adbar/trafilatura

Extracts text and metadata from the web

View on index · View in 3D Map

Related repos

• Extracts structured data from websites with natural language prompts
• automates extracting data from web pages using example content
• Converts websites into markdown using OCR and stealth scraping
• extracts main content from web pages
• extracts text from documents and images using OCR
• Data acquisition framework for GitHub and web sources
• extracts data from any document to markdown, csv, json, html
• extracts and decrypts browser data for security research
• Go library for retrieval-augmented generation and document search