Compare commits
10 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
4cb2a62551 | ||
|
|
5b4fad9e25 | ||
|
|
ea0ac25f38 | ||
|
|
7688aca7d6 | ||
|
|
a7215ad972 | ||
|
|
318554e6bf | ||
|
|
c64979b8dd | ||
|
|
bfe21b29d4 | ||
|
|
e9d9a6ffe8 | ||
|
|
3e769a9c6c |
@@ -11,7 +11,7 @@
|
||||
[](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)
|
||||
@@ -20,9 +20,9 @@
|
||||
|
||||
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 v0.4.24](#-recent-updates)
|
||||
[✨ Check out latest update v0.4.24x](#-recent-updates)
|
||||
|
||||
🎉 **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)
|
||||
🎉 **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)
|
||||
|
||||
## 🧐 Why Crawl4AI?
|
||||
|
||||
@@ -38,7 +38,7 @@ Crawl4AI is the #1 trending GitHub repository, actively maintained by a vibrant
|
||||
1. Install Crawl4AI:
|
||||
```bash
|
||||
# Install the package
|
||||
pip install crawl4ai
|
||||
pip install -U crawl4ai
|
||||
|
||||
# Run post-installation setup
|
||||
crawl4ai-setup
|
||||
|
||||
@@ -1,2 +1,2 @@
|
||||
# crawl4ai/_version.py
|
||||
__version__ = "0.4.241"
|
||||
__version__ = "0.4.245"
|
||||
|
||||
@@ -35,7 +35,9 @@ 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: "chrome".
|
||||
is "chromium". Default: "chromium".
|
||||
channel (str): The channel to launch (e.g., "chromium", "chrome", "msedge"). Only applies if browser_type
|
||||
is "chromium". Default: "chromium".
|
||||
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": "..."}.
|
||||
@@ -77,7 +79,8 @@ class BrowserConfig:
|
||||
use_managed_browser: bool = False,
|
||||
use_persistent_context: bool = False,
|
||||
user_data_dir: str = None,
|
||||
chrome_channel: str = "chrome",
|
||||
chrome_channel: str = "chromium",
|
||||
channel: str = "chromium",
|
||||
proxy: str = None,
|
||||
proxy_config: dict = None,
|
||||
viewport_width: int = 1080,
|
||||
@@ -107,14 +110,8 @@ class BrowserConfig:
|
||||
self.use_managed_browser = use_managed_browser
|
||||
self.use_persistent_context = use_persistent_context
|
||||
self.user_data_dir = user_data_dir
|
||||
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.chrome_channel = chrome_channel or self.browser_type or "chromium"
|
||||
self.channel = channel or self.browser_type or "chromium"
|
||||
self.proxy = proxy
|
||||
self.proxy_config = proxy_config
|
||||
self.viewport_width = viewport_width
|
||||
@@ -161,7 +158,8 @@ 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", "chrome"),
|
||||
chrome_channel=kwargs.get("chrome_channel", "chromium"),
|
||||
channel=kwargs.get("channel", "chromium"),
|
||||
proxy=kwargs.get("proxy"),
|
||||
proxy_config=kwargs.get("proxy_config"),
|
||||
viewport_width=kwargs.get("viewport_width", 1080),
|
||||
|
||||
@@ -69,8 +69,10 @@ crawl4ai-doctor = "crawl4ai.install:doctor"
|
||||
crawl = "crawl4ai.cli:cli"
|
||||
|
||||
[tool.setuptools]
|
||||
packages = ["crawl4ai"]
|
||||
package-data = {"crawl4ai" = ["js_snippet/*.js"]}
|
||||
packages = {find = {where = ["."], include = ["crawl4ai*"]}}
|
||||
|
||||
[tool.setuptools.package-data]
|
||||
crawl4ai = ["js_snippet/*.js"]
|
||||
|
||||
[tool.setuptools.dynamic]
|
||||
version = {attr = "crawl4ai.__version__.__version__"}
|
||||
version = {attr = "crawl4ai.__version__.__version__"}
|
||||
Reference in New Issue
Block a user