--- !ruby/object:Gem::Specification name: boilerpipe-ruby version: !ruby/object:Gem::Version version: 0.4.4 platform: ruby authors: - Gregory Ostermayr autorequire: bindir: exe cert_chain: [] date: 2021-02-13 00:00:00.000000000 Z dependencies: - !ruby/object:Gem::Dependency name: bundler requirement: !ruby/object:Gem::Requirement requirements: - - "~>" - !ruby/object:Gem::Version version: '2.0' type: :development prerelease: false version_requirements: !ruby/object:Gem::Requirement requirements: - - "~>" - !ruby/object:Gem::Version version: '2.0' - !ruby/object:Gem::Dependency name: rake requirement: !ruby/object:Gem::Requirement requirements: - - ">=" - !ruby/object:Gem::Version version: 12.3.3 type: :development prerelease: false version_requirements: !ruby/object:Gem::Requirement requirements: - - ">=" - !ruby/object:Gem::Version version: 12.3.3 - !ruby/object:Gem::Dependency name: rickshaw requirement: !ruby/object:Gem::Requirement requirements: - - "~>" - !ruby/object:Gem::Version version: 0.5.0 type: :development prerelease: false version_requirements: !ruby/object:Gem::Requirement requirements: - - "~>" - !ruby/object:Gem::Version version: 0.5.0 - !ruby/object:Gem::Dependency name: rspec requirement: !ruby/object:Gem::Requirement requirements: - - "~>" - !ruby/object:Gem::Version version: '3.10' type: :development prerelease: false version_requirements: !ruby/object:Gem::Requirement requirements: - - "~>" - !ruby/object:Gem::Version version: '3.10' - !ruby/object:Gem::Dependency name: nokogiri requirement: !ruby/object:Gem::Requirement requirements: - - "~>" - !ruby/object:Gem::Version version: '1.10' type: :runtime prerelease: false version_requirements: !ruby/object:Gem::Requirement requirements: - - "~>" - !ruby/object:Gem::Version version: '1.10' description: A pure ruby implementation of the boilerpipe web content extraction algorithm email: - "" executables: [] extensions: [] extra_rdoc_files: [] files: - ".circleci/config.yml" - ".dockerignore" - ".gitignore" - ".rspec" - CHANGELOG.md - Dockerfile - Gemfile - LICENSE.txt - README.md - Rakefile - bin/console - bin/setup - boilerpipe-ruby.gemspec - boilerpipe_flow.md - lib/boilerpipe.rb - lib/boilerpipe/document/text_block.rb - lib/boilerpipe/document/text_document.rb - lib/boilerpipe/errors.rb - lib/boilerpipe/extractors/article_extractor.rb - lib/boilerpipe/extractors/article_sentence_extractor.rb - lib/boilerpipe/extractors/canola_extractor.rb - lib/boilerpipe/extractors/default_extractor.rb - lib/boilerpipe/extractors/keep_everything_extractor.rb - lib/boilerpipe/extractors/keep_everything_with_k_min_words_extractor.rb - lib/boilerpipe/extractors/largest_content_extractor.rb - lib/boilerpipe/extractors/num_words_rules_extractor.rb - lib/boilerpipe/filters/block_proximity_fusion.rb - lib/boilerpipe/filters/boilerplate_block_filter.rb - lib/boilerpipe/filters/canola_classifier.rb - lib/boilerpipe/filters/density_rules_classifier.rb - lib/boilerpipe/filters/document_title_match_classifier.rb - lib/boilerpipe/filters/expand_title_to_content_filter.rb - lib/boilerpipe/filters/heuristic_filter_base.rb - lib/boilerpipe/filters/ignore_blocks_after_content_filter.rb - lib/boilerpipe/filters/keep_largest_block_filter.rb - lib/boilerpipe/filters/large_block_same_tag_level_to_content_filter.rb - lib/boilerpipe/filters/list_at_end_filter.rb - lib/boilerpipe/filters/mark_everything_content_filter.rb - lib/boilerpipe/filters/min_clause_words_filter.rb - lib/boilerpipe/filters/min_words_filter.rb - lib/boilerpipe/filters/num_words_rules_classifier.rb - lib/boilerpipe/filters/simple_block_fusion_processor.rb - lib/boilerpipe/filters/split_paragraph_blocks_filter.rb - lib/boilerpipe/filters/terminating_blocks_finder.rb - lib/boilerpipe/filters/trailing_headline_to_boilerplate_filter.rb - lib/boilerpipe/labels/default.rb - lib/boilerpipe/labels/label_action.rb - lib/boilerpipe/sax/boilerpipe_html_parser.rb - lib/boilerpipe/sax/html_content_handler.rb - lib/boilerpipe/sax/preprocessor.rb - lib/boilerpipe/sax/tag_action_map.rb - lib/boilerpipe/sax/tag_actions/anchor_text.rb - lib/boilerpipe/sax/tag_actions/block_level.rb - lib/boilerpipe/sax/tag_actions/block_tag_label.rb - lib/boilerpipe/sax/tag_actions/body.rb - lib/boilerpipe/sax/tag_actions/chained.rb - lib/boilerpipe/sax/tag_actions/font.rb - lib/boilerpipe/sax/tag_actions/ignorable_element.rb - lib/boilerpipe/sax/tag_actions/inline_no_whitespace.rb - lib/boilerpipe/sax/tag_actions/inline_tag_label.rb - lib/boilerpipe/sax/tag_actions/inline_whitespace.rb - lib/boilerpipe/util/unicode_tokenizer.rb - lib/boilerpipe/version.rb - stuff.txt homepage: https://github.com/gregors/boilerpipe-ruby licenses: - Apache 2.0 metadata: {} post_install_message: rdoc_options: [] require_paths: - lib required_ruby_version: !ruby/object:Gem::Requirement requirements: - - ">=" - !ruby/object:Gem::Version version: '0' required_rubygems_version: !ruby/object:Gem::Requirement requirements: - - ">=" - !ruby/object:Gem::Version version: '0' requirements: [] rubygems_version: 3.0.8 signing_key: specification_version: 4 summary: A pure ruby implementation of the boilerpipe web content extraction algorithm test_files: []