inc/3rdparty/site_config/standard/redtape.msnbc.msn.com.txt

   1 # Think there might be something up with your parser that it strips out 'print' from the title :)
   2
   3 title: //meta[@name='title']/@content
   4 author: //meta[@name='author']/@content
   5 date: //meta[@name='date']/@content
   6
   7 body: //div[@class='articleText']
   8
   9 strip: //div[contains(@class, 'day')]
  10 strip: //div[contains(@class, 'month')]
  11 strip: //div[contains(@class, 'year')]
  12 strip: //div[contains(@class, 'time')]
  13 strip: //h1[@class='gl_headline']
  14 strip: //div[@class='byline']
  15 strip: //div[@id='left_ear']
  16 strip: //div[@id='right_ear']
  17 strip: //div[contains(@class, 'PopularPosts')]
  18 strip ://div[@class='discuss_page_break']
  19 strip ://div[contains(@class, 'p-content_TagList')]
  20 test_url: http://redtape.msnbc.msn.com/_news/2011/09/28/8020661-sprint-raises-fee-but-wont-free-users-from-two-year-contracts?preview=true