{"library":"maincontentextractor","type":"library","category":null,"description":"MainContentExtractor is a Python library designed to extract the core content from HTML documents. It aims to address limitations found in other extraction tools, such as the inability to output clean HTML directly. The library is useful for LLM-related tasks and for feeding data into frameworks like LangChain and LlamaIndex by providing output in HTML, Text, or Markdown formats. It is currently at version 0.0.4, with a relatively active development cadence.","language":"python","status":"active","version":"0.0.4","tags":["html","content-extraction","web-scraping","llm","langchain","llamaindex","markdown"],"install":[{"cmd":"pip install MainContentExtractor","imports":["from main_content_extractor import MainContentExtractor"]}],"homepage":null,"github":"https://github.com/HawkClaws/main_content_extractor","docs":null,"changelog":null,"pypi":"https://pypi.org/project/maincontentextractor/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":100,"avg_install_s":5,"avg_import_s":3.45,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/maincontentextractor/compatibility"},"provenance":{"verified_status":"passing","verified_at":"Sun Jun 28","last_verified":"Sun Jun 28","next_check":"Tue Jul 28","install_tag":null}}