inc/3rdparty/site_config/standard/bbc.co.uk.txt

   1 body: //div[@class="story-body"]
   2 # for video entries
   3 body: //div[contains(@class, "videoInStory") or @id="meta-information"]
   4 title: //h1[@class="story-header"]
   5 date: //span[@class="story-date"]/span[@class='date']
   6 # for sport site
   7 date: //meta[@name='DCTERMS.created']/@content
   8 author: //div[@id='headline']//span[@class='byline-name']
   9
  10 # recipes, e.g. http://www.bbc.co.uk/food/recipes/mymincepies_71055
  11 body: //div[contains(@class, 'hrecipe')]//div[@id='subcolumn-1']
  12
  13 #strip: //div[@class="story-feature narrow"]
  14 #strip: //div[@class="story-feature wide"]
  15 #strip: //div[@class="story-feature dslideshow-enclosure"]
  16 strip: //div[contains(@class, "story-feature")]
  17 strip: //span[@class="story-date"]
  18 #strip: //div[@class="caption body-narrow-width"]
  19 strip: //div[@class="warning"]//p
  20 strip: //div[@id='page-bookmark-links-head']
  21 strip: //object
  22 strip: //div[contains(@class, "bbccom_advert_placeholder")]
  23 strip: //div[contains(@class, "embedded-hyper")]
  24 strip: //div[contains(@class, 'market-data')]
  25 strip: //a[contains(@class, 'hidden')]
  26 strip: //div[contains(@class, 'hypertabs')]
  27 strip: //div[contains(@class, 'related')]
  28 strip: //form[@id='comment-form']
  29 strip: //div[contains(@class, 'comment-introduction')]
  30 strip: //div[contains(@class, 'share-tools')]
  31 strip: //div[@id='also-related-links']
  32
  33 replace_string(<noscript>): <div>
  34 replace_string(</noscript>): </div>
  35
  36 prune: no
  37
  38 dissolve: //h2
  39 test_url: http://www.bbc.co.uk/sport/0/football/23224017
  40 test_url: http://www.bbc.co.uk/news/business-15060862
  41 # video entry
  42 test_url: http://www.bbc.co.uk/news/world-asia-22056933