Contents

# Marks all blocks as content.

module Boilerpipe::Extractors
  class KeepEverythingExtractor
    def self.text(contents)
      doc = ::Boilerpipe::SAX::BoilerpipeHTMLParser.parse(contents)
      ::Boilerpipe::Extractors::KeepEverythingExtractor.process doc
      doc.content
    end

    def self.process(doc)
      ::Boilerpipe::Filters::MarkEverythingContentFilter.process doc
      doc
    end
  end
end

Version data entries

5 entries across 5 versions & 1 rubygems

Version	Path
boilerpipe-ruby-0.5.0	lib/boilerpipe/extractors/keep_everything_extractor.rb
boilerpipe-ruby-0.4.4	lib/boilerpipe/extractors/keep_everything_extractor.rb
boilerpipe-ruby-0.4.3	lib/boilerpipe/extractors/keep_everything_extractor.rb
boilerpipe-ruby-0.4.2	lib/boilerpipe/extractors/keep_everything_extractor.rb
boilerpipe-ruby-0.4.1	lib/boilerpipe/extractors/keep_everything_extractor.rb