Compare commits
1 Commits
unclecode-
...
v0.4.242
| Author | SHA1 | Date | |
|---|---|---|---|
|
f76886b32b |
220
.codeiumignore
Normal file
220
.codeiumignore
Normal file
@@ -0,0 +1,220 @@
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
share/python-wheels/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
MANIFEST
|
||||
|
||||
# PyInstaller
|
||||
# Usually these files are written by a python script from a template
|
||||
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||||
*.manifest
|
||||
*.spec
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
pip-delete-this-directory.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
htmlcov/
|
||||
.tox/
|
||||
.nox/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*.cover
|
||||
*.py,cover
|
||||
.hypothesis/
|
||||
.pytest_cache/
|
||||
cover/
|
||||
|
||||
# Translations
|
||||
*.mo
|
||||
*.pot
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
local_settings.py
|
||||
db.sqlite3
|
||||
db.sqlite3-journal
|
||||
|
||||
# Flask stuff:
|
||||
instance/
|
||||
.webassets-cache
|
||||
|
||||
# Scrapy stuff:
|
||||
.scrapy
|
||||
|
||||
# Sphinx documentation
|
||||
docs/_build/
|
||||
|
||||
# PyBuilder
|
||||
.pybuilder/
|
||||
target/
|
||||
|
||||
# Jupyter Notebook
|
||||
.ipynb_checkpoints
|
||||
|
||||
# IPython
|
||||
profile_default/
|
||||
ipython_config.py
|
||||
|
||||
# pyenv
|
||||
# For a library or package, you might want to ignore these files since the code is
|
||||
# intended to run in multiple environments; otherwise, check them in:
|
||||
# .python-version
|
||||
|
||||
# pipenv
|
||||
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
||||
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
||||
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
||||
# install all needed dependencies.
|
||||
#Pipfile.lock
|
||||
|
||||
# poetry
|
||||
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
||||
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
||||
# commonly ignored for libraries.
|
||||
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
||||
#poetry.lock
|
||||
|
||||
# pdm
|
||||
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
||||
#pdm.lock
|
||||
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
||||
# in version control.
|
||||
# https://pdm.fming.dev/latest/usage/project/#working-with-version-control
|
||||
.pdm.toml
|
||||
.pdm-python
|
||||
.pdm-build/
|
||||
|
||||
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
||||
__pypackages__/
|
||||
|
||||
# Celery stuff
|
||||
celerybeat-schedule
|
||||
celerybeat.pid
|
||||
|
||||
# SageMath parsed files
|
||||
*.sage.py
|
||||
|
||||
# Environments
|
||||
.env
|
||||
.venv
|
||||
env/
|
||||
venv/
|
||||
ENV/
|
||||
env.bak/
|
||||
venv.bak/
|
||||
|
||||
# Spyder project settings
|
||||
.spyderproject
|
||||
.spyproject
|
||||
|
||||
# Rope project settings
|
||||
.ropeproject
|
||||
|
||||
# mkdocs documentation
|
||||
/site
|
||||
|
||||
# mypy
|
||||
.mypy_cache/
|
||||
.dmypy.json
|
||||
dmypy.json
|
||||
|
||||
# Pyre type checker
|
||||
.pyre/
|
||||
|
||||
# pytype static type analyzer
|
||||
.pytype/
|
||||
|
||||
# Cython debug symbols
|
||||
cython_debug/
|
||||
|
||||
# PyCharm
|
||||
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
||||
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
||||
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
||||
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
||||
#.idea/
|
||||
|
||||
Crawl4AI.egg-info/
|
||||
Crawl4AI.egg-info/*
|
||||
crawler_data.db
|
||||
.vscode/
|
||||
.tests/
|
||||
.test_pads/
|
||||
test_pad.py
|
||||
test_pad*.py
|
||||
.data/
|
||||
Crawl4AI.egg-info/
|
||||
|
||||
requirements0.txt
|
||||
a.txt
|
||||
|
||||
*.sh
|
||||
.idea
|
||||
docs/examples/.chainlit/
|
||||
docs/examples/.chainlit/*
|
||||
.chainlit/config.toml
|
||||
.chainlit/translations/en-US.json
|
||||
|
||||
local/
|
||||
.files/
|
||||
|
||||
a.txt
|
||||
.lambda_function.py
|
||||
ec2*
|
||||
|
||||
update_changelog.sh
|
||||
|
||||
.DS_Store
|
||||
docs/.DS_Store
|
||||
tmp/
|
||||
test_env/
|
||||
**/.DS_Store
|
||||
**/.DS_Store
|
||||
|
||||
todo.md
|
||||
todo_executor.md
|
||||
git_changes.py
|
||||
git_changes.md
|
||||
pypi_build.sh
|
||||
git_issues.py
|
||||
git_issues.md
|
||||
|
||||
.next/
|
||||
.tests/
|
||||
.docs/
|
||||
.gitboss/
|
||||
todo_executor.md
|
||||
protect-all-except-feature.sh
|
||||
manage-collab.sh
|
||||
publish.sh
|
||||
combine.sh
|
||||
combined_output.txt
|
||||
tree.md
|
||||
|
||||
2
.gitignore
vendored
2
.gitignore
vendored
@@ -225,5 +225,3 @@ tree.md
|
||||
.scripts
|
||||
.local
|
||||
.do
|
||||
/plans
|
||||
plans/
|
||||
37
CHANGELOG.md
37
CHANGELOG.md
@@ -5,43 +5,6 @@ All notable changes to Crawl4AI will be documented in this file.
