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

   1 # Seems to be redirecting to articles.washingtonpost.com for many users
   2
   3 body: //div[contains(@class, "article_body")]
   4 # print view
   5 body: //div[@id='print_facet']//div[@id='body']
   6
   7 author://meta[@name='DC.creator']/@content
   8 title://meta[@name='title']/@content
   9 date://div[contains(@class,'byline')]//span[contains(@class,'published')]/@title
  10 date://meta[@name="DC.date.issued"]/@content
  11 strip://div[@class="relative primary-slot padding-top img-border gallery-container photo-wrapper"]
  12 strip://div[@id="wp-column six end"]
  13 strip://div[contains(@class,'hidden')]
  14 strip://div[@id='article-side-rail']
  15 strip://div[@class="module component todays-paper-module curved"]
  16 strip://div[@class="module component live-qa curved img-border"]
  17 strip://div[@class="module component newsletter-signup curved"]
  18 strip://div[@class="module featured-stories component curved img-border"]
  19
  20 strip_id_or_class: carousel
  21 strip_id_or_class: toolbar
  22 strip_id_or_class: module
  23
  24 # Change gJQAwdJG4U_story.html to gJQAwdJG4U_print.html
  25 single_page_link: concat(substring-before(//link[@rel="canonical"]/@href, "_story.html"), "_print.html")
  26
  27 # [OLD] Change gJQAwdJG4U_story.html to gJQAwdJG4U_story_print.html
  28 #single_page_link: concat(substring-before(//link[@rel="canonical"]/@href, "_story.html"), "_story_print.html")
  29
  30 test_url: http://www.washingtonpost.com/world/europe/in-europe-new-fears-of-german-might/2011/10/19/gIQA3baZ7L_story.html?hpid=z1
  31 test_url: http://www.washingtonpost.com/national/health-science/radical-theory-of-first-americans-places-stone-age-europeans-in-delmarva-20000-years-ago/2012/02/28/gIQA4mriiR_story.html
  32 test_url: http://www.washingtonpost.com/lifestyle/magazine/the-sorry-fate-of-a-tech-pioneer-halsey-minor-and-historic-virginia-estate-carters-grove/2012/05/30/gJQAwdJG4U_story.html