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

   1 title: //h1
   2 date: //div[@class='datum']
   3 single_page_link: //a[contains(@href, '?type=99')]
   4
   5 # this hack preserves the intro text, because it would be striped otherwise if the title is set to //h1
   6 dissolve: //div[@class='artikelMeldung']
   7
   8
   9 strip_id_or_class: anzeige
  10 strip_id_or_class: top_page_navigation
  11 strip_id_or_class: cr_image_container
  12 strip_id_or_class: cr_image_reference
  13 strip_id_or_class: cr_image_icon
  14 strip_id_or_class: _close_txt
  15 strip_id_or_class: _close_ico
  16 strip_id_or_class: clearer
  17
  18 strip://h1
  19 strip://h6
  20 strip://div[contains(@id, 'plista')]
  21 strip://img[contains(@id,'tiny')]
  22 strip://img[@class='cr_image']
  23
  24 # strip url at the top
  25 strip: //p[@style='font-size: 10px;']
  26
  27 test_url: http://www.elektroniknet.de/automotive/technik-know-how/sicherheitselektronik/article/87717/0/Besser_als_die_Wirklichkeit/