{"full_name":"opendatalab/MinerU-HTML","owner":"opendatalab","name":"MinerU-HTML","shard":"1","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":["article-extractor","corpus-tools","nlp","rag","scraping","text-extraction","trafilatura","web-scraping","webagent"],"tag_pages":["nlp","rag","scraping","text-extraction","web-scraping"],"language":"Python","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/97503431?v=4","created_at":"2025-11-26T10:31:36Z","pushed_at":"2026-11-06T07:38:39Z","metrics":{"stars":301,"forks":28,"watchers":5,"issues":24,"prs":13,"releases":3,"issues_open":1,"issues_closed":23,"prs_open":1,"prs_closed":3,"prs_merged":9,"discussions":0},"growth":{"day":{"stars":-1,"forks":0,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[300,302,302,302,302,302,301],"forks":[28,28,28,28,28,28,28],"watchers":[null,5,5,5,5,5,5],"issues_open":[null,1,1,1,1,1,1],"prs_open":[null,1,1,1,1,1,1]},"boards":{},"same_owner":[{"full_name":"opendatalab/MinerU","name":"MinerU","shard":"1","boards":{}}],"issues":[{"number":32,"title":"数据重复采集","comments":1,"created_at":"2026-01-22T08:21:08Z"}],"discussions":[],"latest_release":{"name":"v1.1.3-qwen","tag":"v1.1.3-qwen","published_at":"2026-11-06T07:42:18Z","body":"**Full Changelog**: https://github.com/opendatalab/MinerU-HTML/compare/v1.1...v1.1.3-qwen","is_prerelease":false},"readme":true,"readme_zh":true,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}