web-search-api / documents /webpage_content_extractor.py

Commit History

  1. :boom: [Fix] WebpageContentExtractor: UnicodeDecodeError

    cff1afc
  2. :gem: [Feature] New BatchWebpageContentExtractor: Extract webpage content from multiple html_paths concurrently

    1db460d

  1. :zap: [Enhance] ignore classes pattern, especially for 163.com

    3dda344
  2. :recycle: [Refactor] WebpageContentExtractor: Separate html and markdown processing

    a636bcb
  3. :recycle: [Refactor] Move hardcoded consts to network_configs

    af2c647
  4. :gem: [Feature] SearchAPIApp: New extract_content param

    4d3e890
  5. :gem: [Feature] New WebpageContentExtractor: extract webpage content as clean markdown

    e773696