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

   1 title://div[contains(@class, "article")]/h1
   2 body://div[contains(@class,"story-text")]
   3
   4 # Why doesn't this work? next_page_link://ul[contains(@class,"pagination")]/li/a[@rel="next"]
   5
   6 next_page_link://ul[contains(@class,"pagination")]/li[contains(@class, "current")]/following-sibling::node()/a
   7 date://meta[@name="publish_date"]/@content
   8
   9 strip://div[contains(@class, "breadcrumbs")]
  10 strip://a[contains(@class, "hidden")]
  11 strip://div[contains(@class, "story-embed")]
  12 strip://div[contains(@class, "story-text")]//p/a[contains(text(), "Also on POLITICO:")]/..
  13 test_url: http://www.politico.com/news/stories/0712/78105.html