Contents

 # Removes TextBlocks which have explicitly been marked as "not content".

module Boilerpipe::Filters
  class BoilerplateBlockFilter

    def initialize(label)
      @label_to_keep = label
    end
    INSTANCE_KEEP_TITLE = BoilerplateBlockFilter.new(:TITLE)

    def process(doc)
      combined = doc.text_blocks.delete_if do |tb|
        if tb.is_not_content? &&
           (@label_to_keep.nil? || !tb.has_label?(:TITLE))
          true
        else
          false
        end
      end
      doc.replace_text_blocks!(combined)
      doc
    end

  end
end

Version data entries

5 entries across 5 versions & 1 rubygems

Version	Path
boilerpipe-ruby-0.4.0	lib/boilerpipe/filters/boilerplate_block_filter.rb
boilerpipe-ruby-0.3.0	lib/boilerpipe/filters/boilerplate_block_filter.rb
boilerpipe-ruby-0.2.0	lib/boilerpipe/filters/boilerplate_block_filter.rb
boilerpipe-ruby-0.1.1	lib/boilerpipe/filters/boilerplate_block_filter.rb
boilerpipe-ruby-0.1.0	lib/boilerpipe/filters/boilerplate_block_filter.rb