|
||||
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
|
||||
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
||||
|
||||
---
|
||||
|
||||
## [0.4.267] - 2025 - 01 - 06
|
||||
|
||||
### Added
|
||||
- **Windows Event Loop Configuration**: Introduced a utility function `configure_windows_event_loop` to resolve `NotImplementedError` for asyncio subprocesses on Windows. ([#utils.py](crawl4ai/utils.py), [#tutorials/async-webcrawler-basics.md](docs/md_v3/tutorials/async-webcrawler-basics.md))
|
||||
- **`page_need_scroll` Method**: Added a method to determine if a page requires scrolling before taking actions in `AsyncPlaywrightCrawlerStrategy`. ([#async_crawler_strategy.py](crawl4ai/async_crawler_strategy.py))
|
||||
|
||||
### Changed
|
||||
- **Version Bump**: Updated the version from `0.4.246` to `0.4.247`. ([#__version__.py](crawl4ai/__version__.py))
|
||||
- **Improved Scrolling Logic**: Enhanced scrolling methods in `AsyncPlaywrightCrawlerStrategy` by adding a `scroll_delay` parameter for better control. ([#async_crawler_strategy.py](crawl4ai/async_crawler_strategy.py))
|
||||
- **Markdown Generation Example**: Updated the `hello_world.py` example to reflect the latest API changes and better illustrate features. ([#examples/hello_world.py](docs/examples/hello_world.py))
|
||||
- **Documentation Update**:
|
||||
- Added Windows-specific instructions for handling asyncio event loops. ([#async-webcrawler-basics.md](docs/md_v3/tutorials/async-webcrawler-basics.md))
|
||||
|
||||
### Removed
|
||||
- **Legacy Markdown Generation Code**: Removed outdated and unused code for markdown generation in `content_scraping_strategy.py`. ([#content_scraping_strategy.py](crawl4ai/content_scraping_strategy.py))
|
||||
|
||||
### Fixed
|
||||
- **Page Closing to Prevent Memory Leaks**:
|
||||
- **Description**: Added a `finally` block to ensure pages are closed when no `session_id` is provided.
|
||||
- **Impact**: Prevents memory leaks caused by lingering pages after a crawl.
|
||||
- **File**: [`async_crawler_strategy.py`](crawl4ai/async_crawler_strategy.py)
|
||||
- **Code**:
|
||||
```python
|
||||
finally:
|
||||
# If no session_id is given we should close the page
|
||||
if not config.session_id:
|
||||
await page.close()
|
||||
```
|
||||
- **Multiple Element Selection**: Modified `_get_elements` in `JsonCssExtractionStrategy` to return all matching elements instead of just the first one, ensuring comprehensive extraction. ([#extraction_strategy.py](crawl4ai/extraction_strategy.py))
|
||||
- **Error Handling in Scrolling**: Added robust error handling to ensure scrolling proceeds safely even if a configuration is missing. ([#async_crawler_strategy.py](crawl4ai/async_crawler_strategy.py))
|
||||
|
||||
### Other
|
||||
- **Git Ignore Update**: Added `/plans` to `.gitignore` for better development environment consistency. ([#.gitignore](.gitignore))
|
||||
|
||||
|
||||
## [0.4.24] - 2024-12-31
|
||||
|
||||
### Added
|
||||
|
||||
@@ -1,131 +0,0 @@
|
||||
# Crawl4AI Code of Conduct
|
||||
|
||||
## Our Pledge
|
||||
|
||||
We as members, contributors, and leaders pledge to make participation in our
|
||||
community a harassment-free experience for everyone, regardless of age, body
|
||||
size, visible or invisible disability, ethnicity, sex characteristics, gender
|
||||
identity and expression, level of experience, education, socio-economic status,
|
||||
nationality, personal appearance, race, caste, color, religion, or sexual
|
||||
identity and orientation.
|
||||
|
||||
We pledge to act and interact in ways that contribute to an open, welcoming,
|
||||
diverse, inclusive, and healthy community.
|
||||
|
||||
## Our Standards
|
||||
|
||||
Examples of behavior that contributes to a positive environment for our
|
||||
community include:
|
||||
|
||||
* Demonstrating empathy and kindness toward other people
|
||||
* Being respectful of differing opinions, viewpoints, and experiences
|
||||
* Giving and gracefully accepting constructive feedback
|
||||
* Accepting responsibility and apologizing to those affected by our mistakes,
|
||||
and learning from the experience
|
||||
* Focusing on what is best not just for us as individuals, but for the overall
|
||||
community
|
||||
|
||||
Examples of unacceptable behavior include:
|
||||
|
||||
* The use of sexualized language or imagery, and sexual attention or advances of
|
||||
any kind
|
||||
* Trolling, insulting or derogatory comments, and personal or political attacks
|
||||
* Public or private harassment
|
||||
* Publishing others' private information, such as a physical or email address,
|
||||
without their explicit permission
|
||||
* Other conduct which could reasonably be considered inappropriate in a
|
||||
professional setting
|
||||
|
||||
## Enforcement Responsibilities
|
||||
|
||||
Community leaders are responsible for clarifying and enforcing our standards of
|
||||
acceptable behavior and will take appropriate and fair corrective action in
|
||||
response to any behavior that they deem inappropriate, threatening, offensive,
|
||||
or harmful.
|
||||
|
||||
Community leaders have the right and responsibility to remove, edit, or reject
|
||||
comments, commits, code, wiki edits, issues, and other contributions that are
|
||||
not aligned to this Code of Conduct, and will communicate reasons for moderation
|
||||
decisions when appropriate.
