, or file-like
object to send in the body of the :class:`Request`.
:param \*\*kwargs: Optional arguments that ``request`` takes.
:rtype: requests.Response
"""
return self.request("PATCH", url, data=data, **kwargs)
def delete(self, url, **kwargs):
r"""Sends a DELETE request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes.
:rtype: requests.Response
"""
return self.request("DELETE", url, **kwargs)
def send(self, request, **kwargs):
"""Send a given PreparedRequest.
:rtype: requests.Response
"""
# Set defaults that the hooks can utilize to ensure they always have
# the correct parameters to reproduce the previous request.
kwargs.setdefault("stream", self.stream)
kwargs.setdefault("verify", self.verify)
kwargs.setdefault("cert", self.cert)
if "proxies" not in kwargs:
kwargs["proxies"] = resolve_proxies(request, self.proxies, self.trust_env)
# It's possible that users might accidentally send a Request object.
# Guard against that specific failure case.
if isinstance(request, Request):
raise ValueError("You can only send PreparedRequests.")
# Set up variables needed for resolve_redirects and dispatching of hooks
allow_redirects = kwargs.pop("allow_redirects", True)
stream = kwargs.get("stream")
hooks = request.hooks
# Get the appropriate adapter to use
adapter = self.get_adapter(url=request.url)
# Start time (approximately) of the request
start = preferred_clock()
# Send the request
r = adapter.send(request, **kwargs)
# Total elapsed time of the request (approximately)
elapsed = preferred_clock() - start
r.elapsed = timedelta(seconds=elapsed)
# Response manipulation hooks
r = dispatch_hook("response", hooks, r, **kwargs)
# Persist cookies
if r.history:
# If the hooks create history then we want those cookies too
for resp in r.history:
extract_cookies_to_jar(self.cookies, resp.request, resp.raw)
extract_cookies_to_jar(self.cookies, request, r.raw)
# Resolve redirects if allowed.
if allow_redirects:
# Redirect resolving generator.
gen = self.resolve_redirects(r, request, **kwargs)
history = [resp for resp in gen]
else:
history = []
# Shuffle things around if there's history.
if history:
# Insert the first (original) request at the start
history.insert(0, r)
# Get the last request made
r = history.pop()
r.history = history
# If redirects aren't being followed, store the response on the Request for Response.next().
if not allow_redirects:
try:
r._next = next(
self.resolve_redirects(r, request, yield_requests=True, **kwargs)
)
except StopIteration:
pass
if not stream:
r.content
return r
def merge_environment_settings(self, url, proxies, stream, verify, cert):
"""
Check the environment and merge it with some settings.
:rtype: dict
"""
# Gather clues from the surrounding environment.
if self.trust_env:
# Set environment's proxies.
no_proxy = proxies.get("no_proxy") if proxies is not None else None
env_proxies = get_environ_proxies(url, no_proxy=no_proxy)
for k, v in env_proxies.items():
proxies.setdefault(k, v)
# Look for requests environment configuration
# and be compatible with cURL.
if verify is True or verify is None:
verify = (
os.environ.get("REQUESTS_CA_BUNDLE")
or os.environ.get("CURL_CA_BUNDLE")
or verify
)
# Merge all the kwargs.
proxies = merge_setting(proxies, self.proxies)
stream = merge_setting(stream, self.stream)
verify = merge_setting(verify, self.verify)
cert = merge_setting(cert, self.cert)
return {"proxies": proxies, "stream": stream, "verify": verify, "cert": cert}
def get_adapter(self, url):
"""
Returns the appropriate connection adapter for the given URL.
:rtype: requests.adapters.BaseAdapter
"""
for prefix, adapter in self.adapters.items():
if url.lower().startswith(prefix.lower()):
return adapter
# Nothing matches :-/
raise InvalidSchema(f"No connection adapters were found for {url!r}")
def close(self):
"""Closes all adapters and as such the session"""
for v in self.adapters.values():
v.close()
def mount(self, prefix, adapter):
"""Registers a connection adapter to a prefix.
Adapters are sorted in descending order by prefix length.
"""
self.adapters[prefix] = adapter
keys_to_move = [k for k in self.adapters if len(k) < len(prefix)]
for key in keys_to_move:
self.adapters[key] = self.adapters.pop(key)
def __getstate__(self):
state = {attr: getattr(self, attr, None) for attr in self.__attrs__}
return state
def __setstate__(self, state):
for attr, value in state.items():
setattr(self, attr, value)
def session():
"""
Returns a :class:`Session` for context-management.
.. deprecated:: 1.0.0
This method has been deprecated since version 1.0.0 and is only kept for
backwards compatibility. New code should use :class:`~requests.sessions.Session`
to create a session. This may be removed at a future date.
:rtype: Session
"""
return Session()

128
venv/lib/python3.12/site-packages/requests/status_codes.py Normal file
View File

@@ -0,0 +1,128 @@
r"""
The ``codes`` object defines a mapping from common names for HTTP statuses
to their numerical codes, accessible either as attributes or as dictionary
items.
Example::
>>> import requests
>>> requests.codes['temporary_redirect']
307
>>> requests.codes.teapot
418
>>> requests.codes['\o/']
200
Some codes have multiple names, and both upper- and lower-case versions of
the names are allowed. For example, ``codes.ok``, ``codes.OK``, and
``codes.okay`` all correspond to the HTTP status code 200.
"""
from .structures import LookupDict
_codes = {
# Informational.
100: ("continue",),
101: ("switching_protocols",),
102: ("processing", "early-hints"),
103: ("checkpoint",),
122: ("uri_too_long", "request_uri_too_long"),
200: ("ok", "okay", "all_ok", "all_okay", "all_good", "\\o/", "✓"),
201: ("created",),
202: ("accepted",),
203: ("non_authoritative_info", "non_authoritative_information"),
204: ("no_content",),
205: ("reset_content", "reset"),
206: ("partial_content", "partial"),
207: ("multi_status", "multiple_status", "multi_stati", "multiple_stati"),
208: ("already_reported",),
226: ("im_used",),
# Redirection.
300: ("multiple_choices",),
301: ("moved_permanently", "moved", "\\o-"),
302: ("found",),
303: ("see_other", "other"),
304: ("not_modified",),
305: ("use_proxy",),
306: ("switch_proxy",),
307: ("temporary_redirect", "temporary_moved", "temporary"),
308: (
"permanent_redirect",
"resume_incomplete",
"resume",
), # "resume" and "resume_incomplete" to be removed in 3.0
# Client Error.
400: ("bad_request", "bad"),
401: ("unauthorized",),
402: ("payment_required", "payment"),
403: ("forbidden",),
404: ("not_found", "-o-"),
405: ("method_not_allowed", "not_allowed"),
406: ("not_acceptable",),
407: ("proxy_authentication_required", "proxy_auth", "proxy_authentication"),
408: ("request_timeout", "timeout"),
409: ("conflict",),
410: ("gone",),
411: ("length_required",),
412: ("precondition_failed", "precondition"),
413: ("request_entity_too_large", "content_too_large"),
414: ("request_uri_too_large", "uri_too_long"),
415: ("unsupported_media_type", "unsupported_media", "media_type"),
416: (
"requested_range_not_satisfiable",
"requested_range",
"range_not_satisfiable",
),
417: ("expectation_failed",),
418: ("im_a_teapot", "teapot", "i_am_a_teapot"),
421: ("misdirected_request",),
422: ("unprocessable_entity", "unprocessable", "unprocessable_content"),
423: ("locked",),
424: ("failed_dependency", "dependency"),
425: ("unordered_collection", "unordered", "too_early"),
426: ("upgrade_required", "upgrade"),
428: ("precondition_required", "precondition"),
429: ("too_many_requests", "too_many"),
431: ("header_fields_too_large", "fields_too_large"),
444: ("no_response", "none"),
449: ("retry_with", "retry"),
450: ("blocked_by_windows_parental_controls", "parental_controls"),
451: ("unavailable_for_legal_reasons", "legal_reasons"),
499: ("client_closed_request",),
# Server Error.
500: ("internal_server_error", "server_error", "/o\\", "✗"),
501: ("not_implemented",),
502: ("bad_gateway",),
503: ("service_unavailable", "unavailable"),
504: ("gateway_timeout",),
505: ("http_version_not_supported", "http_version"),
506: ("variant_also_negotiates",),
507: ("insufficient_storage",),
509: ("bandwidth_limit_exceeded", "bandwidth"),
510: ("not_extended",),
511: ("network_authentication_required", "network_auth", "network_authentication"),
}
codes = LookupDict(name="status_codes")
def _init():
for code, titles in _codes.items():
for title in titles:
setattr(codes, title, code)
if not title.startswith(("\\", "/")):
setattr(codes, title.upper(), code)
def doc(code):
names = ", ".join(f"``{n}``" for n in _codes[code])
return "* %d: %s" % (code, names)
global __doc__
__doc__ = (
__doc__ + "\n" + "\n".join(doc(code) for code in sorted(_codes))
if __doc__ is not None
else None
)
_init()

99
venv/lib/python3.12/site-packages/requests/structures.py Normal file
View File

@@ -0,0 +1,99 @@
"""
requests.structures
~~~~~~~~~~~~~~~~~~~
Data structures that power Requests.
"""
from collections import OrderedDict
from .compat import Mapping, MutableMapping
class CaseInsensitiveDict(MutableMapping):
"""A case-insensitive ``dict``-like object.
Implements all methods and operations of
``MutableMapping`` as well as dict's ``copy``. Also
provides ``lower_items``.
All keys are expected to be strings. The structure remembers the
case of the last key to be set, and ``iter(instance)``,
``keys()``, ``items()``, ``iterkeys()``, and ``iteritems()``
will contain case-sensitive keys. However, querying and contains
testing is case insensitive::
cid = CaseInsensitiveDict()
cid['Accept'] = 'application/json'
cid['aCCEPT'] == 'application/json' # True
list(cid) == ['Accept'] # True
For example, ``headers['content-encoding']`` will return the
value of a ``'Content-Encoding'`` response header, regardless
of how the header name was originally stored.
If the constructor, ``.update``, or equality comparison
operations are given keys that have equal ``.lower()``s, the
behavior is undefined.
"""
def __init__(self, data=None, **kwargs):
self._store = OrderedDict()
if data is None:
data = {}
self.update(data, **kwargs)
def __setitem__(self, key, value):
# Use the lowercased key for lookups, but store the actual
# key alongside the value.
self._store[key.lower()] = (key, value)
def __getitem__(self, key):
return self._store[key.lower()][1]
def __delitem__(self, key):
del self._store[key.lower()]
def __iter__(self):
return (casedkey for casedkey, mappedvalue in self._store.values())
def __len__(self):
return len(self._store)
def lower_items(self):
"""Like iteritems(), but with all lowercase keys."""
return ((lowerkey, keyval[1]) for (lowerkey, keyval) in self._store.items())
def __eq__(self, other):
if isinstance(other, Mapping):
other = CaseInsensitiveDict(other)
else:
return NotImplemented
# Compare insensitively
return dict(self.lower_items()) == dict(other.lower_items())
# Copy is required
def copy(self):
return CaseInsensitiveDict(self._store.values())
def __repr__(self):
return str(dict(self.items()))
class LookupDict(dict):
"""Dictionary lookup object."""
def __init__(self, name=None):
self.name = name
super().__init__()
def __repr__(self):
return f"<lookup '{self.name}'>"
def __getitem__(self, key):
# We allow fall-through here, so values default to None
return self.__dict__.get(key, None)
def get(self, key, default=None):
return self.__dict__.get(key, default)

1086
venv/lib/python3.12/site-packages/requests/utils.py Normal file
View File

File diff suppressed because it is too large Load Diff

1
venv/lib/python3.12/site-packages/urllib3-2.5.0.dist-info/INSTALLER Normal file
View File

@@ -0,0 +1 @@
pip

154
venv/lib/python3.12/site-packages/urllib3-2.5.0.dist-info/METADATA Normal file
View File

@@ -0,0 +1,154 @@
Metadata-Version: 2.4
Name: urllib3
Version: 2.5.0
Summary: HTTP library with thread-safe connection pooling, file post, and more.
Project-URL: Changelog, https://github.com/urllib3/urllib3/blob/main/CHANGES.rst
Project-URL: Documentation, https://urllib3.readthedocs.io
Project-URL: Code, https://github.com/urllib3/urllib3
Project-URL: Issue tracker, https://github.com/urllib3/urllib3/issues
Author-email: Andrey Petrov <andrey.petrov@shazow.net>
Maintainer-email: Seth Michael Larson <sethmichaellarson@gmail.com>, Quentin Pradet <quentin@pradet.me>, Illia Volochii <illia.volochii@gmail.com>
License-Expression: MIT
License-File: LICENSE.txt
Keywords: filepost,http,httplib,https,pooling,ssl,threadsafe,urllib
Classifier: Environment :: Web Environment
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Classifier: Topic :: Internet :: WWW/HTTP
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.9
Provides-Extra: brotli
Requires-Dist: brotli>=1.0.9; (platform_python_implementation == 'CPython') and extra == 'brotli'
Requires-Dist: brotlicffi>=0.8.0; (platform_python_implementation != 'CPython') and extra == 'brotli'
Provides-Extra: h2
Requires-Dist: h2<5,>=4; extra == 'h2'
Provides-Extra: socks
Requires-Dist: pysocks!=1.5.7,<2.0,>=1.5.6; extra == 'socks'
Provides-Extra: zstd
Requires-Dist: zstandard>=0.18.0; extra == 'zstd'
Description-Content-Type: text/markdown
<h1 align="center">
![urllib3](https://github.com/urllib3/urllib3/raw/main/docs/_static/banner_github.svg)
</h1>
<p align="center">
<a href="https://pypi.org/project/urllib3"><img alt="PyPI Version" src="https://img.shields.io/pypi/v/urllib3.svg?maxAge=86400" /></a>
<a href="https://pypi.org/project/urllib3"><img alt="Python Versions" src="https://img.shields.io/pypi/pyversions/urllib3.svg?maxAge=86400" /></a>
<a href="https://discord.gg/urllib3"><img alt="Join our Discord" src="https://img.shields.io/discord/756342717725933608?color=%237289da&label=discord" /></a>
<a href="https://github.com/urllib3/urllib3/actions?query=workflow%3ACI"><img alt="Coverage Status" src="https://img.shields.io/badge/coverage-100%25-success" /></a>
<a href="https://github.com/urllib3/urllib3/actions/workflows/ci.yml?query=branch%3Amain"><img alt="Build Status on GitHub" src="https://github.com/urllib3/urllib3/actions/workflows/ci.yml/badge.svg?branch:main&workflow:CI" /></a>
<a href="https://urllib3.readthedocs.io"><img alt="Documentation Status" src="https://readthedocs.org/projects/urllib3/badge/?version=latest" /></a><br>
<a href="https://deps.dev/pypi/urllib3"><img alt="OpenSSF Scorecard" src="https://api.securityscorecards.dev/projects/github.com/urllib3/urllib3/badge" /></a>
<a href="https://slsa.dev"><img alt="SLSA 3" src="https://slsa.dev/images/gh-badge-level3.svg" /></a>
<a href="https://bestpractices.coreinfrastructure.org/projects/6227"><img alt="CII Best Practices" src="https://bestpractices.coreinfrastructure.org/projects/6227/badge" /></a>
</p>
urllib3 is a powerful, *user-friendly* HTTP client for Python. Much of the
Python ecosystem already uses urllib3 and you should too.
urllib3 brings many critical features that are missing from the Python
standard libraries:
- Thread safety.
- Connection pooling.
- Client-side SSL/TLS verification.
- File uploads with multipart encoding.
- Helpers for retrying requests and dealing with HTTP redirects.
- Support for gzip, deflate, brotli, and zstd encoding.
- Proxy support for HTTP and SOCKS.
- 100% test coverage.
urllib3 is powerful and easy to use:
```python3
>>> import urllib3
>>> resp = urllib3.request("GET", "http://httpbin.org/robots.txt")
>>> resp.status
200
>>> resp.data
b"User-agent: *\nDisallow: /deny\n"
```
## Installing
urllib3 can be installed with [pip](https://pip.pypa.io):
```bash
$ python -m pip install urllib3
```
Alternatively, you can grab the latest source code from [GitHub](https://github.com/urllib3/urllib3):
```bash
$ git clone https://github.com/urllib3/urllib3.git
$ cd urllib3
$ pip install .
```
## Documentation
urllib3 has usage and reference documentation at [urllib3.readthedocs.io](https://urllib3.readthedocs.io).
## Community
urllib3 has a [community Discord channel](https://discord.gg/urllib3) for asking questions and
collaborating with other contributors. Drop by and say hello 👋
## Contributing
urllib3 happily accepts contributions. Please see our
[contributing documentation](https://urllib3.readthedocs.io/en/latest/contributing.html)
for some tips on getting started.
## Security Disclosures
To report a security vulnerability, please use the
[Tidelift security contact](https://tidelift.com/security).
Tidelift will coordinate the fix and disclosure with maintainers.
## Maintainers
- [@sethmlarson](https://github.com/sethmlarson) (Seth M. Larson)
- [@pquentin](https://github.com/pquentin) (Quentin Pradet)
- [@illia-v](https://github.com/illia-v) (Illia Volochii)
- [@theacodes](https://github.com/theacodes) (Thea Flowers)
- [@haikuginger](https://github.com/haikuginger) (Jess Shapiro)
- [@lukasa](https://github.com/lukasa) (Cory Benfield)
- [@sigmavirus24](https://github.com/sigmavirus24) (Ian Stapleton Cordasco)
- [@shazow](https://github.com/shazow) (Andrey Petrov)
👋
## Sponsorship
If your company benefits from this library, please consider [sponsoring its
development](https://urllib3.readthedocs.io/en/latest/sponsors.html).
## For Enterprise
Professional support for urllib3 is available as part of the [Tidelift
Subscription][1]. Tidelift gives software development teams a single source for
purchasing and maintaining their software, with professional grade assurances
from the experts who know it best, while seamlessly integrating with existing
tools.
[1]: https://tidelift.com/subscription/pkg/pypi-urllib3?utm_source=pypi-urllib3&utm_medium=referral&utm_campaign=readme

79
venv/lib/python3.12/site-packages/urllib3-2.5.0.dist-info/RECORD Normal file
View File

@@ -0,0 +1,79 @@
urllib3-2.5.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
urllib3-2.5.0.dist-info/METADATA,sha256=maYkTIZt0a-lkEC-hMZWbCBmcGZyJcYOeRk4_nuTrNc,6461
urllib3-2.5.0.dist-info/RECORD,,
urllib3-2.5.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
urllib3-2.5.0.dist-info/licenses/LICENSE.txt,sha256=Ew46ZNX91dCWp1JpRjSn2d8oRGnehuVzIQAmgEHj1oY,1093
urllib3/__init__.py,sha256=JMo1tg1nIV1AeJ2vENC_Txfl0e5h6Gzl9DGVk1rWRbo,6979
urllib3/__pycache__/__init__.cpython-312.pyc,,
urllib3/__pycache__/_base_connection.cpython-312.pyc,,
urllib3/__pycache__/_collections.cpython-312.pyc,,
urllib3/__pycache__/_request_methods.cpython-312.pyc,,
urllib3/__pycache__/_version.cpython-312.pyc,,
urllib3/__pycache__/connection.cpython-312.pyc,,
urllib3/__pycache__/connectionpool.cpython-312.pyc,,
urllib3/__pycache__/exceptions.cpython-312.pyc,,
urllib3/__pycache__/fields.cpython-312.pyc,,
urllib3/__pycache__/filepost.cpython-312.pyc,,
urllib3/__pycache__/poolmanager.cpython-312.pyc,,
urllib3/__pycache__/response.cpython-312.pyc,,
urllib3/_base_connection.py,sha256=T1cwH3RhzsrBh6Bz3AOGVDboRsE7veijqZPXXQTR2Rg,5568
urllib3/_collections.py,sha256=tM7c6J1iKtWZYV_QGYb8-r7Nr1524Dehnsa0Ufh6_mU,17295
urllib3/_request_methods.py,sha256=gCeF85SO_UU4WoPwYHIoz_tw-eM_EVOkLFp8OFsC7DA,9931
urllib3/_version.py,sha256=ZlSUkBo_Pd90B6pM0GDO7l2vitQD3QCK3xPR_K0zFJA,511
urllib3/connection.py,sha256=iP4pgSJtpusXyYlejzNn-gih_wWCxMU-qy6OU1kaapc,42613
urllib3/connectionpool.py,sha256=ZEhudsa8BIubD2M0XoxBBsjxbsXwMgUScH7oQ9i-j1Y,43371
urllib3/contrib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
urllib3/contrib/__pycache__/__init__.cpython-312.pyc,,
urllib3/contrib/__pycache__/pyopenssl.cpython-312.pyc,,
urllib3/contrib/__pycache__/socks.cpython-312.pyc,,
urllib3/contrib/emscripten/__init__.py,sha256=u6KNgzjlFZbuAAXa_ybCR7gQ71VJESnF-IIdDA73brw,733
urllib3/contrib/emscripten/__pycache__/__init__.cpython-312.pyc,,
urllib3/contrib/emscripten/__pycache__/connection.cpython-312.pyc,,
urllib3/contrib/emscripten/__pycache__/fetch.cpython-312.pyc,,
urllib3/contrib/emscripten/__pycache__/request.cpython-312.pyc,,
urllib3/contrib/emscripten/__pycache__/response.cpython-312.pyc,,
urllib3/contrib/emscripten/connection.py,sha256=j8DR_flE7hsoFhNfiqHLiaPaCsVbzG44jgahwvsQ52A,8771
urllib3/contrib/emscripten/emscripten_fetch_worker.js,sha256=CDfYF_9CDobtx2lGidyJ1zjDEvwNT5F-dchmVWXDh0E,3655
urllib3/contrib/emscripten/fetch.py,sha256=kco06lWoQ-fdFfN51-nzeTywPVBEHg89WIst33H3xcg,23484
urllib3/contrib/emscripten/request.py,sha256=mL28szy1KvE3NJhWor5jNmarp8gwplDU-7gwGZY5g0Q,566
urllib3/contrib/emscripten/response.py,sha256=7oVPENYZHuzEGRtG40HonpH5tAIYHsGcHPbJt2Z0U-Y,9507
urllib3/contrib/pyopenssl.py,sha256=Xp5Ym05VgXGhHa0C4wlutvHxY8SnKSS6WLb2t5Miu0s,19720
urllib3/contrib/socks.py,sha256=-iardc61GypsJzD6W6yuRS7KVCyfowcQrl_719H7lIM,7549
urllib3/exceptions.py,sha256=pziumHf0Vwx3z4gvUy7ou8nlM2yIYX0N3l3znEdeF5U,9938
urllib3/fields.py,sha256=FCf7UULSkf10cuTRUWTQESzxgl1WT8e2aCy3kfyZins,10829
urllib3/filepost.py,sha256=U8eNZ-mpKKHhrlbHEEiTxxgK16IejhEa7uz42yqA_dI,2388
urllib3/http2/__init__.py,sha256=xzrASH7R5ANRkPJOot5lGnATOq3KKuyXzI42rcnwmqs,1741
urllib3/http2/__pycache__/__init__.cpython-312.pyc,,
urllib3/http2/__pycache__/connection.cpython-312.pyc,,
urllib3/http2/__pycache__/probe.cpython-312.pyc,,
urllib3/http2/connection.py,sha256=4DB0DkZEC3yIkhGjUDIHB17wrYCLaL0Ag5bDW2_mGPI,12694
urllib3/http2/probe.py,sha256=nnAkqbhAakOiF75rz7W0udZ38Eeh_uD8fjV74N73FEI,3014
urllib3/poolmanager.py,sha256=oKsgP1EsAI4OVgK9-9D3AYXZS5HYV8yKUSog-QbJ8Ts,23866
urllib3/py.typed,sha256=UaCuPFa3H8UAakbt-5G8SPacldTOGvJv18pPjUJ5gDY,93
urllib3/response.py,sha256=TVTSu6Q1U0U7hoHYMIRxxuh4zroeMo8b5EI4DOA13Eo,46480
urllib3/util/__init__.py,sha256=-qeS0QceivazvBEKDNFCAI-6ACcdDOE4TMvo7SLNlAQ,1001
urllib3/util/__pycache__/__init__.cpython-312.pyc,,
urllib3/util/__pycache__/connection.cpython-312.pyc,,
urllib3/util/__pycache__/proxy.cpython-312.pyc,,
urllib3/util/__pycache__/request.cpython-312.pyc,,
urllib3/util/__pycache__/response.cpython-312.pyc,,
urllib3/util/__pycache__/retry.cpython-312.pyc,,
urllib3/util/__pycache__/ssl_.cpython-312.pyc,,
urllib3/util/__pycache__/ssl_match_hostname.cpython-312.pyc,,
urllib3/util/__pycache__/ssltransport.cpython-312.pyc,,
urllib3/util/__pycache__/timeout.cpython-312.pyc,,
urllib3/util/__pycache__/url.cpython-312.pyc,,
urllib3/util/__pycache__/util.cpython-312.pyc,,
urllib3/util/__pycache__/wait.cpython-312.pyc,,
urllib3/util/connection.py,sha256=JjO722lzHlzLXPTkr9ZWBdhseXnMVjMSb1DJLVrXSnQ,4444
urllib3/util/proxy.py,sha256=seP8-Q5B6bB0dMtwPj-YcZZQ30vHuLqRu-tI0JZ2fzs,1148
urllib3/util/request.py,sha256=XuAsEBT58DAZYUTwpMH5Hr3A1OPoMNvNIYIunbIqbc8,8411
urllib3/util/response.py,sha256=vQE639uoEhj1vpjEdxu5lNIhJCSUZkd7pqllUI0BZOA,3374
urllib3/util/retry.py,sha256=bj-2YUqblxLlv8THg5fxww-DM54XCbjgZXIQ71XioCY,18459
urllib3/util/ssl_.py,sha256=jxnQ3msYkVaokJVWqHNnAVdVtDdidrTHDeyk50gwqaQ,19786
urllib3/util/ssl_match_hostname.py,sha256=Di7DU7zokoltapT_F0Sj21ffYxwaS_cE5apOtwueeyA,5845
urllib3/util/ssltransport.py,sha256=Ez4O8pR_vT8dan_FvqBYS6dgDfBXEMfVfrzcdUoWfi4,8847
urllib3/util/timeout.py,sha256=4eT1FVeZZU7h7mYD1Jq2OXNe4fxekdNvhoWUkZusRpA,10346
urllib3/util/url.py,sha256=WRh-TMYXosmgp8m8lT4H5spoHw5yUjlcMCfU53AkoAs,15205
urllib3/util/util.py,sha256=j3lbZK1jPyiwD34T8IgJzdWEZVT-4E-0vYIJi9UjeNA,1146
urllib3/util/wait.py,sha256=_ph8IrUR3sqPqi0OopQgJUlH4wzkGeM5CiyA7XGGtmI,4423

4
venv/lib/python3.12/site-packages/urllib3-2.5.0.dist-info/WHEEL Normal file
View File

@@ -0,0 +1,4 @@
Wheel-Version: 1.0
Generator: hatchling 1.27.0
Root-Is-Purelib: true
Tag: py3-none-any

21
venv/lib/python3.12/site-packages/urllib3-2.5.0.dist-info/licenses/LICENSE.txt Normal file
View File

@@ -0,0 +1,21 @@
MIT License
Copyright (c) 2008-2020 Andrey Petrov and contributors.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

211
venv/lib/python3.12/site-packages/urllib3/__init__.py Normal file
View File

@@ -0,0 +1,211 @@
"""
Python HTTP library with thread-safe connection pooling, file post support, user friendly, and more
"""
from __future__ import annotations
# Set default logging handler to avoid "No handler found" warnings.
import logging
import sys
import typing
import warnings
from logging import NullHandler
from . import exceptions
from ._base_connection import _TYPE_BODY
from ._collections import HTTPHeaderDict
from ._version import __version__
from .connectionpool import HTTPConnectionPool, HTTPSConnectionPool, connection_from_url
from .filepost import _TYPE_FIELDS, encode_multipart_formdata
from .poolmanager import PoolManager, ProxyManager, proxy_from_url
from .response import BaseHTTPResponse, HTTPResponse
from .util.request import make_headers
from .util.retry import Retry
from .util.timeout import Timeout
# Ensure that Python is compiled with OpenSSL 1.1.1+
# If the 'ssl' module isn't available at all that's
# fine, we only care if the module is available.
try:
import ssl
except ImportError:
pass
else:
if not ssl.OPENSSL_VERSION.startswith("OpenSSL "): # Defensive:
warnings.warn(
"urllib3 v2 only supports OpenSSL 1.1.1+, currently "
f"the 'ssl' module is compiled with {ssl.OPENSSL_VERSION!r}. "
"See: https://github.com/urllib3/urllib3/issues/3020",
exceptions.NotOpenSSLWarning,
)
elif ssl.OPENSSL_VERSION_INFO < (1, 1, 1): # Defensive:
raise ImportError(
"urllib3 v2 only supports OpenSSL 1.1.1+, currently "
f"the 'ssl' module is compiled with {ssl.OPENSSL_VERSION!r}. "
"See: https://github.com/urllib3/urllib3/issues/2168"
)
__author__ = "Andrey Petrov (andrey.petrov@shazow.net)"
__license__ = "MIT"
__version__ = __version__
__all__ = (
"HTTPConnectionPool",
"HTTPHeaderDict",
"HTTPSConnectionPool",
"PoolManager",
"ProxyManager",
"HTTPResponse",
"Retry",
"Timeout",
"add_stderr_logger",
"connection_from_url",
"disable_warnings",
"encode_multipart_formdata",
"make_headers",
"proxy_from_url",
"request",
"BaseHTTPResponse",
)
logging.getLogger(__name__).addHandler(NullHandler())
def add_stderr_logger(
level: int = logging.DEBUG,
) -> logging.StreamHandler[typing.TextIO]:
"""
Helper for quickly adding a StreamHandler to the logger. Useful for
debugging.
Returns the handler after adding it.
"""
# This method needs to be in this __init__.py to get the __name__ correct
# even if urllib3 is vendored within another package.
logger = logging.getLogger(__name__)
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter("%(asctime)s %(levelname)s %(message)s"))
logger.addHandler(handler)
logger.setLevel(level)
logger.debug("Added a stderr logging handler to logger: %s", __name__)
return handler
# ... Clean up.
del NullHandler
# All warning filters *must* be appended unless you're really certain that they
# shouldn't be: otherwise, it's very hard for users to use most Python
# mechanisms to silence them.
# SecurityWarning's always go off by default.
warnings.simplefilter("always", exceptions.SecurityWarning, append=True)
# InsecurePlatformWarning's don't vary between requests, so we keep it default.
warnings.simplefilter("default", exceptions.InsecurePlatformWarning, append=True)
def disable_warnings(category: type[Warning] = exceptions.HTTPWarning) -> None:
"""
Helper for quickly disabling all urllib3 warnings.
"""
warnings.simplefilter("ignore", category)
_DEFAULT_POOL = PoolManager()
def request(
method: str,
url: str,
*,
body: _TYPE_BODY | None = None,
fields: _TYPE_FIELDS | None = None,
headers: typing.Mapping[str, str] | None = None,
preload_content: bool | None = True,
decode_content: bool | None = True,
redirect: bool | None = True,
retries: Retry | bool | int | None = None,
timeout: Timeout | float | int | None = 3,
json: typing.Any | None = None,
) -> BaseHTTPResponse:
"""
A convenience, top-level request method. It uses a module-global ``PoolManager`` instance.
Therefore, its side effects could be shared across dependencies relying on it.
To avoid side effects create a new ``PoolManager`` instance and use it instead.
The method does not accept low-level ``**urlopen_kw`` keyword arguments.
:param method:
HTTP request method (such as GET, POST, PUT, etc.)
:param url:
The URL to perform the request on.
:param body:
Data to send in the request body, either :class:`str`, :class:`bytes`,
an iterable of :class:`str`/:class:`bytes`, or a file-like object.
:param fields:
Data to encode and send in the request body.
:param headers:
Dictionary of custom headers to send, such as User-Agent,
If-None-Match, etc.
:param bool preload_content:
If True, the response's body will be preloaded into memory.
:param bool decode_content:
If True, will attempt to decode the body based on the
'content-encoding' header.
:param redirect:
If True, automatically handle redirects (status codes 301, 302,
303, 307, 308). Each redirect counts as a retry. Disabling retries
will disable redirect, too.
:param retries:
Configure the number of retries to allow before raising a
:class:`~urllib3.exceptions.MaxRetryError` exception.
If ``None`` (default) will retry 3 times, see ``Retry.DEFAULT``. Pass a
:class:`~urllib3.util.retry.Retry` object for fine-grained control
over different types of retries.
Pass an integer number to retry connection errors that many times,
but no other types of errors. Pass zero to never retry.
If ``False``, then retries are disabled and any exception is raised
immediately. Also, instead of raising a MaxRetryError on redirects,
the redirect response will be returned.
:type retries: :class:`~urllib3.util.retry.Retry`, False, or an int.
:param timeout:
If specified, overrides the default timeout for this one
request. It may be a float (in seconds) or an instance of
:class:`urllib3.util.Timeout`.
:param json:
Data to encode and send as JSON with UTF-encoded in the request body.
The ``"Content-Type"`` header will be set to ``"application/json"``
unless specified otherwise.
