6a728cbe5b
- Add playwright-stealth integration with enable_stealth parameter in BrowserConfig - Merge undetected browser strategy into main async_crawler_strategy.py using adapter pattern - Add browser adapters (BrowserAdapter, PlaywrightAdapter, UndetectedAdapter) for flexible browser switching - Update install.py to install both playwright and patchright browsers automatically - Add comprehensive documentation for anti-bot features (stealth mode + undetected browser) - Create examples demonstrating stealth mode usage and comparison tests - Update pyproject.toml and requirements.txt with patchright>=1.49.0 and other dependencies - Remove duplicate/unused dependencies (alphashape, cssselect, pyperclip, shapely, selenium) - Add dependency checker tool in tests/check_dependencies.py Breaking changes: None - all existing functionality preserved 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
97 lines
2.4 KiB
TOML
97 lines
2.4 KiB
TOML
[build-system]
|
|
requires = ["setuptools>=64.0.0", "wheel"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "Crawl4AI"
|
|
dynamic = ["version"]
|
|
description = "🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & scraper"
|
|
readme = "README.md"
|
|
requires-python = ">=3.9"
|
|
license = "Apache-2.0"
|
|
authors = [
|
|
{name = "Unclecode", email = "unclecode@kidocode.com"}
|
|
]
|
|
dependencies = [
|
|
"aiofiles>=24.1.0",
|
|
"aiohttp>=3.11.11",
|
|
"aiosqlite~=0.20",
|
|
"anyio>=4.0.0",
|
|
"lxml~=5.3",
|
|
"litellm>=1.53.1",
|
|
"numpy>=1.26.0,<3",
|
|
"pillow>=10.4",
|
|
"playwright>=1.49.0",
|
|
"patchright>=1.49.0",
|
|
"python-dotenv~=1.0",
|
|
"requests~=2.26",
|
|
"beautifulsoup4~=4.12",
|
|
"tf-playwright-stealth>=1.1.0",
|
|
"xxhash~=3.4",
|
|
"rank-bm25~=0.2",
|
|
"snowballstemmer~=2.2",
|
|
"pydantic>=2.10",
|
|
"pyOpenSSL>=24.3.0",
|
|
"psutil>=6.1.1",
|
|
"PyYAML>=6.0",
|
|
"nltk>=3.9.1",
|
|
"rich>=13.9.4",
|
|
"httpx>=0.27.2",
|
|
"httpx[http2]>=0.27.2",
|
|
"fake-useragent>=2.0.3",
|
|
"click>=8.1.7",
|
|
"chardet>=5.2.0",
|
|
"brotli>=1.1.0",
|
|
"humanize>=4.10.0",
|
|
"lark>=1.2.2",
|
|
"sentence-transformers>=2.2.0"
|
|
]
|
|
classifiers = [
|
|
"Development Status :: 4 - Beta",
|
|
"Intended Audience :: Developers",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.9",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Programming Language :: Python :: 3.13",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
pdf = ["PyPDF2>=3.0.0"]
|
|
torch = ["torch>=2.0.0", "nltk>=3.9.1", "scikit-learn>=1.3.0"]
|
|
transformer = ["transformers>=4.30.0", "tokenizers>=0.13.0"]
|
|
cosine = ["torch>=2.0.0", "transformers>=4.30.0", "nltk>=3.9.1"]
|
|
all = [
|
|
"PyPDF2>=3.0.0",
|
|
"torch>=2.0.0",
|
|
"nltk>=3.9.1",
|
|
"scikit-learn>=1.3.0",
|
|
"transformers>=4.30.0",
|
|
"tokenizers>=0.13.0"
|
|
]
|
|
|
|
[project.scripts]
|
|
crawl4ai-download-models = "crawl4ai.model_loader:main"
|
|
crawl4ai-migrate = "crawl4ai.migrations:main"
|
|
crawl4ai-setup = "crawl4ai.install:post_install"
|
|
crawl4ai-doctor = "crawl4ai.install:doctor"
|
|
crwl = "crawl4ai.cli:main"
|
|
|
|
[tool.setuptools]
|
|
packages = {find = {where = ["."], include = ["crawl4ai*"]}}
|
|
|
|
[tool.setuptools.package-data]
|
|
crawl4ai = ["js_snippet/*.js"]
|
|
|
|
[tool.setuptools.dynamic]
|
|
version = {attr = "crawl4ai.__version__.__version__"}
|
|
|
|
[tool.uv.sources]
|
|
crawl4ai = { workspace = true }
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"crawl4ai",
|
|
]
|