class Boilerpipe::Extractors::ArticleSentenceExtractor

Public Class Methods

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