inc/3rdparty/site_config/standard/theguardian.com.txt

   1 title: //div[@id='main-article-info']//h1
   2 body: //div[@id='article-wrapper']
   3 date: //li[@class='publication']//time[@pubdate] | //li[@class='publication']//data[@pubdate]
   4 strip: //div[contains(@class, 'email-subscription')]
   5 strip: //div[contains(@class, 'kindleWidget')]
   6 #strip: //a[not(text())]
   7 strip_id_or_class: pocket-btn
   8 author: //li[@class='byline']
   9 prune: no
  10 tidy: no
  11 test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption
  12 test_url: http://www.theguardian.com/world/2013/oct/03/edward-snowden-files-john-lanchester
  13 test_url: http://www.theguardian.com/commentisfree/2014/jun/15/britishness-search-identity-my-part-in-camerons-odyssey