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

   1 # Jens Kohl, jens.kohl@...
   2 # - Added publication date
   3 # - Striped pagination block
   4 # - Added single page link
   5 # - Added xpath-querys for the printer friendly version
   6
   7 title: //h1
   8 body: //div[@class='formatted']
   9 prune: no
  10
  11 date: substring-after(//li[2][@class="text1"], 'Datum:')
  12 strip: //ol[@class="list-chapters"]
  13 strip_comments: yes
  14
  15 # next: commands for printer friendly pages
  16 single_page_link: //a[contains(@href, 'print.php?a=')]/@href
  17 title: //body/h3
  18 strip_image_src: staticrl/images/logo.jpg
  19 strip_image_src: http://cpx.golem.de/cpx.php?class=7
  20 strip: //body/h3
  21 strip: //body/b[1]
  22 strip: //body/b[2]
  23 strip: //body/b[3]
  24 strip: //div[1]
  25 test_url: http://www.golem.de/1112/88696.html