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

   1 date: //meta[@name="published"]/@content
   2 date: //div[@class="timeLine"]
   3 title: //div[@id='contentBody']//h1
   4 author: //dl[@class="storyBlogByline"]/dd/a
   5 body: //div[@id='storyMediaBox'] | //div[contains(@class, 'storyText')]
   6
   7 # Content Pruning
   8 strip: //div[@class="scrollingArrows"]
   9 strip: //div[@class="timeLine"]
  10 strip: //dl[@class="storyBlogByline"]
  11
  12 prune: no
  13
  14 test_url: http://www.cbsnews.com/8301-201_162-57366361/rescued-americans-dad-proud-of-the-u.s/