{"full_name":"opendatalab/MinerU-HTML","owner":"opendatalab","name":"MinerU-HTML","url":"https://github.com/opendatalab/MinerU-HTML","description":"MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.","homepage":"https://opendatalab.com/ai-ready/AICC#playground","topics":[],"language":"Python","license":null,"avatar":null,"created_at":"2025-11-26T10:31:36Z","pushed_at":"2026-11-06T07:38:39Z","metrics":{"stars":300,"forks":28,"watchers":null,"issues":null,"prs":null,"releases":null,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":null},"growth":{},"history":{"dates":["2026-11-10"],"stars":[300],"forks":[28],"watchers":[null],"issues_open":[null],"prs_open":[null]},"boards":{},"same_owner":[{"full_name":"opendatalab/MinerU","name":"MinerU","boards":{"monthly":200}}],"issues":[],"discussions":[],"latest_release":null,"readme":false,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}