|
||||
|
||||
## Scope
|
||||
|
||||
This Code of Conduct applies within all community spaces, and also applies when
|
||||
an individual is officially representing the community in public spaces.
|
||||
Examples of representing our community include using an official email address,
|
||||
posting via an official social media account, or acting as an appointed
|
||||
representative at an online or offline event.
|
||||
|
||||
## Enforcement
|
||||
|
||||
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
||||
reported to the community leaders responsible for enforcement at
|
||||
unclecode@crawl4ai.com. All complaints will be reviewed and investigated promptly and fairly.
|
||||
|
||||
All community leaders are obligated to respect the privacy and security of the
|
||||
reporter of any incident.
|
||||
|
||||
## Enforcement Guidelines
|
||||
|
||||
Community leaders will follow these Community Impact Guidelines in determining
|
||||
the consequences for any action they deem in violation of this Code of Conduct:
|
||||
|
||||
### 1. Correction
|
||||
|
||||
**Community Impact**: Use of inappropriate language or other behavior deemed
|
||||
unprofessional or unwelcome in the community.
|
||||
|
||||
**Consequence**: A private, written warning from community leaders, providing
|
||||
clarity around the nature of the violation and an explanation of why the
|
||||
behavior was inappropriate. A public apology may be requested.
|
||||
|
||||
### 2. Warning
|
||||
|
||||
**Community Impact**: A violation through a single incident or series of
|
||||
actions.
|
||||
|
||||
**Consequence**: A warning with consequences for continued behavior. No
|
||||
interaction with the people involved, including unsolicited interaction with
|
||||
those enforcing the Code of Conduct, for a specified period of time. This
|
||||
includes avoiding interactions in community spaces as well as external channels
|
||||
like social media. Violating these terms may lead to a temporary or permanent
|
||||
ban.
|
||||
|
||||
### 3. Temporary Ban
|
||||
|
||||
**Community Impact**: A serious violation of community standards, including
|
||||
sustained inappropriate behavior.
|
||||
|
||||
**Consequence**: A temporary ban from any sort of interaction or public
|
||||
communication with the community for a specified period of time. No public or
|
||||
private interaction with the people involved, including unsolicited interaction
|
||||
with those enforcing the Code of Conduct, is allowed during this period.
|
||||
Violating these terms may lead to a permanent ban.
|
||||
|
||||
### 4. Permanent Ban
|
||||
|
||||
**Community Impact**: Demonstrating a pattern of violation of community
|
||||
standards, including sustained inappropriate behavior, harassment of an
|
||||
individual, or aggression toward or disparagement of classes of individuals.
|
||||
|
||||
**Consequence**: A permanent ban from any sort of public interaction within the
|
||||
community.
|
||||
|
||||
## Attribution
|
||||
|
||||
This Code of Conduct is adapted from the [Contributor Covenant][homepage],
|
||||
version 2.1, available at
|
||||
[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
|
||||
|
||||
Community Impact Guidelines were inspired by
|
||||
[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
|
||||
|
||||
For answers to common questions about this code of conduct, see the FAQ at
|
||||
[https://www.contributor-covenant.org/faq][FAQ]. Translations are available at
|
||||
[https://www.contributor-covenant.org/translations][translations].
|
||||
|
||||
[homepage]: https://www.contributor-covenant.org
|
||||
[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
|
||||
[Mozilla CoC]: https://github.com/mozilla/diversity
|
||||
[FAQ]: https://www.contributor-covenant.org/faq
|
||||
[translations]: https://www.contributor-covenant.org/translations
|
||||
@@ -11,19 +11,18 @@
|
||||
[](https://pypi.org/project/crawl4ai/)
|
||||
[](https://pepy.tech/project/crawl4ai)
|
||||
|
||||
<!-- [](https://crawl4ai.readthedocs.io/) -->
|
||||
[](https://crawl4ai.readthedocs.io/)
|
||||
[](https://github.com/unclecode/crawl4ai/blob/main/LICENSE)
|
||||
[](https://github.com/psf/black)
|
||||
[](https://github.com/PyCQA/bandit)
|
||||
[](code_of_conduct.md)
|
||||
|
||||
</div>
|
||||
|
||||
Crawl4AI is the #1 trending GitHub repository, actively maintained by a vibrant community. It delivers blazing-fast, AI-ready web crawling tailored for LLMs, AI agents, and data pipelines. Open source, flexible, and built for real-time performance, Crawl4AI empowers developers with unmatched speed, precision, and deployment ease.
|
||||
|
||||
[✨ Check out latest update v0.4.24x](#-recent-updates)
|
||||
[✨ Check out latest update v0.4.24](#-recent-updates)
|
||||
|
||||
🎉 **Version 0.4.24x is out!** Major improvements in extraction strategies with enhanced JSON handling, SSL security, and Amazon product extraction. Plus, a completely revamped content filtering system! [Read the release notes →](https://crawl4ai.com/mkdocs/blog)
|
||||
🎉 **Version 0.4.24 is out!** Major improvements in extraction strategies with enhanced JSON handling, SSL security, and Amazon product extraction. Plus, a completely revamped content filtering system! [Read the release notes →](https://crawl4ai.com/mkdocs/blog)
|
||||
|
||||
## 🧐 Why Crawl4AI?
|
||||
|
||||
@@ -39,7 +38,7 @@ Crawl4AI is the #1 trending GitHub repository, actively maintained by a vibrant
|
||||
1. Install Crawl4AI:
|
||||
```bash
|
||||
# Install the package
|
||||
pip install -U crawl4ai
|
||||
pip install crawl4ai
|
||||
|
||||
# Run post-installation setup
|
||||
crawl4ai-setup
|
||||
|
||||
@@ -1,2 +1,2 @@
|
||||
# crawl4ai/_version.py
|
||||
__version__ = "0.4.247"
|
||||
__version__ = "0.4.244"
|
||||
|
||||
@@ -35,9 +35,7 @@ class BrowserConfig:
|
||||
user_data_dir (str or None): Path to a user data directory for persistent sessions. If None, a
|
||||
temporary directory may be used. Default: None.
