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

   1 title: //title
   2 author: //div[@id='byline']
   3
   4 date: //div[contains(@class,'timestamp')]/abbr/text()
   5
   6 body: //div[@id='intellitTXT']
   7
   8 strip: //div[@id='byline']
   9 strip: //div[contains(@class,'timestamp')]
  10 strip: //div[contains(@class, 'ad-label')]
  11 strip: //div[contains(@class, 'ad-break')]
  12 strip: //span[contains(@class, 'x-video')]
  13 strip: //span[contains(@class, 'inline')]
  14 strip: //div[contains(@class, 'video')]
  15 strip: //div[contains(@class, 'discuss')]
  16 strip: //div[@id='most-popular']
  17 strip: //div[contains(@class,'drawer')]
  18 strip: //*[contains(@class, 'hide')]
  19
  20 footnotes: no
  21 test_url: http://www.msnbc.msn.com/id/44748412/ns/business-world_business/#.TolUv-vfDbE