{"library":"readability-lxml","type":"library","category":null,"description":"readability-lxml is a Python library that provides a fast HTML to text parser, designed to extract and clean up the main body text and title from an HTML document. It is a Python port of a Ruby port of arc90's Readability project. The library is actively maintained, with the latest version being 0.8.4.1 as of May 2025 (last PyPI upload date), and new releases typically occur to add Python version support, fix bugs, or add minor features.","language":"python","status":"active","version":"0.8.4.1","tags":["HTML parsing","readability","text extraction","web scraping","lxml"],"install":[{"cmd":"pip install readability-lxml","imports":["from readability import Document"]}],"homepage":null,"github":"http://github.com/buriy/python-readability","docs":null,"changelog":null,"pypi":"https://pypi.org/project/readability-lxml/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":100,"avg_install_s":2.4,"avg_import_s":0.24,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/readability-lxml/compatibility"},"provenance":{"verified_status":"passing","verified_at":"Sun Jun 28","last_verified":"Sun Jun 28","next_check":"Tue Jul 28","install_tag":null}}