|
||||
chrome_channel (str): The Chrome channel to launch (e.g., "chrome", "msedge"). Only applies if browser_type
|
||||
is "chromium". Default: "chromium".
|
||||
channel (str): The channel to launch (e.g., "chromium", "chrome", "msedge"). Only applies if browser_type
|
||||
is "chromium". Default: "chromium".
|
||||
is "chromium". Default: "chrome".
|
||||
proxy (str or None): Proxy server URL (e.g., "http://username:password@proxy:port"). If None, no proxy is used.
|
||||
Default: None.
|
||||
proxy_config (dict or None): Detailed proxy configuration, e.g. {"server": "...", "username": "..."}.
|
||||
@@ -79,8 +77,7 @@ class BrowserConfig:
|
||||
use_managed_browser: bool = False,
|
||||
use_persistent_context: bool = False,
|
||||
user_data_dir: str = None,
|
||||
chrome_channel: str = "chromium",
|
||||
channel: str = "chromium",
|
||||
chrome_channel: str = "chrome",
|
||||
proxy: str = None,
|
||||
proxy_config: dict = None,
|
||||
viewport_width: int = 1080,
|
||||
@@ -110,8 +107,14 @@ class BrowserConfig:
|
||||
self.use_managed_browser = use_managed_browser
|
||||
self.use_persistent_context = use_persistent_context
|
||||
self.user_data_dir = user_data_dir
|
||||
self.chrome_channel = chrome_channel or self.browser_type or "chromium"
|
||||
self.channel = channel or self.browser_type or "chromium"
|
||||
if self.browser_type == "chromium":
|
||||
self.chrome_channel = "chrome"
|
||||
elif self.browser_type == "firefox":
|
||||
self.chrome_channel = "firefox"
|
||||
elif self.browser_type == "webkit":
|
||||
self.chrome_channel = "webkit"
|
||||
else:
|
||||
self.chrome_channel = chrome_channel or "chrome"
|
||||
self.proxy = proxy
|
||||
self.proxy_config = proxy_config
|
||||
self.viewport_width = viewport_width
|
||||
@@ -158,8 +161,7 @@ class BrowserConfig:
|
||||
use_managed_browser=kwargs.get("use_managed_browser", False),
|
||||
use_persistent_context=kwargs.get("use_persistent_context", False),
|
||||
user_data_dir=kwargs.get("user_data_dir"),
|
||||
chrome_channel=kwargs.get("chrome_channel", "chromium"),
|
||||
channel=kwargs.get("channel", "chromium"),
|
||||
chrome_channel=kwargs.get("chrome_channel", "chrome"),
|
||||
proxy=kwargs.get("proxy"),
|
||||
proxy_config=kwargs.get("proxy_config"),
|
||||
viewport_width=kwargs.get("viewport_width", 1080),
|
||||
@@ -246,7 +248,7 @@ class CrawlerRunConfig:
|
||||
wait_for (str or None): A CSS selector or JS condition to wait for before extracting content.
|
||||
Default: None.
|
||||
wait_for_images (bool): If True, wait for images to load before extracting content.
|
||||
Default: False.
|
||||
Default: True.
|
||||
delay_before_return_html (float): Delay in seconds before retrieving final HTML.
|
||||
Default: 0.1.
|
||||
mean_delay (float): Mean base delay between requests when calling arun_many.
|
||||
@@ -345,7 +347,7 @@ class CrawlerRunConfig:
|
||||
wait_until: str = "domcontentloaded",
|
||||
page_timeout: int = PAGE_TIMEOUT,
|
||||
wait_for: str = None,
|
||||
wait_for_images: bool = False,
|
||||
wait_for_images: bool = True,
|
||||
delay_before_return_html: float = 0.1,
|
||||
mean_delay: float = 0.1,
|
||||
max_range: float = 0.3,
|
||||
@@ -503,7 +505,7 @@ class CrawlerRunConfig:
|
||||
wait_until=kwargs.get("wait_until", "domcontentloaded"),
|
||||
page_timeout=kwargs.get("page_timeout", 60000),
|
||||
wait_for=kwargs.get("wait_for"),
|
||||
wait_for_images=kwargs.get("wait_for_images", False),
|
||||
wait_for_images=kwargs.get("wait_for_images", True),
|
||||
delay_before_return_html=kwargs.get("delay_before_return_html", 0.1),
|
||||
mean_delay=kwargs.get("mean_delay", 0.1),
|
||||
max_range=kwargs.get("max_range", 0.3),
|
||||
|
||||
@@ -1475,13 +1475,8 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
|
||||
|
||||
except Exception as e:
|
||||
raise e
|
||||
|
||||
finally:
|
||||
# If no session_id is given we should close the page
|
||||
if not config.session_id:
|
||||
await page.close()
|
||||
|
||||
async def _handle_full_page_scan(self, page: Page, scroll_delay: float = 0.1):
|
||||
async def _handle_full_page_scan(self, page: Page, scroll_delay: float):
|
||||
"""
|
||||
Helper method to handle full page scanning.
