{"data":{"slug":"adbar-trafilatura","name":"trafilatura","tagline":"Python tool for web text and metadata extraction","github_url":"https://github.com/adbar/trafilatura","owner":"adbar","repo":"trafilatura","owner_avatar_url":"https://avatars.githubusercontent.com/u/2125866?v=4","primary_language":"Python","stars":6657,"forks":415,"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"],"archived":false,"github_pushed_at":"2026-08-15T16:13:21+00:00","maintenance_label":"Very active","stars_delta_30d":343,"url":"https://www.graphcanon.com/tools/adbar-trafilatura","markdown_url":"https://www.graphcanon.com/tools/adbar-trafilatura.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/adbar-trafilatura","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=adbar-trafilatura","description":"Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML","homepage_url":"https://trafilatura.readthedocs.io","license":"Apache-2.0","open_issues":62,"watchers":35,"ai_summary":"trafilatura is a Python and command-line tool designed for web crawling, scraping, and text extraction, supporting output formats like CSV, JSON, HTML, MD, TXT, XML.","readme_excerpt":"## License\n\nThis package is distributed under the [Apache 2.0 license](https://www.apache.org/licenses/LICENSE-2.0.html).\n\nVersions prior to v1.8.0 are under GPLv3+ license.","github_created_at":"2019-04-08T11:38:48+00:00","created_at":"2026-07-07T17:37:42.423006+00:00","updated_at":"2026-09-30T21:37:40.126422+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"}],"tags":[{"slug":"article-extractor","name":"article-extractor"},{"slug":"corpus-builder","name":"corpus-builder"},{"slug":"crawler","name":"crawler"},{"slug":"html-to-markdown","name":"html-to-markdown"},{"slug":"llm","name":"llm"},{"slug":"news-aggregator","name":"news-aggregator"},{"slug":"nlp","name":"nlp"},{"slug":"rag","name":"rag"}],"trust":{"provenance":{"is_fork":false,"github_id":180136168,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-18T18:01:04.148Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":2,"days_since_push":3,"last_release_at":"2026-07-31T16:07:10Z","stars_delta_30d":343,"open_issues_delta_30d":-5},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:10:14.459Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-18T18:01:04.643Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-18T18:01:04.643Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-18T18:01:04.643Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-18T18:01:04.643Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need a tool that supports multiple output formats, including less common ones like TEI and XML, for detailed text and metadata extraction.","For projects requiring a balance between ease of use and customization, as trafilatura offers both command-line and Python API access.","If you are working with a variety of web content types, including articles, news, and RSS feeds, and need robust text cleaning and preprocessing capabilities."],"when_not_to_use":["When your project strictly requires a tool under the GPL license, as trafilatura is now distributed under the Apache 2.0 license.","If your use case demands real-time scraping capabilities, as trafilatura focuses more on accuracy and quality of extracted content rather than speed."],"source":"enrich:decision_facts","observed_at":"2026-09-30T21:37:37.166Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"trafilatura is a Python and command-line tool for web crawling, scraping, and text extraction, supporting various output formats including CSV, JSON, HTML, MD, TXT, and XML."}]}}