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 native_ad_clue: //meta[@property="article:tag" and contains(@content, "Partner zone")]
  10 native_ad_clue: //meta[@property="video:tag" and contains(@content, "Partner zone")]
  11 prune: no
  12 tidy: no
  13
  14 test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption
  15 test_contains: The National Security Agency has made repeated attempts to develop
  16 test_contains: The agency did not directly address those questions, instead providing a statement.
  17
  18 test_url: http://www.theguardian.com/world/2013/oct/03/edward-snowden-files-john-lanchester
  19 test_contains: In August, the editor of the Guardian rang me up and asked if I would spend a week in New York
  20 test_contains: As the second most senior judge in the country, Lord Hoffmann, said in 2004 about a previous version of our anti-terrorism laws
  21
  22 test_url: http://www.theguardian.com/commentisfree/2014/jun/15/britishness-search-identity-my-part-in-camerons-odyssey
  23 # Native ad
  24 test_url: http://www.theguardian.com/sustainable-business/2014/jul/18/ben-jerry-turn-ice-cream-into-energy