|
||||
|
||||
@@ -1505,7 +1500,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
|
||||
current_position = viewport_height
|
||||
|
||||
# await page.evaluate(f"window.scrollTo(0, {current_position})")
|
||||
await self.safe_scroll(page, 0, current_position, delay=scroll_delay)
|
||||
await self.safe_scroll(page, 0, current_position)
|
||||
# await self.csp_scroll_to(page, 0, current_position)
|
||||
# await asyncio.sleep(scroll_delay)
|
||||
|
||||
@@ -1515,7 +1510,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
|
||||
|
||||
while current_position < total_height:
|
||||
current_position = min(current_position + viewport_height, total_height)
|
||||
await self.safe_scroll(page, 0, current_position, delay=scroll_delay)
|
||||
await self.safe_scroll(page, 0, current_position)
|
||||
# await page.evaluate(f"window.scrollTo(0, {current_position})")
|
||||
# await asyncio.sleep(scroll_delay)
|
||||
|
||||
@@ -1644,9 +1639,11 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
|
||||
Returns:
|
||||
str: The base64-encoded screenshot data
|
||||
"""
|
||||
need_scroll = await self.page_need_scroll(page)
|
||||
|
||||
if not need_scroll:
|
||||
dimensions = await self.get_page_dimensions(page)
|
||||
page_height = dimensions['height']
|
||||
if page_height < kwargs.get(
|
||||
"screenshot_height_threshold", SCREENSHOT_HEIGHT_TRESHOLD
|
||||
):
|
||||
# Page is short enough, just take a screenshot
|
||||
return await self.take_screenshot_naive(page)
|
||||
else:
|
||||
@@ -2069,7 +2066,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
|
||||
}
|
||||
""")
|
||||
|
||||
async def safe_scroll(self, page: Page, x: int, y: int, delay: float = 0.1):
|
||||
async def safe_scroll(self, page: Page, x: int, y: int):
|
||||
"""
|
||||
Safely scroll the page with rendering time.
|
||||
|
||||
@@ -2080,7 +2077,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
|
||||
"""
|
||||
result = await self.csp_scroll_to(page, x, y)
|
||||
if result['success']:
|
||||
await page.wait_for_timeout(delay * 1000)
|
||||
await page.wait_for_timeout(100) # Allow for rendering
|
||||
return result
|
||||
|
||||
async def csp_scroll_to(self, page: Page, x: int, y: int) -> Dict[str, Any]:
|
||||
@@ -2161,31 +2158,4 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
|
||||
const {scrollWidth, scrollHeight} = document.documentElement;
|
||||
return {width: scrollWidth, height: scrollHeight};
|
||||
}
|
||||
""")
|
||||
|
||||
async def page_need_scroll(self, page: Page) -> bool:
|
||||
"""
|
||||
Determine whether the page need to scroll
|
||||
|
||||
Args:
|
||||
page: Playwright page object
|
||||
|
||||
Returns:
|
||||
bool: True if page needs scrolling
|
||||
"""
|
||||
try:
|
||||
need_scroll = await page.evaluate("""
|
||||
() => {
|
||||
const scrollHeight = document.documentElement.scrollHeight;
|
||||
const viewportHeight = window.innerHeight;
|
||||
return scrollHeight > viewportHeight;
|
||||
}
|
||||
""")
|
||||
return need_scroll
|
||||
except Exception as e:
|
||||
self.logger.warning(
|
||||
message="Failed to check scroll need: {error}. Defaulting to True for safety.",
|
||||
tag="SCROLL",
|
||||
params={"error": str(e)}
|
||||
)
|
||||
return True # Default to scrolling if check fails
|
||||
""")
|
||||
@@ -418,30 +418,34 @@ class AsyncWebCrawler:
|
||||
**kwargs
|
||||
)
|
||||
|
||||
crawl_result.status_code = async_response.status_code
|
||||
crawl_result.response_headers = async_response.response_headers
|
||||
crawl_result.downloaded_files = async_response.downloaded_files
|
||||
crawl_result.ssl_certificate = async_response.ssl_certificate # Add SSL certificate
|
||||
# crawl_result.status_code = async_response.status_code
|
||||
# crawl_result.response_headers = async_response.response_headers
|
||||
# crawl_result.downloaded_files = async_response.downloaded_files
|
||||
# crawl_result.ssl_certificate = async_response.ssl_certificate # Add SSL certificate
|
||||
# else:
|
||||
# crawl_result.status_code = 200
|
||||
# crawl_result.response_headers = cached_result.response_headers if cached_result else {}
|
||||
# crawl_result.ssl_certificate = cached_result.ssl_certificate if cached_result else None # Add SSL certificate from cache
|
||||
|
||||
# # Check and set values from async_response to crawl_result
|
||||
# try:
|
||||
# for key in vars(async_response):
|
||||
# if hasattr(crawl_result, key):
|
||||
# value = getattr(async_response, key, None)
|
||||
# current_value = getattr(crawl_result, key, None)
|
||||
# if value is not None and not current_value:
|
||||
# try:
|
||||
# setattr(crawl_result, key, value)
|
||||
# except Exception as e:
|
||||
# self.logger.warning(
|
||||
# message=f"Failed to set attribute {key}: {str(e)}",
|
||||
# tag="WARNING"
|
||||
# )
|
||||
# except Exception as e:
|
||||
# self.logger.warning(
|
||||
# message=f"Error copying response attributes: {str(e)}",
|
||||
# tag="WARNING"
|
||||
# )
|
||||
try:
|
||||
for key in vars(async_response):
|
||||
