Media Crawler is a powerful multi-platform self-media data collection tool designed for personal efficiency. It provides a robust service architecture for scraping public information from major platforms such as Bilibili, Xiaohongshu, Douyin, Kuaishou, Weibo, Tieba, and Zhihu. Leveraging FastMCP, it enables AI assistants like Claude and ChatGPT to directly invoke its crawling capabilities. The tool emphasizes ease of use, a clear architecture, and features like persistent browser contexts, dynamic task-level configurations, and a streamlined login process, all while offering clear extension points for customization.
主な機能
01Native MCP support for direct AI assistant integration
02Persistent browser context for faster data retrieval
03Modular architecture with clear Endpoint, Service, and Crawler layers
04Task-level configuration using Pydantic Settings
05Decoupled login flow with real-time status and background polling
067 GitHub stars