"""
return _DEFAULT_POOL.request(
method,
url,
body=body,
fields=fields,
headers=headers,
preload_content=preload_content,
decode_content=decode_content,
redirect=redirect,
retries=retries,
timeout=timeout,
json=json,
)
if sys.platform == "emscripten":
from .contrib.emscripten import inject_into_urllib3 # noqa: 401
inject_into_urllib3()

165
venv/lib/python3.12/site-packages/urllib3/_base_connection.py Normal file
View File

@@ -0,0 +1,165 @@
from __future__ import annotations
import typing
from .util.connection import _TYPE_SOCKET_OPTIONS
from .util.timeout import _DEFAULT_TIMEOUT, _TYPE_TIMEOUT
from .util.url import Url
_TYPE_BODY = typing.Union[bytes, typing.IO[typing.Any], typing.Iterable[bytes], str]
class ProxyConfig(typing.NamedTuple):
ssl_context: ssl.SSLContext | None
use_forwarding_for_https: bool
assert_hostname: None | str | typing.Literal[False]
assert_fingerprint: str | None
class _ResponseOptions(typing.NamedTuple):
# TODO: Remove this in favor of a better
# HTTP request/response lifecycle tracking.
request_method: str
request_url: str
preload_content: bool
decode_content: bool
enforce_content_length: bool
if typing.TYPE_CHECKING:
import ssl
from typing import Protocol
from .response import BaseHTTPResponse
class BaseHTTPConnection(Protocol):
default_port: typing.ClassVar[int]
default_socket_options: typing.ClassVar[_TYPE_SOCKET_OPTIONS]
host: str
port: int
timeout: None | (
float
) # Instance doesn't store _DEFAULT_TIMEOUT, must be resolved.
blocksize: int
source_address: tuple[str, int] | None
socket_options: _TYPE_SOCKET_OPTIONS | None
proxy: Url | None
proxy_config: ProxyConfig | None
is_verified: bool
proxy_is_verified: bool | None
def __init__(
self,
host: str,
port: int | None = None,
*,
timeout: _TYPE_TIMEOUT = _DEFAULT_TIMEOUT,
source_address: tuple[str, int] | None = None,
blocksize: int = 8192,
socket_options: _TYPE_SOCKET_OPTIONS | None = ...,
proxy: Url | None = None,
proxy_config: ProxyConfig | None = None,
) -> None: ...
def set_tunnel(
self,
host: str,
port: int | None = None,
headers: typing.Mapping[str, str] | None = None,
scheme: str = "http",
) -> None: ...
def connect(self) -> None: ...
def request(
self,
method: str,
url: str,
body: _TYPE_BODY | None = None,
headers: typing.Mapping[str, str] | None = None,
# We know *at least* botocore is depending on the order of the
# first 3 parameters so to be safe we only mark the later ones
# as keyword-only to ensure we have space to extend.
*,
chunked: bool = False,
preload_content: bool = True,
decode_content: bool = True,
enforce_content_length: bool = True,
) -> None: ...
def getresponse(self) -> BaseHTTPResponse: ...
def close(self) -> None: ...
@property
def is_closed(self) -> bool:
"""Whether the connection either is brand new or has been previously closed.
If this property is True then both ``is_connected`` and ``has_connected_to_proxy``
properties must be False.
"""
@property
def is_connected(self) -> bool:
"""Whether the connection is actively connected to any origin (proxy or target)"""
@property
def has_connected_to_proxy(self) -> bool:
"""Whether the connection has successfully connected to its proxy.
This returns False if no proxy is in use. Used to determine whether
errors are coming from the proxy layer or from tunnelling to the target origin.
"""
class BaseHTTPSConnection(BaseHTTPConnection, Protocol):
default_port: typing.ClassVar[int]
default_socket_options: typing.ClassVar[_TYPE_SOCKET_OPTIONS]
# Certificate verification methods
cert_reqs: int | str | None
assert_hostname: None | str | typing.Literal[False]
assert_fingerprint: str | None
ssl_context: ssl.SSLContext | None
# Trusted CAs
ca_certs: str | None
ca_cert_dir: str | None
ca_cert_data: None | str | bytes
# TLS version
ssl_minimum_version: int | None
ssl_maximum_version: int | None
ssl_version: int | str | None # Deprecated
# Client certificates
cert_file: str | None
key_file: str | None
key_password: str | None
def __init__(
self,
host: str,
port: int | None = None,
*,
timeout: _TYPE_TIMEOUT = _DEFAULT_TIMEOUT,
source_address: tuple[str, int] | None = None,
blocksize: int = 16384,
socket_options: _TYPE_SOCKET_OPTIONS | None = ...,
proxy: Url | None = None,
proxy_config: ProxyConfig | None = None,
cert_reqs: int | str | None = None,
assert_hostname: None | str | typing.Literal[False] = None,
assert_fingerprint: str | None = None,
server_hostname: str | None = None,
ssl_context: ssl.SSLContext | None = None,
ca_certs: str | None = None,
ca_cert_dir: str | None = None,
ca_cert_data: None | str | bytes = None,
ssl_minimum_version: int | None = None,
ssl_maximum_version: int | None = None,
ssl_version: int | str | None = None, # Deprecated
cert_file: str | None = None,
key_file: str | None = None,
key_password: str | None = None,
) -> None: ...

479
venv/lib/python3.12/site-packages/urllib3/_collections.py Normal file
View File

@@ -0,0 +1,479 @@
from __future__ import annotations
import typing
from collections import OrderedDict
from enum import Enum, auto
from threading import RLock
if typing.TYPE_CHECKING:
# We can only import Protocol if TYPE_CHECKING because it's a development
# dependency, and is not available at runtime.
from typing import Protocol
from typing_extensions import Self
class HasGettableStringKeys(Protocol):
def keys(self) -> typing.Iterator[str]: ...
def __getitem__(self, key: str) -> str: ...
__all__ = ["RecentlyUsedContainer", "HTTPHeaderDict"]
# Key type
_KT = typing.TypeVar("_KT")
# Value type
_VT = typing.TypeVar("_VT")
# Default type
_DT = typing.TypeVar("_DT")
ValidHTTPHeaderSource = typing.Union[
"HTTPHeaderDict",
typing.Mapping[str, str],
typing.Iterable[tuple[str, str]],
"HasGettableStringKeys",
]
class _Sentinel(Enum):
not_passed = auto()
def ensure_can_construct_http_header_dict(
potential: object,
) -> ValidHTTPHeaderSource | None:
if isinstance(potential, HTTPHeaderDict):
return potential
elif isinstance(potential, typing.Mapping):
# Full runtime checking of the contents of a Mapping is expensive, so for the
# purposes of typechecking, we assume that any Mapping is the right shape.
return typing.cast(typing.Mapping[str, str], potential)
elif isinstance(potential, typing.Iterable):
# Similarly to Mapping, full runtime checking of the contents of an Iterable is
# expensive, so for the purposes of typechecking, we assume that any Iterable
# is the right shape.
return typing.cast(typing.Iterable[tuple[str, str]], potential)
elif hasattr(potential, "keys") and hasattr(potential, "__getitem__"):
return typing.cast("HasGettableStringKeys", potential)
else:
return None
class RecentlyUsedContainer(typing.Generic[_KT, _VT], typing.MutableMapping[_KT, _VT]):
"""
Provides a thread-safe dict-like container which maintains up to
``maxsize`` keys while throwing away the least-recently-used keys beyond
``maxsize``.
:param maxsize:
Maximum number of recent elements to retain.
:param dispose_func:
Every time an item is evicted from the container,
``dispose_func(value)`` is called. Callback which will get called
"""
_container: typing.OrderedDict[_KT, _VT]
_maxsize: int
dispose_func: typing.Callable[[_VT], None] | None
lock: RLock
def __init__(
self,
maxsize: int = 10,
dispose_func: typing.Callable[[_VT], None] | None = None,
) -> None:
super().__init__()
self._maxsize = maxsize
self.dispose_func = dispose_func
self._container = OrderedDict()
self.lock = RLock()
def __getitem__(self, key: _KT) -> _VT:
# Re-insert the item, moving it to the end of the eviction line.
with self.lock:
item = self._container.pop(key)
self._container[key] = item
return item
def __setitem__(self, key: _KT, value: _VT) -> None:
evicted_item = None
with self.lock:
# Possibly evict the existing value of 'key'
try:
# If the key exists, we'll overwrite it, which won't change the
# size of the pool. Because accessing a key should move it to
# the end of the eviction line, we pop it out first.
evicted_item = key, self._container.pop(key)
self._container[key] = value
except KeyError:
# When the key does not exist, we insert the value first so that
# evicting works in all cases, including when self._maxsize is 0
self._container[key] = value
if len(self._container) > self._maxsize:
# If we didn't evict an existing value, and we've hit our maximum
# size, then we have to evict the least recently used item from
# the beginning of the container.
evicted_item = self._container.popitem(last=False)
# After releasing the lock on the pool, dispose of any evicted value.
if evicted_item is not None and self.dispose_func:
_, evicted_value = evicted_item
self.dispose_func(evicted_value)
def __delitem__(self, key: _KT) -> None:
with self.lock:
value = self._container.pop(key)
if self.dispose_func:
self.dispose_func(value)
def __len__(self) -> int:
with self.lock:
return len(self._container)
def __iter__(self) -> typing.NoReturn:
raise NotImplementedError(
"Iteration over this class is unlikely to be threadsafe."
)
def clear(self) -> None:
with self.lock:
# Copy pointers to all values, then wipe the mapping
values = list(self._container.values())
self._container.clear()
if self.dispose_func:
for value in values:
self.dispose_func(value)
def keys(self) -> set[_KT]: # type: ignore[override]
with self.lock:
return set(self._container.keys())
class HTTPHeaderDictItemView(set[tuple[str, str]]):
"""
HTTPHeaderDict is unusual for a Mapping[str, str] in that it has two modes of
address.
If we directly try to get an item with a particular name, we will get a string
back that is the concatenated version of all the values:
>>> d['X-Header-Name']
'Value1, Value2, Value3'
However, if we iterate over an HTTPHeaderDict's items, we will optionally combine
these values based on whether combine=True was called when building up the dictionary
>>> d = HTTPHeaderDict({"A": "1", "B": "foo"})
>>> d.add("A", "2", combine=True)
>>> d.add("B", "bar")
>>> list(d.items())
[
('A', '1, 2'),
('B', 'foo'),
('B', 'bar'),
]
This class conforms to the interface required by the MutableMapping ABC while
also giving us the nonstandard iteration behavior we want; items with duplicate
keys, ordered by time of first insertion.
"""
_headers: HTTPHeaderDict
def __init__(self, headers: HTTPHeaderDict) -> None:
self._headers = headers
def __len__(self) -> int:
return len(list(self._headers.iteritems()))
def __iter__(self) -> typing.Iterator[tuple[str, str]]:
return self._headers.iteritems()
def __contains__(self, item: object) -> bool:
if isinstance(item, tuple) and len(item) == 2:
passed_key, passed_val = item
if isinstance(passed_key, str) and isinstance(passed_val, str):
return self._headers._has_value_for_header(passed_key, passed_val)
return False
class HTTPHeaderDict(typing.MutableMapping[str, str]):
"""
:param headers:
An iterable of field-value pairs. Must not contain multiple field names
when compared case-insensitively.
:param kwargs:
Additional field-value pairs to pass in to ``dict.update``.
A ``dict`` like container for storing HTTP Headers.
Field names are stored and compared case-insensitively in compliance with
RFC 7230. Iteration provides the first case-sensitive key seen for each
case-insensitive pair.
Using ``__setitem__`` syntax overwrites fields that compare equal
case-insensitively in order to maintain ``dict``'s api. For fields that
compare equal, instead create a new ``HTTPHeaderDict`` and use ``.add``
in a loop.
If multiple fields that are equal case-insensitively are passed to the
constructor or ``.update``, the behavior is undefined and some will be
lost.
>>> headers = HTTPHeaderDict()
>>> headers.add('Set-Cookie', 'foo=bar')
>>> headers.add('set-cookie', 'baz=quxx')
>>> headers['content-length'] = '7'
>>> headers['SET-cookie']
'foo=bar, baz=quxx'
>>> headers['Content-Length']
'7'
"""
_container: typing.MutableMapping[str, list[str]]
def __init__(self, headers: ValidHTTPHeaderSource | None = None, **kwargs: str):
super().__init__()
self._container = {} # 'dict' is insert-ordered
if headers is not None:
if isinstance(headers, HTTPHeaderDict):
self._copy_from(headers)
else:
self.extend(headers)
if kwargs:
self.extend(kwargs)
def __setitem__(self, key: str, val: str) -> None:
# avoid a bytes/str comparison by decoding before httplib
if isinstance(key, bytes):
key = key.decode("latin-1")
self._container[key.lower()] = [key, val]
def __getitem__(self, key: str) -> str:
val = self._container[key.lower()]
return ", ".join(val[1:])
def __delitem__(self, key: str) -> None:
del self._container[key.lower()]
def __contains__(self, key: object) -> bool:
if isinstance(key, str):
return key.lower() in self._container
return False
def setdefault(self, key: str, default: str = "") -> str:
return super().setdefault(key, default)
def __eq__(self, other: object) -> bool:
maybe_constructable = ensure_can_construct_http_header_dict(other)
if maybe_constructable is None:
return False
else:
other_as_http_header_dict = type(self)(maybe_constructable)
return {k.lower(): v for k, v in self.itermerged()} == {
k.lower(): v for k, v in other_as_http_header_dict.itermerged()
}
def __ne__(self, other: object) -> bool:
return not self.__eq__(other)
def __len__(self) -> int:
return len(self._container)
def __iter__(self) -> typing.Iterator[str]:
# Only provide the originally cased names
for vals in self._container.values():
yield vals[0]
def discard(self, key: str) -> None:
try:
del self[key]
except KeyError:
pass
def add(self, key: str, val: str, *, combine: bool = False) -> None:
"""Adds a (name, value) pair, doesn't overwrite the value if it already
exists.
If this is called with combine=True, instead of adding a new header value
as a distinct item during iteration, this will instead append the value to
any existing header value with a comma. If no existing header value exists
for the key, then the value will simply be added, ignoring the combine parameter.
>>> headers = HTTPHeaderDict(foo='bar')
>>> headers.add('Foo', 'baz')
>>> headers['foo']
'bar, baz'
>>> list(headers.items())
[('foo', 'bar'), ('foo', 'baz')]
>>> headers.add('foo', 'quz', combine=True)
>>> list(headers.items())
[('foo', 'bar, baz, quz')]
"""
# avoid a bytes/str comparison by decoding before httplib
if isinstance(key, bytes):
key = key.decode("latin-1")
key_lower = key.lower()
new_vals = [key, val]
# Keep the common case aka no item present as fast as possible
vals = self._container.setdefault(key_lower, new_vals)
if new_vals is not vals:
# if there are values here, then there is at least the initial
# key/value pair
assert len(vals) >= 2
if combine:
vals[-1] = vals[-1] + ", " + val
else:
vals.append(val)
def extend(self, *args: ValidHTTPHeaderSource, **kwargs: str) -> None:
"""Generic import function for any type of header-like object.
Adapted version of MutableMapping.update in order to insert items
with self.add instead of self.__setitem__
"""
if len(args) > 1:
raise TypeError(
f"extend() takes at most 1 positional arguments ({len(args)} given)"
)
other = args[0] if len(args) >= 1 else ()
if isinstance(other, HTTPHeaderDict):
for key, val in other.iteritems():
self.add(key, val)
elif isinstance(other, typing.Mapping):
for key, val in other.items():
self.add(key, val)
elif isinstance(other, typing.Iterable):
other = typing.cast(typing.Iterable[tuple[str, str]], other)
for key, value in other:
self.add(key, value)
elif hasattr(other, "keys") and hasattr(other, "__getitem__"):
# THIS IS NOT A TYPESAFE BRANCH
# In this branch, the object has a `keys` attr but is not a Mapping or any of
# the other types indicated in the method signature. We do some stuff with
# it as though it partially implements the Mapping interface, but we're not
# doing that stuff safely AT ALL.
for key in other.keys():
self.add(key, other[key])
for key, value in kwargs.items():
self.add(key, value)
@typing.overload
def getlist(self, key: str) -> list[str]: ...
@typing.overload
def getlist(self, key: str, default: _DT) -> list[str] | _DT: ...
def getlist(
self, key: str, default: _Sentinel | _DT = _Sentinel.not_passed
) -> list[str] | _DT:
"""Returns a list of all the values for the named field. Returns an
empty list if the key doesn't exist."""
try:
vals = self._container[key.lower()]
except KeyError:
if default is _Sentinel.not_passed:
# _DT is unbound; empty list is instance of List[str]
return []
# _DT is bound; default is instance of _DT
return default
else:
# _DT may or may not be bound; vals[1:] is instance of List[str], which
# meets our external interface requirement of `Union[List[str], _DT]`.
return vals[1:]
def _prepare_for_method_change(self) -> Self:
"""
Remove content-specific header fields before changing the request
method to GET or HEAD according to RFC 9110, Section 15.4.
"""
content_specific_headers = [
"Content-Encoding",
"Content-Language",
"Content-Location",
"Content-Type",
"Content-Length",
"Digest",
"Last-Modified",
]
for header in content_specific_headers:
self.discard(header)
return self
# Backwards compatibility for httplib
getheaders = getlist
getallmatchingheaders = getlist
iget = getlist
# Backwards compatibility for http.cookiejar
get_all = getlist
def __repr__(self) -> str:
return f"{type(self).__name__}({dict(self.itermerged())})"
def _copy_from(self, other: HTTPHeaderDict) -> None:
for key in other:
val = other.getlist(key)
self._container[key.lower()] = [key, *val]
def copy(self) -> Self:
clone = type(self)()
clone._copy_from(self)
return clone
def iteritems(self) -> typing.Iterator[tuple[str, str]]:
"""Iterate over all header lines, including duplicate ones."""
for key in self:
vals = self._container[key.lower()]
for val in vals[1:]:
yield vals[0], val
def itermerged(self) -> typing.Iterator[tuple[str, str]]:
"""Iterate over all headers, merging duplicate ones together."""
for key in self:
val = self._container[key.lower()]
yield val[0], ", ".join(val[1:])
def items(self) -> HTTPHeaderDictItemView: # type: ignore[override]
return HTTPHeaderDictItemView(self)
def _has_value_for_header(self, header_name: str, potential_value: str) -> bool:
if header_name in self:
return potential_value in self._container[header_name.lower()][1:]
return False
def __ior__(self, other: object) -> HTTPHeaderDict:
# Supports extending a header dict in-place using operator |=
# combining items with add instead of __setitem__
maybe_constructable = ensure_can_construct_http_header_dict(other)
if maybe_constructable is None:
return NotImplemented
self.extend(maybe_constructable)
return self
def __or__(self, other: object) -> Self:
# Supports merging header dicts using operator |
# combining items with add instead of __setitem__
maybe_constructable = ensure_can_construct_http_header_dict(other)
if maybe_constructable is None:
return NotImplemented
result = self.copy()
result.extend(maybe_constructable)
return result
def __ror__(self, other: object) -> Self:
# Supports merging header dicts using operator | when other is on left side
# combining items with add instead of __setitem__
maybe_constructable = ensure_can_construct_http_header_dict(other)
if maybe_constructable is None:
return NotImplemented
result = type(self)(maybe_constructable)
result.extend(self)
return result

278
venv/lib/python3.12/site-packages/urllib3/_request_methods.py Normal file
View File

@@ -0,0 +1,278 @@
from __future__ import annotations
import json as _json
import typing
from urllib.parse import urlencode
from ._base_connection import _TYPE_BODY
from ._collections import HTTPHeaderDict
from .filepost import _TYPE_FIELDS, encode_multipart_formdata
from .response import BaseHTTPResponse
__all__ = ["RequestMethods"]
_TYPE_ENCODE_URL_FIELDS = typing.Union[
typing.Sequence[tuple[str, typing.Union[str, bytes]]],
typing.Mapping[str, typing.Union[str, bytes]],
]
class RequestMethods:
"""
Convenience mixin for classes who implement a :meth:`urlopen` method, such
as :class:`urllib3.HTTPConnectionPool` and
:class:`urllib3.PoolManager`.
Provides behavior for making common types of HTTP request methods and
decides which type of request field encoding to use.
Specifically,
:meth:`.request_encode_url` is for sending requests whose fields are
encoded in the URL (such as GET, HEAD, DELETE).
:meth:`.request_encode_body` is for sending requests whose fields are
encoded in the *body* of the request using multipart or www-form-urlencoded
(such as for POST, PUT, PATCH).
:meth:`.request` is for making any kind of request, it will look up the
appropriate encoding format and use one of the above two methods to make
the request.
Initializer parameters:
:param headers:
Headers to include with all requests, unless other headers are given
explicitly.
"""
_encode_url_methods = {"DELETE", "GET", "HEAD", "OPTIONS"}
def __init__(self, headers: typing.Mapping[str, str] | None = None) -> None:
self.headers = headers or {}
def urlopen(
self,
method: str,
url: str,
body: _TYPE_BODY | None = None,
headers: typing.Mapping[str, str] | None = None,
encode_multipart: bool = True,
multipart_boundary: str | None = None,
**kw: typing.Any,
) -> BaseHTTPResponse: # Abstract
raise NotImplementedError(
"Classes extending RequestMethods must implement "
"their own ``urlopen`` method."
)
def request(
self,
method: str,
url: str,
body: _TYPE_BODY | None = None,
fields: _TYPE_FIELDS | None = None,
headers: typing.Mapping[str, str] | None = None,
json: typing.Any | None = None,
**urlopen_kw: typing.Any,
) -> BaseHTTPResponse:
"""
Make a request using :meth:`urlopen` with the appropriate encoding of
``fields`` based on the ``method`` used.
This is a convenience method that requires the least amount of manual
effort. It can be used in most situations, while still having the
option to drop down to more specific methods when necessary, such as
:meth:`request_encode_url`, :meth:`request_encode_body`,
or even the lowest level :meth:`urlopen`.
:param method:
HTTP request method (such as GET, POST, PUT, etc.)
:param url:
The URL to perform the request on.
:param body:
Data to send in the request body, either :class:`str`, :class:`bytes`,
an iterable of :class:`str`/:class:`bytes`, or a file-like object.
:param fields:
Data to encode and send in the URL or request body, depending on ``method``.
:param headers:
Dictionary of custom headers to send, such as User-Agent,
If-None-Match, etc. If None, pool headers are used. If provided,
these headers completely replace any pool-specific headers.
:param json:
Data to encode and send as JSON with UTF-encoded in the request body.
The ``"Content-Type"`` header will be set to ``"application/json"``
unless specified otherwise.
"""
method = method.upper()
if json is not None and body is not None:
raise TypeError(
"request got values for both 'body' and 'json' parameters which are mutually exclusive"
)
if json is not None:
if headers is None:
headers = self.headers
if not ("content-type" in map(str.lower, headers.keys())):
headers = HTTPHeaderDict(headers)
headers["Content-Type"] = "application/json"
body = _json.dumps(json, separators=(",", ":"), ensure_ascii=False).encode(
"utf-8"
)
if body is not None:
urlopen_kw["body"] = body
if method in self._encode_url_methods:
return self.request_encode_url(
method,
url,
fields=fields, # type: ignore[arg-type]
headers=headers,
**urlopen_kw,
)
else:
return self.request_encode_body(
method, url, fields=fields, headers=headers, **urlopen_kw
)
def request_encode_url(
self,
method: str,
url: str,
fields: _TYPE_ENCODE_URL_FIELDS | None = None,
headers: typing.Mapping[str, str] | None = None,
**urlopen_kw: str,
) -> BaseHTTPResponse:
"""
Make a request using :meth:`urlopen` with the ``fields`` encoded in
the url. This is useful for request methods like GET, HEAD, DELETE, etc.
:param method:
HTTP request method (such as GET, POST, PUT, etc.)
:param url:
The URL to perform the request on.
:param fields:
Data to encode and send in the URL.
:param headers:
Dictionary of custom headers to send, such as User-Agent,
If-None-Match, etc. If None, pool headers are used. If provided,
these headers completely replace any pool-specific headers.
"""
if headers is None:
headers = self.headers
extra_kw: dict[str, typing.Any] = {"headers": headers}
extra_kw.update(urlopen_kw)
if fields:
url += "?" + urlencode(fields)
return self.urlopen(method, url, **extra_kw)
def request_encode_body(
self,
method: str,
url: str,
fields: _TYPE_FIELDS | None = None,
headers: typing.Mapping[str, str] | None = None,
encode_multipart: bool = True,
multipart_boundary: str | None = None,
**urlopen_kw: str,
) -> BaseHTTPResponse:
"""
Make a request using :meth:`urlopen` with the ``fields`` encoded in
the body. This is useful for request methods like POST, PUT, PATCH, etc.
When ``encode_multipart=True`` (default), then
:func:`urllib3.encode_multipart_formdata` is used to encode
the payload with the appropriate content type. Otherwise
:func:`urllib.parse.urlencode` is used with the
'application/x-www-form-urlencoded' content type.
Multipart encoding must be used when posting files, and it's reasonably
safe to use it in other times too. However, it may break request
signing, such as with OAuth.
Supports an optional ``fields`` parameter of key/value strings AND
key/filetuple. A filetuple is a (filename, data, MIME type) tuple where
the MIME type is optional. For example::
fields = {
'foo': 'bar',
'fakefile': ('foofile.txt', 'contents of foofile'),
'realfile': ('barfile.txt', open('realfile').read()),
'typedfile': ('bazfile.bin', open('bazfile').read(),
'image/jpeg'),
'nonamefile': 'contents of nonamefile field',
}
When uploading a file, providing a filename (the first parameter of the
tuple) is optional but recommended to best mimic behavior of browsers.
Note that if ``headers`` are supplied, the 'Content-Type' header will
be overwritten because it depends on the dynamic random boundary string
which is used to compose the body of the request. The random boundary
string can be explicitly set with the ``multipart_boundary`` parameter.
:param method:
HTTP request method (such as GET, POST, PUT, etc.)
:param url:
The URL to perform the request on.
:param fields:
Data to encode and send in the request body.
:param headers:
Dictionary of custom headers to send, such as User-Agent,
If-None-Match, etc. If None, pool headers are used. If provided,
these headers completely replace any pool-specific headers.
:param encode_multipart:
If True, encode the ``fields`` using the multipart/form-data MIME
format.
:param multipart_boundary:
If not specified, then a random boundary will be generated using
:func:`urllib3.filepost.choose_boundary`.
"""
if headers is None:
headers = self.headers
extra_kw: dict[str, typing.Any] = {"headers": HTTPHeaderDict(headers)}
body: bytes | str
if fields:
if "body" in urlopen_kw:
raise TypeError(
"request got values for both 'fields' and 'body', can only specify one."
)
if encode_multipart:
body, content_type = encode_multipart_formdata(
fields, boundary=multipart_boundary
)
else:
body, content_type = (
urlencode(fields), # type: ignore[arg-type]
"application/x-www-form-urlencoded",
)
extra_kw["body"] = body
extra_kw["headers"].setdefault("Content-Type", content_type)
extra_kw.update(urlopen_kw)
return self.urlopen(method, url, **extra_kw)

21
venv/lib/python3.12/site-packages/urllib3/_version.py Normal file
View File

@@ -0,0 +1,21 @@
# file generated by setuptools-scm
# don't change, don't track in version control
__all__ = ["__version__", "__version_tuple__", "version", "version_tuple"]
TYPE_CHECKING = False
if TYPE_CHECKING:
from typing import Tuple
from typing import Union
VERSION_TUPLE = Tuple[Union[int, str], ...]
else:
VERSION_TUPLE = object
version: str
__version__: str
__version_tuple__: VERSION_TUPLE
version_tuple: VERSION_TUPLE
__version__ = version = '2.5.0'
__version_tuple__ = version_tuple = (2, 5, 0)

1093
venv/lib/python3.12/site-packages/urllib3/connection.py Normal file
View File

File diff suppressed because it is too large Load Diff

1178
venv/lib/python3.12/site-packages/urllib3/connectionpool.py Normal file
View File

File diff suppressed because it is too large Load Diff

0
venv/lib/python3.12/site-packages/urllib3/contrib/__init__.py Normal file
View File

16
venv/lib/python3.12/site-packages/urllib3/contrib/emscripten/__init__.py Normal file
View File

@@ -0,0 +1,16 @@
from __future__ import annotations
import urllib3.connection
from ...connectionpool import HTTPConnectionPool, HTTPSConnectionPool
from .connection import EmscriptenHTTPConnection, EmscriptenHTTPSConnection
def inject_into_urllib3() -> None:
# override connection classes to use emscripten specific classes
# n.b. mypy complains about the overriding of classes below
# if it isn't ignored
HTTPConnectionPool.ConnectionCls = EmscriptenHTTPConnection
HTTPSConnectionPool.ConnectionCls = EmscriptenHTTPSConnection
urllib3.connection.HTTPConnection = EmscriptenHTTPConnection # type: ignore[misc,assignment]
urllib3.connection.HTTPSConnection = EmscriptenHTTPSConnection # type: ignore[misc,assignment]

255
venv/lib/python3.12/site-packages/urllib3/contrib/emscripten/connection.py Normal file
View File

@@ -0,0 +1,255 @@
from __future__ import annotations
import os
import typing
# use http.client.HTTPException for consistency with non-emscripten
from http.client import HTTPException as HTTPException # noqa: F401
from http.client import ResponseNotReady
from ..._base_connection import _TYPE_BODY
from ...connection import HTTPConnection, ProxyConfig, port_by_scheme
from ...exceptions import TimeoutError
from ...response import BaseHTTPResponse
from ...util.connection import _TYPE_SOCKET_OPTIONS
from ...util.timeout import _DEFAULT_TIMEOUT, _TYPE_TIMEOUT
from ...util.url import Url
from .fetch import _RequestError, _TimeoutError, send_request, send_streaming_request
from .request import EmscriptenRequest
from .response import EmscriptenHttpResponseWrapper, EmscriptenResponse
if typing.TYPE_CHECKING:
from ..._base_connection import BaseHTTPConnection, BaseHTTPSConnection
class EmscriptenHTTPConnection:
default_port: typing.ClassVar[int] = port_by_scheme["http"]
default_socket_options: typing.ClassVar[_TYPE_SOCKET_OPTIONS]
timeout: None | (float)
host: str
port: int
blocksize: int
source_address: tuple[str, int] | None
socket_options: _TYPE_SOCKET_OPTIONS | None
proxy: Url | None
proxy_config: ProxyConfig | None
is_verified: bool = False
proxy_is_verified: bool | None = None
_response: EmscriptenResponse | None
def __init__(
self,
host: str,
port: int = 0,
*,
timeout: _TYPE_TIMEOUT = _DEFAULT_TIMEOUT,
source_address: tuple[str, int] | None = None,
blocksize: int = 8192,
socket_options: _TYPE_SOCKET_OPTIONS | None = None,
proxy: Url | None = None,
proxy_config: ProxyConfig | None = None,
) -> None:
self.host = host
self.port = port
self.timeout = timeout if isinstance(timeout, float) else 0.0
self.scheme = "http"
self._closed = True
self._response = None
# ignore these things because we don't
# have control over that stuff
self.proxy = None
self.proxy_config = None
self.blocksize = blocksize
self.source_address = None
self.socket_options = None
self.is_verified = False
def set_tunnel(
self,
host: str,
port: int | None = 0,
headers: typing.Mapping[str, str] | None = None,
scheme: str = "http",
) -> None:
pass
def connect(self) -> None:
pass
def request(
self,
method: str,
url: str,
body: _TYPE_BODY | None = None,
headers: typing.Mapping[str, str] | None = None,
# We know *at least* botocore is depending on the order of the
# first 3 parameters so to be safe we only mark the later ones
# as keyword-only to ensure we have space to extend.
*,
chunked: bool = False,
preload_content: bool = True,
decode_content: bool = True,
enforce_content_length: bool = True,
) -> None:
self._closed = False
if url.startswith("/"):
# no scheme / host / port included, make a full url
url = f"{self.scheme}://{self.host}:{self.port}" + url
request = EmscriptenRequest(
url=url,
method=method,
timeout=self.timeout if self.timeout else 0,
decode_content=decode_content,
)
request.set_body(body)
if headers:
for k, v in headers.items():
request.set_header(k, v)
self._response = None
try:
if not preload_content:
self._response = send_streaming_request(request)
if self._response is None:
self._response = send_request(request)
except _TimeoutError as e:
raise TimeoutError(e.message) from e
except _RequestError as e:
raise HTTPException(e.message) from e
def getresponse(self) -> BaseHTTPResponse:
if self._response is not None:
return EmscriptenHttpResponseWrapper(
internal_response=self._response,
url=self._response.request.url,
connection=self,
)
else:
raise ResponseNotReady()
def close(self) -> None:
self._closed = True
self._response = None
@property
def is_closed(self) -> bool:
"""Whether the connection either is brand new or has been previously closed.
If this property is True then both ``is_connected`` and ``has_connected_to_proxy``
properties must be False.
"""
return self._closed
@property
def is_connected(self) -> bool:
"""Whether the connection is actively connected to any origin (proxy or target)"""
return True
@property
def has_connected_to_proxy(self) -> bool:
"""Whether the connection has successfully connected to its proxy.
This returns False if no proxy is in use. Used to determine whether
errors are coming from the proxy layer or from tunnelling to the target origin.
