inc/3rdparty/site_config/standard/theglobalmail.org.txt

   1 title: //h1[@id="headline"]
   2 author: //div[contains(@class, "editorial-byline-author")]/a
   3 date: substring-after(//div[contains(@class, "editorial-byline-meta")], " | ")
   4
   5 # The article body contains a mix or article and non-article elements, so lot of manual tweaks are needed
   6 body: //div[@id="template"]
   7 strip_id_or_class: editorial-byline-pic
   8 strip_id_or_class: editorial-byline
   9 strip_id_or_class: headline
  10
  11 # Include the leadin paragraph in the body text, but remove quotes because they're out of context
  12 dissolve: //div[contains(@id, "leadin")]
  13 strip_id_or_class: pullquote
  14
  15 # Image captions removed because they're confusing in body text
  16 strip_id_or_class: image-caption-content
  17
  18 # Remove header and footer
  19 strip_id_or_class: header
  20 strip_id_or_class: footer
  21
  22 # Remove the hidden logo that seems to be used to cause Facebook to show the logo instead of a random article image
  23 strip: /html/body/span[contains(@style, "display: none")]
  24
  25 # Remove search box
  26 strip_id_or_class: searchContainer
  27 strip: //div[contains(@class, "searchInstruction")]
  28 strip: //div[contains(@class, "searchResults")]/h4
  29
  30 # Remove the 'Letters to the Editor' section
  31 strip_id_or_class: letter-text
  32 strip_id_or_class: letter-from
  33 strip_id_or_class: letter-date
  34
  35 # Remove Like/Tweet links
  36 strip_id_or_class: social-tab
  37
  38 # Remove 'divider' which causes an inexplicable slash to appear in the article body
  39 strip_id_or_class: divider
  40
  41 test_url: http://www.theglobalmail.org/feature/tiramisu-time-in-pyongyang/88/