{"slug":"trafilatura","name":"trafilatura","category":"rag-docs","categoryName":"Document parsing & web scraping","audience":["for-ai"],"primary":"for-ai","openClosed":"open","pricing":"open-source","license":"Apache-2.0","maintained":"yes","officialUrl":"https://trafilatura.readthedocs.io","repo":"https://github.com/adbar/trafilatura","latestVersion":"v2.3.1","latestRelease":"2026-10-06","stars":7003,"starsAsOf":"2026-10-22","description":"Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML","descriptionZh":"网页正文与元数据抽取","callMethods":["CLI","SDK"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["article-extractor","corpus-builder","corpus-tools","crawler","html-to-markdown","html2text","llm","news-aggregator","news-crawler","nlp","rag","readability","rss-feed","scraping","tei","text-cleaning","text-extraction","text-mining","text-preprocessing","web-scraping"],"language":"Python","lastPush":"2026-10-21","formerly":null,"packages":[{"registry":"pypi","name":"trafilatura","url":"https://pypi.org/project/trafilatura/","versionsUrl":"https://pypi.org/project/trafilatura/#history","latestVersion":"2.3.1","latestDate":"2026-10-06"}],"recentVersions":[{"version":"v2.3.1","date":"2026-10-06","prerelease":false,"url":"https://github.com/adbar/trafilatura/releases/tag/v2.3.1","source":"GitHub Release"},{"version":"v2.3.0","date":"2026-10-02","prerelease":false,"url":"https://github.com/adbar/trafilatura/releases/tag/v2.3.0","source":"GitHub Release"},{"version":"v2.2.0","date":"2026-07-31","prerelease":false,"url":"https://github.com/adbar/trafilatura/releases/tag/v2.2.0","source":"GitHub Release"},{"version":"v2.1.0","date":"2026-06-07","prerelease":false,"url":"https://github.com/adbar/trafilatura/releases/tag/v2.1.0","source":"GitHub Release"},{"version":"v2.0.0","date":"2024-12-03","prerelease":false,"url":"https://github.com/adbar/trafilatura/releases/tag/v2.0.0","source":"GitHub Release"}],"alternatives":["scrapegraph-ai","scrapling","scrapy","crawlee","firecrawl","crawl4ai","graphrag","vane"],"stacks":[],"scenarios":["rag-and-documents"],"problems":[],"reasonZh":"正文抽取","sources":["priority","oss","github-pool"],"record":"https://aimap.page/api/v1/software/trafilatura.json","pages":{"en":"https://aimap.page/en/software/trafilatura/","zh-hans":"https://aimap.page/zh-hans/software/trafilatura/"}}