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

   1 title://h1[1]
   2
   3 author: substring-after(//em, 'Von ')
   4 author:string('tagesschau.de')
   5
   6 date:substring-after(//div[@class='standDatum'], 'Stand: ')
   7
   8 body://div[contains(@class, 'article')] | //div[contains(@class, 'centerCol')]
   9
  10 strip://h1[1]
  11 strip: //div[contains(@class, 'directLinks')]
  12 strip: //div[contains(@class, 'zitatBox')]
  13 strip: //div[contains(@class, 'teaserBox metaBlock')]
  14 strip: //*[contains(@class, 'inv')]
  15 strip: //span[@class='imgSubline']
  16 strip: //*[contains(@class, 'topline')][1]
  17 strip: //div[@id='rightCol'][1]
  18 strip: //div[@id="footer"][1]
  19 strip: //div[@class="fPlayer"]
  20 strip: //div[@id='seitenanfang']
  21 strip: //div[@class='standDatum']
  22 strip: //em
  23 test_url: http://www.tagesschau.de/ausland/wahlkampffrankreich102.html