"""
return False
class EmscriptenHTTPSConnection(EmscriptenHTTPConnection):
default_port = port_by_scheme["https"]
# all this is basically ignored, as browser handles https
cert_reqs: int | str | None = None
ca_certs: str | None = None
ca_cert_dir: str | None = None
ca_cert_data: None | str | bytes = None
cert_file: str | None
key_file: str | None
key_password: str | None
ssl_context: typing.Any | None
ssl_version: int | str | None = None
ssl_minimum_version: int | None = None
ssl_maximum_version: int | None = None
assert_hostname: None | str | typing.Literal[False]
assert_fingerprint: str | None = None
def __init__(
self,
host: str,
port: int = 0,
*,
timeout: _TYPE_TIMEOUT = _DEFAULT_TIMEOUT,
source_address: tuple[str, int] | None = None,
blocksize: int = 16384,
socket_options: (
None | _TYPE_SOCKET_OPTIONS
) = HTTPConnection.default_socket_options,
proxy: Url | None = None,
proxy_config: ProxyConfig | None = None,
cert_reqs: int | str | None = None,
assert_hostname: None | str | typing.Literal[False] = None,
assert_fingerprint: str | None = None,
server_hostname: str | None = None,
ssl_context: typing.Any | None = None,
ca_certs: str | None = None,
ca_cert_dir: str | None = None,
ca_cert_data: None | str | bytes = None,
ssl_minimum_version: int | None = None,
ssl_maximum_version: int | None = None,
ssl_version: int | str | None = None, # Deprecated
cert_file: str | None = None,
key_file: str | None = None,
key_password: str | None = None,
) -> None:
super().__init__(
host,
port=port,
timeout=timeout,
source_address=source_address,
blocksize=blocksize,
socket_options=socket_options,
proxy=proxy,
proxy_config=proxy_config,
)
self.scheme = "https"
self.key_file = key_file
self.cert_file = cert_file
self.key_password = key_password
self.ssl_context = ssl_context
self.server_hostname = server_hostname
self.assert_hostname = assert_hostname
self.assert_fingerprint = assert_fingerprint
self.ssl_version = ssl_version
self.ssl_minimum_version = ssl_minimum_version
self.ssl_maximum_version = ssl_maximum_version
self.ca_certs = ca_certs and os.path.expanduser(ca_certs)
self.ca_cert_dir = ca_cert_dir and os.path.expanduser(ca_cert_dir)
self.ca_cert_data = ca_cert_data
self.cert_reqs = None
# The browser will automatically verify all requests.
# We have no control over that setting.
self.is_verified = True
def set_cert(
self,
key_file: str | None = None,
cert_file: str | None = None,
cert_reqs: int | str | None = None,
key_password: str | None = None,
ca_certs: str | None = None,
assert_hostname: None | str | typing.Literal[False] = None,
assert_fingerprint: str | None = None,
ca_cert_dir: str | None = None,
ca_cert_data: None | str | bytes = None,
) -> None:
pass
# verify that this class implements BaseHTTP(s) connection correctly
if typing.TYPE_CHECKING:
_supports_http_protocol: BaseHTTPConnection = EmscriptenHTTPConnection("", 0)
_supports_https_protocol: BaseHTTPSConnection = EmscriptenHTTPSConnection("", 0)

110
venv/lib/python3.12/site-packages/urllib3/contrib/emscripten/emscripten_fetch_worker.js Normal file
View File

@@ -0,0 +1,110 @@
let Status = {
SUCCESS_HEADER: -1,
SUCCESS_EOF: -2,
ERROR_TIMEOUT: -3,
ERROR_EXCEPTION: -4,
};
let connections = {};
let nextConnectionID = 1;
const encoder = new TextEncoder();
self.addEventListener("message", async function (event) {
if (event.data.close) {
let connectionID = event.data.close;
delete connections[connectionID];
return;
} else if (event.data.getMore) {
let connectionID = event.data.getMore;
let { curOffset, value, reader, intBuffer, byteBuffer } =
connections[connectionID];
// if we still have some in buffer, then just send it back straight away
if (!value || curOffset >= value.length) {
// read another buffer if required
try {
let readResponse = await reader.read();
if (readResponse.done) {
// read everything - clear connection and return
delete connections[connectionID];
Atomics.store(intBuffer, 0, Status.SUCCESS_EOF);
Atomics.notify(intBuffer, 0);
// finished reading successfully
// return from event handler
return;
}
curOffset = 0;
connections[connectionID].value = readResponse.value;
value = readResponse.value;
} catch (error) {
console.log("Request exception:", error);
let errorBytes = encoder.encode(error.message);
let written = errorBytes.length;
byteBuffer.set(errorBytes);
intBuffer[1] = written;
Atomics.store(intBuffer, 0, Status.ERROR_EXCEPTION);
Atomics.notify(intBuffer, 0);
}
}
// send as much buffer as we can
let curLen = value.length - curOffset;
if (curLen > byteBuffer.length) {
curLen = byteBuffer.length;
}
byteBuffer.set(value.subarray(curOffset, curOffset + curLen), 0);
Atomics.store(intBuffer, 0, curLen); // store current length in bytes
Atomics.notify(intBuffer, 0);
curOffset += curLen;
connections[connectionID].curOffset = curOffset;
return;
} else {
// start fetch
let connectionID = nextConnectionID;
nextConnectionID += 1;
const intBuffer = new Int32Array(event.data.buffer);
const byteBuffer = new Uint8Array(event.data.buffer, 8);
try {
const response = await fetch(event.data.url, event.data.fetchParams);
// return the headers first via textencoder
var headers = [];
for (const pair of response.headers.entries()) {
headers.push([pair[0], pair[1]]);
}
let headerObj = {
headers: headers,
status: response.status,
connectionID,
};
const headerText = JSON.stringify(headerObj);
let headerBytes = encoder.encode(headerText);
let written = headerBytes.length;
byteBuffer.set(headerBytes);
intBuffer[1] = written;
// make a connection
connections[connectionID] = {
reader: response.body.getReader(),
intBuffer: intBuffer,
byteBuffer: byteBuffer,
value: undefined,
curOffset: 0,
};
// set header ready
Atomics.store(intBuffer, 0, Status.SUCCESS_HEADER);
Atomics.notify(intBuffer, 0);
// all fetching after this goes through a new postmessage call with getMore
// this allows for parallel requests
} catch (error) {
console.log("Request exception:", error);
let errorBytes = encoder.encode(error.message);
let written = errorBytes.length;
byteBuffer.set(errorBytes);
intBuffer[1] = written;
Atomics.store(intBuffer, 0, Status.ERROR_EXCEPTION);
Atomics.notify(intBuffer, 0);
}
}
});
self.postMessage({ inited: true });

728
venv/lib/python3.12/site-packages/urllib3/contrib/emscripten/fetch.py Normal file
View File

@@ -0,0 +1,728 @@
"""
Support for streaming http requests in emscripten.
A few caveats -
If your browser (or Node.js) has WebAssembly JavaScript Promise Integration enabled
https://github.com/WebAssembly/js-promise-integration/blob/main/proposals/js-promise-integration/Overview.md
*and* you launch pyodide using `pyodide.runPythonAsync`, this will fetch data using the
JavaScript asynchronous fetch api (wrapped via `pyodide.ffi.call_sync`). In this case
timeouts and streaming should just work.
Otherwise, it uses a combination of XMLHttpRequest and a web-worker for streaming.
This approach has several caveats:
Firstly, you can't do streaming http in the main UI thread, because atomics.wait isn't allowed.
Streaming only works if you're running pyodide in a web worker.
Secondly, this uses an extra web worker and SharedArrayBuffer to do the asynchronous fetch
operation, so it requires that you have crossOriginIsolation enabled, by serving over https
(or from localhost) with the two headers below set:
Cross-Origin-Opener-Policy: same-origin
Cross-Origin-Embedder-Policy: require-corp
You can tell if cross origin isolation is successfully enabled by looking at the global crossOriginIsolated variable in
JavaScript console. If it isn't, streaming requests will fallback to XMLHttpRequest, i.e. getting the whole
request into a buffer and then returning it. it shows a warning in the JavaScript console in this case.
Finally, the webworker which does the streaming fetch is created on initial import, but will only be started once
control is returned to javascript. Call `await wait_for_streaming_ready()` to wait for streaming fetch.
NB: in this code, there are a lot of JavaScript objects. They are named js_*
to make it clear what type of object they are.
"""
from __future__ import annotations
import io
import json
from email.parser import Parser
from importlib.resources import files
from typing import TYPE_CHECKING, Any
import js # type: ignore[import-not-found]
from pyodide.ffi import ( # type: ignore[import-not-found]
JsArray,
JsException,
JsProxy,
to_js,
)
if TYPE_CHECKING:
from typing_extensions import Buffer
from .request import EmscriptenRequest
from .response import EmscriptenResponse
"""
There are some headers that trigger unintended CORS preflight requests.
See also https://github.com/koenvo/pyodide-http/issues/22
"""
HEADERS_TO_IGNORE = ("user-agent",)
SUCCESS_HEADER = -1
SUCCESS_EOF = -2
ERROR_TIMEOUT = -3
ERROR_EXCEPTION = -4
_STREAMING_WORKER_CODE = (
files(__package__)
.joinpath("emscripten_fetch_worker.js")
.read_text(encoding="utf-8")
)
class _RequestError(Exception):
def __init__(
self,
message: str | None = None,
*,
request: EmscriptenRequest | None = None,
response: EmscriptenResponse | None = None,
):
self.request = request
self.response = response
self.message = message
super().__init__(self.message)
class _StreamingError(_RequestError):
pass
class _TimeoutError(_RequestError):
pass
def _obj_from_dict(dict_val: dict[str, Any]) -> JsProxy:
return to_js(dict_val, dict_converter=js.Object.fromEntries)
class _ReadStream(io.RawIOBase):
def __init__(
self,
int_buffer: JsArray,
byte_buffer: JsArray,
timeout: float,
worker: JsProxy,
connection_id: int,
request: EmscriptenRequest,
):
self.int_buffer = int_buffer
self.byte_buffer = byte_buffer
self.read_pos = 0
self.read_len = 0
self.connection_id = connection_id
self.worker = worker
self.timeout = int(1000 * timeout) if timeout > 0 else None
self.is_live = True
self._is_closed = False
self.request: EmscriptenRequest | None = request
def __del__(self) -> None:
self.close()
# this is compatible with _base_connection
def is_closed(self) -> bool:
return self._is_closed
# for compatibility with RawIOBase
@property
def closed(self) -> bool:
return self.is_closed()
def close(self) -> None:
if self.is_closed():
return
self.read_len = 0
self.read_pos = 0
self.int_buffer = None
self.byte_buffer = None
self._is_closed = True
self.request = None
if self.is_live:
self.worker.postMessage(_obj_from_dict({"close": self.connection_id}))
self.is_live = False
super().close()
def readable(self) -> bool:
return True
def writable(self) -> bool:
return False
def seekable(self) -> bool:
return False
def readinto(self, byte_obj: Buffer) -> int:
if not self.int_buffer:
raise _StreamingError(
"No buffer for stream in _ReadStream.readinto",
request=self.request,
response=None,
)
if self.read_len == 0:
# wait for the worker to send something
js.Atomics.store(self.int_buffer, 0, ERROR_TIMEOUT)
self.worker.postMessage(_obj_from_dict({"getMore": self.connection_id}))
if (
js.Atomics.wait(self.int_buffer, 0, ERROR_TIMEOUT, self.timeout)
== "timed-out"
):
raise _TimeoutError
data_len = self.int_buffer[0]
if data_len > 0:
self.read_len = data_len
self.read_pos = 0
elif data_len == ERROR_EXCEPTION:
string_len = self.int_buffer[1]
# decode the error string
js_decoder = js.TextDecoder.new()
json_str = js_decoder.decode(self.byte_buffer.slice(0, string_len))
raise _StreamingError(
f"Exception thrown in fetch: {json_str}",
request=self.request,
response=None,
)
else:
# EOF, free the buffers and return zero
# and free the request
self.is_live = False
self.close()
return 0
# copy from int32array to python bytes
ret_length = min(self.read_len, len(memoryview(byte_obj)))
subarray = self.byte_buffer.subarray(
self.read_pos, self.read_pos + ret_length
).to_py()
memoryview(byte_obj)[0:ret_length] = subarray
self.read_len -= ret_length
self.read_pos += ret_length
return ret_length
class _StreamingFetcher:
def __init__(self) -> None:
# make web-worker and data buffer on startup
self.streaming_ready = False
js_data_blob = js.Blob.new(
to_js([_STREAMING_WORKER_CODE], create_pyproxies=False),
_obj_from_dict({"type": "application/javascript"}),
)
def promise_resolver(js_resolve_fn: JsProxy, js_reject_fn: JsProxy) -> None:
def onMsg(e: JsProxy) -> None:
self.streaming_ready = True
js_resolve_fn(e)
def onErr(e: JsProxy) -> None:
js_reject_fn(e) # Defensive: never happens in ci
self.js_worker.onmessage = onMsg
self.js_worker.onerror = onErr
js_data_url = js.URL.createObjectURL(js_data_blob)
self.js_worker = js.globalThis.Worker.new(js_data_url)
self.js_worker_ready_promise = js.globalThis.Promise.new(promise_resolver)
def send(self, request: EmscriptenRequest) -> EmscriptenResponse:
headers = {
k: v for k, v in request.headers.items() if k not in HEADERS_TO_IGNORE
}
body = request.body
fetch_data = {"headers": headers, "body": to_js(body), "method": request.method}
# start the request off in the worker
timeout = int(1000 * request.timeout) if request.timeout > 0 else None
js_shared_buffer = js.SharedArrayBuffer.new(1048576)
js_int_buffer = js.Int32Array.new(js_shared_buffer)
js_byte_buffer = js.Uint8Array.new(js_shared_buffer, 8)
js.Atomics.store(js_int_buffer, 0, ERROR_TIMEOUT)
js.Atomics.notify(js_int_buffer, 0)
js_absolute_url = js.URL.new(request.url, js.location).href
self.js_worker.postMessage(
_obj_from_dict(
{
"buffer": js_shared_buffer,
"url": js_absolute_url,
"fetchParams": fetch_data,
}
)
)
# wait for the worker to send something
js.Atomics.wait(js_int_buffer, 0, ERROR_TIMEOUT, timeout)
if js_int_buffer[0] == ERROR_TIMEOUT:
raise _TimeoutError(
"Timeout connecting to streaming request",
request=request,
response=None,
)
elif js_int_buffer[0] == SUCCESS_HEADER:
# got response
# header length is in second int of intBuffer
string_len = js_int_buffer[1]
# decode the rest to a JSON string
js_decoder = js.TextDecoder.new()
# this does a copy (the slice) because decode can't work on shared array
# for some silly reason
json_str = js_decoder.decode(js_byte_buffer.slice(0, string_len))
# get it as an object
response_obj = json.loads(json_str)
return EmscriptenResponse(
request=request,
status_code=response_obj["status"],
headers=response_obj["headers"],
body=_ReadStream(
js_int_buffer,
js_byte_buffer,
request.timeout,
self.js_worker,
response_obj["connectionID"],
request,
),
)
elif js_int_buffer[0] == ERROR_EXCEPTION:
string_len = js_int_buffer[1]
# decode the error string
js_decoder = js.TextDecoder.new()
json_str = js_decoder.decode(js_byte_buffer.slice(0, string_len))
raise _StreamingError(
f"Exception thrown in fetch: {json_str}", request=request, response=None
)
else:
raise _StreamingError(
f"Unknown status from worker in fetch: {js_int_buffer[0]}",
request=request,
response=None,
)
class _JSPIReadStream(io.RawIOBase):
"""
A read stream that uses pyodide.ffi.run_sync to read from a JavaScript fetch
response. This requires support for WebAssembly JavaScript Promise Integration
in the containing browser, and for pyodide to be launched via runPythonAsync.
:param js_read_stream:
The JavaScript stream reader
:param timeout:
Timeout in seconds
:param request:
The request we're handling
:param response:
The response this stream relates to
:param js_abort_controller:
A JavaScript AbortController object, used for timeouts
"""
def __init__(
self,
js_read_stream: Any,
timeout: float,
request: EmscriptenRequest,
response: EmscriptenResponse,
js_abort_controller: Any, # JavaScript AbortController for timeouts
):
self.js_read_stream = js_read_stream
self.timeout = timeout
self._is_closed = False
self._is_done = False
self.request: EmscriptenRequest | None = request
self.response: EmscriptenResponse | None = response
self.current_buffer = None
self.current_buffer_pos = 0
self.js_abort_controller = js_abort_controller
def __del__(self) -> None:
self.close()
# this is compatible with _base_connection
def is_closed(self) -> bool:
return self._is_closed
# for compatibility with RawIOBase
@property
def closed(self) -> bool:
return self.is_closed()
def close(self) -> None:
if self.is_closed():
return
self.read_len = 0
self.read_pos = 0
self.js_read_stream.cancel()
self.js_read_stream = None
self._is_closed = True
self._is_done = True
self.request = None
self.response = None
super().close()
def readable(self) -> bool:
return True
def writable(self) -> bool:
return False
def seekable(self) -> bool:
return False
def _get_next_buffer(self) -> bool:
result_js = _run_sync_with_timeout(
self.js_read_stream.read(),
self.timeout,
self.js_abort_controller,
request=self.request,
response=self.response,
)
if result_js.done:
self._is_done = True
return False
else:
self.current_buffer = result_js.value.to_py()
self.current_buffer_pos = 0
return True
def readinto(self, byte_obj: Buffer) -> int:
if self.current_buffer is None:
if not self._get_next_buffer() or self.current_buffer is None:
self.close()
return 0
ret_length = min(
len(byte_obj), len(self.current_buffer) - self.current_buffer_pos
)
byte_obj[0:ret_length] = self.current_buffer[
self.current_buffer_pos : self.current_buffer_pos + ret_length
]
self.current_buffer_pos += ret_length
if self.current_buffer_pos == len(self.current_buffer):
self.current_buffer = None
return ret_length
# check if we are in a worker or not
def is_in_browser_main_thread() -> bool:
return hasattr(js, "window") and hasattr(js, "self") and js.self == js.window
def is_cross_origin_isolated() -> bool:
return hasattr(js, "crossOriginIsolated") and js.crossOriginIsolated
def is_in_node() -> bool:
return (
hasattr(js, "process")
and hasattr(js.process, "release")
and hasattr(js.process.release, "name")
and js.process.release.name == "node"
)
def is_worker_available() -> bool:
return hasattr(js, "Worker") and hasattr(js, "Blob")
_fetcher: _StreamingFetcher | None = None
if is_worker_available() and (
(is_cross_origin_isolated() and not is_in_browser_main_thread())
and (not is_in_node())
):
_fetcher = _StreamingFetcher()
else:
_fetcher = None
NODE_JSPI_ERROR = (
"urllib3 only works in Node.js with pyodide.runPythonAsync"
" and requires the flag --experimental-wasm-stack-switching in "
" versions of node <24."
)
def send_streaming_request(request: EmscriptenRequest) -> EmscriptenResponse | None:
if has_jspi():
return send_jspi_request(request, True)
elif is_in_node():
raise _RequestError(
message=NODE_JSPI_ERROR,
request=request,
response=None,
)
if _fetcher and streaming_ready():
return _fetcher.send(request)
else:
_show_streaming_warning()
return None
_SHOWN_TIMEOUT_WARNING = False
def _show_timeout_warning() -> None:
global _SHOWN_TIMEOUT_WARNING
if not _SHOWN_TIMEOUT_WARNING:
_SHOWN_TIMEOUT_WARNING = True
message = "Warning: Timeout is not available on main browser thread"
js.console.warn(message)
_SHOWN_STREAMING_WARNING = False
def _show_streaming_warning() -> None:
global _SHOWN_STREAMING_WARNING
if not _SHOWN_STREAMING_WARNING:
_SHOWN_STREAMING_WARNING = True
message = "Can't stream HTTP requests because: \n"
if not is_cross_origin_isolated():
message += " Page is not cross-origin isolated\n"
if is_in_browser_main_thread():
message += " Python is running in main browser thread\n"
if not is_worker_available():
message += " Worker or Blob classes are not available in this environment." # Defensive: this is always False in browsers that we test in
if streaming_ready() is False:
message += """ Streaming fetch worker isn't ready. If you want to be sure that streaming fetch
is working, you need to call: 'await urllib3.contrib.emscripten.fetch.wait_for_streaming_ready()`"""
from js import console
console.warn(message)
def send_request(request: EmscriptenRequest) -> EmscriptenResponse:
if has_jspi():
return send_jspi_request(request, False)
elif is_in_node():
raise _RequestError(
message=NODE_JSPI_ERROR,
request=request,
response=None,
)
try:
js_xhr = js.XMLHttpRequest.new()
if not is_in_browser_main_thread():
js_xhr.responseType = "arraybuffer"
if request.timeout:
js_xhr.timeout = int(request.timeout * 1000)
else:
js_xhr.overrideMimeType("text/plain; charset=ISO-8859-15")
if request.timeout:
# timeout isn't available on the main thread - show a warning in console
# if it is set
_show_timeout_warning()
js_xhr.open(request.method, request.url, False)
for name, value in request.headers.items():
if name.lower() not in HEADERS_TO_IGNORE:
js_xhr.setRequestHeader(name, value)
js_xhr.send(to_js(request.body))
headers = dict(Parser().parsestr(js_xhr.getAllResponseHeaders()))
if not is_in_browser_main_thread():
body = js_xhr.response.to_py().tobytes()
else:
body = js_xhr.response.encode("ISO-8859-15")
return EmscriptenResponse(
status_code=js_xhr.status, headers=headers, body=body, request=request
)
except JsException as err:
if err.name == "TimeoutError":
raise _TimeoutError(err.message, request=request)
elif err.name == "NetworkError":
raise _RequestError(err.message, request=request)
else:
# general http error
raise _RequestError(err.message, request=request)
def send_jspi_request(
request: EmscriptenRequest, streaming: bool
) -> EmscriptenResponse:
"""
Send a request using WebAssembly JavaScript Promise Integration
to wrap the asynchronous JavaScript fetch api (experimental).
:param request:
Request to send
:param streaming:
Whether to stream the response
:return: The response object
:rtype: EmscriptenResponse
"""
timeout = request.timeout
js_abort_controller = js.AbortController.new()
headers = {k: v for k, v in request.headers.items() if k not in HEADERS_TO_IGNORE}
req_body = request.body
fetch_data = {
"headers": headers,
"body": to_js(req_body),
"method": request.method,
"signal": js_abort_controller.signal,
}
# Node.js returns the whole response (unlike opaqueredirect in browsers),
# so urllib3 can set `redirect: manual` to control redirects itself.
# https://stackoverflow.com/a/78524615
if _is_node_js():
fetch_data["redirect"] = "manual"
# Call JavaScript fetch (async api, returns a promise)
fetcher_promise_js = js.fetch(request.url, _obj_from_dict(fetch_data))
# Now suspend WebAssembly until we resolve that promise
# or time out.
response_js = _run_sync_with_timeout(
fetcher_promise_js,
timeout,
js_abort_controller,
request=request,
response=None,
)
headers = {}
header_iter = response_js.headers.entries()
while True:
iter_value_js = header_iter.next()
if getattr(iter_value_js, "done", False):
break
else:
headers[str(iter_value_js.value[0])] = str(iter_value_js.value[1])
status_code = response_js.status
body: bytes | io.RawIOBase = b""
response = EmscriptenResponse(
status_code=status_code, headers=headers, body=b"", request=request
)
if streaming:
# get via inputstream
if response_js.body is not None:
# get a reader from the fetch response
body_stream_js = response_js.body.getReader()
body = _JSPIReadStream(
body_stream_js, timeout, request, response, js_abort_controller
)
else:
# get directly via arraybuffer
# n.b. this is another async JavaScript call.
body = _run_sync_with_timeout(
response_js.arrayBuffer(),
timeout,
js_abort_controller,
request=request,
response=response,
).to_py()
response.body = body
return response
def _run_sync_with_timeout(
promise: Any,
timeout: float,
js_abort_controller: Any,
request: EmscriptenRequest | None,
response: EmscriptenResponse | None,
) -> Any:
"""
Await a JavaScript promise synchronously with a timeout which is implemented
via the AbortController
:param promise:
Javascript promise to await
:param timeout:
Timeout in seconds
:param js_abort_controller:
A JavaScript AbortController object, used on timeout
:param request:
The request being handled
:param response:
The response being handled (if it exists yet)
:raises _TimeoutError: If the request times out
:raises _RequestError: If the request raises a JavaScript exception
:return: The result of awaiting the promise.
"""
timer_id = None
if timeout > 0:
timer_id = js.setTimeout(
js_abort_controller.abort.bind(js_abort_controller), int(timeout * 1000)
)
try:
from pyodide.ffi import run_sync
# run_sync here uses WebAssembly JavaScript Promise Integration to
# suspend python until the JavaScript promise resolves.
return run_sync(promise)
except JsException as err:
if err.name == "AbortError":
raise _TimeoutError(
message="Request timed out", request=request, response=response
)
else:
raise _RequestError(message=err.message, request=request, response=response)
finally:
if timer_id is not None:
js.clearTimeout(timer_id)
def has_jspi() -> bool:
"""
Return true if jspi can be used.
This requires both browser support and also WebAssembly
to be in the correct state - i.e. that the javascript
call into python was async not sync.
:return: True if jspi can be used.
:rtype: bool
"""
try:
from pyodide.ffi import can_run_sync, run_sync # noqa: F401
return bool(can_run_sync())
except ImportError:
return False
def _is_node_js() -> bool:
"""
Check if we are in Node.js.
:return: True if we are in Node.js.
:rtype: bool
"""
return (
hasattr(js, "process")
and hasattr(js.process, "release")
# According to the Node.js documentation, the release name is always "node".
and js.process.release.name == "node"
)
def streaming_ready() -> bool | None:
if _fetcher:
return _fetcher.streaming_ready
else:
return None # no fetcher, return None to signify that
async def wait_for_streaming_ready() -> bool:
if _fetcher:
await _fetcher.js_worker_ready_promise
return True
else:
return False

22
venv/lib/python3.12/site-packages/urllib3/contrib/emscripten/request.py Normal file
View File

@@ -0,0 +1,22 @@
from __future__ import annotations
from dataclasses import dataclass, field
from ..._base_connection import _TYPE_BODY
@dataclass
class EmscriptenRequest:
method: str
url: str
params: dict[str, str] | None = None
body: _TYPE_BODY | None = None
headers: dict[str, str] = field(default_factory=dict)
timeout: float = 0
decode_content: bool = True
def set_header(self, name: str, value: str) -> None:
self.headers[name.capitalize()] = value
def set_body(self, body: _TYPE_BODY | None) -> None:
self.body = body

277
venv/lib/python3.12/site-packages/urllib3/contrib/emscripten/response.py Normal file
View File

@@ -0,0 +1,277 @@
from __future__ import annotations
import json as _json
import logging
import typing
from contextlib import contextmanager
from dataclasses import dataclass
from http.client import HTTPException as HTTPException
from io import BytesIO, IOBase
from ...exceptions import InvalidHeader, TimeoutError
from ...response import BaseHTTPResponse
from ...util.retry import Retry
from .request import EmscriptenRequest
if typing.TYPE_CHECKING:
from ..._base_connection import BaseHTTPConnection, BaseHTTPSConnection
log = logging.getLogger(__name__)
@dataclass
class EmscriptenResponse:
status_code: int
headers: dict[str, str]
body: IOBase | bytes
request: EmscriptenRequest
class EmscriptenHttpResponseWrapper(BaseHTTPResponse):
def __init__(
self,
internal_response: EmscriptenResponse,
url: str | None = None,
connection: BaseHTTPConnection | BaseHTTPSConnection | None = None,
):
self._pool = None # set by pool class
self._body = None
self._response = internal_response
self._url = url
self._connection = connection
self._closed = False
super().__init__(
headers=internal_response.headers,
status=internal_response.status_code,
request_url=url,
version=0,
version_string="HTTP/?",
reason="",
decode_content=True,
)
self.length_remaining = self._init_length(self._response.request.method)
self.length_is_certain = False
@property
def url(self) -> str | None:
return self._url
@url.setter
def url(self, url: str | None) -> None:
self._url = url
@property
def connection(self) -> BaseHTTPConnection | BaseHTTPSConnection | None:
return self._connection
@property
def retries(self) -> Retry | None:
return self._retries
@retries.setter
def retries(self, retries: Retry | None) -> None:
# Override the request_url if retries has a redirect location.
self._retries = retries
def stream(
self, amt: int | None = 2**16, decode_content: bool | None = None
) -> typing.Generator[bytes]:
"""
A generator wrapper for the read() method. A call will block until
``amt`` bytes have been read from the connection or until the
connection is closed.
:param amt:
How much of the content to read. The generator will return up to
much data per iteration, but may return less. This is particularly
likely when using compressed data. However, the empty string will
never be returned.
:param decode_content:
If True, will attempt to decode the body based on the
'content-encoding' header.
"""
while True:
data = self.read(amt=amt, decode_content=decode_content)
if data:
yield data
else:
break
def _init_length(self, request_method: str | None) -> int | None:
length: int | None
content_length: str | None = self.headers.get("content-length")
if content_length is not None:
try:
# RFC 7230 section 3.3.2 specifies multiple content lengths can
# be sent in a single Content-Length header
# (e.g. Content-Length: 42, 42). This line ensures the values
# are all valid ints and that as long as the `set` length is 1,
# all values are the same. Otherwise, the header is invalid.
lengths = {int(val) for val in content_length.split(",")}
if len(lengths) > 1:
raise InvalidHeader(
"Content-Length contained multiple "
"unmatching values (%s)" % content_length
)
length = lengths.pop()
except ValueError:
length = None
else:
if length < 0:
length = None
else: # if content_length is None
length = None
# Check for responses that shouldn't include a body
if (
self.status in (204, 304)
or 100 <= self.status < 200
or request_method == "HEAD"
):
length = 0
return length
def read(
self,
amt: int | None = None,
decode_content: bool | None = None, # ignored because browser decodes always
cache_content: bool = False,
) -> bytes:
if (
self._closed
or self._response is None
or (isinstance(self._response.body, IOBase) and self._response.body.closed)
):
return b""
with self._error_catcher():
# body has been preloaded as a string by XmlHttpRequest
if not isinstance(self._response.body, IOBase):
self.length_remaining = len(self._response.body)
self.length_is_certain = True
# wrap body in IOStream
self._response.body = BytesIO(self._response.body)
if amt is not None and amt >= 0:
# don't cache partial content
cache_content = False
data = self._response.body.read(amt)
else: # read all we can (and cache it)
data = self._response.body.read()
if cache_content:
self._body = data
if self.length_remaining is not None:
self.length_remaining = max(self.length_remaining - len(data), 0)
if len(data) == 0 or (
self.length_is_certain and self.length_remaining == 0
):
# definitely finished reading, close response stream
self._response.body.close()
return typing.cast(bytes, data)
def read_chunked(
self,
amt: int | None = None,
decode_content: bool | None = None,
) -> typing.Generator[bytes]:
# chunked is handled by browser
while True:
bytes = self.read(amt, decode_content)
if not bytes:
break
yield bytes
def release_conn(self) -> None:
if not self._pool or not self._connection:
return None
self._pool._put_conn(self._connection)
self._connection = None
def drain_conn(self) -> None:
self.close()
@property
def data(self) -> bytes:
if self._body:
return self._body
else:
return self.read(cache_content=True)
def json(self) -> typing.Any:
"""
Deserializes the body of the HTTP response as a Python object.
The body of the HTTP response must be encoded using UTF-8, as per
`RFC 8529 Section 8.1 <https://www.rfc-editor.org/rfc/rfc8259#section-8.1>`_.
To use a custom JSON decoder pass the result of :attr:`HTTPResponse.data` to
your custom decoder instead.
If the body of the HTTP response is not decodable to UTF-8, a
`UnicodeDecodeError` will be raised. If the body of the HTTP response is not a
valid JSON document, a `json.JSONDecodeError` will be raised.
Read more :ref:`here <json_content>`.
:returns: The body of the HTTP response as a Python object.
"""
data = self.data.decode("utf-8")
return _json.loads(data)
def close(self) -> None:
if not self._closed:
if isinstance(self._response.body, IOBase):
self._response.body.close()
if self._connection:
self._connection.close()
self._connection = None
self._closed = True
@contextmanager
def _error_catcher(self) -> typing.Generator[None]:
"""
Catch Emscripten specific exceptions thrown by fetch.py,
instead re-raising urllib3 variants, so that low-level exceptions
are not leaked in the high-level api.
On exit, release the connection back to the pool.
"""
from .fetch import _RequestError, _TimeoutError # avoid circular import
clean_exit = False
try:
yield
# If no exception is thrown, we should avoid cleaning up
# unnecessarily.
clean_exit = True
except _TimeoutError as e:
raise TimeoutError(str(e))
except _RequestError as e:
raise HTTPException(str(e))
finally:
# If we didn't terminate cleanly, we need to throw away our
# connection.
if not clean_exit:
# The response may not be closed but we're not going to use it
# anymore so close it now
if (
isinstance(self._response.body, IOBase)
and not self._response.body.closed
):
self._response.body.close()
# release the connection back to the pool
self.release_conn()
else:
# If we have read everything from the response stream,
# return the connection back to the pool.
if (
isinstance(self._response.body, IOBase)
and self._response.body.closed
):
self.release_conn()

564
venv/lib/python3.12/site-packages/urllib3/contrib/pyopenssl.py Normal file
View File

@@ -0,0 +1,564 @@
"""
Module for using pyOpenSSL as a TLS backend. This module was relevant before
the standard library ``ssl`` module supported SNI, but now that we've dropped
support for Python 2.7 all relevant Python versions support SNI so
**this module is no longer recommended**.
This needs the following packages installed:
* `pyOpenSSL`_ (tested with 16.0.0)
* `cryptography`_ (minimum 1.3.4, from pyopenssl)
* `idna`_ (minimum 2.0)
However, pyOpenSSL depends on cryptography, so while we use all three directly here we
end up having relatively few packages required.