if hasattr(crawl_result, key):
|
||||
value = getattr(async_response, key, None)
|
||||
current_value = getattr(crawl_result, key, None)
|
||||
if value is not None and not current_value:
|
||||
try:
|
||||
setattr(crawl_result, key, value)
|
||||
except Exception as e:
|
||||
self.logger.warning(
|
||||
message=f"Failed to set attribute {key}: {str(e)}",
|
||||
tag="WARNING"
|
||||
)
|
||||
except Exception as e:
|
||||
self.logger.warning(
|
||||
message=f"Error copying response attributes: {str(e)}",
|
||||
tag="WARNING"
|
||||
)
|
||||
|
||||
crawl_result.success = bool(html)
|
||||
crawl_result.session_id = getattr(config, 'session_id', None)
|
||||
@@ -581,10 +585,8 @@ class AsyncWebCrawler:
|
||||
|
||||
# Markdown Generation
|
||||
markdown_generator: Optional[MarkdownGenerationStrategy] = config.markdown_generator or DefaultMarkdownGenerator()
|
||||
|
||||
# Uncomment if by default we want to use PruningContentFilter
|
||||
# if not config.content_filter and not markdown_generator.content_filter:
|
||||
# markdown_generator.content_filter = PruningContentFilter()
|
||||
if not config.content_filter and not markdown_generator.content_filter:
|
||||
markdown_generator.content_filter = PruningContentFilter()
|
||||
|
||||
markdown_result: MarkdownGenerationResult = markdown_generator.generate_markdown(
|
||||
cleaned_html=cleaned_html,
|
||||
|
||||
@@ -122,6 +122,92 @@ class WebScrapingStrategy(ContentScrapingStrategy):
|
||||
"""
|
||||
return await asyncio.to_thread(self._scrap, url, html, **kwargs)
|
||||
|
||||
def _generate_markdown_content(self, cleaned_html: str,html: str,url: str, success: bool, **kwargs) -> Dict[str, Any]:
|
||||
"""
|
||||
Generate markdown content from cleaned HTML.
|
||||
|
||||
Args:
|
||||
cleaned_html (str): The cleaned HTML content.
|
||||
html (str): The original HTML content.
|
||||
url (str): The URL of the page.
|
||||
success (bool): Whether the content was successfully cleaned.
|
||||
**kwargs: Additional keyword arguments.
|
||||
|
||||
Returns:
|
||||
Dict[str, Any]: A dictionary containing the generated markdown content.
|
||||
"""
|
||||
markdown_generator: Optional[MarkdownGenerationStrategy] = kwargs.get('markdown_generator', DefaultMarkdownGenerator())
|
||||
|
||||
if markdown_generator:
|
||||
try:
|
||||
if kwargs.get('fit_markdown', False) and not markdown_generator.content_filter:
|
||||
markdown_generator.content_filter = BM25ContentFilter(
|
||||
user_query=kwargs.get('fit_markdown_user_query', None),
|
||||
bm25_threshold=kwargs.get('fit_markdown_bm25_threshold', 1.0)
|
||||
)
|
||||
|
||||
markdown_result: MarkdownGenerationResult = markdown_generator.generate_markdown(
|
||||
cleaned_html=cleaned_html,
|
||||
base_url=url,
|
||||
html2text_options=kwargs.get('html2text', {})
|
||||
)
|
||||
|
||||
return {
|
||||
'markdown': markdown_result.raw_markdown,
|
||||
'fit_markdown': markdown_result.fit_markdown,
|
||||
'fit_html': markdown_result.fit_html,
|
||||
'markdown_v2': markdown_result
|
||||
}
|
||||
except Exception as e:
|
||||
self._log('error',
|
||||
message="Error using new markdown generation strategy: {error}",
|
||||
tag="SCRAPE",
|
||||
params={"error": str(e)}
|
||||
)
|
||||
markdown_generator = None
|
||||
return {
|
||||
'markdown': f"Error using new markdown generation strategy: {str(e)}",
|
||||
'fit_markdown': "Set flag 'fit_markdown' to True to get cleaned HTML content.",
|
||||
'fit_html': "Set flag 'fit_markdown' to True to get cleaned HTML content.",
|
||||
'markdown_v2': None
|
||||
}
|
||||
|
||||
# Legacy method
|
||||
"""
|
||||
# h = CustomHTML2Text()
|
||||
# h.update_params(**kwargs.get('html2text', {}))
|
||||
# markdown = h.handle(cleaned_html)
|
||||
# markdown = markdown.replace(' ```', '```')
|
||||
|
||||
# fit_markdown = "Set flag 'fit_markdown' to True to get cleaned HTML content."
|
||||
# fit_html = "Set flag 'fit_markdown' to True to get cleaned HTML content."
|
||||
|
||||
# if kwargs.get('content_filter', None) or kwargs.get('fit_markdown', False):
|
||||
# content_filter = kwargs.get('content_filter', None)
|
||||
# if not content_filter:
|
||||
# content_filter = BM25ContentFilter(
|
||||
# user_query=kwargs.get('fit_markdown_user_query', None),
|
||||
# bm25_threshold=kwargs.get('fit_markdown_bm25_threshold', 1.0)
|
||||
# )
|
||||
# fit_html = content_filter.filter_content(html)
|
||||
# fit_html = '\n'.join('<div>{}</div>'.format(s) for s in fit_html)
|
||||
# fit_markdown = h.handle(fit_html)
|
||||
|
||||
# markdown_v2 = MarkdownGenerationResult(
|
||||
# raw_markdown=markdown,
|
||||
# markdown_with_citations=markdown,
|
||||
# references_markdown=markdown,
|
||||
# fit_markdown=fit_markdown
|
||||
# )
|
||||
|
||||
# return {
|
||||
# 'markdown': markdown,
|
||||
# 'fit_markdown': fit_markdown,
|
||||
# 'fit_html': fit_html,
|
||||
# 'markdown_v2' : markdown_v2
|
||||
# }
|
||||
"""
|
||||
|
||||
def flatten_nested_elements(self, node):
|
||||
"""
|
||||
Flatten nested elements in a HTML tree.
