class Boilerpipe::Extractors::KeepEverythingExtractor

Public Class Methods

process(doc) click to toggle source
# File lib/boilerpipe/extractors/keep_everything_extractor.rb, line 11
def self.process(doc)
  ::Boilerpipe::Filters::MarkEverythingContentFilter.process doc
  doc
end
text(contents) click to toggle source
# File lib/boilerpipe/extractors/keep_everything_extractor.rb, line 5
def self.text(contents)
  doc = ::Boilerpipe::SAX::BoilerpipeHTMLParser.parse(contents)
  ::Boilerpipe::Extractors::KeepEverythingExtractor.process doc
  doc.content
end