You can install them with the following command:
.. code-block:: bash
$ python -m pip install pyopenssl cryptography idna
To activate certificate checking, call
:func:`~urllib3.contrib.pyopenssl.inject_into_urllib3` from your Python code
before you begin making HTTP requests. This can be done in a ``sitecustomize``
module, or at any other time before your application begins using ``urllib3``,
like this:
.. code-block:: python
try:
import urllib3.contrib.pyopenssl
urllib3.contrib.pyopenssl.inject_into_urllib3()
except ImportError:
pass
.. _pyopenssl: https://www.pyopenssl.org
.. _cryptography: https://cryptography.io
.. _idna: https://github.com/kjd/idna
"""
from __future__ import annotations
import OpenSSL.SSL # type: ignore[import-untyped]
from cryptography import x509
try:
from cryptography.x509 import UnsupportedExtension # type: ignore[attr-defined]
except ImportError:
# UnsupportedExtension is gone in cryptography >= 2.1.0
class UnsupportedExtension(Exception): # type: ignore[no-redef]
pass
import logging
import ssl
import typing
from io import BytesIO
from socket import socket as socket_cls
from socket import timeout
from .. import util
if typing.TYPE_CHECKING:
from OpenSSL.crypto import X509 # type: ignore[import-untyped]
__all__ = ["inject_into_urllib3", "extract_from_urllib3"]
# Map from urllib3 to PyOpenSSL compatible parameter-values.
_openssl_versions: dict[int, int] = {
util.ssl_.PROTOCOL_TLS: OpenSSL.SSL.SSLv23_METHOD, # type: ignore[attr-defined]
util.ssl_.PROTOCOL_TLS_CLIENT: OpenSSL.SSL.SSLv23_METHOD, # type: ignore[attr-defined]
ssl.PROTOCOL_TLSv1: OpenSSL.SSL.TLSv1_METHOD,
}
if hasattr(ssl, "PROTOCOL_TLSv1_1") and hasattr(OpenSSL.SSL, "TLSv1_1_METHOD"):
_openssl_versions[ssl.PROTOCOL_TLSv1_1] = OpenSSL.SSL.TLSv1_1_METHOD
if hasattr(ssl, "PROTOCOL_TLSv1_2") and hasattr(OpenSSL.SSL, "TLSv1_2_METHOD"):
_openssl_versions[ssl.PROTOCOL_TLSv1_2] = OpenSSL.SSL.TLSv1_2_METHOD
_stdlib_to_openssl_verify = {
ssl.CERT_NONE: OpenSSL.SSL.VERIFY_NONE,
ssl.CERT_OPTIONAL: OpenSSL.SSL.VERIFY_PEER,
ssl.CERT_REQUIRED: OpenSSL.SSL.VERIFY_PEER
+ OpenSSL.SSL.VERIFY_FAIL_IF_NO_PEER_CERT,
}
_openssl_to_stdlib_verify = {v: k for k, v in _stdlib_to_openssl_verify.items()}
# The SSLvX values are the most likely to be missing in the future
# but we check them all just to be sure.
_OP_NO_SSLv2_OR_SSLv3: int = getattr(OpenSSL.SSL, "OP_NO_SSLv2", 0) | getattr(
OpenSSL.SSL, "OP_NO_SSLv3", 0
)
_OP_NO_TLSv1: int = getattr(OpenSSL.SSL, "OP_NO_TLSv1", 0)
_OP_NO_TLSv1_1: int = getattr(OpenSSL.SSL, "OP_NO_TLSv1_1", 0)
_OP_NO_TLSv1_2: int = getattr(OpenSSL.SSL, "OP_NO_TLSv1_2", 0)
_OP_NO_TLSv1_3: int = getattr(OpenSSL.SSL, "OP_NO_TLSv1_3", 0)
_openssl_to_ssl_minimum_version: dict[int, int] = {
ssl.TLSVersion.MINIMUM_SUPPORTED: _OP_NO_SSLv2_OR_SSLv3,
ssl.TLSVersion.TLSv1: _OP_NO_SSLv2_OR_SSLv3,
ssl.TLSVersion.TLSv1_1: _OP_NO_SSLv2_OR_SSLv3 | _OP_NO_TLSv1,
ssl.TLSVersion.TLSv1_2: _OP_NO_SSLv2_OR_SSLv3 | _OP_NO_TLSv1 | _OP_NO_TLSv1_1,
ssl.TLSVersion.TLSv1_3: (
_OP_NO_SSLv2_OR_SSLv3 | _OP_NO_TLSv1 | _OP_NO_TLSv1_1 | _OP_NO_TLSv1_2
),
ssl.TLSVersion.MAXIMUM_SUPPORTED: (
_OP_NO_SSLv2_OR_SSLv3 | _OP_NO_TLSv1 | _OP_NO_TLSv1_1 | _OP_NO_TLSv1_2
),
}
_openssl_to_ssl_maximum_version: dict[int, int] = {
ssl.TLSVersion.MINIMUM_SUPPORTED: (
_OP_NO_SSLv2_OR_SSLv3
| _OP_NO_TLSv1
| _OP_NO_TLSv1_1
| _OP_NO_TLSv1_2
| _OP_NO_TLSv1_3
),
ssl.TLSVersion.TLSv1: (
_OP_NO_SSLv2_OR_SSLv3 | _OP_NO_TLSv1_1 | _OP_NO_TLSv1_2 | _OP_NO_TLSv1_3
),
ssl.TLSVersion.TLSv1_1: _OP_NO_SSLv2_OR_SSLv3 | _OP_NO_TLSv1_2 | _OP_NO_TLSv1_3,
ssl.TLSVersion.TLSv1_2: _OP_NO_SSLv2_OR_SSLv3 | _OP_NO_TLSv1_3,
ssl.TLSVersion.TLSv1_3: _OP_NO_SSLv2_OR_SSLv3,
ssl.TLSVersion.MAXIMUM_SUPPORTED: _OP_NO_SSLv2_OR_SSLv3,
}
# OpenSSL will only write 16K at a time
SSL_WRITE_BLOCKSIZE = 16384
orig_util_SSLContext = util.ssl_.SSLContext
log = logging.getLogger(__name__)
def inject_into_urllib3() -> None:
"Monkey-patch urllib3 with PyOpenSSL-backed SSL-support."
_validate_dependencies_met()
util.SSLContext = PyOpenSSLContext # type: ignore[assignment]
util.ssl_.SSLContext = PyOpenSSLContext # type: ignore[assignment]
util.IS_PYOPENSSL = True
util.ssl_.IS_PYOPENSSL = True
def extract_from_urllib3() -> None:
"Undo monkey-patching by :func:`inject_into_urllib3`."
util.SSLContext = orig_util_SSLContext
util.ssl_.SSLContext = orig_util_SSLContext
util.IS_PYOPENSSL = False
util.ssl_.IS_PYOPENSSL = False
def _validate_dependencies_met() -> None:
"""
Verifies that PyOpenSSL's package-level dependencies have been met.
Throws `ImportError` if they are not met.
"""
# Method added in `cryptography==1.1`; not available in older versions
from cryptography.x509.extensions import Extensions
if getattr(Extensions, "get_extension_for_class", None) is None:
raise ImportError(
"'cryptography' module missing required functionality. "
"Try upgrading to v1.3.4 or newer."
)
# pyOpenSSL 0.14 and above use cryptography for OpenSSL bindings. The _x509
# attribute is only present on those versions.
from OpenSSL.crypto import X509
x509 = X509()
if getattr(x509, "_x509", None) is None:
raise ImportError(
"'pyOpenSSL' module missing required functionality. "
"Try upgrading to v0.14 or newer."
)
def _dnsname_to_stdlib(name: str) -> str | None:
"""
Converts a dNSName SubjectAlternativeName field to the form used by the
standard library on the given Python version.
Cryptography produces a dNSName as a unicode string that was idna-decoded
from ASCII bytes. We need to idna-encode that string to get it back, and
then on Python 3 we also need to convert to unicode via UTF-8 (the stdlib
uses PyUnicode_FromStringAndSize on it, which decodes via UTF-8).
If the name cannot be idna-encoded then we return None signalling that
the name given should be skipped.
"""
def idna_encode(name: str) -> bytes | None:
"""
Borrowed wholesale from the Python Cryptography Project. It turns out
that we can't just safely call `idna.encode`: it can explode for
wildcard names. This avoids that problem.
"""
import idna
try:
for prefix in ["*.", "."]:
if name.startswith(prefix):
name = name[len(prefix) :]
return prefix.encode("ascii") + idna.encode(name)
return idna.encode(name)
except idna.core.IDNAError:
return None
# Don't send IPv6 addresses through the IDNA encoder.
if ":" in name:
return name
encoded_name = idna_encode(name)
if encoded_name is None:
return None
return encoded_name.decode("utf-8")
def get_subj_alt_name(peer_cert: X509) -> list[tuple[str, str]]:
"""
Given an PyOpenSSL certificate, provides all the subject alternative names.
"""
cert = peer_cert.to_cryptography()
# We want to find the SAN extension. Ask Cryptography to locate it (it's
# faster than looping in Python)
try:
ext = cert.extensions.get_extension_for_class(x509.SubjectAlternativeName).value
except x509.ExtensionNotFound:
# No such extension, return the empty list.
return []
except (
x509.DuplicateExtension,
UnsupportedExtension,
x509.UnsupportedGeneralNameType,
UnicodeError,
) as e:
# A problem has been found with the quality of the certificate. Assume
# no SAN field is present.
log.warning(
"A problem was encountered with the certificate that prevented "
"urllib3 from finding the SubjectAlternativeName field. This can "
"affect certificate validation. The error was %s",
e,
)
return []
# We want to return dNSName and iPAddress fields. We need to cast the IPs
# back to strings because the match_hostname function wants them as
# strings.
# Sadly the DNS names need to be idna encoded and then, on Python 3, UTF-8
# decoded. This is pretty frustrating, but that's what the standard library
# does with certificates, and so we need to attempt to do the same.
# We also want to skip over names which cannot be idna encoded.
names = [
("DNS", name)
for name in map(_dnsname_to_stdlib, ext.get_values_for_type(x509.DNSName))
if name is not None
]
names.extend(
("IP Address", str(name)) for name in ext.get_values_for_type(x509.IPAddress)
)
return names
class WrappedSocket:
"""API-compatibility wrapper for Python OpenSSL's Connection-class."""
def __init__(
self,
connection: OpenSSL.SSL.Connection,
socket: socket_cls,
suppress_ragged_eofs: bool = True,
) -> None:
self.connection = connection
self.socket = socket
self.suppress_ragged_eofs = suppress_ragged_eofs
self._io_refs = 0
self._closed = False
def fileno(self) -> int:
return self.socket.fileno()
# Copy-pasted from Python 3.5 source code
def _decref_socketios(self) -> None:
if self._io_refs > 0:
self._io_refs -= 1
if self._closed:
self.close()
def recv(self, *args: typing.Any, **kwargs: typing.Any) -> bytes:
try:
data = self.connection.recv(*args, **kwargs)
except OpenSSL.SSL.SysCallError as e:
if self.suppress_ragged_eofs and e.args == (-1, "Unexpected EOF"):
return b""
else:
raise OSError(e.args[0], str(e)) from e
except OpenSSL.SSL.ZeroReturnError:
if self.connection.get_shutdown() == OpenSSL.SSL.RECEIVED_SHUTDOWN:
return b""
else:
raise
except OpenSSL.SSL.WantReadError as e:
if not util.wait_for_read(self.socket, self.socket.gettimeout()):
raise timeout("The read operation timed out") from e
else:
return self.recv(*args, **kwargs)
# TLS 1.3 post-handshake authentication
except OpenSSL.SSL.Error as e:
raise ssl.SSLError(f"read error: {e!r}") from e
else:
return data # type: ignore[no-any-return]
def recv_into(self, *args: typing.Any, **kwargs: typing.Any) -> int:
try:
return self.connection.recv_into(*args, **kwargs) # type: ignore[no-any-return]
except OpenSSL.SSL.SysCallError as e:
if self.suppress_ragged_eofs and e.args == (-1, "Unexpected EOF"):
return 0
else:
raise OSError(e.args[0], str(e)) from e
except OpenSSL.SSL.ZeroReturnError:
if self.connection.get_shutdown() == OpenSSL.SSL.RECEIVED_SHUTDOWN:
return 0
else:
raise
except OpenSSL.SSL.WantReadError as e:
if not util.wait_for_read(self.socket, self.socket.gettimeout()):
raise timeout("The read operation timed out") from e
else:
return self.recv_into(*args, **kwargs)
# TLS 1.3 post-handshake authentication
except OpenSSL.SSL.Error as e:
raise ssl.SSLError(f"read error: {e!r}") from e
def settimeout(self, timeout: float) -> None:
return self.socket.settimeout(timeout)
def _send_until_done(self, data: bytes) -> int:
while True:
try:
return self.connection.send(data) # type: ignore[no-any-return]
except OpenSSL.SSL.WantWriteError as e:
if not util.wait_for_write(self.socket, self.socket.gettimeout()):
raise timeout() from e
continue
except OpenSSL.SSL.SysCallError as e:
raise OSError(e.args[0], str(e)) from e
def sendall(self, data: bytes) -> None:
total_sent = 0
while total_sent < len(data):
sent = self._send_until_done(
data[total_sent : total_sent + SSL_WRITE_BLOCKSIZE]
)
total_sent += sent
def shutdown(self, how: int) -> None:
try:
self.connection.shutdown()
except OpenSSL.SSL.Error as e:
raise ssl.SSLError(f"shutdown error: {e!r}") from e
def close(self) -> None:
self._closed = True
if self._io_refs <= 0:
self._real_close()
def _real_close(self) -> None:
try:
return self.connection.close() # type: ignore[no-any-return]
except OpenSSL.SSL.Error:
return
def getpeercert(
self, binary_form: bool = False
) -> dict[str, list[typing.Any]] | None:
x509 = self.connection.get_peer_certificate()
if not x509:
return x509 # type: ignore[no-any-return]
if binary_form:
return OpenSSL.crypto.dump_certificate(OpenSSL.crypto.FILETYPE_ASN1, x509) # type: ignore[no-any-return]
return {
"subject": ((("commonName", x509.get_subject().CN),),), # type: ignore[dict-item]
"subjectAltName": get_subj_alt_name(x509),
}
def version(self) -> str:
return self.connection.get_protocol_version_name() # type: ignore[no-any-return]
def selected_alpn_protocol(self) -> str | None:
alpn_proto = self.connection.get_alpn_proto_negotiated()
return alpn_proto.decode() if alpn_proto else None
WrappedSocket.makefile = socket_cls.makefile # type: ignore[attr-defined]
class PyOpenSSLContext:
"""
I am a wrapper class for the PyOpenSSL ``Context`` object. I am responsible
for translating the interface of the standard library ``SSLContext`` object
to calls into PyOpenSSL.
"""
def __init__(self, protocol: int) -> None:
self.protocol = _openssl_versions[protocol]
self._ctx = OpenSSL.SSL.Context(self.protocol)
self._options = 0
self.check_hostname = False
self._minimum_version: int = ssl.TLSVersion.MINIMUM_SUPPORTED
self._maximum_version: int = ssl.TLSVersion.MAXIMUM_SUPPORTED
self._verify_flags: int = ssl.VERIFY_X509_TRUSTED_FIRST
@property
def options(self) -> int:
return self._options
@options.setter
def options(self, value: int) -> None:
self._options = value
self._set_ctx_options()
@property
def verify_flags(self) -> int:
return self._verify_flags
@verify_flags.setter
def verify_flags(self, value: int) -> None:
self._verify_flags = value
self._ctx.get_cert_store().set_flags(self._verify_flags)
@property
def verify_mode(self) -> int:
return _openssl_to_stdlib_verify[self._ctx.get_verify_mode()]
@verify_mode.setter
def verify_mode(self, value: ssl.VerifyMode) -> None:
self._ctx.set_verify(_stdlib_to_openssl_verify[value], _verify_callback)
def set_default_verify_paths(self) -> None:
self._ctx.set_default_verify_paths()
def set_ciphers(self, ciphers: bytes | str) -> None:
if isinstance(ciphers, str):
ciphers = ciphers.encode("utf-8")
self._ctx.set_cipher_list(ciphers)
def load_verify_locations(
self,
cafile: str | None = None,
capath: str | None = None,
cadata: bytes | None = None,
) -> None:
if cafile is not None:
cafile = cafile.encode("utf-8") # type: ignore[assignment]
if capath is not None:
capath = capath.encode("utf-8") # type: ignore[assignment]
try:
self._ctx.load_verify_locations(cafile, capath)
if cadata is not None:
self._ctx.load_verify_locations(BytesIO(cadata))
except OpenSSL.SSL.Error as e:
raise ssl.SSLError(f"unable to load trusted certificates: {e!r}") from e
def load_cert_chain(
self,
certfile: str,
keyfile: str | None = None,
password: str | None = None,
) -> None:
try:
self._ctx.use_certificate_chain_file(certfile)
if password is not None:
if not isinstance(password, bytes):
password = password.encode("utf-8") # type: ignore[assignment]
self._ctx.set_passwd_cb(lambda *_: password)
self._ctx.use_privatekey_file(keyfile or certfile)
except OpenSSL.SSL.Error as e:
raise ssl.SSLError(f"Unable to load certificate chain: {e!r}") from e
def set_alpn_protocols(self, protocols: list[bytes | str]) -> None:
protocols = [util.util.to_bytes(p, "ascii") for p in protocols]
return self._ctx.set_alpn_protos(protocols) # type: ignore[no-any-return]
def wrap_socket(
self,
sock: socket_cls,
server_side: bool = False,
do_handshake_on_connect: bool = True,
suppress_ragged_eofs: bool = True,
server_hostname: bytes | str | None = None,
) -> WrappedSocket:
cnx = OpenSSL.SSL.Connection(self._ctx, sock)
# If server_hostname is an IP, don't use it for SNI, per RFC6066 Section 3
if server_hostname and not util.ssl_.is_ipaddress(server_hostname):
if isinstance(server_hostname, str):
server_hostname = server_hostname.encode("utf-8")
cnx.set_tlsext_host_name(server_hostname)
cnx.set_connect_state()
while True:
try:
cnx.do_handshake()
except OpenSSL.SSL.WantReadError as e:
if not util.wait_for_read(sock, sock.gettimeout()):
raise timeout("select timed out") from e
continue
except OpenSSL.SSL.Error as e:
raise ssl.SSLError(f"bad handshake: {e!r}") from e
break
return WrappedSocket(cnx, sock)
def _set_ctx_options(self) -> None:
self._ctx.set_options(
self._options
| _openssl_to_ssl_minimum_version[self._minimum_version]
| _openssl_to_ssl_maximum_version[self._maximum_version]
)
@property
def minimum_version(self) -> int:
return self._minimum_version
@minimum_version.setter
def minimum_version(self, minimum_version: int) -> None:
self._minimum_version = minimum_version
self._set_ctx_options()
@property
def maximum_version(self) -> int:
return self._maximum_version
@maximum_version.setter
def maximum_version(self, maximum_version: int) -> None:
self._maximum_version = maximum_version
self._set_ctx_options()
def _verify_callback(
cnx: OpenSSL.SSL.Connection,
x509: X509,
err_no: int,
err_depth: int,
return_code: int,
) -> bool:
return err_no == 0

228
venv/lib/python3.12/site-packages/urllib3/contrib/socks.py Normal file
View File

@@ -0,0 +1,228 @@
"""
This module contains provisional support for SOCKS proxies from within
urllib3. This module supports SOCKS4, SOCKS4A (an extension of SOCKS4), and
SOCKS5. To enable its functionality, either install PySocks or install this
module with the ``socks`` extra.
The SOCKS implementation supports the full range of urllib3 features. It also
supports the following SOCKS features:
- SOCKS4A (``proxy_url='socks4a://...``)
- SOCKS4 (``proxy_url='socks4://...``)
- SOCKS5 with remote DNS (``proxy_url='socks5h://...``)
- SOCKS5 with local DNS (``proxy_url='socks5://...``)
- Usernames and passwords for the SOCKS proxy
.. note::
It is recommended to use ``socks5h://`` or ``socks4a://`` schemes in
your ``proxy_url`` to ensure that DNS resolution is done from the remote
server instead of client-side when connecting to a domain name.
SOCKS4 supports IPv4 and domain names with the SOCKS4A extension. SOCKS5
supports IPv4, IPv6, and domain names.
When connecting to a SOCKS4 proxy the ``username`` portion of the ``proxy_url``
will be sent as the ``userid`` section of the SOCKS request:
.. code-block:: python
proxy_url="socks4a://<userid>@proxy-host"
When connecting to a SOCKS5 proxy the ``username`` and ``password`` portion
of the ``proxy_url`` will be sent as the username/password to authenticate
with the proxy:
.. code-block:: python
proxy_url="socks5h://<username>:<password>@proxy-host"
"""
from __future__ import annotations
try:
import socks # type: ignore[import-not-found]
except ImportError:
import warnings
from ..exceptions import DependencyWarning
warnings.warn(
(
"SOCKS support in urllib3 requires the installation of optional "
"dependencies: specifically, PySocks. For more information, see "
"https://urllib3.readthedocs.io/en/latest/advanced-usage.html#socks-proxies"
),
DependencyWarning,
)
raise
import typing
from socket import timeout as SocketTimeout
from ..connection import HTTPConnection, HTTPSConnection
from ..connectionpool import HTTPConnectionPool, HTTPSConnectionPool
from ..exceptions import ConnectTimeoutError, NewConnectionError
from ..poolmanager import PoolManager
from ..util.url import parse_url
try:
import ssl
except ImportError:
ssl = None # type: ignore[assignment]
class _TYPE_SOCKS_OPTIONS(typing.TypedDict):
socks_version: int
proxy_host: str | None
proxy_port: str | None
username: str | None
password: str | None
rdns: bool
class SOCKSConnection(HTTPConnection):
"""
A plain-text HTTP connection that connects via a SOCKS proxy.
"""
def __init__(
self,
_socks_options: _TYPE_SOCKS_OPTIONS,
*args: typing.Any,
**kwargs: typing.Any,
) -> None:
self._socks_options = _socks_options
super().__init__(*args, **kwargs)
def _new_conn(self) -> socks.socksocket:
"""
Establish a new connection via the SOCKS proxy.
"""
extra_kw: dict[str, typing.Any] = {}
if self.source_address:
extra_kw["source_address"] = self.source_address
if self.socket_options:
extra_kw["socket_options"] = self.socket_options
try:
conn = socks.create_connection(
(self.host, self.port),
proxy_type=self._socks_options["socks_version"],
proxy_addr=self._socks_options["proxy_host"],
proxy_port=self._socks_options["proxy_port"],
proxy_username=self._socks_options["username"],
proxy_password=self._socks_options["password"],
proxy_rdns=self._socks_options["rdns"],
timeout=self.timeout,
**extra_kw,
)
except SocketTimeout as e:
raise ConnectTimeoutError(
self,
f"Connection to {self.host} timed out. (connect timeout={self.timeout})",
) from e
except socks.ProxyError as e:
# This is fragile as hell, but it seems to be the only way to raise
# useful errors here.
if e.socket_err:
error = e.socket_err
if isinstance(error, SocketTimeout):
raise ConnectTimeoutError(
self,
f"Connection to {self.host} timed out. (connect timeout={self.timeout})",
) from e
else:
# Adding `from e` messes with coverage somehow, so it's omitted.
# See #2386.
raise NewConnectionError(
self, f"Failed to establish a new connection: {error}"
)
else:
raise NewConnectionError(
self, f"Failed to establish a new connection: {e}"
) from e
except OSError as e: # Defensive: PySocks should catch all these.
raise NewConnectionError(
self, f"Failed to establish a new connection: {e}"
) from e
return conn
# We don't need to duplicate the Verified/Unverified distinction from
# urllib3/connection.py here because the HTTPSConnection will already have been
# correctly set to either the Verified or Unverified form by that module. This
# means the SOCKSHTTPSConnection will automatically be the correct type.
class SOCKSHTTPSConnection(SOCKSConnection, HTTPSConnection):
pass
class SOCKSHTTPConnectionPool(HTTPConnectionPool):
ConnectionCls = SOCKSConnection
class SOCKSHTTPSConnectionPool(HTTPSConnectionPool):
ConnectionCls = SOCKSHTTPSConnection
class SOCKSProxyManager(PoolManager):
"""
A version of the urllib3 ProxyManager that routes connections via the
defined SOCKS proxy.
"""
pool_classes_by_scheme = {
"http": SOCKSHTTPConnectionPool,
"https": SOCKSHTTPSConnectionPool,
}
def __init__(
self,
proxy_url: str,
username: str | None = None,
password: str | None = None,
num_pools: int = 10,
headers: typing.Mapping[str, str] | None = None,
**connection_pool_kw: typing.Any,
):
parsed = parse_url(proxy_url)
if username is None and password is None and parsed.auth is not None:
split = parsed.auth.split(":")
if len(split) == 2:
username, password = split
if parsed.scheme == "socks5":
socks_version = socks.PROXY_TYPE_SOCKS5
rdns = False
elif parsed.scheme == "socks5h":
socks_version = socks.PROXY_TYPE_SOCKS5
rdns = True
elif parsed.scheme == "socks4":
socks_version = socks.PROXY_TYPE_SOCKS4
rdns = False
elif parsed.scheme == "socks4a":
socks_version = socks.PROXY_TYPE_SOCKS4
rdns = True
else:
raise ValueError(f"Unable to determine SOCKS version from {proxy_url}")
self.proxy_url = proxy_url
socks_options = {
"socks_version": socks_version,
"proxy_host": parsed.host,
"proxy_port": parsed.port,
"username": username,
"password": password,
"rdns": rdns,
}
connection_pool_kw["_socks_options"] = socks_options
super().__init__(num_pools, headers, **connection_pool_kw)
self.pool_classes_by_scheme = SOCKSProxyManager.pool_classes_by_scheme

335
venv/lib/python3.12/site-packages/urllib3/exceptions.py Normal file
View File

@@ -0,0 +1,335 @@
from __future__ import annotations
import socket
import typing
import warnings
from email.errors import MessageDefect
from http.client import IncompleteRead as httplib_IncompleteRead
if typing.TYPE_CHECKING:
from .connection import HTTPConnection
from .connectionpool import ConnectionPool
from .response import HTTPResponse
from .util.retry import Retry
# Base Exceptions
class HTTPError(Exception):
"""Base exception used by this module."""
class HTTPWarning(Warning):
"""Base warning used by this module."""
_TYPE_REDUCE_RESULT = tuple[typing.Callable[..., object], tuple[object, ...]]
class PoolError(HTTPError):
"""Base exception for errors caused within a pool."""
def __init__(self, pool: ConnectionPool, message: str) -> None:
self.pool = pool
self._message = message
super().__init__(f"{pool}: {message}")
def __reduce__(self) -> _TYPE_REDUCE_RESULT:
# For pickling purposes.
return self.__class__, (None, self._message)
class RequestError(PoolError):
"""Base exception for PoolErrors that have associated URLs."""
def __init__(self, pool: ConnectionPool, url: str, message: str) -> None:
self.url = url
super().__init__(pool, message)
def __reduce__(self) -> _TYPE_REDUCE_RESULT:
# For pickling purposes.
return self.__class__, (None, self.url, self._message)
class SSLError(HTTPError):
"""Raised when SSL certificate fails in an HTTPS connection."""
class ProxyError(HTTPError):
"""Raised when the connection to a proxy fails."""
# The original error is also available as __cause__.
original_error: Exception
def __init__(self, message: str, error: Exception) -> None:
super().__init__(message, error)
self.original_error = error
class DecodeError(HTTPError):
"""Raised when automatic decoding based on Content-Type fails."""
class ProtocolError(HTTPError):
"""Raised when something unexpected happens mid-request/response."""
#: Renamed to ProtocolError but aliased for backwards compatibility.
ConnectionError = ProtocolError
# Leaf Exceptions
class MaxRetryError(RequestError):
"""Raised when the maximum number of retries is exceeded.
:param pool: The connection pool
:type pool: :class:`~urllib3.connectionpool.HTTPConnectionPool`
:param str url: The requested Url
:param reason: The underlying error
:type reason: :class:`Exception`
"""
def __init__(
self, pool: ConnectionPool, url: str, reason: Exception | None = None
) -> None:
self.reason = reason
message = f"Max retries exceeded with url: {url} (Caused by {reason!r})"
super().__init__(pool, url, message)
def __reduce__(self) -> _TYPE_REDUCE_RESULT:
# For pickling purposes.
return self.__class__, (None, self.url, self.reason)
class HostChangedError(RequestError):
"""Raised when an existing pool gets a request for a foreign host."""
def __init__(
self, pool: ConnectionPool, url: str, retries: Retry | int = 3
) -> None:
message = f"Tried to open a foreign host with url: {url}"
super().__init__(pool, url, message)
self.retries = retries
class TimeoutStateError(HTTPError):
"""Raised when passing an invalid state to a timeout"""
class TimeoutError(HTTPError):
"""Raised when a socket timeout error occurs.
Catching this error will catch both :exc:`ReadTimeoutErrors
<ReadTimeoutError>` and :exc:`ConnectTimeoutErrors <ConnectTimeoutError>`.
"""
class ReadTimeoutError(TimeoutError, RequestError):
"""Raised when a socket timeout occurs while receiving data from a server"""
# This timeout error does not have a URL attached and needs to inherit from the
# base HTTPError
class ConnectTimeoutError(TimeoutError):
"""Raised when a socket timeout occurs while connecting to a server"""
class NewConnectionError(ConnectTimeoutError, HTTPError):
"""Raised when we fail to establish a new connection. Usually ECONNREFUSED."""
def __init__(self, conn: HTTPConnection, message: str) -> None:
self.conn = conn
self._message = message
super().__init__(f"{conn}: {message}")
def __reduce__(self) -> _TYPE_REDUCE_RESULT:
# For pickling purposes.
return self.__class__, (None, self._message)
@property
def pool(self) -> HTTPConnection:
warnings.warn(
"The 'pool' property is deprecated and will be removed "
"in urllib3 v2.1.0. Use 'conn' instead.",
DeprecationWarning,
stacklevel=2,
)
return self.conn
class NameResolutionError(NewConnectionError):
"""Raised when host name resolution fails."""
def __init__(self, host: str, conn: HTTPConnection, reason: socket.gaierror):
message = f"Failed to resolve '{host}' ({reason})"
self._host = host
self._reason = reason
super().__init__(conn, message)
def __reduce__(self) -> _TYPE_REDUCE_RESULT:
# For pickling purposes.
return self.__class__, (self._host, None, self._reason)
class EmptyPoolError(PoolError):
"""Raised when a pool runs out of connections and no more are allowed."""
class FullPoolError(PoolError):
"""Raised when we try to add a connection to a full pool in blocking mode."""
class ClosedPoolError(PoolError):
"""Raised when a request enters a pool after the pool has been closed."""
class LocationValueError(ValueError, HTTPError):
"""Raised when there is something wrong with a given URL input."""
class LocationParseError(LocationValueError):
"""Raised when get_host or similar fails to parse the URL input."""
def __init__(self, location: str) -> None:
message = f"Failed to parse: {location}"
super().__init__(message)
self.location = location
class URLSchemeUnknown(LocationValueError):
"""Raised when a URL input has an unsupported scheme."""
def __init__(self, scheme: str):
message = f"Not supported URL scheme {scheme}"
super().__init__(message)
self.scheme = scheme
class ResponseError(HTTPError):
"""Used as a container for an error reason supplied in a MaxRetryError."""
GENERIC_ERROR = "too many error responses"
SPECIFIC_ERROR = "too many {status_code} error responses"
class SecurityWarning(HTTPWarning):
"""Warned when performing security reducing actions"""
class InsecureRequestWarning(SecurityWarning):
"""Warned when making an unverified HTTPS request."""
class NotOpenSSLWarning(SecurityWarning):
"""Warned when using unsupported SSL library"""
class SystemTimeWarning(SecurityWarning):
"""Warned when system time is suspected to be wrong"""
class InsecurePlatformWarning(SecurityWarning):
"""Warned when certain TLS/SSL configuration is not available on a platform."""
class DependencyWarning(HTTPWarning):
"""
Warned when an attempt is made to import a module with missing optional
dependencies.
"""
class ResponseNotChunked(ProtocolError, ValueError):
"""Response needs to be chunked in order to read it as chunks."""
class BodyNotHttplibCompatible(HTTPError):
"""
Body should be :class:`http.client.HTTPResponse` like
(have an fp attribute which returns raw chunks) for read_chunked().
"""
class IncompleteRead(HTTPError, httplib_IncompleteRead):
"""
Response length doesn't match expected Content-Length
Subclass of :class:`http.client.IncompleteRead` to allow int value
for ``partial`` to avoid creating large objects on streamed reads.
"""
partial: int # type: ignore[assignment]
expected: int
def __init__(self, partial: int, expected: int) -> None:
self.partial = partial
self.expected = expected
def __repr__(self) -> str:
return "IncompleteRead(%i bytes read, %i more expected)" % (
self.partial,
self.expected,
)
class InvalidChunkLength(HTTPError, httplib_IncompleteRead):
"""Invalid chunk length in a chunked response."""
def __init__(self, response: HTTPResponse, length: bytes) -> None:
self.partial: int = response.tell() # type: ignore[assignment]
self.expected: int | None = response.length_remaining
self.response = response
self.length = length
def __repr__(self) -> str:
return "InvalidChunkLength(got length %r, %i bytes read)" % (
self.length,
self.partial,
)
class InvalidHeader(HTTPError):
"""The header provided was somehow invalid."""
class ProxySchemeUnknown(AssertionError, URLSchemeUnknown):
"""ProxyManager does not support the supplied scheme"""
# TODO(t-8ch): Stop inheriting from AssertionError in v2.0.
def __init__(self, scheme: str | None) -> None:
# 'localhost' is here because our URL parser parses
# localhost:8080 -> scheme=localhost, remove if we fix this.
if scheme == "localhost":
scheme = None
if scheme is None:
message = "Proxy URL had no scheme, should start with http:// or https://"
else:
message = f"Proxy URL had unsupported scheme {scheme}, should use http:// or https://"
super().__init__(message)
class ProxySchemeUnsupported(ValueError):
"""Fetching HTTPS resources through HTTPS proxies is unsupported"""
class HeaderParsingError(HTTPError):
"""Raised by assert_header_parsing, but we convert it to a log.warning statement."""
def __init__(
self, defects: list[MessageDefect], unparsed_data: bytes | str | None
) -> None:
message = f"{defects or 'Unknown'}, unparsed data: {unparsed_data!r}"
super().__init__(message)
class UnrewindableBodyError(HTTPError):
"""urllib3 encountered an error when trying to rewind a body"""

341
venv/lib/python3.12/site-packages/urllib3/fields.py Normal file
View File

@@ -0,0 +1,341 @@
from __future__ import annotations
import email.utils
import mimetypes
import typing
_TYPE_FIELD_VALUE = typing.Union[str, bytes]
_TYPE_FIELD_VALUE_TUPLE = typing.Union[
_TYPE_FIELD_VALUE,
tuple[str, _TYPE_FIELD_VALUE],
tuple[str, _TYPE_FIELD_VALUE, str],
]
def guess_content_type(
filename: str | None, default: str = "application/octet-stream"
) -> str:
"""
Guess the "Content-Type" of a file.
:param filename:
The filename to guess the "Content-Type" of using :mod:`mimetypes`.
:param default:
If no "Content-Type" can be guessed, default to `default`.
"""
if filename:
return mimetypes.guess_type(filename)[0] or default
return default
def format_header_param_rfc2231(name: str, value: _TYPE_FIELD_VALUE) -> str:
"""
Helper function to format and quote a single header parameter using the
strategy defined in RFC 2231.
Particularly useful for header parameters which might contain
non-ASCII values, like file names. This follows
`RFC 2388 Section 4.4 <https://tools.ietf.org/html/rfc2388#section-4.4>`_.
:param name:
The name of the parameter, a string expected to be ASCII only.
:param value:
The value of the parameter, provided as ``bytes`` or `str``.
:returns:
An RFC-2231-formatted unicode string.
