Web Fetch

Fetch web content and convert to clean Markdown and PDF formats. Supports general websites and WeChat (微信公众号) articles.

Features

• Automatic noise removal (navigation, headers, footers, sidebars)
• Image preservation with alt text
• WeChat article special handling (lazy-loaded images, metadata extraction)
• Clean Markdown output ready for translation or processing
• PDF conversion with clean reading style
• CJK font support for Chinese content
• Both MD and PDF output by default

Dependencies

# Core dependencies
pip install crawl4ai requests beautifulsoup4 markdownify