Markdown Content Extraction From Web Pages

via “web content extraction with rss and youtube support”

Python tool for converting files and office documents to Markdown.

Unique: Integrates HTML parsing, RSS feed handling, and YouTube metadata/transcript extraction in a unified converter interface. Unlike generic web scrapers, it specifically optimizes for Markdown output and LLM token efficiency, filtering navigation/ads and preserving semantic structure.

vs others: More specialized for LLM workflows than generic web scrapers because it outputs Markdown, filters boilerplate content, and integrates RSS and YouTube support natively without separate tools.