Trafilatura

소개

This server acts as a Model Context Protocol (MCP) interface to the powerful Trafilatura library, enabling developers and models to programmatically extract the main textual content and various metadata from web pages. It exposes a simple `fetch_and_extract` tool for efficient asynchronous operations, making it suitable for integration with MCP-compatible clients like IDEs or coding agents.

주요 기능

• Web scraping for main text content
• Metadata extraction (title, author, date, etc.)
• Configurable content inclusion (comments, tables)
• Single, easy-to-use `fetch_and_extract` tool
• Asynchronous architecture for efficient I/O
• 0 GitHub stars

사용 사례

• Programmatically fetching and parsing news articles or blog posts
• Integrating web content extraction into AI agents or models
• Building data collection pipelines that require clean web page content