{"library":"resiliparse","type":"library","category":null,"description":"Resiliparse is a collection of robust and fast processing tools for parsing and analyzing web archive data, encompassing utilities for character encoding, HTML parsing, content extraction, and process guarding. It is currently at version 0.16.0 and is actively maintained as part of the ChatNoir web analytics toolkit.","language":"python","status":"active","version":"0.16.0","tags":["web scraping","HTML parsing","web archives","NLP","encoding detection","DOM manipulation"],"install":[{"cmd":"pip install resiliparse","imports":["from resiliparse.parse.html import HTMLTree","from resiliparse.parse.encoding import detect_encoding","from resiliparse.parse.encoding import bytes_to_str","from resiliparse.extract.html2text import extract_plain_text"]},{"cmd":"pip install fastwarc","imports":[]},{"cmd":"pip install 'resiliparse[cli]'","imports":[]}],"homepage":"https://resiliparse.chatnoir.eu","github":"https://github.com/chatnoir-eu/chatnoir-resiliparse","docs":"https://resiliparse.chatnoir.eu","changelog":null,"pypi":"https://pypi.org/project/resiliparse/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":40,"avg_install_s":2.4,"avg_import_s":0.02,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/resiliparse/compatibility"},"provenance":{"verified_status":"passing","verified_at":"Sun Jun 28","last_verified":"Sun Jun 28","next_check":"Tue Jul 28","install_tag":null}}