|
||||
@@ -712,6 +798,13 @@ class WebScrapingStrategy(ContentScrapingStrategy):
|
||||
|
||||
cleaned_html = str_body.replace('\n\n', '\n').replace(' ', ' ')
|
||||
|
||||
# markdown_content = self._generate_markdown_content(
|
||||
# cleaned_html=cleaned_html,
|
||||
# html=html,
|
||||
# url=url,
|
||||
# success=success,
|
||||
# **kwargs
|
||||
# )
|
||||
|
||||
return {
|
||||
# **markdown_content,
|
||||
|
||||
@@ -974,9 +974,8 @@ class JsonCssExtractionStrategy(JsonElementExtractionStrategy):
|
||||
return parsed_html.select(selector)
|
||||
|
||||
def _get_elements(self, element, selector: str):
|
||||
# Return all matching elements using select() instead of select_one()
|
||||
# This ensures that we get all elements that match the selector, not just the first one
|
||||
return element.select(selector)
|
||||
selected = element.select_one(selector)
|
||||
return [selected] if selected else []
|
||||
|
||||
def _get_element_text(self, element) -> str:
|
||||
return element.get_text(strip=True)
|
||||
@@ -1050,3 +1049,4 @@ class JsonXPathExtractionStrategy(JsonElementExtractionStrategy):
|
||||
|
||||
def _get_element_attribute(self, element, attribute: str):
|
||||
return element.get(attribute)
|
||||
|
||||
|
||||
@@ -143,83 +143,41 @@ class DefaultMarkdownGenerator(MarkdownGenerationStrategy):
|
||||
Returns:
|
||||
MarkdownGenerationResult: Result containing raw markdown, fit markdown, fit HTML, and references markdown.
|
||||
"""
|
||||
try:
|
||||
# Initialize HTML2Text with default options for better conversion
|
||||
h = CustomHTML2Text(baseurl=base_url)
|
||||
default_options = {
|
||||
'body_width': 0, # Disable text wrapping
|
||||
'ignore_emphasis': False,
|
||||
'ignore_links': False,
|
||||
'ignore_images': False,
|
||||
'protect_links': True,
|
||||
'single_line_break': True,
|
||||
'mark_code': True,
|
||||
'escape_snob': False
|
||||
}
|
||||
|
||||
# Update with custom options if provided
|
||||
if html2text_options:
|
||||
default_options.update(html2text_options)
|
||||
elif options:
|
||||
default_options.update(options)
|
||||
elif self.options:
|
||||
default_options.update(self.options)
|
||||
|
||||
h.update_params(**default_options)
|
||||
# Initialize HTML2Text with options
|
||||
h = CustomHTML2Text()
|
||||
if html2text_options:
|
||||
h.update_params(**html2text_options)
|
||||
elif options:
|
||||
h.update_params(**options)
|
||||
elif self.options:
|
||||
h.update_params(**self.options)
|
||||
|
||||
# Ensure we have valid input
|
||||
if not cleaned_html:
|
||||
cleaned_html = ""
|
||||
elif not isinstance(cleaned_html, str):
|
||||
cleaned_html = str(cleaned_html)
|
||||
# Generate raw markdown
|
||||
raw_markdown = h.handle(cleaned_html)
|
||||
raw_markdown = raw_markdown.replace(' ```', '```')
|
||||
|
||||
# Generate raw markdown
|
||||
try:
|
||||
raw_markdown = h.handle(cleaned_html)
|
||||
except Exception as e:
|
||||
raw_markdown = f"Error converting HTML to markdown: {str(e)}"
|
||||
|
||||
raw_markdown = raw_markdown.replace(' ```', '```')
|
||||
|
||||
# Convert links to citations
|
||||
markdown_with_citations: str = raw_markdown
|
||||
references_markdown: str = ""
|
||||
if citations:
|
||||
try:
|
||||
markdown_with_citations, references_markdown = self.convert_links_to_citations(
|
||||
raw_markdown, base_url
|
||||
)
|
||||
except Exception as e:
|
||||
markdown_with_citations = raw_markdown
|
||||
references_markdown = f"Error generating citations: {str(e)}"
|
||||
|
||||
# Generate fit markdown if content filter is provided
|
||||
fit_markdown: Optional[str] = ""
|
||||
filtered_html: Optional[str] = ""
|
||||
if content_filter or self.content_filter:
|
||||
try:
|
||||
content_filter = content_filter or self.content_filter
|
||||
filtered_html = content_filter.filter_content(cleaned_html)
|
||||
filtered_html = '\n'.join('<div>{}</div>'.format(s) for s in filtered_html)
|
||||
fit_markdown = h.handle(filtered_html)
|
||||
except Exception as e:
|
||||
fit_markdown = f"Error generating fit markdown: {str(e)}"
|
||||
filtered_html = ""
|
||||
|
||||
return MarkdownGenerationResult(
|
||||
raw_markdown=raw_markdown or "",
|
||||
markdown_with_citations=markdown_with_citations or "",
|
||||
references_markdown=references_markdown or "",
|
||||
fit_markdown=fit_markdown or "",
|
||||
fit_html=filtered_html or "",
|
||||
)
|
||||
except Exception as e:
|
||||
# If anything fails, return empty strings with error message
|
||||
error_msg = f"Error in markdown generation: {str(e)}"
|
||||
return MarkdownGenerationResult(
|
||||
raw_markdown=error_msg,
|
||||
markdown_with_citations=error_msg,