.. deprecated:: 2.0.0
Will be removed in urllib3 v2.1.0. This is not valid for
``multipart/form-data`` header parameters.
"""
import warnings
warnings.warn(
"'format_header_param_rfc2231' is deprecated and will be "
"removed in urllib3 v2.1.0. This is not valid for "
"multipart/form-data header parameters.",
DeprecationWarning,
stacklevel=2,
)
if isinstance(value, bytes):
value = value.decode("utf-8")
if not any(ch in value for ch in '"\\\r\n'):
result = f'{name}="{value}"'
try:
result.encode("ascii")
except (UnicodeEncodeError, UnicodeDecodeError):
pass
else:
return result
value = email.utils.encode_rfc2231(value, "utf-8")
value = f"{name}*={value}"
return value
def format_multipart_header_param(name: str, value: _TYPE_FIELD_VALUE) -> str:
"""
Format and quote a single multipart header parameter.
This follows the `WHATWG HTML Standard`_ as of 2021/06/10, matching
the behavior of current browser and curl versions. Values are
assumed to be UTF-8. The ``\\n``, ``\\r``, and ``"`` characters are
percent encoded.
.. _WHATWG HTML Standard:
https://html.spec.whatwg.org/multipage/
form-control-infrastructure.html#multipart-form-data
:param name:
The name of the parameter, an ASCII-only ``str``.
:param value:
The value of the parameter, a ``str`` or UTF-8 encoded
``bytes``.
:returns:
A string ``name="value"`` with the escaped value.
.. versionchanged:: 2.0.0
Matches the WHATWG HTML Standard as of 2021/06/10. Control
characters are no longer percent encoded.
.. versionchanged:: 2.0.0
Renamed from ``format_header_param_html5`` and
``format_header_param``. The old names will be removed in
urllib3 v2.1.0.
"""
if isinstance(value, bytes):
value = value.decode("utf-8")
# percent encode \n \r "
value = value.translate({10: "%0A", 13: "%0D", 34: "%22"})
return f'{name}="{value}"'
def format_header_param_html5(name: str, value: _TYPE_FIELD_VALUE) -> str:
"""
.. deprecated:: 2.0.0
Renamed to :func:`format_multipart_header_param`. Will be
removed in urllib3 v2.1.0.
"""
import warnings
warnings.warn(
"'format_header_param_html5' has been renamed to "
"'format_multipart_header_param'. The old name will be "
"removed in urllib3 v2.1.0.",
DeprecationWarning,
stacklevel=2,
)
return format_multipart_header_param(name, value)
def format_header_param(name: str, value: _TYPE_FIELD_VALUE) -> str:
"""
.. deprecated:: 2.0.0
Renamed to :func:`format_multipart_header_param`. Will be
removed in urllib3 v2.1.0.
"""
import warnings
warnings.warn(
"'format_header_param' has been renamed to "
"'format_multipart_header_param'. The old name will be "
"removed in urllib3 v2.1.0.",
DeprecationWarning,
stacklevel=2,
)
return format_multipart_header_param(name, value)
class RequestField:
"""
A data container for request body parameters.
:param name:
The name of this request field. Must be unicode.
:param data:
The data/value body.
:param filename:
An optional filename of the request field. Must be unicode.
:param headers:
An optional dict-like object of headers to initially use for the field.
.. versionchanged:: 2.0.0
The ``header_formatter`` parameter is deprecated and will
be removed in urllib3 v2.1.0.
"""
def __init__(
self,
name: str,
data: _TYPE_FIELD_VALUE,
filename: str | None = None,
headers: typing.Mapping[str, str] | None = None,
header_formatter: typing.Callable[[str, _TYPE_FIELD_VALUE], str] | None = None,
):
self._name = name
self._filename = filename
self.data = data
self.headers: dict[str, str | None] = {}
if headers:
self.headers = dict(headers)
if header_formatter is not None:
import warnings
warnings.warn(
"The 'header_formatter' parameter is deprecated and "
"will be removed in urllib3 v2.1.0.",
DeprecationWarning,
stacklevel=2,
)
self.header_formatter = header_formatter
else:
self.header_formatter = format_multipart_header_param
@classmethod
def from_tuples(
cls,
fieldname: str,
value: _TYPE_FIELD_VALUE_TUPLE,
header_formatter: typing.Callable[[str, _TYPE_FIELD_VALUE], str] | None = None,
) -> RequestField:
"""
A :class:`~urllib3.fields.RequestField` factory from old-style tuple parameters.
Supports constructing :class:`~urllib3.fields.RequestField` from
parameter of key/value strings AND key/filetuple. A filetuple is a
(filename, data, MIME type) tuple where the MIME type is optional.
For example::
'foo': 'bar',
'fakefile': ('foofile.txt', 'contents of foofile'),
'realfile': ('barfile.txt', open('realfile').read()),
'typedfile': ('bazfile.bin', open('bazfile').read(), 'image/jpeg'),
'nonamefile': 'contents of nonamefile field',
Field names and filenames must be unicode.
"""
filename: str | None
content_type: str | None
data: _TYPE_FIELD_VALUE
if isinstance(value, tuple):
if len(value) == 3:
filename, data, content_type = value
else:
filename, data = value
content_type = guess_content_type(filename)
else:
filename = None
content_type = None
data = value
request_param = cls(
fieldname, data, filename=filename, header_formatter=header_formatter
)
request_param.make_multipart(content_type=content_type)
return request_param
def _render_part(self, name: str, value: _TYPE_FIELD_VALUE) -> str:
"""
Override this method to change how each multipart header
parameter is formatted. By default, this calls
:func:`format_multipart_header_param`.
:param name:
The name of the parameter, an ASCII-only ``str``.
:param value:
The value of the parameter, a ``str`` or UTF-8 encoded
``bytes``.
:meta public:
"""
return self.header_formatter(name, value)
def _render_parts(
self,
header_parts: (
dict[str, _TYPE_FIELD_VALUE | None]
| typing.Sequence[tuple[str, _TYPE_FIELD_VALUE | None]]
),
) -> str:
"""
Helper function to format and quote a single header.
Useful for single headers that are composed of multiple items. E.g.,
'Content-Disposition' fields.
:param header_parts:
A sequence of (k, v) tuples or a :class:`dict` of (k, v) to format
as `k1="v1"; k2="v2"; ...`.
"""
iterable: typing.Iterable[tuple[str, _TYPE_FIELD_VALUE | None]]
parts = []
if isinstance(header_parts, dict):
iterable = header_parts.items()
else:
iterable = header_parts
for name, value in iterable:
if value is not None:
parts.append(self._render_part(name, value))
return "; ".join(parts)
def render_headers(self) -> str:
"""
Renders the headers for this request field.
"""
lines = []
sort_keys = ["Content-Disposition", "Content-Type", "Content-Location"]
for sort_key in sort_keys:
if self.headers.get(sort_key, False):
lines.append(f"{sort_key}: {self.headers[sort_key]}")
for header_name, header_value in self.headers.items():
if header_name not in sort_keys:
if header_value:
lines.append(f"{header_name}: {header_value}")
lines.append("\r\n")
return "\r\n".join(lines)
def make_multipart(
self,
content_disposition: str | None = None,
content_type: str | None = None,
content_location: str | None = None,
) -> None:
"""
Makes this request field into a multipart request field.
This method overrides "Content-Disposition", "Content-Type" and
"Content-Location" headers to the request parameter.
:param content_disposition:
The 'Content-Disposition' of the request body. Defaults to 'form-data'
:param content_type:
The 'Content-Type' of the request body.
:param content_location:
The 'Content-Location' of the request body.
"""
content_disposition = (content_disposition or "form-data") + "; ".join(
[
"",
self._render_parts(
(("name", self._name), ("filename", self._filename))
),
]
)
self.headers["Content-Disposition"] = content_disposition
self.headers["Content-Type"] = content_type
self.headers["Content-Location"] = content_location

89
venv/lib/python3.12/site-packages/urllib3/filepost.py Normal file
View File

@@ -0,0 +1,89 @@
from __future__ import annotations
import binascii
import codecs
import os
import typing
from io import BytesIO
from .fields import _TYPE_FIELD_VALUE_TUPLE, RequestField
writer = codecs.lookup("utf-8")[3]
_TYPE_FIELDS_SEQUENCE = typing.Sequence[
typing.Union[tuple[str, _TYPE_FIELD_VALUE_TUPLE], RequestField]
]
_TYPE_FIELDS = typing.Union[
_TYPE_FIELDS_SEQUENCE,
typing.Mapping[str, _TYPE_FIELD_VALUE_TUPLE],
]
def choose_boundary() -> str:
"""
Our embarrassingly-simple replacement for mimetools.choose_boundary.
"""
return binascii.hexlify(os.urandom(16)).decode()
def iter_field_objects(fields: _TYPE_FIELDS) -> typing.Iterable[RequestField]:
"""
Iterate over fields.
Supports list of (k, v) tuples and dicts, and lists of
:class:`~urllib3.fields.RequestField`.
"""
iterable: typing.Iterable[RequestField | tuple[str, _TYPE_FIELD_VALUE_TUPLE]]
if isinstance(fields, typing.Mapping):
iterable = fields.items()
else:
iterable = fields
for field in iterable:
if isinstance(field, RequestField):
yield field
else:
yield RequestField.from_tuples(*field)
def encode_multipart_formdata(
fields: _TYPE_FIELDS, boundary: str | None = None
) -> tuple[bytes, str]:
"""
Encode a dictionary of ``fields`` using the multipart/form-data MIME format.
:param fields:
Dictionary of fields or list of (key, :class:`~urllib3.fields.RequestField`).
Values are processed by :func:`urllib3.fields.RequestField.from_tuples`.
:param boundary:
If not specified, then a random boundary will be generated using
:func:`urllib3.filepost.choose_boundary`.
"""
body = BytesIO()
if boundary is None:
boundary = choose_boundary()
for field in iter_field_objects(fields):
body.write(f"--{boundary}\r\n".encode("latin-1"))
writer(body).write(field.render_headers())
data = field.data
if isinstance(data, int):
data = str(data) # Backwards compatibility
if isinstance(data, str):
writer(body).write(data)
else:
body.write(data)
body.write(b"\r\n")
body.write(f"--{boundary}--\r\n".encode("latin-1"))
content_type = f"multipart/form-data; boundary={boundary}"
return body.getvalue(), content_type

53
venv/lib/python3.12/site-packages/urllib3/http2/__init__.py Normal file
View File

@@ -0,0 +1,53 @@
from __future__ import annotations
from importlib.metadata import version
__all__ = [
"inject_into_urllib3",
"extract_from_urllib3",
]
import typing
orig_HTTPSConnection: typing.Any = None
def inject_into_urllib3() -> None:
# First check if h2 version is valid
h2_version = version("h2")
if not h2_version.startswith("4."):
raise ImportError(
"urllib3 v2 supports h2 version 4.x.x, currently "
f"the 'h2' module is compiled with {h2_version!r}. "
"See: https://github.com/urllib3/urllib3/issues/3290"
)
# Import here to avoid circular dependencies.
from .. import connection as urllib3_connection
from .. import util as urllib3_util
from ..connectionpool import HTTPSConnectionPool
from ..util import ssl_ as urllib3_util_ssl
from .connection import HTTP2Connection
global orig_HTTPSConnection
orig_HTTPSConnection = urllib3_connection.HTTPSConnection
HTTPSConnectionPool.ConnectionCls = HTTP2Connection
urllib3_connection.HTTPSConnection = HTTP2Connection # type: ignore[misc]
# TODO: Offer 'http/1.1' as well, but for testing purposes this is handy.
urllib3_util.ALPN_PROTOCOLS = ["h2"]
urllib3_util_ssl.ALPN_PROTOCOLS = ["h2"]
def extract_from_urllib3() -> None:
from .. import connection as urllib3_connection
from .. import util as urllib3_util
from ..connectionpool import HTTPSConnectionPool
from ..util import ssl_ as urllib3_util_ssl
HTTPSConnectionPool.ConnectionCls = orig_HTTPSConnection
urllib3_connection.HTTPSConnection = orig_HTTPSConnection # type: ignore[misc]
urllib3_util.ALPN_PROTOCOLS = ["http/1.1"]
urllib3_util_ssl.ALPN_PROTOCOLS = ["http/1.1"]

356
venv/lib/python3.12/site-packages/urllib3/http2/connection.py Normal file
View File

@@ -0,0 +1,356 @@
from __future__ import annotations
import logging
import re
import threading
import types
import typing
import h2.config # type: ignore[import-untyped]
import h2.connection # type: ignore[import-untyped]
import h2.events # type: ignore[import-untyped]
from .._base_connection import _TYPE_BODY
from .._collections import HTTPHeaderDict
from ..connection import HTTPSConnection, _get_default_user_agent
from ..exceptions import ConnectionError
from ..response import BaseHTTPResponse
orig_HTTPSConnection = HTTPSConnection
T = typing.TypeVar("T")
log = logging.getLogger(__name__)
RE_IS_LEGAL_HEADER_NAME = re.compile(rb"^[!#$%&'*+\-.^_`|~0-9a-z]+$")
RE_IS_ILLEGAL_HEADER_VALUE = re.compile(rb"[\0\x00\x0a\x0d\r\n]|^[ \r\n\t]|[ \r\n\t]$")
def _is_legal_header_name(name: bytes) -> bool:
"""
"An implementation that validates fields according to the definitions in Sections
5.1 and 5.5 of [HTTP] only needs an additional check that field names do not
include uppercase characters." (https://httpwg.org/specs/rfc9113.html#n-field-validity)
`http.client._is_legal_header_name` does not validate the field name according to the
HTTP 1.1 spec, so we do that here, in addition to checking for uppercase characters.
This does not allow for the `:` character in the header name, so should not
be used to validate pseudo-headers.
"""
return bool(RE_IS_LEGAL_HEADER_NAME.match(name))
def _is_illegal_header_value(value: bytes) -> bool:
"""
"A field value MUST NOT contain the zero value (ASCII NUL, 0x00), line feed
(ASCII LF, 0x0a), or carriage return (ASCII CR, 0x0d) at any position. A field
value MUST NOT start or end with an ASCII whitespace character (ASCII SP or HTAB,
0x20 or 0x09)." (https://httpwg.org/specs/rfc9113.html#n-field-validity)
"""
return bool(RE_IS_ILLEGAL_HEADER_VALUE.search(value))
class _LockedObject(typing.Generic[T]):
"""
A wrapper class that hides a specific object behind a lock.
The goal here is to provide a simple way to protect access to an object
that cannot safely be simultaneously accessed from multiple threads. The
intended use of this class is simple: take hold of it with a context
manager, which returns the protected object.
"""
__slots__ = (
"lock",
"_obj",
)
def __init__(self, obj: T):
self.lock = threading.RLock()
self._obj = obj
def __enter__(self) -> T:
self.lock.acquire()
return self._obj
def __exit__(
self,
exc_type: type[BaseException] | None,
exc_val: BaseException | None,
exc_tb: types.TracebackType | None,
) -> None:
self.lock.release()
class HTTP2Connection(HTTPSConnection):
def __init__(
self, host: str, port: int | None = None, **kwargs: typing.Any
) -> None:
self._h2_conn = self._new_h2_conn()
self._h2_stream: int | None = None
self._headers: list[tuple[bytes, bytes]] = []
if "proxy" in kwargs or "proxy_config" in kwargs: # Defensive:
raise NotImplementedError("Proxies aren't supported with HTTP/2")
super().__init__(host, port, **kwargs)
if self._tunnel_host is not None:
raise NotImplementedError("Tunneling isn't supported with HTTP/2")
def _new_h2_conn(self) -> _LockedObject[h2.connection.H2Connection]:
config = h2.config.H2Configuration(client_side=True)
return _LockedObject(h2.connection.H2Connection(config=config))
def connect(self) -> None:
super().connect()
with self._h2_conn as conn:
conn.initiate_connection()
if data_to_send := conn.data_to_send():
self.sock.sendall(data_to_send)
def putrequest( # type: ignore[override]
self,
method: str,
url: str,
**kwargs: typing.Any,
) -> None:
"""putrequest
This deviates from the HTTPConnection method signature since we never need to override
sending accept-encoding headers or the host header.
"""
if "skip_host" in kwargs:
raise NotImplementedError("`skip_host` isn't supported")
if "skip_accept_encoding" in kwargs:
raise NotImplementedError("`skip_accept_encoding` isn't supported")
self._request_url = url or "/"
self._validate_path(url) # type: ignore[attr-defined]
if ":" in self.host:
authority = f"[{self.host}]:{self.port or 443}"
else:
authority = f"{self.host}:{self.port or 443}"
self._headers.append((b":scheme", b"https"))
self._headers.append((b":method", method.encode()))
self._headers.append((b":authority", authority.encode()))
self._headers.append((b":path", url.encode()))
with self._h2_conn as conn:
self._h2_stream = conn.get_next_available_stream_id()
def putheader(self, header: str | bytes, *values: str | bytes) -> None: # type: ignore[override]
# TODO SKIPPABLE_HEADERS from urllib3 are ignored.
header = header.encode() if isinstance(header, str) else header
header = header.lower() # A lot of upstream code uses capitalized headers.
if not _is_legal_header_name(header):
raise ValueError(f"Illegal header name {str(header)}")
for value in values:
value = value.encode() if isinstance(value, str) else value
if _is_illegal_header_value(value):
raise ValueError(f"Illegal header value {str(value)}")
self._headers.append((header, value))
def endheaders(self, message_body: typing.Any = None) -> None: # type: ignore[override]
if self._h2_stream is None:
raise ConnectionError("Must call `putrequest` first.")
with self._h2_conn as conn:
conn.send_headers(
stream_id=self._h2_stream,
headers=self._headers,
end_stream=(message_body is None),
)
if data_to_send := conn.data_to_send():
self.sock.sendall(data_to_send)
self._headers = [] # Reset headers for the next request.
def send(self, data: typing.Any) -> None:
"""Send data to the server.
`data` can be: `str`, `bytes`, an iterable, or file-like objects
that support a .read() method.
"""
if self._h2_stream is None:
raise ConnectionError("Must call `putrequest` first.")
with self._h2_conn as conn:
if data_to_send := conn.data_to_send():
self.sock.sendall(data_to_send)
if hasattr(data, "read"): # file-like objects
while True:
chunk = data.read(self.blocksize)
if not chunk:
break
if isinstance(chunk, str):
chunk = chunk.encode() # pragma: no cover
conn.send_data(self._h2_stream, chunk, end_stream=False)
if data_to_send := conn.data_to_send():
self.sock.sendall(data_to_send)
conn.end_stream(self._h2_stream)
return
if isinstance(data, str): # str -> bytes
data = data.encode()
try:
if isinstance(data, bytes):
conn.send_data(self._h2_stream, data, end_stream=True)
if data_to_send := conn.data_to_send():
self.sock.sendall(data_to_send)
else:
for chunk in data:
conn.send_data(self._h2_stream, chunk, end_stream=False)
if data_to_send := conn.data_to_send():
self.sock.sendall(data_to_send)
conn.end_stream(self._h2_stream)
except TypeError:
raise TypeError(
"`data` should be str, bytes, iterable, or file. got %r"
% type(data)
)
def set_tunnel(
self,
host: str,
port: int | None = None,
headers: typing.Mapping[str, str] | None = None,
scheme: str = "http",
) -> None:
raise NotImplementedError(
"HTTP/2 does not support setting up a tunnel through a proxy"
)
def getresponse( # type: ignore[override]
self,
) -> HTTP2Response:
status = None
data = bytearray()
with self._h2_conn as conn:
end_stream = False
while not end_stream:
# TODO: Arbitrary read value.
if received_data := self.sock.recv(65535):
events = conn.receive_data(received_data)
for event in events:
if isinstance(event, h2.events.ResponseReceived):
headers = HTTPHeaderDict()
for header, value in event.headers:
if header == b":status":
status = int(value.decode())
else:
headers.add(
header.decode("ascii"), value.decode("ascii")
)
elif isinstance(event, h2.events.DataReceived):
data += event.data
conn.acknowledge_received_data(
event.flow_controlled_length, event.stream_id
)
elif isinstance(event, h2.events.StreamEnded):
end_stream = True
if data_to_send := conn.data_to_send():
self.sock.sendall(data_to_send)
assert status is not None
return HTTP2Response(
status=status,
headers=headers,
request_url=self._request_url,
data=bytes(data),
)
def request( # type: ignore[override]
self,
method: str,
url: str,
body: _TYPE_BODY | None = None,
headers: typing.Mapping[str, str] | None = None,
*,
preload_content: bool = True,
decode_content: bool = True,
enforce_content_length: bool = True,
**kwargs: typing.Any,
) -> None:
"""Send an HTTP/2 request"""
if "chunked" in kwargs:
# TODO this is often present from upstream.
# raise NotImplementedError("`chunked` isn't supported with HTTP/2")
pass
if self.sock is not None:
self.sock.settimeout(self.timeout)
self.putrequest(method, url)
headers = headers or {}
for k, v in headers.items():
if k.lower() == "transfer-encoding" and v == "chunked":
continue
else:
self.putheader(k, v)
if b"user-agent" not in dict(self._headers):
self.putheader(b"user-agent", _get_default_user_agent())
if body:
self.endheaders(message_body=body)
self.send(body)
else:
self.endheaders()
def close(self) -> None:
with self._h2_conn as conn:
try:
conn.close_connection()
if data := conn.data_to_send():
self.sock.sendall(data)
except Exception:
pass
# Reset all our HTTP/2 connection state.
self._h2_conn = self._new_h2_conn()
self._h2_stream = None
self._headers = []
super().close()
class HTTP2Response(BaseHTTPResponse):
# TODO: This is a woefully incomplete response object, but works for non-streaming.
def __init__(
self,
status: int,
headers: HTTPHeaderDict,
request_url: str,
data: bytes,
decode_content: bool = False, # TODO: support decoding
) -> None:
super().__init__(
status=status,
headers=headers,
# Following CPython, we map HTTP versions to major * 10 + minor integers
version=20,
version_string="HTTP/2",
# No reason phrase in HTTP/2
reason=None,
decode_content=decode_content,
request_url=request_url,
)
self._data = data
self.length_remaining = 0
@property
def data(self) -> bytes:
return self._data
def get_redirect_location(self) -> None:
return None
def close(self) -> None:
pass

87
venv/lib/python3.12/site-packages/urllib3/http2/probe.py Normal file
View File

@@ -0,0 +1,87 @@
from __future__ import annotations
import threading
class _HTTP2ProbeCache:
__slots__ = (
"_lock",
"_cache_locks",
"_cache_values",
)
def __init__(self) -> None:
self._lock = threading.Lock()
self._cache_locks: dict[tuple[str, int], threading.RLock] = {}
self._cache_values: dict[tuple[str, int], bool | None] = {}
def acquire_and_get(self, host: str, port: int) -> bool | None:
# By the end of this block we know that
# _cache_[values,locks] is available.
value = None
with self._lock:
key = (host, port)
try:
value = self._cache_values[key]
# If it's a known value we return right away.
if value is not None:
return value
except KeyError:
self._cache_locks[key] = threading.RLock()
self._cache_values[key] = None
# If the value is unknown, we acquire the lock to signal
# to the requesting thread that the probe is in progress
# or that the current thread needs to return their findings.
key_lock = self._cache_locks[key]
key_lock.acquire()
try:
# If the by the time we get the lock the value has been
# updated we want to return the updated value.
value = self._cache_values[key]
# In case an exception like KeyboardInterrupt is raised here.
except BaseException as e: # Defensive:
assert not isinstance(e, KeyError) # KeyError shouldn't be possible.
key_lock.release()
raise
return value
def set_and_release(
self, host: str, port: int, supports_http2: bool | None
) -> None:
key = (host, port)
key_lock = self._cache_locks[key]
with key_lock: # Uses an RLock, so can be locked again from same thread.
if supports_http2 is None and self._cache_values[key] is not None:
raise ValueError(
"Cannot reset HTTP/2 support for origin after value has been set."
) # Defensive: not expected in normal usage
self._cache_values[key] = supports_http2
key_lock.release()
def _values(self) -> dict[tuple[str, int], bool | None]:
"""This function is for testing purposes only. Gets the current state of the probe cache"""
with self._lock:
return {k: v for k, v in self._cache_values.items()}
def _reset(self) -> None:
"""This function is for testing purposes only. Reset the cache values"""
with self._lock:
self._cache_locks = {}
self._cache_values = {}
_HTTP2_PROBE_CACHE = _HTTP2ProbeCache()
set_and_release = _HTTP2_PROBE_CACHE.set_and_release
acquire_and_get = _HTTP2_PROBE_CACHE.acquire_and_get
_values = _HTTP2_PROBE_CACHE._values
_reset = _HTTP2_PROBE_CACHE._reset
__all__ = [
"set_and_release",
"acquire_and_get",
]

653
venv/lib/python3.12/site-packages/urllib3/poolmanager.py Normal file
View File

@@ -0,0 +1,653 @@
from __future__ import annotations
import functools
import logging
import typing
import warnings
from types import TracebackType
from urllib.parse import urljoin
from ._collections import HTTPHeaderDict, RecentlyUsedContainer
from ._request_methods import RequestMethods
from .connection import ProxyConfig
from .connectionpool import HTTPConnectionPool, HTTPSConnectionPool, port_by_scheme
from .exceptions import (
LocationValueError,
MaxRetryError,
ProxySchemeUnknown,
URLSchemeUnknown,
)
from .response import BaseHTTPResponse
from .util.connection import _TYPE_SOCKET_OPTIONS
from .util.proxy import connection_requires_http_tunnel
from .util.retry import Retry
from .util.timeout import Timeout
from .util.url import Url, parse_url
if typing.TYPE_CHECKING:
import ssl
from typing_extensions import Self
__all__ = ["PoolManager", "ProxyManager", "proxy_from_url"]
log = logging.getLogger(__name__)
SSL_KEYWORDS = (
"key_file",
"cert_file",
"cert_reqs",
"ca_certs",
"ca_cert_data",
"ssl_version",
"ssl_minimum_version",
"ssl_maximum_version",
"ca_cert_dir",
"ssl_context",
"key_password",
"server_hostname",
)
# Default value for `blocksize` - a new parameter introduced to
# http.client.HTTPConnection & http.client.HTTPSConnection in Python 3.7
_DEFAULT_BLOCKSIZE = 16384
class PoolKey(typing.NamedTuple):
"""
All known keyword arguments that could be provided to the pool manager, its
pools, or the underlying connections.
All custom key schemes should include the fields in this key at a minimum.
"""
key_scheme: str
key_host: str
key_port: int | None
key_timeout: Timeout | float | int | None
key_retries: Retry | bool | int | None
key_block: bool | None
key_source_address: tuple[str, int] | None
key_key_file: str | None
key_key_password: str | None
key_cert_file: str | None
key_cert_reqs: str | None
key_ca_certs: str | None
key_ca_cert_data: str | bytes | None
key_ssl_version: int | str | None
key_ssl_minimum_version: ssl.TLSVersion | None
key_ssl_maximum_version: ssl.TLSVersion | None
key_ca_cert_dir: str | None
key_ssl_context: ssl.SSLContext | None
key_maxsize: int | None
key_headers: frozenset[tuple[str, str]] | None
key__proxy: Url | None
key__proxy_headers: frozenset[tuple[str, str]] | None
key__proxy_config: ProxyConfig | None
key_socket_options: _TYPE_SOCKET_OPTIONS | None
key__socks_options: frozenset[tuple[str, str]] | None
key_assert_hostname: bool | str | None
key_assert_fingerprint: str | None
key_server_hostname: str | None
key_blocksize: int | None
def _default_key_normalizer(
key_class: type[PoolKey], request_context: dict[str, typing.Any]
) -> PoolKey:
"""
Create a pool key out of a request context dictionary.
According to RFC 3986, both the scheme and host are case-insensitive.
Therefore, this function normalizes both before constructing the pool
key for an HTTPS request. If you wish to change this behaviour, provide
alternate callables to ``key_fn_by_scheme``.
:param key_class:
The class to use when constructing the key. This should be a namedtuple
with the ``scheme`` and ``host`` keys at a minimum.
:type key_class: namedtuple
:param request_context:
A dictionary-like object that contain the context for a request.
:type request_context: dict
:return: A namedtuple that can be used as a connection pool key.
:rtype: PoolKey
"""
# Since we mutate the dictionary, make a copy first
context = request_context.copy()
context["scheme"] = context["scheme"].lower()
context["host"] = context["host"].lower()
# These are both dictionaries and need to be transformed into frozensets
for key in ("headers", "_proxy_headers", "_socks_options"):
if key in context and context[key] is not None:
context[key] = frozenset(context[key].items())
# The socket_options key may be a list and needs to be transformed into a
# tuple.
socket_opts = context.get("socket_options")
if socket_opts is not None:
context["socket_options"] = tuple(socket_opts)
# Map the kwargs to the names in the namedtuple - this is necessary since
# namedtuples can't have fields starting with '_'.
for key in list(context.keys()):
context["key_" + key] = context.pop(key)
# Default to ``None`` for keys missing from the context
for field in key_class._fields:
if field not in context:
context[field] = None
# Default key_blocksize to _DEFAULT_BLOCKSIZE if missing from the context
if context.get("key_blocksize") is None:
context["key_blocksize"] = _DEFAULT_BLOCKSIZE
return key_class(**context)
#: A dictionary that maps a scheme to a callable that creates a pool key.
#: This can be used to alter the way pool keys are constructed, if desired.
#: Each PoolManager makes a copy of this dictionary so they can be configured
#: globally here, or individually on the instance.
key_fn_by_scheme = {
"http": functools.partial(_default_key_normalizer, PoolKey),
"https": functools.partial(_default_key_normalizer, PoolKey),
}
pool_classes_by_scheme = {"http": HTTPConnectionPool, "https": HTTPSConnectionPool}
class PoolManager(RequestMethods):
"""
Allows for arbitrary requests while transparently keeping track of
necessary connection pools for you.
:param num_pools:
Number of connection pools to cache before discarding the least
recently used pool.
:param headers:
Headers to include with all requests, unless other headers are given
explicitly.
:param \\**connection_pool_kw:
Additional parameters are used to create fresh
:class:`urllib3.connectionpool.ConnectionPool` instances.
Example:
.. code-block:: python
import urllib3
http = urllib3.PoolManager(num_pools=2)
resp1 = http.request("GET", "https://google.com/")
resp2 = http.request("GET", "https://google.com/mail")
resp3 = http.request("GET", "https://yahoo.com/")
print(len(http.pools))
# 2
"""
proxy: Url | None = None
proxy_config: ProxyConfig | None = None
def __init__(
self,
num_pools: int = 10,
headers: typing.Mapping[str, str] | None = None,
**connection_pool_kw: typing.Any,
) -> None:
super().__init__(headers)
if "retries" in connection_pool_kw:
retries = connection_pool_kw["retries"]
if not isinstance(retries, Retry):
# When Retry is initialized, raise_on_redirect is based
# on a redirect boolean value.
# But requests made via a pool manager always set
# redirect to False, and raise_on_redirect always ends
# up being False consequently.
# Here we fix the issue by setting raise_on_redirect to
# a value needed by the pool manager without considering
# the redirect boolean.
raise_on_redirect = retries is not False
retries = Retry.from_int(retries, redirect=False)
retries.raise_on_redirect = raise_on_redirect
connection_pool_kw = connection_pool_kw.copy()
connection_pool_kw["retries"] = retries
self.connection_pool_kw = connection_pool_kw
self.pools: RecentlyUsedContainer[PoolKey, HTTPConnectionPool]
self.pools = RecentlyUsedContainer(num_pools)
# Locally set the pool classes and keys so other PoolManagers can
# override them.
self.pool_classes_by_scheme = pool_classes_by_scheme
self.key_fn_by_scheme = key_fn_by_scheme.copy()
def __enter__(self) -> Self:
return self
def __exit__(
self,
exc_type: type[BaseException] | None,
exc_val: BaseException | None,
exc_tb: TracebackType | None,
) -> typing.Literal[False]:
self.clear()
# Return False to re-raise any potential exceptions
return False
def _new_pool(
self,
scheme: str,
host: str,
port: int,
request_context: dict[str, typing.Any] | None = None,
) -> HTTPConnectionPool:
"""
Create a new :class:`urllib3.connectionpool.ConnectionPool` based on host, port, scheme, and
any additional pool keyword arguments.
If ``request_context`` is provided, it is provided as keyword arguments
to the pool class used. This method is used to actually create the
connection pools handed out by :meth:`connection_from_url` and
companion methods. It is intended to be overridden for customization.
"""
pool_cls: type[HTTPConnectionPool] = self.pool_classes_by_scheme[scheme]
if request_context is None:
request_context = self.connection_pool_kw.copy()
# Default blocksize to _DEFAULT_BLOCKSIZE if missing or explicitly
# set to 'None' in the request_context.
if request_context.get("blocksize") is None:
request_context["blocksize"] = _DEFAULT_BLOCKSIZE
# Although the context has everything necessary to create the pool,
# this function has historically only used the scheme, host, and port
# in the positional args. When an API change is acceptable these can
# be removed.
for key in ("scheme", "host", "port"):
request_context.pop(key, None)
if scheme == "http":
for kw in SSL_KEYWORDS:
request_context.pop(kw, None)
return pool_cls(host, port, **request_context)
def clear(self) -> None:
"""
Empty our store of pools and direct them all to close.
This will not affect in-flight connections, but they will not be
re-used after completion.
"""
self.pools.clear()
def connection_from_host(
self,
host: str | None,
port: int | None = None,
scheme: str | None = "http",
pool_kwargs: dict[str, typing.Any] | None = None,
) -> HTTPConnectionPool:
"""
Get a :class:`urllib3.connectionpool.ConnectionPool` based on the host, port, and scheme.
If ``port`` isn't given, it will be derived from the ``scheme`` using
``urllib3.connectionpool.port_by_scheme``. If ``pool_kwargs`` is
provided, it is merged with the instance's ``connection_pool_kw``
variable and used to create the new connection pool, if one is
needed.
