WeChat Article Parser

概要

This server, built on the FastMCP framework, provides robust capabilities to interact with WeChat official account articles. It leverages Playwright for browser simulation, allowing it to extract comprehensive information such as titles, authors, publication dates, and full article content. Users can retrieve data in various formats, including JSON, Markdown, HTML, and plain text, with options to include media resources and clean up distracting elements like ads or recommendations. It supports both HTTP and STDIO protocols for versatile deployment and integration within various environments, including Claude Desktop.

主な機能

• Simulates browser access to WeChat articles using Playwright
• 0 GitHub stars
• Supports multiple output formats: JSON, Markdown, HTML, and plain text
• Extracts images, videos, and other media resources from articles
• Extracts article titles, authors, publication dates, and main content
• Cleans up advertisements and recommended content for focused extraction

ユースケース

• Extracting clean, ad-free content from WeChat articles for research or publishing
• Automating the collection and archiving of WeChat official account articles
• Converting WeChat article content into structured data for analysis or display