|
||||
references_markdown="",
|
||||
fit_markdown="",
|
||||
fit_html="",
|
||||
# Convert links to citations
|
||||
markdown_with_citations: str = ""
|
||||
references_markdown: str = ""
|
||||
if citations:
|
||||
markdown_with_citations, references_markdown = self.convert_links_to_citations(
|
||||
raw_markdown, base_url
|
||||
)
|
||||
|
||||
# Generate fit markdown if content filter is provided
|
||||
fit_markdown: Optional[str] = ""
|
||||
filtered_html: Optional[str] = ""
|
||||
if content_filter or self.content_filter:
|
||||
content_filter = content_filter or self.content_filter
|
||||
filtered_html = content_filter.filter_content(cleaned_html)
|
||||
filtered_html = '\n'.join('<div>{}</div>'.format(s) for s in filtered_html)
|
||||
fit_markdown = h.handle(filtered_html)
|
||||
|
||||
return MarkdownGenerationResult(
|
||||
raw_markdown=raw_markdown,
|
||||
markdown_with_citations=markdown_with_citations,
|
||||
references_markdown=references_markdown,
|
||||
fit_markdown=fit_markdown,
|
||||
fit_html=filtered_html,
|
||||
)
|
||||
|
||||
|
||||
@@ -21,8 +21,6 @@ import textwrap
|
||||
import cProfile
|
||||
import pstats
|
||||
from functools import wraps
|
||||
import asyncio
|
||||
|
||||
|
||||
class InvalidCSSSelectorError(Exception):
|
||||
pass
|
||||
@@ -1581,25 +1579,6 @@ def ensure_content_dirs(base_path: str) -> Dict[str, str]:
|
||||
|
||||
return content_paths
|
||||
|
||||
def configure_windows_event_loop():
|
||||
"""
|
||||
Configure the Windows event loop to use ProactorEventLoop.
|
||||
This resolves the NotImplementedError that occurs on Windows when using asyncio subprocesses.
|
||||
|
||||
This function should only be called on Windows systems and before any async operations.
|
||||
On non-Windows systems, this function does nothing.
|
||||
|
||||
Example:
|
||||
```python
|
||||
from crawl4ai.async_configs import configure_windows_event_loop
|
||||
|
||||
# Call this before any async operations if you're on Windows
|
||||
configure_windows_event_loop()
|
||||
```
|
||||
"""
|
||||
if platform.system() == 'Windows':
|
||||
asyncio.set_event_loop_policy(asyncio.WindowsProactorEventLoopPolicy())
|
||||
|
||||
def get_error_context(exc_info, context_lines: int = 5):
|
||||
"""
|
||||
Extract error context with more reliable line number tracking.
|
||||
|
||||
@@ -1,20 +0,0 @@
|
||||
import asyncio
|
||||
from crawl4ai import *
|
||||
|
||||
async def main():
|
||||
browser_config = BrowserConfig(headless=True, verbose=True)
|
||||
async with AsyncWebCrawler(config=browser_config) as crawler:
|
||||
crawler_config = CrawlerRunConfig(
|
||||
cache_mode=CacheMode.BYPASS,
|
||||
markdown_generator=DefaultMarkdownGenerator(
|
||||
content_filter=PruningContentFilter(threshold=0.48, threshold_type="fixed", min_word_threshold=0)
|
||||
)
|
||||
)
|
||||
result = await crawler.arun(
|
||||
url="https://www.helloworld.org",
|
||||
config=crawler_config
|
||||
)
|
||||
print(result.markdown_v2.raw_markdown[:500])
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
@@ -148,24 +148,7 @@ Below are a few `BrowserConfig` and `CrawlerRunConfig` parameters you might twea
|
||||
|
||||
---
|
||||
|
||||
## 5. Windows-Specific Configuration
|
||||
|
||||
When using AsyncWebCrawler on Windows, you might encounter a `NotImplementedError` related to `asyncio.create_subprocess_exec`. This is a known Windows-specific issue that occurs because Windows' default event loop doesn't support subprocess operations.
|
||||
|
||||
To resolve this, Crawl4AI provides a utility function to configure Windows to use the ProactorEventLoop. Call this function before running any async operations:
|
||||
|
||||
```python
|
||||
from crawl4ai.utils import configure_windows_event_loop
|
||||
|
||||
# Call this before any async operations if you're on Windows
|
||||
configure_windows_event_loop()
|
||||
|
||||
# Your AsyncWebCrawler code here
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 6. Putting It All Together
|
||||
## 5. Putting It All Together
|
||||
|
||||
Here’s a slightly more in-depth example that shows off a few key config parameters at once:
|
||||
|
||||
@@ -210,7 +193,7 @@ if __name__ == "__main__":
|
||||
|
||||
---
|
||||
|
||||
## 7. Next Steps
|
||||
## 6. Next Steps
|
||||
|
||||
- **Smart Crawling Techniques**: Learn to handle iframes, advanced caching, and selective extraction in the [next tutorial](./smart-crawling.md).
|
||||
- **Hooks & Custom Code**: See how to inject custom logic before and after navigation in a dedicated [Hooks Tutorial](./hooks-custom.md).
|
||||
|
||||
Reference in New Issue
Block a user