"""
if not host:
raise LocationValueError("No host specified.")
request_context = self._merge_pool_kwargs(pool_kwargs)
request_context["scheme"] = scheme or "http"
if not port:
port = port_by_scheme.get(request_context["scheme"].lower(), 80)
request_context["port"] = port
request_context["host"] = host
return self.connection_from_context(request_context)
def connection_from_context(
self, request_context: dict[str, typing.Any]
) -> HTTPConnectionPool:
"""
Get a :class:`urllib3.connectionpool.ConnectionPool` based on the request context.
``request_context`` must at least contain the ``scheme`` key and its
value must be a key in ``key_fn_by_scheme`` instance variable.
"""
if "strict" in request_context:
warnings.warn(
"The 'strict' parameter is no longer needed on Python 3+. "
"This will raise an error in urllib3 v2.1.0.",
DeprecationWarning,
)
request_context.pop("strict")
scheme = request_context["scheme"].lower()
pool_key_constructor = self.key_fn_by_scheme.get(scheme)
if not pool_key_constructor:
raise URLSchemeUnknown(scheme)
pool_key = pool_key_constructor(request_context)
return self.connection_from_pool_key(pool_key, request_context=request_context)
def connection_from_pool_key(
self, pool_key: PoolKey, request_context: dict[str, typing.Any]
) -> HTTPConnectionPool:
"""
Get a :class:`urllib3.connectionpool.ConnectionPool` based on the provided pool key.
``pool_key`` should be a namedtuple that only contains immutable
objects. At a minimum it must have the ``scheme``, ``host``, and
``port`` fields.
"""
with self.pools.lock:
# If the scheme, host, or port doesn't match existing open
# connections, open a new ConnectionPool.
pool = self.pools.get(pool_key)
if pool:
return pool
# Make a fresh ConnectionPool of the desired type
scheme = request_context["scheme"]
host = request_context["host"]
port = request_context["port"]
pool = self._new_pool(scheme, host, port, request_context=request_context)
self.pools[pool_key] = pool
return pool
def connection_from_url(
self, url: str, pool_kwargs: dict[str, typing.Any] | None = None
) -> HTTPConnectionPool:
"""
Similar to :func:`urllib3.connectionpool.connection_from_url`.
If ``pool_kwargs`` is not provided and a new pool needs to be
constructed, ``self.connection_pool_kw`` is used to initialize
the :class:`urllib3.connectionpool.ConnectionPool`. If ``pool_kwargs``
is provided, it is used instead. Note that if a new pool does not
need to be created for the request, the provided ``pool_kwargs`` are
not used.
"""
u = parse_url(url)
return self.connection_from_host(
u.host, port=u.port, scheme=u.scheme, pool_kwargs=pool_kwargs
)
def _merge_pool_kwargs(
self, override: dict[str, typing.Any] | None
) -> dict[str, typing.Any]:
"""
Merge a dictionary of override values for self.connection_pool_kw.
This does not modify self.connection_pool_kw and returns a new dict.
Any keys in the override dictionary with a value of ``None`` are
removed from the merged dictionary.
"""
base_pool_kwargs = self.connection_pool_kw.copy()
if override:
for key, value in override.items():
if value is None:
try:
del base_pool_kwargs[key]
except KeyError:
pass
else:
base_pool_kwargs[key] = value
return base_pool_kwargs
def _proxy_requires_url_absolute_form(self, parsed_url: Url) -> bool:
"""
Indicates if the proxy requires the complete destination URL in the
request. Normally this is only needed when not using an HTTP CONNECT
tunnel.
"""
if self.proxy is None:
return False
return not connection_requires_http_tunnel(
self.proxy, self.proxy_config, parsed_url.scheme
)
def urlopen( # type: ignore[override]
self, method: str, url: str, redirect: bool = True, **kw: typing.Any
) -> BaseHTTPResponse:
"""
Same as :meth:`urllib3.HTTPConnectionPool.urlopen`
with custom cross-host redirect logic and only sends the request-uri
portion of the ``url``.
The given ``url`` parameter must be absolute, such that an appropriate
:class:`urllib3.connectionpool.ConnectionPool` can be chosen for it.
"""
u = parse_url(url)
if u.scheme is None:
warnings.warn(
"URLs without a scheme (ie 'https://') are deprecated and will raise an error "
"in a future version of urllib3. To avoid this DeprecationWarning ensure all URLs "
"start with 'https://' or 'http://'. Read more in this issue: "
"https://github.com/urllib3/urllib3/issues/2920",
category=DeprecationWarning,
stacklevel=2,
)
conn = self.connection_from_host(u.host, port=u.port, scheme=u.scheme)
kw["assert_same_host"] = False
kw["redirect"] = False
if "headers" not in kw:
kw["headers"] = self.headers
if self._proxy_requires_url_absolute_form(u):
response = conn.urlopen(method, url, **kw)
else:
response = conn.urlopen(method, u.request_uri, **kw)
redirect_location = redirect and response.get_redirect_location()
if not redirect_location:
return response
# Support relative URLs for redirecting.
redirect_location = urljoin(url, redirect_location)
if response.status == 303:
# Change the method according to RFC 9110, Section 15.4.4.
method = "GET"
# And lose the body not to transfer anything sensitive.
kw["body"] = None
kw["headers"] = HTTPHeaderDict(kw["headers"])._prepare_for_method_change()
retries = kw.get("retries", response.retries)
if not isinstance(retries, Retry):
retries = Retry.from_int(retries, redirect=redirect)
# Strip headers marked as unsafe to forward to the redirected location.
# Check remove_headers_on_redirect to avoid a potential network call within
# conn.is_same_host() which may use socket.gethostbyname() in the future.
if retries.remove_headers_on_redirect and not conn.is_same_host(
redirect_location
):
new_headers = kw["headers"].copy()
for header in kw["headers"]:
if header.lower() in retries.remove_headers_on_redirect:
new_headers.pop(header, None)
kw["headers"] = new_headers
try:
retries = retries.increment(method, url, response=response, _pool=conn)
except MaxRetryError:
if retries.raise_on_redirect:
response.drain_conn()
raise
return response
kw["retries"] = retries
kw["redirect"] = redirect
log.info("Redirecting %s -> %s", url, redirect_location)
response.drain_conn()
return self.urlopen(method, redirect_location, **kw)
class ProxyManager(PoolManager):
"""
Behaves just like :class:`PoolManager`, but sends all requests through
the defined proxy, using the CONNECT method for HTTPS URLs.
:param proxy_url:
The URL of the proxy to be used.
:param proxy_headers:
A dictionary containing headers that will be sent to the proxy. In case
of HTTP they are being sent with each request, while in the
HTTPS/CONNECT case they are sent only once. Could be used for proxy
authentication.
:param proxy_ssl_context:
The proxy SSL context is used to establish the TLS connection to the
proxy when using HTTPS proxies.
:param use_forwarding_for_https:
(Defaults to False) If set to True will forward requests to the HTTPS
proxy to be made on behalf of the client instead of creating a TLS
tunnel via the CONNECT method. **Enabling this flag means that request
and response headers and content will be visible from the HTTPS proxy**
whereas tunneling keeps request and response headers and content
private. IP address, target hostname, SNI, and port are always visible
to an HTTPS proxy even when this flag is disabled.
:param proxy_assert_hostname:
The hostname of the certificate to verify against.
:param proxy_assert_fingerprint:
The fingerprint of the certificate to verify against.
Example:
.. code-block:: python
import urllib3
proxy = urllib3.ProxyManager("https://localhost:3128/")
resp1 = proxy.request("GET", "https://google.com/")
resp2 = proxy.request("GET", "https://httpbin.org/")
print(len(proxy.pools))
# 1
resp3 = proxy.request("GET", "https://httpbin.org/")
resp4 = proxy.request("GET", "https://twitter.com/")
print(len(proxy.pools))
# 3
"""
def __init__(
self,
proxy_url: str,
num_pools: int = 10,
headers: typing.Mapping[str, str] | None = None,
proxy_headers: typing.Mapping[str, str] | None = None,
proxy_ssl_context: ssl.SSLContext | None = None,
use_forwarding_for_https: bool = False,
proxy_assert_hostname: None | str | typing.Literal[False] = None,
proxy_assert_fingerprint: str | None = None,
**connection_pool_kw: typing.Any,
) -> None:
if isinstance(proxy_url, HTTPConnectionPool):
str_proxy_url = f"{proxy_url.scheme}://{proxy_url.host}:{proxy_url.port}"
else:
str_proxy_url = proxy_url
proxy = parse_url(str_proxy_url)
if proxy.scheme not in ("http", "https"):
raise ProxySchemeUnknown(proxy.scheme)
if not proxy.port:
port = port_by_scheme.get(proxy.scheme, 80)
proxy = proxy._replace(port=port)
self.proxy = proxy
self.proxy_headers = proxy_headers or {}
self.proxy_ssl_context = proxy_ssl_context
self.proxy_config = ProxyConfig(
proxy_ssl_context,
use_forwarding_for_https,
proxy_assert_hostname,
proxy_assert_fingerprint,
)
connection_pool_kw["_proxy"] = self.proxy
connection_pool_kw["_proxy_headers"] = self.proxy_headers
connection_pool_kw["_proxy_config"] = self.proxy_config
super().__init__(num_pools, headers, **connection_pool_kw)
def connection_from_host(
self,
host: str | None,
port: int | None = None,
scheme: str | None = "http",
pool_kwargs: dict[str, typing.Any] | None = None,
) -> HTTPConnectionPool:
if scheme == "https":
return super().connection_from_host(
host, port, scheme, pool_kwargs=pool_kwargs
)
return super().connection_from_host(
self.proxy.host, self.proxy.port, self.proxy.scheme, pool_kwargs=pool_kwargs # type: ignore[union-attr]
)
def _set_proxy_headers(
self, url: str, headers: typing.Mapping[str, str] | None = None
) -> typing.Mapping[str, str]:
"""
Sets headers needed by proxies: specifically, the Accept and Host
headers. Only sets headers not provided by the user.
"""
headers_ = {"Accept": "*/*"}
netloc = parse_url(url).netloc
if netloc:
headers_["Host"] = netloc
if headers:
headers_.update(headers)
return headers_
def urlopen( # type: ignore[override]
self, method: str, url: str, redirect: bool = True, **kw: typing.Any
) -> BaseHTTPResponse:
"Same as HTTP(S)ConnectionPool.urlopen, ``url`` must be absolute."
u = parse_url(url)
if not connection_requires_http_tunnel(self.proxy, self.proxy_config, u.scheme):
# For connections using HTTP CONNECT, httplib sets the necessary
# headers on the CONNECT to the proxy. If we're not using CONNECT,
# we'll definitely need to set 'Host' at the very least.
headers = kw.get("headers", self.headers)
kw["headers"] = self._set_proxy_headers(url, headers)
return super().urlopen(method, url, redirect=redirect, **kw)
def proxy_from_url(url: str, **kw: typing.Any) -> ProxyManager:
return ProxyManager(proxy_url=url, **kw)

2
venv/lib/python3.12/site-packages/urllib3/py.typed Normal file
View File

@@ -0,0 +1,2 @@
# Instruct type checkers to look for inline type annotations in this package.
# See PEP 561.

1307
venv/lib/python3.12/site-packages/urllib3/response.py Normal file
View File

File diff suppressed because it is too large Load Diff

42
venv/lib/python3.12/site-packages/urllib3/util/__init__.py Normal file
View File

@@ -0,0 +1,42 @@
# For backwards compatibility, provide imports that used to be here.
from __future__ import annotations
from .connection import is_connection_dropped
from .request import SKIP_HEADER, SKIPPABLE_HEADERS, make_headers
from .response import is_fp_closed
from .retry import Retry
from .ssl_ import (
ALPN_PROTOCOLS,
IS_PYOPENSSL,
SSLContext,
assert_fingerprint,
create_urllib3_context,
resolve_cert_reqs,
resolve_ssl_version,
ssl_wrap_socket,
)
from .timeout import Timeout
from .url import Url, parse_url
from .wait import wait_for_read, wait_for_write
__all__ = (
"IS_PYOPENSSL",
"SSLContext",
"ALPN_PROTOCOLS",
"Retry",
"Timeout",
"Url",
"assert_fingerprint",
"create_urllib3_context",
"is_connection_dropped",
"is_fp_closed",
"parse_url",
"make_headers",
"resolve_cert_reqs",
"resolve_ssl_version",
"ssl_wrap_socket",
"wait_for_read",
"wait_for_write",
"SKIP_HEADER",
"SKIPPABLE_HEADERS",
)

137
venv/lib/python3.12/site-packages/urllib3/util/connection.py Normal file
View File

@@ -0,0 +1,137 @@
from __future__ import annotations
import socket
import typing
from ..exceptions import LocationParseError
from .timeout import _DEFAULT_TIMEOUT, _TYPE_TIMEOUT
_TYPE_SOCKET_OPTIONS = list[tuple[int, int, typing.Union[int, bytes]]]
if typing.TYPE_CHECKING:
from .._base_connection import BaseHTTPConnection
def is_connection_dropped(conn: BaseHTTPConnection) -> bool: # Platform-specific
"""
Returns True if the connection is dropped and should be closed.
:param conn: :class:`urllib3.connection.HTTPConnection` object.
"""
return not conn.is_connected
# This function is copied from socket.py in the Python 2.7 standard
# library test suite. Added to its signature is only `socket_options`.
# One additional modification is that we avoid binding to IPv6 servers
# discovered in DNS if the system doesn't have IPv6 functionality.
def create_connection(
address: tuple[str, int],
timeout: _TYPE_TIMEOUT = _DEFAULT_TIMEOUT,
source_address: tuple[str, int] | None = None,
socket_options: _TYPE_SOCKET_OPTIONS | None = None,
) -> socket.socket:
"""Connect to *address* and return the socket object.
Convenience function. Connect to *address* (a 2-tuple ``(host,
port)``) and return the socket object. Passing the optional
*timeout* parameter will set the timeout on the socket instance
before attempting to connect. If no *timeout* is supplied, the
global default timeout setting returned by :func:`socket.getdefaulttimeout`
is used. If *source_address* is set it must be a tuple of (host, port)
for the socket to bind as a source address before making the connection.
An host of '' or port 0 tells the OS to use the default.
"""
host, port = address
if host.startswith("["):
host = host.strip("[]")
err = None
# Using the value from allowed_gai_family() in the context of getaddrinfo lets
# us select whether to work with IPv4 DNS records, IPv6 records, or both.
# The original create_connection function always returns all records.
family = allowed_gai_family()
try:
host.encode("idna")
except UnicodeError:
raise LocationParseError(f"'{host}', label empty or too long") from None
for res in socket.getaddrinfo(host, port, family, socket.SOCK_STREAM):
af, socktype, proto, canonname, sa = res
sock = None
try:
sock = socket.socket(af, socktype, proto)
# If provided, set socket level options before connecting.
_set_socket_options(sock, socket_options)
if timeout is not _DEFAULT_TIMEOUT:
sock.settimeout(timeout)
if source_address:
sock.bind(source_address)
sock.connect(sa)
# Break explicitly a reference cycle
err = None
return sock
except OSError as _:
err = _
if sock is not None:
sock.close()
if err is not None:
try:
raise err
finally:
# Break explicitly a reference cycle
err = None
else:
raise OSError("getaddrinfo returns an empty list")
def _set_socket_options(
sock: socket.socket, options: _TYPE_SOCKET_OPTIONS | None
) -> None:
if options is None:
return
for opt in options:
sock.setsockopt(*opt)
def allowed_gai_family() -> socket.AddressFamily:
"""This function is designed to work in the context of
getaddrinfo, where family=socket.AF_UNSPEC is the default and
will perform a DNS search for both IPv6 and IPv4 records."""
family = socket.AF_INET
if HAS_IPV6:
family = socket.AF_UNSPEC
return family
def _has_ipv6(host: str) -> bool:
"""Returns True if the system can bind an IPv6 address."""
sock = None
has_ipv6 = False
if socket.has_ipv6:
# has_ipv6 returns true if cPython was compiled with IPv6 support.
# It does not tell us if the system has IPv6 support enabled. To
# determine that we must bind to an IPv6 address.
# https://github.com/urllib3/urllib3/pull/611
# https://bugs.python.org/issue658327
try:
sock = socket.socket(socket.AF_INET6)
sock.bind((host, 0))
has_ipv6 = True
except Exception:
pass
if sock:
sock.close()
return has_ipv6
HAS_IPV6 = _has_ipv6("::1")

43
venv/lib/python3.12/site-packages/urllib3/util/proxy.py Normal file
View File

@@ -0,0 +1,43 @@
from __future__ import annotations
import typing
from .url import Url
if typing.TYPE_CHECKING:
from ..connection import ProxyConfig
def connection_requires_http_tunnel(
proxy_url: Url | None = None,
proxy_config: ProxyConfig | None = None,
destination_scheme: str | None = None,
) -> bool:
"""
Returns True if the connection requires an HTTP CONNECT through the proxy.
:param URL proxy_url:
URL of the proxy.
:param ProxyConfig proxy_config:
Proxy configuration from poolmanager.py
:param str destination_scheme:
The scheme of the destination. (i.e https, http, etc)
"""
# If we're not using a proxy, no way to use a tunnel.
if proxy_url is None:
return False
# HTTP destinations never require tunneling, we always forward.
if destination_scheme == "http":
return False
# Support for forwarding with HTTPS proxies and HTTPS destinations.
if (
proxy_url.scheme == "https"
and proxy_config
and proxy_config.use_forwarding_for_https
):
return False
# Otherwise always use a tunnel.
return True

266
venv/lib/python3.12/site-packages/urllib3/util/request.py Normal file
View File

@@ -0,0 +1,266 @@
from __future__ import annotations
import io
import typing
from base64 import b64encode
from enum import Enum
from ..exceptions import UnrewindableBodyError
from .util import to_bytes
if typing.TYPE_CHECKING:
from typing import Final
# Pass as a value within ``headers`` to skip
# emitting some HTTP headers that are added automatically.
# The only headers that are supported are ``Accept-Encoding``,
# ``Host``, and ``User-Agent``.
SKIP_HEADER = "@@@SKIP_HEADER@@@"
SKIPPABLE_HEADERS = frozenset(["accept-encoding", "host", "user-agent"])
ACCEPT_ENCODING = "gzip,deflate"
try:
try:
import brotlicffi as _unused_module_brotli # type: ignore[import-not-found] # noqa: F401
except ImportError:
import brotli as _unused_module_brotli # type: ignore[import-not-found] # noqa: F401
except ImportError:
pass
else:
ACCEPT_ENCODING += ",br"
try:
from compression import ( # type: ignore[import-not-found] # noqa: F401
zstd as _unused_module_zstd,
)
ACCEPT_ENCODING += ",zstd"
except ImportError:
try:
import zstandard as _unused_module_zstd # noqa: F401
ACCEPT_ENCODING += ",zstd"
except ImportError:
pass
class _TYPE_FAILEDTELL(Enum):
token = 0
_FAILEDTELL: Final[_TYPE_FAILEDTELL] = _TYPE_FAILEDTELL.token
_TYPE_BODY_POSITION = typing.Union[int, _TYPE_FAILEDTELL]
# When sending a request with these methods we aren't expecting
# a body so don't need to set an explicit 'Content-Length: 0'
# The reason we do this in the negative instead of tracking methods
# which 'should' have a body is because unknown methods should be
# treated as if they were 'POST' which *does* expect a body.
_METHODS_NOT_EXPECTING_BODY = {"GET", "HEAD", "DELETE", "TRACE", "OPTIONS", "CONNECT"}
def make_headers(
keep_alive: bool | None = None,
accept_encoding: bool | list[str] | str | None = None,
user_agent: str | None = None,
basic_auth: str | None = None,
proxy_basic_auth: str | None = None,
disable_cache: bool | None = None,
) -> dict[str, str]:
"""
Shortcuts for generating request headers.
:param keep_alive:
If ``True``, adds 'connection: keep-alive' header.
:param accept_encoding:
Can be a boolean, list, or string.
``True`` translates to 'gzip,deflate'. If the dependencies for
Brotli (either the ``brotli`` or ``brotlicffi`` package) and/or Zstandard
(the ``zstandard`` package) algorithms are installed, then their encodings are
included in the string ('br' and 'zstd', respectively).
List will get joined by comma.
String will be used as provided.
:param user_agent:
String representing the user-agent you want, such as
"python-urllib3/0.6"
:param basic_auth:
Colon-separated username:password string for 'authorization: basic ...'
auth header.
:param proxy_basic_auth:
Colon-separated username:password string for 'proxy-authorization: basic ...'
auth header.
:param disable_cache:
If ``True``, adds 'cache-control: no-cache' header.
Example:
.. code-block:: python
import urllib3
print(urllib3.util.make_headers(keep_alive=True, user_agent="Batman/1.0"))
# {'connection': 'keep-alive', 'user-agent': 'Batman/1.0'}
print(urllib3.util.make_headers(accept_encoding=True))
# {'accept-encoding': 'gzip,deflate'}
"""
headers: dict[str, str] = {}
if accept_encoding:
if isinstance(accept_encoding, str):
pass
elif isinstance(accept_encoding, list):
accept_encoding = ",".join(accept_encoding)
else:
accept_encoding = ACCEPT_ENCODING
headers["accept-encoding"] = accept_encoding
if user_agent:
headers["user-agent"] = user_agent
if keep_alive:
headers["connection"] = "keep-alive"
if basic_auth:
headers["authorization"] = (
f"Basic {b64encode(basic_auth.encode('latin-1')).decode()}"
)
if proxy_basic_auth:
headers["proxy-authorization"] = (
f"Basic {b64encode(proxy_basic_auth.encode('latin-1')).decode()}"
)
if disable_cache:
headers["cache-control"] = "no-cache"
return headers
def set_file_position(
body: typing.Any, pos: _TYPE_BODY_POSITION | None
) -> _TYPE_BODY_POSITION | None:
"""
If a position is provided, move file to that point.
Otherwise, we'll attempt to record a position for future use.
"""
if pos is not None:
rewind_body(body, pos)
elif getattr(body, "tell", None) is not None:
try:
pos = body.tell()
except OSError:
# This differentiates from None, allowing us to catch
# a failed `tell()` later when trying to rewind the body.
pos = _FAILEDTELL
return pos
def rewind_body(body: typing.IO[typing.AnyStr], body_pos: _TYPE_BODY_POSITION) -> None:
"""
Attempt to rewind body to a certain position.
Primarily used for request redirects and retries.
:param body:
File-like object that supports seek.
:param int pos:
Position to seek to in file.
"""
body_seek = getattr(body, "seek", None)
if body_seek is not None and isinstance(body_pos, int):
try:
body_seek(body_pos)
except OSError as e:
raise UnrewindableBodyError(
"An error occurred when rewinding request body for redirect/retry."
) from e
elif body_pos is _FAILEDTELL:
raise UnrewindableBodyError(
"Unable to record file position for rewinding "
"request body during a redirect/retry."
)
else:
raise ValueError(
f"body_pos must be of type integer, instead it was {type(body_pos)}."
)
class ChunksAndContentLength(typing.NamedTuple):
chunks: typing.Iterable[bytes] | None
content_length: int | None
def body_to_chunks(
body: typing.Any | None, method: str, blocksize: int
) -> ChunksAndContentLength:
"""Takes the HTTP request method, body, and blocksize and
transforms them into an iterable of chunks to pass to
socket.sendall() and an optional 'Content-Length' header.
A 'Content-Length' of 'None' indicates the length of the body
can't be determined so should use 'Transfer-Encoding: chunked'
for framing instead.
"""
chunks: typing.Iterable[bytes] | None
content_length: int | None
# No body, we need to make a recommendation on 'Content-Length'
# based on whether that request method is expected to have
# a body or not.
if body is None:
chunks = None
if method.upper() not in _METHODS_NOT_EXPECTING_BODY:
content_length = 0
else:
content_length = None
# Bytes or strings become bytes
elif isinstance(body, (str, bytes)):
chunks = (to_bytes(body),)
content_length = len(chunks[0])
# File-like object, TODO: use seek() and tell() for length?
elif hasattr(body, "read"):
def chunk_readable() -> typing.Iterable[bytes]:
nonlocal body, blocksize
encode = isinstance(body, io.TextIOBase)
while True:
datablock = body.read(blocksize)
if not datablock:
break
if encode:
datablock = datablock.encode("utf-8")
yield datablock
chunks = chunk_readable()
content_length = None
# Otherwise we need to start checking via duck-typing.
else:
try:
# Check if the body implements the buffer API.
mv = memoryview(body)
except TypeError:
try:
# Check if the body is an iterable
chunks = iter(body)
content_length = None
except TypeError:
raise TypeError(
f"'body' must be a bytes-like object, file-like "
f"object, or iterable. Instead was {body!r}"
) from None
else:
# Since it implements the buffer API can be passed directly to socket.sendall()
chunks = (body,)
content_length = mv.nbytes
return ChunksAndContentLength(chunks=chunks, content_length=content_length)

101
venv/lib/python3.12/site-packages/urllib3/util/response.py Normal file
View File

@@ -0,0 +1,101 @@
from __future__ import annotations
import http.client as httplib
from email.errors import MultipartInvariantViolationDefect, StartBoundaryNotFoundDefect
from ..exceptions import HeaderParsingError
def is_fp_closed(obj: object) -> bool:
"""
Checks whether a given file-like object is closed.
:param obj:
The file-like object to check.
"""
try:
# Check `isclosed()` first, in case Python3 doesn't set `closed`.
# GH Issue #928
return obj.isclosed() # type: ignore[no-any-return, attr-defined]
except AttributeError:
pass
try:
# Check via the official file-like-object way.
return obj.closed # type: ignore[no-any-return, attr-defined]
except AttributeError:
pass
try:
# Check if the object is a container for another file-like object that
# gets released on exhaustion (e.g. HTTPResponse).
return obj.fp is None # type: ignore[attr-defined]
except AttributeError:
pass
raise ValueError("Unable to determine whether fp is closed.")
def assert_header_parsing(headers: httplib.HTTPMessage) -> None:
"""
Asserts whether all headers have been successfully parsed.
Extracts encountered errors from the result of parsing headers.
Only works on Python 3.
:param http.client.HTTPMessage headers: Headers to verify.
:raises urllib3.exceptions.HeaderParsingError:
If parsing errors are found.
"""
# This will fail silently if we pass in the wrong kind of parameter.
# To make debugging easier add an explicit check.
if not isinstance(headers, httplib.HTTPMessage):
raise TypeError(f"expected httplib.Message, got {type(headers)}.")
unparsed_data = None
# get_payload is actually email.message.Message.get_payload;
# we're only interested in the result if it's not a multipart message
if not headers.is_multipart():
payload = headers.get_payload()
if isinstance(payload, (bytes, str)):
unparsed_data = payload
# httplib is assuming a response body is available
# when parsing headers even when httplib only sends
# header data to parse_headers() This results in
# defects on multipart responses in particular.
# See: https://github.com/urllib3/urllib3/issues/800
# So we ignore the following defects:
# - StartBoundaryNotFoundDefect:
# The claimed start boundary was never found.
# - MultipartInvariantViolationDefect:
# A message claimed to be a multipart but no subparts were found.
defects = [
defect
for defect in headers.defects
if not isinstance(
defect, (StartBoundaryNotFoundDefect, MultipartInvariantViolationDefect)
)
]
if defects or unparsed_data:
raise HeaderParsingError(defects=defects, unparsed_data=unparsed_data)
def is_response_to_head(response: httplib.HTTPResponse) -> bool:
"""
Checks whether the request of a response has been a HEAD-request.
:param http.client.HTTPResponse response:
Response to check if the originating request
used 'HEAD' as a method.
"""
# FIXME: Can we do this somehow without accessing private httplib _method?
method_str = response._method # type: str # type: ignore[attr-defined]
return method_str.upper() == "HEAD"

533
venv/lib/python3.12/site-packages/urllib3/util/retry.py Normal file
View File

@@ -0,0 +1,533 @@
from __future__ import annotations
import email
import logging
import random
import re
import time
import typing
from itertools import takewhile
from types import TracebackType
from ..exceptions import (
ConnectTimeoutError,
InvalidHeader,
MaxRetryError,
ProtocolError,
ProxyError,
ReadTimeoutError,
ResponseError,
)
from .util import reraise
if typing.TYPE_CHECKING:
from typing_extensions import Self
from ..connectionpool import ConnectionPool
from ..response import BaseHTTPResponse
log = logging.getLogger(__name__)
# Data structure for representing the metadata of requests that result in a retry.
class RequestHistory(typing.NamedTuple):
method: str | None
url: str | None
error: Exception | None
status: int | None
redirect_location: str | None
class Retry:
"""Retry configuration.
Each retry attempt will create a new Retry object with updated values, so
they can be safely reused.
Retries can be defined as a default for a pool:
.. code-block:: python
retries = Retry(connect=5, read=2, redirect=5)
http = PoolManager(retries=retries)
response = http.request("GET", "https://example.com/")
Or per-request (which overrides the default for the pool):
.. code-block:: python
response = http.request("GET", "https://example.com/", retries=Retry(10))
Retries can be disabled by passing ``False``:
.. code-block:: python
response = http.request("GET", "https://example.com/", retries=False)
Errors will be wrapped in :class:`~urllib3.exceptions.MaxRetryError` unless
retries are disabled, in which case the causing exception will be raised.
:param int total:
Total number of retries to allow. Takes precedence over other counts.
Set to ``None`` to remove this constraint and fall back on other
counts.
Set to ``0`` to fail on the first retry.
Set to ``False`` to disable and imply ``raise_on_redirect=False``.
:param int connect:
How many connection-related errors to retry on.
These are errors raised before the request is sent to the remote server,
which we assume has not triggered the server to process the request.
Set to ``0`` to fail on the first retry of this type.
:param int read:
How many times to retry on read errors.
These errors are raised after the request was sent to the server, so the
request may have side-effects.
Set to ``0`` to fail on the first retry of this type.
:param int redirect:
How many redirects to perform. Limit this to avoid infinite redirect
loops.
A redirect is a HTTP response with a status code 301, 302, 303, 307 or
308.
Set to ``0`` to fail on the first retry of this type.
Set to ``False`` to disable and imply ``raise_on_redirect=False``.
:param int status:
How many times to retry on bad status codes.
These are retries made on responses, where status code matches
``status_forcelist``.
Set to ``0`` to fail on the first retry of this type.
:param int other:
How many times to retry on other errors.
Other errors are errors that are not connect, read, redirect or status errors.
These errors might be raised after the request was sent to the server, so the
request might have side-effects.
Set to ``0`` to fail on the first retry of this type.
If ``total`` is not set, it's a good idea to set this to 0 to account
for unexpected edge cases and avoid infinite retry loops.
:param Collection allowed_methods:
Set of uppercased HTTP method verbs that we should retry on.
By default, we only retry on methods which are considered to be
idempotent (multiple requests with the same parameters end with the
same state). See :attr:`Retry.DEFAULT_ALLOWED_METHODS`.
Set to a ``None`` value to retry on any verb.
:param Collection status_forcelist:
A set of integer HTTP status codes that we should force a retry on.
A retry is initiated if the request method is in ``allowed_methods``
and the response status code is in ``status_forcelist``.
By default, this is disabled with ``None``.
:param float backoff_factor:
A backoff factor to apply between attempts after the second try
(most errors are resolved immediately by a second try without a
delay). urllib3 will sleep for::
{backoff factor} * (2 ** ({number of previous retries}))
seconds. If `backoff_jitter` is non-zero, this sleep is extended by::
random.uniform(0, {backoff jitter})
seconds. For example, if the backoff_factor is 0.1, then :func:`Retry.sleep` will
sleep for [0.0s, 0.2s, 0.4s, 0.8s, ...] between retries. No backoff will ever
be longer than `backoff_max`.
By default, backoff is disabled (factor set to 0).
:param bool raise_on_redirect: Whether, if the number of redirects is
exhausted, to raise a MaxRetryError, or to return a response with a
response code in the 3xx range.
:param bool raise_on_status: Similar meaning to ``raise_on_redirect``:
whether we should raise an exception, or return a response,
if status falls in ``status_forcelist`` range and retries have
been exhausted.
:param tuple history: The history of the request encountered during
each call to :meth:`~Retry.increment`. The list is in the order
the requests occurred. Each list item is of class :class:`RequestHistory`.
:param bool respect_retry_after_header:
Whether to respect Retry-After header on status codes defined as
:attr:`Retry.RETRY_AFTER_STATUS_CODES` or not.
:param Collection remove_headers_on_redirect:
Sequence of headers to remove from the request when a response
indicating a redirect is returned before firing off the redirected
request.
"""
#: Default methods to be used for ``allowed_methods``
DEFAULT_ALLOWED_METHODS = frozenset(
["HEAD", "GET", "PUT", "DELETE", "OPTIONS", "TRACE"]
)
#: Default status codes to be used for ``status_forcelist``
RETRY_AFTER_STATUS_CODES = frozenset([413, 429, 503])
#: Default headers to be used for ``remove_headers_on_redirect``
DEFAULT_REMOVE_HEADERS_ON_REDIRECT = frozenset(
["Cookie", "Authorization", "Proxy-Authorization"]
)
#: Default maximum backoff time.
