inc/3rdparty/site_config/standard/mainpost.de.txt

   1 title: substring-before(//title, '|')
   2 body: //*[@id='content-left']
   3
   4 # Why is this not working here?
   5 # body: //*[@id='content-left']/div[@class='content-container'][2]/div[@class='content-body']/div[@class='inner-container']/div[@class='detail']
   6
   7
   8 #Header
   9 strip_id_or_class: 'subHead'
  10 strip_id_or_class: 'fl_right'
  11 strip_id_or_class: 'infolink'
  12 strip_id_or_class: 'content-head'
  13 strip_id_or_class: 'tab'
  14 strip_id_or_class: 'tab-active'
  15 strip: //*[contains(@class,'trenner')]
  16
  17 # Headline
  18 strip: //h1/*
  19 strip_id_or_class: 'font16'
  20
  21 #Images
  22 strip_id_or_class: 'leftimage'
  23 strip_id_or_class: 'rightimage'
  24
  25 #Comments
  26 strip: //table
  27 strip: //p/following-sibling::*[0]
  28 test_url: http://www.mainpost.de/ueberregional/meinung/Dioxin-Skandal-bringt-Agrarministerin-in-Bedraengnis;art9517,5920211