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

   1 body: //div[@class="story-body"]
   2 title: //h1[@class="story-header"]
   3 date: //span[@class="story-date"]/span[@class='date']
   4
   5 # recipes, e.g. http://www.bbc.co.uk/food/recipes/mymincepies_71055
   6 body: //div[contains(@class, 'hrecipe')]//div[@id='subcolumn-1']
   7
   8 #strip: //div[@class="story-feature narrow"]
   9 #strip: //div[@class="story-feature wide"]
  10 #strip: //div[@class="story-feature dslideshow-enclosure"]
  11 strip: //div[contains(@class, "story-feature")]
  12 strip: //span[@class="story-date"]
  13 #strip: //div[@class="caption body-narrow-width"]
  14 strip: //div[@class="warning"]//p
  15 strip: //div[@id='page-bookmark-links-head']
  16 strip: //object
  17 strip: //div[contains(@class, "bbccom_advert_placeholder")]
  18 strip: //div[contains(@class, "embedded-hyper")]
  19 strip: //div[contains(@class, 'market-data')]
  20 strip: //a[contains(@class, 'hidden')]
  21 strip: //div[contains(@class, 'hypertabs')]
  22 strip: //div[contains(@class, 'related')]
  23 strip: //form[@id='comment-form']
  24 strip: //div[contains(@class, 'comment-introduction')]
  25
  26 replace_string(<noscript>): <div>
  27 replace_string(</noscript>): </div>
  28
  29 prune: no
  30
  31 dissolve: //h2
  32 test_url: http://www.bbc.co.uk/news/business-15060862