DEFAULT_BACKOFF_MAX = 120
# Backward compatibility; assigned outside of the class.
DEFAULT: typing.ClassVar[Retry]
def __init__(
self,
total: bool | int | None = 10,
connect: int | None = None,
read: int | None = None,
redirect: bool | int | None = None,
status: int | None = None,
other: int | None = None,
allowed_methods: typing.Collection[str] | None = DEFAULT_ALLOWED_METHODS,
status_forcelist: typing.Collection[int] | None = None,
backoff_factor: float = 0,
backoff_max: float = DEFAULT_BACKOFF_MAX,
raise_on_redirect: bool = True,
raise_on_status: bool = True,
history: tuple[RequestHistory, ...] | None = None,
respect_retry_after_header: bool = True,
remove_headers_on_redirect: typing.Collection[
str
] = DEFAULT_REMOVE_HEADERS_ON_REDIRECT,
backoff_jitter: float = 0.0,
) -> None:
self.total = total
self.connect = connect
self.read = read
self.status = status
self.other = other
if redirect is False or total is False:
redirect = 0
raise_on_redirect = False
self.redirect = redirect
self.status_forcelist = status_forcelist or set()
self.allowed_methods = allowed_methods
self.backoff_factor = backoff_factor
self.backoff_max = backoff_max
self.raise_on_redirect = raise_on_redirect
self.raise_on_status = raise_on_status
self.history = history or ()
self.respect_retry_after_header = respect_retry_after_header
self.remove_headers_on_redirect = frozenset(
h.lower() for h in remove_headers_on_redirect
)
self.backoff_jitter = backoff_jitter
def new(self, **kw: typing.Any) -> Self:
params = dict(
total=self.total,
connect=self.connect,
read=self.read,
redirect=self.redirect,
status=self.status,
other=self.other,
allowed_methods=self.allowed_methods,
status_forcelist=self.status_forcelist,
backoff_factor=self.backoff_factor,
backoff_max=self.backoff_max,
raise_on_redirect=self.raise_on_redirect,
raise_on_status=self.raise_on_status,
history=self.history,
remove_headers_on_redirect=self.remove_headers_on_redirect,
respect_retry_after_header=self.respect_retry_after_header,
backoff_jitter=self.backoff_jitter,
)
params.update(kw)
return type(self)(**params) # type: ignore[arg-type]
@classmethod
def from_int(
cls,
retries: Retry | bool | int | None,
redirect: bool | int | None = True,
default: Retry | bool | int | None = None,
) -> Retry:
"""Backwards-compatibility for the old retries format."""
if retries is None:
retries = default if default is not None else cls.DEFAULT
if isinstance(retries, Retry):
return retries
redirect = bool(redirect) and None
new_retries = cls(retries, redirect=redirect)
log.debug("Converted retries value: %r -> %r", retries, new_retries)
return new_retries
def get_backoff_time(self) -> float:
"""Formula for computing the current backoff
:rtype: float
"""
# We want to consider only the last consecutive errors sequence (Ignore redirects).
consecutive_errors_len = len(
list(
takewhile(lambda x: x.redirect_location is None, reversed(self.history))
)
)
if consecutive_errors_len <= 1:
return 0
backoff_value = self.backoff_factor * (2 ** (consecutive_errors_len - 1))
if self.backoff_jitter != 0.0:
backoff_value += random.random() * self.backoff_jitter
return float(max(0, min(self.backoff_max, backoff_value)))
def parse_retry_after(self, retry_after: str) -> float:
seconds: float
# Whitespace: https://tools.ietf.org/html/rfc7230#section-3.2.4
if re.match(r"^\s*[0-9]+\s*$", retry_after):
seconds = int(retry_after)
else:
retry_date_tuple = email.utils.parsedate_tz(retry_after)
if retry_date_tuple is None:
raise InvalidHeader(f"Invalid Retry-After header: {retry_after}")
retry_date = email.utils.mktime_tz(retry_date_tuple)
seconds = retry_date - time.time()
seconds = max(seconds, 0)
return seconds
def get_retry_after(self, response: BaseHTTPResponse) -> float | None:
"""Get the value of Retry-After in seconds."""
retry_after = response.headers.get("Retry-After")
if retry_after is None:
return None
return self.parse_retry_after(retry_after)
def sleep_for_retry(self, response: BaseHTTPResponse) -> bool:
retry_after = self.get_retry_after(response)
if retry_after:
time.sleep(retry_after)
return True
return False
def _sleep_backoff(self) -> None:
backoff = self.get_backoff_time()
if backoff <= 0:
return
time.sleep(backoff)
def sleep(self, response: BaseHTTPResponse | None = None) -> None:
"""Sleep between retry attempts.
This method will respect a server's ``Retry-After`` response header
and sleep the duration of the time requested. If that is not present, it
will use an exponential backoff. By default, the backoff factor is 0 and
this method will return immediately.
"""
if self.respect_retry_after_header and response:
slept = self.sleep_for_retry(response)
if slept:
return
self._sleep_backoff()
def _is_connection_error(self, err: Exception) -> bool:
"""Errors when we're fairly sure that the server did not receive the
request, so it should be safe to retry.
"""
if isinstance(err, ProxyError):
err = err.original_error
return isinstance(err, ConnectTimeoutError)
def _is_read_error(self, err: Exception) -> bool:
"""Errors that occur after the request has been started, so we should
assume that the server began processing it.
"""
return isinstance(err, (ReadTimeoutError, ProtocolError))
def _is_method_retryable(self, method: str) -> bool:
"""Checks if a given HTTP method should be retried upon, depending if
it is included in the allowed_methods
"""
if self.allowed_methods and method.upper() not in self.allowed_methods:
return False
return True
def is_retry(
self, method: str, status_code: int, has_retry_after: bool = False
) -> bool:
"""Is this method/status code retryable? (Based on allowlists and control
variables such as the number of total retries to allow, whether to
respect the Retry-After header, whether this header is present, and
whether the returned status code is on the list of status codes to
be retried upon on the presence of the aforementioned header)
"""
if not self._is_method_retryable(method):
return False
if self.status_forcelist and status_code in self.status_forcelist:
return True
return bool(
self.total
and self.respect_retry_after_header
and has_retry_after
and (status_code in self.RETRY_AFTER_STATUS_CODES)
)
def is_exhausted(self) -> bool:
"""Are we out of retries?"""
retry_counts = [
x
for x in (
self.total,
self.connect,
self.read,
self.redirect,
self.status,
self.other,
)
if x
]
if not retry_counts:
return False
return min(retry_counts) < 0
def increment(
self,
method: str | None = None,
url: str | None = None,
response: BaseHTTPResponse | None = None,
error: Exception | None = None,
_pool: ConnectionPool | None = None,
_stacktrace: TracebackType | None = None,
) -> Self:
"""Return a new Retry object with incremented retry counters.
:param response: A response object, or None, if the server did not
return a response.
:type response: :class:`~urllib3.response.BaseHTTPResponse`
:param Exception error: An error encountered during the request, or
None if the response was received successfully.
:return: A new ``Retry`` object.
"""
if self.total is False and error:
# Disabled, indicate to re-raise the error.
raise reraise(type(error), error, _stacktrace)
total = self.total
if total is not None:
total -= 1
connect = self.connect
read = self.read
redirect = self.redirect
status_count = self.status
other = self.other
cause = "unknown"
status = None
redirect_location = None
if error and self._is_connection_error(error):
# Connect retry?
if connect is False:
raise reraise(type(error), error, _stacktrace)
elif connect is not None:
connect -= 1
elif error and self._is_read_error(error):
# Read retry?
if read is False or method is None or not self._is_method_retryable(method):
raise reraise(type(error), error, _stacktrace)
elif read is not None:
read -= 1
elif error:
# Other retry?
if other is not None:
other -= 1
elif response and response.get_redirect_location():
# Redirect retry?
if redirect is not None:
redirect -= 1
cause = "too many redirects"
response_redirect_location = response.get_redirect_location()
if response_redirect_location:
redirect_location = response_redirect_location
status = response.status
else:
# Incrementing because of a server error like a 500 in
# status_forcelist and the given method is in the allowed_methods
cause = ResponseError.GENERIC_ERROR
if response and response.status:
if status_count is not None:
status_count -= 1
cause = ResponseError.SPECIFIC_ERROR.format(status_code=response.status)
status = response.status
history = self.history + (
RequestHistory(method, url, error, status, redirect_location),
)
new_retry = self.new(
total=total,
connect=connect,
read=read,
redirect=redirect,
status=status_count,
other=other,
history=history,
)
if new_retry.is_exhausted():
reason = error or ResponseError(cause)
raise MaxRetryError(_pool, url, reason) from reason # type: ignore[arg-type]
log.debug("Incremented Retry for (url='%s'): %r", url, new_retry)
return new_retry
def __repr__(self) -> str:
return (
f"{type(self).__name__}(total={self.total}, connect={self.connect}, "
f"read={self.read}, redirect={self.redirect}, status={self.status})"
)
# For backwards compatibility (equivalent to pre-v1.9):
Retry.DEFAULT = Retry(3)

524
venv/lib/python3.12/site-packages/urllib3/util/ssl_.py Normal file
View File

@@ -0,0 +1,524 @@
from __future__ import annotations
import hashlib
import hmac
import os
import socket
import sys
import typing
import warnings
from binascii import unhexlify
from ..exceptions import ProxySchemeUnsupported, SSLError
from .url import _BRACELESS_IPV6_ADDRZ_RE, _IPV4_RE
SSLContext = None
SSLTransport = None
HAS_NEVER_CHECK_COMMON_NAME = False
IS_PYOPENSSL = False
ALPN_PROTOCOLS = ["http/1.1"]
_TYPE_VERSION_INFO = tuple[int, int, int, str, int]
# Maps the length of a digest to a possible hash function producing this digest
HASHFUNC_MAP = {
length: getattr(hashlib, algorithm, None)
for length, algorithm in ((32, "md5"), (40, "sha1"), (64, "sha256"))
}
def _is_bpo_43522_fixed(
implementation_name: str,
version_info: _TYPE_VERSION_INFO,
pypy_version_info: _TYPE_VERSION_INFO | None,
) -> bool:
"""Return True for CPython 3.9.3+ or 3.10+ and PyPy 7.3.8+ where
setting SSLContext.hostname_checks_common_name to False works.
Outside of CPython and PyPy we don't know which implementations work
or not so we conservatively use our hostname matching as we know that works
on all implementations.
https://github.com/urllib3/urllib3/issues/2192#issuecomment-821832963
https://foss.heptapod.net/pypy/pypy/-/issues/3539
"""
if implementation_name == "pypy":
# https://foss.heptapod.net/pypy/pypy/-/issues/3129
return pypy_version_info >= (7, 3, 8) # type: ignore[operator]
elif implementation_name == "cpython":
major_minor = version_info[:2]
micro = version_info[2]
return (major_minor == (3, 9) and micro >= 3) or major_minor >= (3, 10)
else: # Defensive:
return False
def _is_has_never_check_common_name_reliable(
openssl_version: str,
openssl_version_number: int,
implementation_name: str,
version_info: _TYPE_VERSION_INFO,
pypy_version_info: _TYPE_VERSION_INFO | None,
) -> bool:
# As of May 2023, all released versions of LibreSSL fail to reject certificates with
# only common names, see https://github.com/urllib3/urllib3/pull/3024
is_openssl = openssl_version.startswith("OpenSSL ")
# Before fixing OpenSSL issue #14579, the SSL_new() API was not copying hostflags
# like X509_CHECK_FLAG_NEVER_CHECK_SUBJECT, which tripped up CPython.
# https://github.com/openssl/openssl/issues/14579
# This was released in OpenSSL 1.1.1l+ (>=0x101010cf)
is_openssl_issue_14579_fixed = openssl_version_number >= 0x101010CF
return is_openssl and (
is_openssl_issue_14579_fixed
or _is_bpo_43522_fixed(implementation_name, version_info, pypy_version_info)
)
if typing.TYPE_CHECKING:
from ssl import VerifyMode
from typing import TypedDict
from .ssltransport import SSLTransport as SSLTransportType
class _TYPE_PEER_CERT_RET_DICT(TypedDict, total=False):
subjectAltName: tuple[tuple[str, str], ...]
subject: tuple[tuple[tuple[str, str], ...], ...]
serialNumber: str
# Mapping from 'ssl.PROTOCOL_TLSX' to 'TLSVersion.X'
_SSL_VERSION_TO_TLS_VERSION: dict[int, int] = {}
try: # Do we have ssl at all?
import ssl
from ssl import ( # type: ignore[assignment]
CERT_REQUIRED,
HAS_NEVER_CHECK_COMMON_NAME,
OP_NO_COMPRESSION,
OP_NO_TICKET,
OPENSSL_VERSION,
OPENSSL_VERSION_NUMBER,
PROTOCOL_TLS,
PROTOCOL_TLS_CLIENT,
VERIFY_X509_STRICT,
OP_NO_SSLv2,
OP_NO_SSLv3,
SSLContext,
TLSVersion,
)
PROTOCOL_SSLv23 = PROTOCOL_TLS
# Needed for Python 3.9 which does not define this
VERIFY_X509_PARTIAL_CHAIN = getattr(ssl, "VERIFY_X509_PARTIAL_CHAIN", 0x80000)
# Setting SSLContext.hostname_checks_common_name = False didn't work before CPython
# 3.9.3, and 3.10 (but OK on PyPy) or OpenSSL 1.1.1l+
if HAS_NEVER_CHECK_COMMON_NAME and not _is_has_never_check_common_name_reliable(
OPENSSL_VERSION,
OPENSSL_VERSION_NUMBER,
sys.implementation.name,
sys.version_info,
sys.pypy_version_info if sys.implementation.name == "pypy" else None, # type: ignore[attr-defined]
): # Defensive: for Python < 3.9.3
HAS_NEVER_CHECK_COMMON_NAME = False
# Need to be careful here in case old TLS versions get
# removed in future 'ssl' module implementations.
for attr in ("TLSv1", "TLSv1_1", "TLSv1_2"):
try:
_SSL_VERSION_TO_TLS_VERSION[getattr(ssl, f"PROTOCOL_{attr}")] = getattr(
TLSVersion, attr
)
except AttributeError: # Defensive:
continue
from .ssltransport import SSLTransport # type: ignore[assignment]
except ImportError:
OP_NO_COMPRESSION = 0x20000 # type: ignore[assignment]
OP_NO_TICKET = 0x4000 # type: ignore[assignment]
OP_NO_SSLv2 = 0x1000000 # type: ignore[assignment]
OP_NO_SSLv3 = 0x2000000 # type: ignore[assignment]
PROTOCOL_SSLv23 = PROTOCOL_TLS = 2 # type: ignore[assignment]
PROTOCOL_TLS_CLIENT = 16 # type: ignore[assignment]
VERIFY_X509_PARTIAL_CHAIN = 0x80000
VERIFY_X509_STRICT = 0x20 # type: ignore[assignment]
_TYPE_PEER_CERT_RET = typing.Union["_TYPE_PEER_CERT_RET_DICT", bytes, None]
def assert_fingerprint(cert: bytes | None, fingerprint: str) -> None:
"""
Checks if given fingerprint matches the supplied certificate.
:param cert:
Certificate as bytes object.
:param fingerprint:
Fingerprint as string of hexdigits, can be interspersed by colons.
"""
if cert is None:
raise SSLError("No certificate for the peer.")
fingerprint = fingerprint.replace(":", "").lower()
digest_length = len(fingerprint)
if digest_length not in HASHFUNC_MAP:
raise SSLError(f"Fingerprint of invalid length: {fingerprint}")
hashfunc = HASHFUNC_MAP.get(digest_length)
if hashfunc is None:
raise SSLError(
f"Hash function implementation unavailable for fingerprint length: {digest_length}"
)
# We need encode() here for py32; works on py2 and p33.
fingerprint_bytes = unhexlify(fingerprint.encode())
cert_digest = hashfunc(cert).digest()
if not hmac.compare_digest(cert_digest, fingerprint_bytes):
raise SSLError(
f'Fingerprints did not match. Expected "{fingerprint}", got "{cert_digest.hex()}"'
)
def resolve_cert_reqs(candidate: None | int | str) -> VerifyMode:
"""
Resolves the argument to a numeric constant, which can be passed to
the wrap_socket function/method from the ssl module.
Defaults to :data:`ssl.CERT_REQUIRED`.
If given a string it is assumed to be the name of the constant in the
:mod:`ssl` module or its abbreviation.
(So you can specify `REQUIRED` instead of `CERT_REQUIRED`.
If it's neither `None` nor a string we assume it is already the numeric
constant which can directly be passed to wrap_socket.
"""
if candidate is None:
return CERT_REQUIRED
if isinstance(candidate, str):
res = getattr(ssl, candidate, None)
if res is None:
res = getattr(ssl, "CERT_" + candidate)
return res # type: ignore[no-any-return]
return candidate # type: ignore[return-value]
def resolve_ssl_version(candidate: None | int | str) -> int:
"""
like resolve_cert_reqs
"""
if candidate is None:
return PROTOCOL_TLS
if isinstance(candidate, str):
res = getattr(ssl, candidate, None)
if res is None:
res = getattr(ssl, "PROTOCOL_" + candidate)
return typing.cast(int, res)
return candidate
def create_urllib3_context(
ssl_version: int | None = None,
cert_reqs: int | None = None,
options: int | None = None,
ciphers: str | None = None,
ssl_minimum_version: int | None = None,
ssl_maximum_version: int | None = None,
verify_flags: int | None = None,
) -> ssl.SSLContext:
"""Creates and configures an :class:`ssl.SSLContext` instance for use with urllib3.
:param ssl_version:
The desired protocol version to use. This will default to
PROTOCOL_SSLv23 which will negotiate the highest protocol that both
the server and your installation of OpenSSL support.
This parameter is deprecated instead use 'ssl_minimum_version'.
:param ssl_minimum_version:
The minimum version of TLS to be used. Use the 'ssl.TLSVersion' enum for specifying the value.
:param ssl_maximum_version:
The maximum version of TLS to be used. Use the 'ssl.TLSVersion' enum for specifying the value.
Not recommended to set to anything other than 'ssl.TLSVersion.MAXIMUM_SUPPORTED' which is the
default value.
:param cert_reqs:
Whether to require the certificate verification. This defaults to
``ssl.CERT_REQUIRED``.
:param options:
Specific OpenSSL options. These default to ``ssl.OP_NO_SSLv2``,
``ssl.OP_NO_SSLv3``, ``ssl.OP_NO_COMPRESSION``, and ``ssl.OP_NO_TICKET``.
:param ciphers:
Which cipher suites to allow the server to select. Defaults to either system configured
ciphers if OpenSSL 1.1.1+, otherwise uses a secure default set of ciphers.
:param verify_flags:
The flags for certificate verification operations. These default to
``ssl.VERIFY_X509_PARTIAL_CHAIN`` and ``ssl.VERIFY_X509_STRICT`` for Python 3.13+.
:returns:
Constructed SSLContext object with specified options
:rtype: SSLContext
"""
if SSLContext is None:
raise TypeError("Can't create an SSLContext object without an ssl module")
# This means 'ssl_version' was specified as an exact value.
if ssl_version not in (None, PROTOCOL_TLS, PROTOCOL_TLS_CLIENT):
# Disallow setting 'ssl_version' and 'ssl_minimum|maximum_version'
# to avoid conflicts.
if ssl_minimum_version is not None or ssl_maximum_version is not None:
raise ValueError(
"Can't specify both 'ssl_version' and either "
"'ssl_minimum_version' or 'ssl_maximum_version'"
)
# 'ssl_version' is deprecated and will be removed in the future.
else:
# Use 'ssl_minimum_version' and 'ssl_maximum_version' instead.
ssl_minimum_version = _SSL_VERSION_TO_TLS_VERSION.get(
ssl_version, TLSVersion.MINIMUM_SUPPORTED
)
ssl_maximum_version = _SSL_VERSION_TO_TLS_VERSION.get(
ssl_version, TLSVersion.MAXIMUM_SUPPORTED
)
# This warning message is pushing users to use 'ssl_minimum_version'
# instead of both min/max. Best practice is to only set the minimum version and
# keep the maximum version to be it's default value: 'TLSVersion.MAXIMUM_SUPPORTED'
warnings.warn(
"'ssl_version' option is deprecated and will be "
"removed in urllib3 v2.6.0. Instead use 'ssl_minimum_version'",
category=DeprecationWarning,
stacklevel=2,
)
# PROTOCOL_TLS is deprecated in Python 3.10 so we always use PROTOCOL_TLS_CLIENT
context = SSLContext(PROTOCOL_TLS_CLIENT)
if ssl_minimum_version is not None:
context.minimum_version = ssl_minimum_version
else: # Python <3.10 defaults to 'MINIMUM_SUPPORTED' so explicitly set TLSv1.2 here
context.minimum_version = TLSVersion.TLSv1_2
if ssl_maximum_version is not None:
context.maximum_version = ssl_maximum_version
# Unless we're given ciphers defer to either system ciphers in
# the case of OpenSSL 1.1.1+ or use our own secure default ciphers.
if ciphers:
context.set_ciphers(ciphers)
# Setting the default here, as we may have no ssl module on import
cert_reqs = ssl.CERT_REQUIRED if cert_reqs is None else cert_reqs
if options is None:
options = 0
# SSLv2 is easily broken and is considered harmful and dangerous
options |= OP_NO_SSLv2
# SSLv3 has several problems and is now dangerous
options |= OP_NO_SSLv3
# Disable compression to prevent CRIME attacks for OpenSSL 1.0+
# (issue #309)
options |= OP_NO_COMPRESSION
# TLSv1.2 only. Unless set explicitly, do not request tickets.
# This may save some bandwidth on wire, and although the ticket is encrypted,
# there is a risk associated with it being on wire,
# if the server is not rotating its ticketing keys properly.
options |= OP_NO_TICKET
context.options |= options
if verify_flags is None:
verify_flags = 0
# In Python 3.13+ ssl.create_default_context() sets VERIFY_X509_PARTIAL_CHAIN
# and VERIFY_X509_STRICT so we do the same
if sys.version_info >= (3, 13):
verify_flags |= VERIFY_X509_PARTIAL_CHAIN
verify_flags |= VERIFY_X509_STRICT
context.verify_flags |= verify_flags
# Enable post-handshake authentication for TLS 1.3, see GH #1634. PHA is
# necessary for conditional client cert authentication with TLS 1.3.
# The attribute is None for OpenSSL <= 1.1.0 or does not exist when using
# an SSLContext created by pyOpenSSL.
if getattr(context, "post_handshake_auth", None) is not None:
context.post_handshake_auth = True
# The order of the below lines setting verify_mode and check_hostname
# matter due to safe-guards SSLContext has to prevent an SSLContext with
# check_hostname=True, verify_mode=NONE/OPTIONAL.
# We always set 'check_hostname=False' for pyOpenSSL so we rely on our own
# 'ssl.match_hostname()' implementation.
if cert_reqs == ssl.CERT_REQUIRED and not IS_PYOPENSSL:
context.verify_mode = cert_reqs
context.check_hostname = True
else:
context.check_hostname = False
context.verify_mode = cert_reqs
try:
context.hostname_checks_common_name = False
except AttributeError: # Defensive: for CPython < 3.9.3; for PyPy < 7.3.8
pass
sslkeylogfile = os.environ.get("SSLKEYLOGFILE")
if sslkeylogfile:
context.keylog_filename = sslkeylogfile
return context
@typing.overload
def ssl_wrap_socket(
sock: socket.socket,
keyfile: str | None = ...,
certfile: str | None = ...,
cert_reqs: int | None = ...,
ca_certs: str | None = ...,
server_hostname: str | None = ...,
ssl_version: int | None = ...,
ciphers: str | None = ...,
ssl_context: ssl.SSLContext | None = ...,
ca_cert_dir: str | None = ...,
key_password: str | None = ...,
ca_cert_data: None | str | bytes = ...,
tls_in_tls: typing.Literal[False] = ...,
) -> ssl.SSLSocket: ...
@typing.overload
def ssl_wrap_socket(
sock: socket.socket,
keyfile: str | None = ...,
certfile: str | None = ...,
cert_reqs: int | None = ...,
ca_certs: str | None = ...,
server_hostname: str | None = ...,
ssl_version: int | None = ...,
ciphers: str | None = ...,
ssl_context: ssl.SSLContext | None = ...,
ca_cert_dir: str | None = ...,
key_password: str | None = ...,
ca_cert_data: None | str | bytes = ...,
tls_in_tls: bool = ...,
) -> ssl.SSLSocket | SSLTransportType: ...
def ssl_wrap_socket(
sock: socket.socket,
keyfile: str | None = None,
certfile: str | None = None,
cert_reqs: int | None = None,
ca_certs: str | None = None,
server_hostname: str | None = None,
ssl_version: int | None = None,
ciphers: str | None = None,
ssl_context: ssl.SSLContext | None = None,
ca_cert_dir: str | None = None,
key_password: str | None = None,
ca_cert_data: None | str | bytes = None,
tls_in_tls: bool = False,
) -> ssl.SSLSocket | SSLTransportType:
"""
All arguments except for server_hostname, ssl_context, tls_in_tls, ca_cert_data and
ca_cert_dir have the same meaning as they do when using
:func:`ssl.create_default_context`, :meth:`ssl.SSLContext.load_cert_chain`,
:meth:`ssl.SSLContext.set_ciphers` and :meth:`ssl.SSLContext.wrap_socket`.
:param server_hostname:
When SNI is supported, the expected hostname of the certificate
:param ssl_context:
A pre-made :class:`SSLContext` object. If none is provided, one will
be created using :func:`create_urllib3_context`.
:param ciphers:
A string of ciphers we wish the client to support.
:param ca_cert_dir:
A directory containing CA certificates in multiple separate files, as
supported by OpenSSL's -CApath flag or the capath argument to
SSLContext.load_verify_locations().
:param key_password:
Optional password if the keyfile is encrypted.
:param ca_cert_data:
Optional string containing CA certificates in PEM format suitable for
passing as the cadata parameter to SSLContext.load_verify_locations()
:param tls_in_tls:
Use SSLTransport to wrap the existing socket.
"""
context = ssl_context
if context is None:
# Note: This branch of code and all the variables in it are only used in tests.
# We should consider deprecating and removing this code.
context = create_urllib3_context(ssl_version, cert_reqs, ciphers=ciphers)
if ca_certs or ca_cert_dir or ca_cert_data:
try:
context.load_verify_locations(ca_certs, ca_cert_dir, ca_cert_data)
except OSError as e:
raise SSLError(e) from e
elif ssl_context is None and hasattr(context, "load_default_certs"):
# try to load OS default certs; works well on Windows.
context.load_default_certs()
# Attempt to detect if we get the goofy behavior of the
# keyfile being encrypted and OpenSSL asking for the
# passphrase via the terminal and instead error out.
if keyfile and key_password is None and _is_key_file_encrypted(keyfile):
raise SSLError("Client private key is encrypted, password is required")
if certfile:
if key_password is None:
context.load_cert_chain(certfile, keyfile)
else:
context.load_cert_chain(certfile, keyfile, key_password)
context.set_alpn_protocols(ALPN_PROTOCOLS)
ssl_sock = _ssl_wrap_socket_impl(sock, context, tls_in_tls, server_hostname)
return ssl_sock
def is_ipaddress(hostname: str | bytes) -> bool:
"""Detects whether the hostname given is an IPv4 or IPv6 address.
Also detects IPv6 addresses with Zone IDs.
:param str hostname: Hostname to examine.
:return: True if the hostname is an IP address, False otherwise.
"""
if isinstance(hostname, bytes):
# IDN A-label bytes are ASCII compatible.
hostname = hostname.decode("ascii")
return bool(_IPV4_RE.match(hostname) or _BRACELESS_IPV6_ADDRZ_RE.match(hostname))
def _is_key_file_encrypted(key_file: str) -> bool:
"""Detects if a key file is encrypted or not."""
with open(key_file) as f:
for line in f:
# Look for Proc-Type: 4,ENCRYPTED
if "ENCRYPTED" in line:
return True
return False
def _ssl_wrap_socket_impl(
sock: socket.socket,
ssl_context: ssl.SSLContext,
tls_in_tls: bool,
server_hostname: str | None = None,
) -> ssl.SSLSocket | SSLTransportType:
if tls_in_tls:
if not SSLTransport:
# Import error, ssl is not available.
raise ProxySchemeUnsupported(
"TLS in TLS requires support for the 'ssl' module"
)
SSLTransport._validate_ssl_context_for_tls_in_tls(ssl_context)
return SSLTransport(sock, ssl_context, server_hostname)
return ssl_context.wrap_socket(sock, server_hostname=server_hostname)

159
venv/lib/python3.12/site-packages/urllib3/util/ssl_match_hostname.py Normal file
View File

@@ -0,0 +1,159 @@
"""The match_hostname() function from Python 3.5, essential when using SSL."""
# Note: This file is under the PSF license as the code comes from the python
# stdlib. http://docs.python.org/3/license.html
# It is modified to remove commonName support.
from __future__ import annotations
import ipaddress
import re
import typing
from ipaddress import IPv4Address, IPv6Address
if typing.TYPE_CHECKING:
from .ssl_ import _TYPE_PEER_CERT_RET_DICT
__version__ = "3.5.0.1"
class CertificateError(ValueError):
pass
def _dnsname_match(
dn: typing.Any, hostname: str, max_wildcards: int = 1
) -> typing.Match[str] | None | bool:
"""Matching according to RFC 6125, section 6.4.3
http://tools.ietf.org/html/rfc6125#section-6.4.3
"""
pats = []
if not dn:
return False
# Ported from python3-syntax:
# leftmost, *remainder = dn.split(r'.')
parts = dn.split(r".")
leftmost = parts[0]
remainder = parts[1:]
wildcards = leftmost.count("*")
if wildcards > max_wildcards:
# Issue #17980: avoid denials of service by refusing more
# than one wildcard per fragment. A survey of established
# policy among SSL implementations showed it to be a
# reasonable choice.
raise CertificateError(
"too many wildcards in certificate DNS name: " + repr(dn)
)
# speed up common case w/o wildcards
if not wildcards:
return bool(dn.lower() == hostname.lower())
# RFC 6125, section 6.4.3, subitem 1.
# The client SHOULD NOT attempt to match a presented identifier in which
# the wildcard character comprises a label other than the left-most label.
if leftmost == "*":
# When '*' is a fragment by itself, it matches a non-empty dotless
# fragment.
pats.append("[^.]+")
elif leftmost.startswith("xn--") or hostname.startswith("xn--"):
# RFC 6125, section 6.4.3, subitem 3.
# The client SHOULD NOT attempt to match a presented identifier
# where the wildcard character is embedded within an A-label or
# U-label of an internationalized domain name.
pats.append(re.escape(leftmost))
else:
# Otherwise, '*' matches any dotless string, e.g. www*
pats.append(re.escape(leftmost).replace(r"\*", "[^.]*"))
# add the remaining fragments, ignore any wildcards
for frag in remainder:
pats.append(re.escape(frag))
pat = re.compile(r"\A" + r"\.".join(pats) + r"\Z", re.IGNORECASE)
return pat.match(hostname)
def _ipaddress_match(ipname: str, host_ip: IPv4Address | IPv6Address) -> bool:
"""Exact matching of IP addresses.
RFC 9110 section 4.3.5: "A reference identity of IP-ID contains the decoded
bytes of the IP address. An IP version 4 address is 4 octets, and an IP
version 6 address is 16 octets. [...] A reference identity of type IP-ID
matches if the address is identical to an iPAddress value of the
subjectAltName extension of the certificate."
"""
# OpenSSL may add a trailing newline to a subjectAltName's IP address
# Divergence from upstream: ipaddress can't handle byte str
ip = ipaddress.ip_address(ipname.rstrip())
return bool(ip.packed == host_ip.packed)
def match_hostname(
cert: _TYPE_PEER_CERT_RET_DICT | None,
hostname: str,
hostname_checks_common_name: bool = False,
) -> None:
"""Verify that *cert* (in decoded format as returned by
SSLSocket.getpeercert()) matches the *hostname*. RFC 2818 and RFC 6125
rules are followed, but IP addresses are not accepted for *hostname*.
CertificateError is raised on failure. On success, the function
returns nothing.
"""
if not cert:
raise ValueError(
"empty or no certificate, match_hostname needs a "
"SSL socket or SSL context with either "
"CERT_OPTIONAL or CERT_REQUIRED"
)
try:
# Divergence from upstream: ipaddress can't handle byte str
#
# The ipaddress module shipped with Python < 3.9 does not support
# scoped IPv6 addresses so we unconditionally strip the Zone IDs for
# now. Once we drop support for Python 3.9 we can remove this branch.
if "%" in hostname:
host_ip = ipaddress.ip_address(hostname[: hostname.rfind("%")])
else:
host_ip = ipaddress.ip_address(hostname)
except ValueError:
# Not an IP address (common case)
host_ip = None
dnsnames = []
san: tuple[tuple[str, str], ...] = cert.get("subjectAltName", ())
key: str
value: str
for key, value in san:
if key == "DNS":
if host_ip is None and _dnsname_match(value, hostname):
return
dnsnames.append(value)
elif key == "IP Address":
if host_ip is not None and _ipaddress_match(value, host_ip):
return
dnsnames.append(value)
# We only check 'commonName' if it's enabled and we're not verifying
# an IP address. IP addresses aren't valid within 'commonName'.
if hostname_checks_common_name and host_ip is None and not dnsnames:
for sub in cert.get("subject", ()):
for key, value in sub:
if key == "commonName":
if _dnsname_match(value, hostname):
return
dnsnames.append(value) # Defensive: for Python < 3.9.3
if len(dnsnames) > 1:
raise CertificateError(
"hostname %r "
"doesn't match either of %s" % (hostname, ", ".join(map(repr, dnsnames)))
)
elif len(dnsnames) == 1:
raise CertificateError(f"hostname {hostname!r} doesn't match {dnsnames[0]!r}")
else:
raise CertificateError("no appropriate subjectAltName fields were found")

271
venv/lib/python3.12/site-packages/urllib3/util/ssltransport.py Normal file
View File

@@ -0,0 +1,271 @@
from __future__ import annotations
import io
import socket
import ssl
import typing
from ..exceptions import ProxySchemeUnsupported
if typing.TYPE_CHECKING:
from typing_extensions import Self
from .ssl_ import _TYPE_PEER_CERT_RET, _TYPE_PEER_CERT_RET_DICT
_WriteBuffer = typing.Union[bytearray, memoryview]
_ReturnValue = typing.TypeVar("_ReturnValue")
SSL_BLOCKSIZE = 16384
class SSLTransport:
"""
The SSLTransport wraps an existing socket and establishes an SSL connection.
Contrary to Python's implementation of SSLSocket, it allows you to chain
multiple TLS connections together. It's particularly useful if you need to
implement TLS within TLS.
The class supports most of the socket API operations.
"""
@staticmethod
def _validate_ssl_context_for_tls_in_tls(ssl_context: ssl.SSLContext) -> None:
"""
Raises a ProxySchemeUnsupported if the provided ssl_context can't be used
for TLS in TLS.
The only requirement is that the ssl_context provides the 'wrap_bio'
methods.
"""
if not hasattr(ssl_context, "wrap_bio"):
raise ProxySchemeUnsupported(
"TLS in TLS requires SSLContext.wrap_bio() which isn't "
"available on non-native SSLContext"
)
def __init__(
self,
socket: socket.socket,
ssl_context: ssl.SSLContext,
server_hostname: str | None = None,
suppress_ragged_eofs: bool = True,
) -> None:
"""
Create an SSLTransport around socket using the provided ssl_context.
