paulpierre/markdown-crawler
A multithreaded 🕸️ web crawler that recursively crawls a website and creates a 🔽 markdown file for each page, designed for LLM RAG
Leverages BeautifulSoup for HTML parsing and markdownify for conversion, with configurable CSS selectors for target content extraction and domain/path filtering. Supports resumable crawling, configurable depth limits, and parallel execution via thread pools. Designed for downstream LLM workflows including RAG chunking, fine-tuning corpus generation, and agent knowledge base construction.
431 stars and 729 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
431
Forks
54
Language
Python
License
MIT
Category
Last pushed
Aug 13, 2024
Monthly downloads
729
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/paulpierre/markdown-crawler"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
any4ai/AnyCrawl
AnyCrawl 🚀: A Node.js/TypeScript crawler that turns websites into LLM-ready data and extracts...
kreuzberg-dev/html-to-markdown
High performance and CommonMark compliant HTML to Markdown converter. Maintained by the...
lightfeed/extractor
Using LLMs and AI browser automation to robustly extract web data
ScrapeGraphAI/Scrapegraph-ai
Python scraper based on AI
adbar/trafilatura
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping,...