"""
self.incoming = ssl.MemoryBIO()
self.outgoing = ssl.MemoryBIO()
self.suppress_ragged_eofs = suppress_ragged_eofs
self.socket = socket
self.sslobj = ssl_context.wrap_bio(
self.incoming, self.outgoing, server_hostname=server_hostname
)
# Perform initial handshake.
self._ssl_io_loop(self.sslobj.do_handshake)
def __enter__(self) -> Self:
return self
def __exit__(self, *_: typing.Any) -> None:
self.close()
def fileno(self) -> int:
return self.socket.fileno()
def read(self, len: int = 1024, buffer: typing.Any | None = None) -> int | bytes:
return self._wrap_ssl_read(len, buffer)
def recv(self, buflen: int = 1024, flags: int = 0) -> int | bytes:
if flags != 0:
raise ValueError("non-zero flags not allowed in calls to recv")
return self._wrap_ssl_read(buflen)
def recv_into(
self,
buffer: _WriteBuffer,
nbytes: int | None = None,
flags: int = 0,
) -> None | int | bytes:
if flags != 0:
raise ValueError("non-zero flags not allowed in calls to recv_into")
if nbytes is None:
nbytes = len(buffer)
return self.read(nbytes, buffer)
def sendall(self, data: bytes, flags: int = 0) -> None:
if flags != 0:
raise ValueError("non-zero flags not allowed in calls to sendall")
count = 0
with memoryview(data) as view, view.cast("B") as byte_view:
amount = len(byte_view)
while count < amount:
v = self.send(byte_view[count:])
count += v
def send(self, data: bytes, flags: int = 0) -> int:
if flags != 0:
raise ValueError("non-zero flags not allowed in calls to send")
return self._ssl_io_loop(self.sslobj.write, data)
def makefile(
self,
mode: str,
buffering: int | None = None,
*,
encoding: str | None = None,
errors: str | None = None,
newline: str | None = None,
) -> typing.BinaryIO | typing.TextIO | socket.SocketIO:
"""
Python's httpclient uses makefile and buffered io when reading HTTP
messages and we need to support it.
This is unfortunately a copy and paste of socket.py makefile with small
changes to point to the socket directly.
"""
if not set(mode) <= {"r", "w", "b"}:
raise ValueError(f"invalid mode {mode!r} (only r, w, b allowed)")
writing = "w" in mode
reading = "r" in mode or not writing
assert reading or writing
binary = "b" in mode
rawmode = ""
if reading:
rawmode += "r"
if writing:
rawmode += "w"
raw = socket.SocketIO(self, rawmode) # type: ignore[arg-type]
self.socket._io_refs += 1 # type: ignore[attr-defined]
if buffering is None:
buffering = -1
if buffering < 0:
buffering = io.DEFAULT_BUFFER_SIZE
if buffering == 0:
if not binary:
raise ValueError("unbuffered streams must be binary")
return raw
buffer: typing.BinaryIO
if reading and writing:
buffer = io.BufferedRWPair(raw, raw, buffering) # type: ignore[assignment]
elif reading:
buffer = io.BufferedReader(raw, buffering)
else:
assert writing
buffer = io.BufferedWriter(raw, buffering)
if binary:
return buffer
text = io.TextIOWrapper(buffer, encoding, errors, newline)
text.mode = mode # type: ignore[misc]
return text
def unwrap(self) -> None:
self._ssl_io_loop(self.sslobj.unwrap)
def close(self) -> None:
self.socket.close()
@typing.overload
def getpeercert(
self, binary_form: typing.Literal[False] = ...
) -> _TYPE_PEER_CERT_RET_DICT | None: ...
@typing.overload
def getpeercert(self, binary_form: typing.Literal[True]) -> bytes | None: ...
def getpeercert(self, binary_form: bool = False) -> _TYPE_PEER_CERT_RET:
return self.sslobj.getpeercert(binary_form) # type: ignore[return-value]
def version(self) -> str | None:
return self.sslobj.version()
def cipher(self) -> tuple[str, str, int] | None:
return self.sslobj.cipher()
def selected_alpn_protocol(self) -> str | None:
return self.sslobj.selected_alpn_protocol()
def shared_ciphers(self) -> list[tuple[str, str, int]] | None:
return self.sslobj.shared_ciphers()
def compression(self) -> str | None:
return self.sslobj.compression()
def settimeout(self, value: float | None) -> None:
self.socket.settimeout(value)
def gettimeout(self) -> float | None:
return self.socket.gettimeout()
def _decref_socketios(self) -> None:
self.socket._decref_socketios() # type: ignore[attr-defined]
def _wrap_ssl_read(self, len: int, buffer: bytearray | None = None) -> int | bytes:
try:
return self._ssl_io_loop(self.sslobj.read, len, buffer)
except ssl.SSLError as e:
if e.errno == ssl.SSL_ERROR_EOF and self.suppress_ragged_eofs:
return 0 # eof, return 0.
else:
raise
# func is sslobj.do_handshake or sslobj.unwrap
@typing.overload
def _ssl_io_loop(self, func: typing.Callable[[], None]) -> None: ...
# func is sslobj.write, arg1 is data
@typing.overload
def _ssl_io_loop(self, func: typing.Callable[[bytes], int], arg1: bytes) -> int: ...
# func is sslobj.read, arg1 is len, arg2 is buffer
@typing.overload
def _ssl_io_loop(
self,
func: typing.Callable[[int, bytearray | None], bytes],
arg1: int,
arg2: bytearray | None,
) -> bytes: ...
def _ssl_io_loop(
self,
func: typing.Callable[..., _ReturnValue],
arg1: None | bytes | int = None,
arg2: bytearray | None = None,
) -> _ReturnValue:
"""Performs an I/O loop between incoming/outgoing and the socket."""
should_loop = True
ret = None
while should_loop:
errno = None
try:
if arg1 is None and arg2 is None:
ret = func()
elif arg2 is None:
ret = func(arg1)
else:
ret = func(arg1, arg2)
except ssl.SSLError as e:
if e.errno not in (ssl.SSL_ERROR_WANT_READ, ssl.SSL_ERROR_WANT_WRITE):
# WANT_READ, and WANT_WRITE are expected, others are not.
raise e
errno = e.errno
buf = self.outgoing.read()
self.socket.sendall(buf)
if errno is None:
should_loop = False
elif errno == ssl.SSL_ERROR_WANT_READ:
buf = self.socket.recv(SSL_BLOCKSIZE)
if buf:
self.incoming.write(buf)
else:
self.incoming.write_eof()
return typing.cast(_ReturnValue, ret)

275
venv/lib/python3.12/site-packages/urllib3/util/timeout.py Normal file
View File

@@ -0,0 +1,275 @@
from __future__ import annotations
import time
import typing
from enum import Enum
from socket import getdefaulttimeout
from ..exceptions import TimeoutStateError
if typing.TYPE_CHECKING:
from typing import Final
class _TYPE_DEFAULT(Enum):
# This value should never be passed to socket.settimeout() so for safety we use a -1.
# socket.settimout() raises a ValueError for negative values.
token = -1
_DEFAULT_TIMEOUT: Final[_TYPE_DEFAULT] = _TYPE_DEFAULT.token
_TYPE_TIMEOUT = typing.Optional[typing.Union[float, _TYPE_DEFAULT]]
class Timeout:
"""Timeout configuration.
Timeouts can be defined as a default for a pool:
.. code-block:: python
import urllib3
timeout = urllib3.util.Timeout(connect=2.0, read=7.0)
http = urllib3.PoolManager(timeout=timeout)
resp = http.request("GET", "https://example.com/")
print(resp.status)
Or per-request (which overrides the default for the pool):
.. code-block:: python
response = http.request("GET", "https://example.com/", timeout=Timeout(10))
Timeouts can be disabled by setting all the parameters to ``None``:
.. code-block:: python
no_timeout = Timeout(connect=None, read=None)
response = http.request("GET", "https://example.com/", timeout=no_timeout)
:param total:
This combines the connect and read timeouts into one; the read timeout
will be set to the time leftover from the connect attempt. In the
event that both a connect timeout and a total are specified, or a read
timeout and a total are specified, the shorter timeout will be applied.
Defaults to None.
:type total: int, float, or None
:param connect:
The maximum amount of time (in seconds) to wait for a connection
attempt to a server to succeed. Omitting the parameter will default the
connect timeout to the system default, probably `the global default
timeout in socket.py
<http://hg.python.org/cpython/file/603b4d593758/Lib/socket.py#l535>`_.
None will set an infinite timeout for connection attempts.
:type connect: int, float, or None
:param read:
The maximum amount of time (in seconds) to wait between consecutive
read operations for a response from the server. Omitting the parameter
will default the read timeout to the system default, probably `the
global default timeout in socket.py
<http://hg.python.org/cpython/file/603b4d593758/Lib/socket.py#l535>`_.
None will set an infinite timeout.
:type read: int, float, or None
.. note::
Many factors can affect the total amount of time for urllib3 to return
an HTTP response.
For example, Python's DNS resolver does not obey the timeout specified
on the socket. Other factors that can affect total request time include
high CPU load, high swap, the program running at a low priority level,
or other behaviors.
In addition, the read and total timeouts only measure the time between
read operations on the socket connecting the client and the server,
not the total amount of time for the request to return a complete
response. For most requests, the timeout is raised because the server
has not sent the first byte in the specified time. This is not always
the case; if a server streams one byte every fifteen seconds, a timeout
of 20 seconds will not trigger, even though the request will take
several minutes to complete.
"""
#: A sentinel object representing the default timeout value
DEFAULT_TIMEOUT: _TYPE_TIMEOUT = _DEFAULT_TIMEOUT
def __init__(
self,
total: _TYPE_TIMEOUT = None,
connect: _TYPE_TIMEOUT = _DEFAULT_TIMEOUT,
read: _TYPE_TIMEOUT = _DEFAULT_TIMEOUT,
) -> None:
self._connect = self._validate_timeout(connect, "connect")
self._read = self._validate_timeout(read, "read")
self.total = self._validate_timeout(total, "total")
self._start_connect: float | None = None
def __repr__(self) -> str:
return f"{type(self).__name__}(connect={self._connect!r}, read={self._read!r}, total={self.total!r})"
# __str__ provided for backwards compatibility
__str__ = __repr__
@staticmethod
def resolve_default_timeout(timeout: _TYPE_TIMEOUT) -> float | None:
return getdefaulttimeout() if timeout is _DEFAULT_TIMEOUT else timeout
@classmethod
def _validate_timeout(cls, value: _TYPE_TIMEOUT, name: str) -> _TYPE_TIMEOUT:
"""Check that a timeout attribute is valid.
:param value: The timeout value to validate
:param name: The name of the timeout attribute to validate. This is
used to specify in error messages.
:return: The validated and casted version of the given value.
:raises ValueError: If it is a numeric value less than or equal to
zero, or the type is not an integer, float, or None.
"""
if value is None or value is _DEFAULT_TIMEOUT:
return value
if isinstance(value, bool):
raise ValueError(
"Timeout cannot be a boolean value. It must "
"be an int, float or None."
)
try:
float(value)
except (TypeError, ValueError):
raise ValueError(
"Timeout value %s was %s, but it must be an "
"int, float or None." % (name, value)
) from None
try:
if value <= 0:
raise ValueError(
"Attempted to set %s timeout to %s, but the "
"timeout cannot be set to a value less "
"than or equal to 0." % (name, value)
)
except TypeError:
raise ValueError(
"Timeout value %s was %s, but it must be an "
"int, float or None." % (name, value)
) from None
return value
@classmethod
def from_float(cls, timeout: _TYPE_TIMEOUT) -> Timeout:
"""Create a new Timeout from a legacy timeout value.
The timeout value used by httplib.py sets the same timeout on the
connect(), and recv() socket requests. This creates a :class:`Timeout`
object that sets the individual timeouts to the ``timeout`` value
passed to this function.
:param timeout: The legacy timeout value.
:type timeout: integer, float, :attr:`urllib3.util.Timeout.DEFAULT_TIMEOUT`, or None
:return: Timeout object
:rtype: :class:`Timeout`
"""
return Timeout(read=timeout, connect=timeout)
def clone(self) -> Timeout:
"""Create a copy of the timeout object
Timeout properties are stored per-pool but each request needs a fresh
Timeout object to ensure each one has its own start/stop configured.
:return: a copy of the timeout object
:rtype: :class:`Timeout`
"""
# We can't use copy.deepcopy because that will also create a new object
# for _GLOBAL_DEFAULT_TIMEOUT, which socket.py uses as a sentinel to
# detect the user default.
return Timeout(connect=self._connect, read=self._read, total=self.total)
def start_connect(self) -> float:
"""Start the timeout clock, used during a connect() attempt
:raises urllib3.exceptions.TimeoutStateError: if you attempt
to start a timer that has been started already.
"""
if self._start_connect is not None:
raise TimeoutStateError("Timeout timer has already been started.")
self._start_connect = time.monotonic()
return self._start_connect
def get_connect_duration(self) -> float:
"""Gets the time elapsed since the call to :meth:`start_connect`.
:return: Elapsed time in seconds.
:rtype: float
:raises urllib3.exceptions.TimeoutStateError: if you attempt
to get duration for a timer that hasn't been started.
"""
if self._start_connect is None:
raise TimeoutStateError(
"Can't get connect duration for timer that has not started."
)
return time.monotonic() - self._start_connect
@property
def connect_timeout(self) -> _TYPE_TIMEOUT:
"""Get the value to use when setting a connection timeout.
This will be a positive float or integer, the value None
(never timeout), or the default system timeout.
:return: Connect timeout.
:rtype: int, float, :attr:`Timeout.DEFAULT_TIMEOUT` or None
"""
if self.total is None:
return self._connect
if self._connect is None or self._connect is _DEFAULT_TIMEOUT:
return self.total
return min(self._connect, self.total) # type: ignore[type-var]
@property
def read_timeout(self) -> float | None:
"""Get the value for the read timeout.
This assumes some time has elapsed in the connection timeout and
computes the read timeout appropriately.
If self.total is set, the read timeout is dependent on the amount of
time taken by the connect timeout. If the connection time has not been
established, a :exc:`~urllib3.exceptions.TimeoutStateError` will be
raised.
:return: Value to use for the read timeout.
:rtype: int, float or None
:raises urllib3.exceptions.TimeoutStateError: If :meth:`start_connect`
has not yet been called on this object.
"""
if (
self.total is not None
and self.total is not _DEFAULT_TIMEOUT
and self._read is not None
and self._read is not _DEFAULT_TIMEOUT
):
# In case the connect timeout has not yet been established.
if self._start_connect is None:
return self._read
return max(0, min(self.total - self.get_connect_duration(), self._read))
elif self.total is not None and self.total is not _DEFAULT_TIMEOUT:
return max(0, self.total - self.get_connect_duration())
else:
return self.resolve_default_timeout(self._read)

469
venv/lib/python3.12/site-packages/urllib3/util/url.py Normal file
View File

@@ -0,0 +1,469 @@
from __future__ import annotations
import re
import typing
from ..exceptions import LocationParseError
from .util import to_str
# We only want to normalize urls with an HTTP(S) scheme.
# urllib3 infers URLs without a scheme (None) to be http.
_NORMALIZABLE_SCHEMES = ("http", "https", None)
# Almost all of these patterns were derived from the
# 'rfc3986' module: https://github.com/python-hyper/rfc3986
_PERCENT_RE = re.compile(r"%[a-fA-F0-9]{2}")
_SCHEME_RE = re.compile(r"^(?:[a-zA-Z][a-zA-Z0-9+-]*:|/)")
_URI_RE = re.compile(
r"^(?:([a-zA-Z][a-zA-Z0-9+.-]*):)?"
r"(?://([^\\/?#]*))?"
r"([^?#]*)"
r"(?:\?([^#]*))?"
r"(?:#(.*))?$",
re.UNICODE | re.DOTALL,
)
_IPV4_PAT = r"(?:[0-9]{1,3}\.){3}[0-9]{1,3}"
_HEX_PAT = "[0-9A-Fa-f]{1,4}"
_LS32_PAT = "(?:{hex}:{hex}|{ipv4})".format(hex=_HEX_PAT, ipv4=_IPV4_PAT)
_subs = {"hex": _HEX_PAT, "ls32": _LS32_PAT}
_variations = [
# 6( h16 ":" ) ls32
"(?:%(hex)s:){6}%(ls32)s",
# "::" 5( h16 ":" ) ls32
"::(?:%(hex)s:){5}%(ls32)s",
# [ h16 ] "::" 4( h16 ":" ) ls32
"(?:%(hex)s)?::(?:%(hex)s:){4}%(ls32)s",
# [ *1( h16 ":" ) h16 ] "::" 3( h16 ":" ) ls32
"(?:(?:%(hex)s:)?%(hex)s)?::(?:%(hex)s:){3}%(ls32)s",
# [ *2( h16 ":" ) h16 ] "::" 2( h16 ":" ) ls32
"(?:(?:%(hex)s:){0,2}%(hex)s)?::(?:%(hex)s:){2}%(ls32)s",
# [ *3( h16 ":" ) h16 ] "::" h16 ":" ls32
"(?:(?:%(hex)s:){0,3}%(hex)s)?::%(hex)s:%(ls32)s",
# [ *4( h16 ":" ) h16 ] "::" ls32
"(?:(?:%(hex)s:){0,4}%(hex)s)?::%(ls32)s",
# [ *5( h16 ":" ) h16 ] "::" h16
"(?:(?:%(hex)s:){0,5}%(hex)s)?::%(hex)s",
# [ *6( h16 ":" ) h16 ] "::"
"(?:(?:%(hex)s:){0,6}%(hex)s)?::",
]
_UNRESERVED_PAT = r"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789._\-~"
_IPV6_PAT = "(?:" + "|".join([x % _subs for x in _variations]) + ")"
_ZONE_ID_PAT = "(?:%25|%)(?:[" + _UNRESERVED_PAT + "]|%[a-fA-F0-9]{2})+"
_IPV6_ADDRZ_PAT = r"\[" + _IPV6_PAT + r"(?:" + _ZONE_ID_PAT + r")?\]"
_REG_NAME_PAT = r"(?:[^\[\]%:/?#]|%[a-fA-F0-9]{2})*"
_TARGET_RE = re.compile(r"^(/[^?#]*)(?:\?([^#]*))?(?:#.*)?$")
_IPV4_RE = re.compile("^" + _IPV4_PAT + "$")
_IPV6_RE = re.compile("^" + _IPV6_PAT + "$")
_IPV6_ADDRZ_RE = re.compile("^" + _IPV6_ADDRZ_PAT + "$")
_BRACELESS_IPV6_ADDRZ_RE = re.compile("^" + _IPV6_ADDRZ_PAT[2:-2] + "$")
_ZONE_ID_RE = re.compile("(" + _ZONE_ID_PAT + r")\]$")
_HOST_PORT_PAT = ("^(%s|%s|%s)(?::0*?(|0|[1-9][0-9]{0,4}))?$") % (
_REG_NAME_PAT,
_IPV4_PAT,
_IPV6_ADDRZ_PAT,
)
_HOST_PORT_RE = re.compile(_HOST_PORT_PAT, re.UNICODE | re.DOTALL)
_UNRESERVED_CHARS = set(
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789._-~"
)
_SUB_DELIM_CHARS = set("!$&'()*+,;=")
_USERINFO_CHARS = _UNRESERVED_CHARS | _SUB_DELIM_CHARS | {":"}
_PATH_CHARS = _USERINFO_CHARS | {"@", "/"}
_QUERY_CHARS = _FRAGMENT_CHARS = _PATH_CHARS | {"?"}
class Url(
typing.NamedTuple(
"Url",
[
("scheme", typing.Optional[str]),
("auth", typing.Optional[str]),
("host", typing.Optional[str]),
("port", typing.Optional[int]),
("path", typing.Optional[str]),
("query", typing.Optional[str]),
("fragment", typing.Optional[str]),
],
)
):
"""
Data structure for representing an HTTP URL. Used as a return value for
:func:`parse_url`. Both the scheme and host are normalized as they are
both case-insensitive according to RFC 3986.
"""
def __new__( # type: ignore[no-untyped-def]
cls,
scheme: str | None = None,
auth: str | None = None,
host: str | None = None,
port: int | None = None,
path: str | None = None,
query: str | None = None,
fragment: str | None = None,
):
if path and not path.startswith("/"):
path = "/" + path
if scheme is not None:
scheme = scheme.lower()
return super().__new__(cls, scheme, auth, host, port, path, query, fragment)
@property
def hostname(self) -> str | None:
"""For backwards-compatibility with urlparse. We're nice like that."""
return self.host
@property
def request_uri(self) -> str:
"""Absolute path including the query string."""
uri = self.path or "/"
if self.query is not None:
uri += "?" + self.query
return uri
@property
def authority(self) -> str | None:
"""
Authority component as defined in RFC 3986 3.2.
This includes userinfo (auth), host and port.
i.e.
userinfo@host:port
"""
userinfo = self.auth
netloc = self.netloc
if netloc is None or userinfo is None:
return netloc
else:
return f"{userinfo}@{netloc}"
@property
def netloc(self) -> str | None:
"""
Network location including host and port.
If you need the equivalent of urllib.parse's ``netloc``,
use the ``authority`` property instead.
"""
if self.host is None:
return None
if self.port:
return f"{self.host}:{self.port}"
return self.host
@property
def url(self) -> str:
"""
Convert self into a url
This function should more or less round-trip with :func:`.parse_url`. The
returned url may not be exactly the same as the url inputted to
:func:`.parse_url`, but it should be equivalent by the RFC (e.g., urls
with a blank port will have : removed).
Example:
.. code-block:: python
import urllib3
U = urllib3.util.parse_url("https://google.com/mail/")
print(U.url)
# "https://google.com/mail/"
print( urllib3.util.Url("https", "username:password",
"host.com", 80, "/path", "query", "fragment"
).url
)
# "https://username:password@host.com:80/path?query#fragment"
"""
scheme, auth, host, port, path, query, fragment = self
url = ""
# We use "is not None" we want things to happen with empty strings (or 0 port)
if scheme is not None:
url += scheme + "://"
if auth is not None:
url += auth + "@"
if host is not None:
url += host
if port is not None:
url += ":" + str(port)
if path is not None:
url += path
if query is not None:
url += "?" + query
if fragment is not None:
url += "#" + fragment
return url
def __str__(self) -> str:
return self.url
@typing.overload
def _encode_invalid_chars(
component: str, allowed_chars: typing.Container[str]
) -> str: # Abstract
...
@typing.overload
def _encode_invalid_chars(
component: None, allowed_chars: typing.Container[str]
) -> None: # Abstract
...
def _encode_invalid_chars(
component: str | None, allowed_chars: typing.Container[str]
) -> str | None:
"""Percent-encodes a URI component without reapplying
onto an already percent-encoded component.
"""
if component is None:
return component
component = to_str(component)
# Normalize existing percent-encoded bytes.
# Try to see if the component we're encoding is already percent-encoded
# so we can skip all '%' characters but still encode all others.
component, percent_encodings = _PERCENT_RE.subn(
lambda match: match.group(0).upper(), component
)
uri_bytes = component.encode("utf-8", "surrogatepass")
is_percent_encoded = percent_encodings == uri_bytes.count(b"%")
encoded_component = bytearray()
for i in range(0, len(uri_bytes)):
# Will return a single character bytestring
byte = uri_bytes[i : i + 1]
byte_ord = ord(byte)
if (is_percent_encoded and byte == b"%") or (
byte_ord < 128 and byte.decode() in allowed_chars
):
encoded_component += byte
continue
encoded_component.extend(b"%" + (hex(byte_ord)[2:].encode().zfill(2).upper()))
return encoded_component.decode()
def _remove_path_dot_segments(path: str) -> str:
# See http://tools.ietf.org/html/rfc3986#section-5.2.4 for pseudo-code
segments = path.split("/") # Turn the path into a list of segments
output = [] # Initialize the variable to use to store output
for segment in segments:
# '.' is the current directory, so ignore it, it is superfluous
if segment == ".":
continue
# Anything other than '..', should be appended to the output
if segment != "..":
output.append(segment)
# In this case segment == '..', if we can, we should pop the last
# element
elif output:
output.pop()
# If the path starts with '/' and the output is empty or the first string
# is non-empty
if path.startswith("/") and (not output or output[0]):
output.insert(0, "")
# If the path starts with '/.' or '/..' ensure we add one more empty
# string to add a trailing '/'
if path.endswith(("/.", "/..")):
output.append("")
return "/".join(output)
@typing.overload
def _normalize_host(host: None, scheme: str | None) -> None: ...
@typing.overload
def _normalize_host(host: str, scheme: str | None) -> str: ...
def _normalize_host(host: str | None, scheme: str | None) -> str | None:
if host:
if scheme in _NORMALIZABLE_SCHEMES:
is_ipv6 = _IPV6_ADDRZ_RE.match(host)
if is_ipv6:
# IPv6 hosts of the form 'a::b%zone' are encoded in a URL as
# such per RFC 6874: 'a::b%25zone'. Unquote the ZoneID
# separator as necessary to return a valid RFC 4007 scoped IP.
match = _ZONE_ID_RE.search(host)
if match:
start, end = match.span(1)
zone_id = host[start:end]
if zone_id.startswith("%25") and zone_id != "%25":
zone_id = zone_id[3:]
else:
zone_id = zone_id[1:]
zone_id = _encode_invalid_chars(zone_id, _UNRESERVED_CHARS)
return f"{host[:start].lower()}%{zone_id}{host[end:]}"
else:
return host.lower()
elif not _IPV4_RE.match(host):
return to_str(
b".".join([_idna_encode(label) for label in host.split(".")]),
"ascii",
)
return host
def _idna_encode(name: str) -> bytes:
if not name.isascii():
try:
import idna
except ImportError:
raise LocationParseError(
"Unable to parse URL without the 'idna' module"
) from None
try:
return idna.encode(name.lower(), strict=True, std3_rules=True)
except idna.IDNAError:
raise LocationParseError(
f"Name '{name}' is not a valid IDNA label"
) from None
return name.lower().encode("ascii")
def _encode_target(target: str) -> str:
"""Percent-encodes a request target so that there are no invalid characters
Pre-condition for this function is that 'target' must start with '/'.
If that is the case then _TARGET_RE will always produce a match.
"""
match = _TARGET_RE.match(target)
if not match: # Defensive:
raise LocationParseError(f"{target!r} is not a valid request URI")
path, query = match.groups()
encoded_target = _encode_invalid_chars(path, _PATH_CHARS)
if query is not None:
query = _encode_invalid_chars(query, _QUERY_CHARS)
encoded_target += "?" + query
return encoded_target
def parse_url(url: str) -> Url:
"""
Given a url, return a parsed :class:`.Url` namedtuple. Best-effort is
performed to parse incomplete urls. Fields not provided will be None.
This parser is RFC 3986 and RFC 6874 compliant.
The parser logic and helper functions are based heavily on
work done in the ``rfc3986`` module.
:param str url: URL to parse into a :class:`.Url` namedtuple.
Partly backwards-compatible with :mod:`urllib.parse`.
Example:
.. code-block:: python
import urllib3
print( urllib3.util.parse_url('http://google.com/mail/'))
# Url(scheme='http', host='google.com', port=None, path='/mail/', ...)
print( urllib3.util.parse_url('google.com:80'))
# Url(scheme=None, host='google.com', port=80, path=None, ...)
print( urllib3.util.parse_url('/foo?bar'))
# Url(scheme=None, host=None, port=None, path='/foo', query='bar', ...)
"""
if not url:
# Empty
return Url()
source_url = url
if not _SCHEME_RE.search(url):
url = "//" + url
scheme: str | None
authority: str | None
auth: str | None
host: str | None
port: str | None
port_int: int | None
path: str | None
query: str | None
fragment: str | None
try:
scheme, authority, path, query, fragment = _URI_RE.match(url).groups() # type: ignore[union-attr]
normalize_uri = scheme is None or scheme.lower() in _NORMALIZABLE_SCHEMES
if scheme:
scheme = scheme.lower()
if authority:
auth, _, host_port = authority.rpartition("@")
auth = auth or None
host, port = _HOST_PORT_RE.match(host_port).groups() # type: ignore[union-attr]
if auth and normalize_uri:
auth = _encode_invalid_chars(auth, _USERINFO_CHARS)
if port == "":
port = None
else:
auth, host, port = None, None, None
if port is not None:
port_int = int(port)
if not (0 <= port_int <= 65535):
raise LocationParseError(url)
else:
port_int = None
host = _normalize_host(host, scheme)
if normalize_uri and path:
path = _remove_path_dot_segments(path)
path = _encode_invalid_chars(path, _PATH_CHARS)
if normalize_uri and query:
query = _encode_invalid_chars(query, _QUERY_CHARS)
if normalize_uri and fragment:
fragment = _encode_invalid_chars(fragment, _FRAGMENT_CHARS)
except (ValueError, AttributeError) as e:
raise LocationParseError(source_url) from e
# For the sake of backwards compatibility we put empty
# string values for path if there are any defined values
# beyond the path in the URL.
# TODO: Remove this when we break backwards compatibility.
if not path:
if query is not None or fragment is not None:
path = ""
else:
path = None
return Url(
scheme=scheme,
auth=auth,
host=host,
port=port_int,
path=path,
query=query,
fragment=fragment,
)

42
venv/lib/python3.12/site-packages/urllib3/util/util.py Normal file
View File

@@ -0,0 +1,42 @@
from __future__ import annotations
import typing
from types import TracebackType
def to_bytes(
x: str | bytes, encoding: str | None = None, errors: str | None = None
) -> bytes:
if isinstance(x, bytes):
return x
elif not isinstance(x, str):
raise TypeError(f"not expecting type {type(x).__name__}")
if encoding or errors:
return x.encode(encoding or "utf-8", errors=errors or "strict")
return x.encode()
def to_str(
x: str | bytes, encoding: str | None = None, errors: str | None = None
) -> str:
if isinstance(x, str):
return x
elif not isinstance(x, bytes):
raise TypeError(f"not expecting type {type(x).__name__}")
if encoding or errors:
return x.decode(encoding or "utf-8", errors=errors or "strict")
return x.decode()
def reraise(
tp: type[BaseException] | None,
value: BaseException,
tb: TracebackType | None = None,
) -> typing.NoReturn:
try:
if value.__traceback__ is not tb:
raise value.with_traceback(tb)
raise value
finally:
value = None # type: ignore[assignment]
tb = None

124
venv/lib/python3.12/site-packages/urllib3/util/wait.py Normal file
View File

@@ -0,0 +1,124 @@
from __future__ import annotations
import select
import socket
from functools import partial
__all__ = ["wait_for_read", "wait_for_write"]
# How should we wait on sockets?
#
# There are two types of APIs you can use for waiting on sockets: the fancy
# modern stateful APIs like epoll/kqueue, and the older stateless APIs like
# select/poll. The stateful APIs are more efficient when you have a lots of
# sockets to keep track of, because you can set them up once and then use them
# lots of times. But we only ever want to wait on a single socket at a time
# and don't want to keep track of state, so the stateless APIs are actually
# more efficient. So we want to use select() or poll().
#
# Now, how do we choose between select() and poll()? On traditional Unixes,
# select() has a strange calling convention that makes it slow, or fail
# altogether, for high-numbered file descriptors. The point of poll() is to fix
# that, so on Unixes, we prefer poll().
#
# On Windows, there is no poll() (or at least Python doesn't provide a wrapper
# for it), but that's OK, because on Windows, select() doesn't have this
# strange calling convention; plain select() works fine.
#
# So: on Windows we use select(), and everywhere else we use poll(). We also
# fall back to select() in case poll() is somehow broken or missing.
def select_wait_for_socket(
sock: socket.socket,
read: bool = False,
write: bool = False,
timeout: float | None = None,
) -> bool:
if not read and not write:
raise RuntimeError("must specify at least one of read=True, write=True")
rcheck = []
wcheck = []
if read:
rcheck.append(sock)
if write:
wcheck.append(sock)
# When doing a non-blocking connect, most systems signal success by
# marking the socket writable. Windows, though, signals success by marked
# it as "exceptional". We paper over the difference by checking the write
# sockets for both conditions. (The stdlib selectors module does the same
# thing.)
fn = partial(select.select, rcheck, wcheck, wcheck)
rready, wready, xready = fn(timeout)
return bool(rready or wready or xready)
def poll_wait_for_socket(
sock: socket.socket,
read: bool = False,
write: bool = False,
timeout: float | None = None,
) -> bool:
if not read and not write:
raise RuntimeError("must specify at least one of read=True, write=True")
mask = 0
if read:
mask |= select.POLLIN
if write:
mask |= select.POLLOUT
poll_obj = select.poll()
poll_obj.register(sock, mask)
# For some reason, poll() takes timeout in milliseconds
def do_poll(t: float | None) -> list[tuple[int, int]]:
if t is not None:
t *= 1000
return poll_obj.poll(t)
return bool(do_poll(timeout))
def _have_working_poll() -> bool:
# Apparently some systems have a select.poll that fails as soon as you try
# to use it, either due to strange configuration or broken monkeypatching
# from libraries like eventlet/greenlet.
try:
poll_obj = select.poll()
poll_obj.poll(0)
except (AttributeError, OSError):
return False
else:
return True
def wait_for_socket(
sock: socket.socket,
read: bool = False,
write: bool = False,
timeout: float | None = None,
) -> bool:
# We delay choosing which implementation to use until the first time we're
# called. We could do it at import time, but then we might make the wrong
# decision if someone goes wild with monkeypatching select.poll after
# we're imported.
global wait_for_socket
if _have_working_poll():
wait_for_socket = poll_wait_for_socket
elif hasattr(select, "select"):
wait_for_socket = select_wait_for_socket
return wait_for_socket(sock, read, write, timeout)
def wait_for_read(sock: socket.socket, timeout: float | None = None) -> bool:
"""Waits for reading to be available on a given socket.
Returns True if the socket is readable, or False if the timeout expired.
"""
return wait_for_socket(sock, read=True, timeout=timeout)
def wait_for_write(sock: socket.socket, timeout: float | None = None) -> bool:
"""Waits for writing to be available on a given socket.
Returns True if the socket is readable, or False if the timeout expired.
"""
return wait_for_socket(sock, write=True, timeout=timeout)