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

   1 # fforst@...
   2
   3 # Use link to print article for single page view
   4 single_page_link: //a[@class="print"]
   5
   6 # set body
   7 tidy: no
   8 body: //div[@class='artikel-content']
   9
  10 # strip title and subtitle since we got it already
  11 strip: //div[@class='issue']
  12 strip: //div[@class='artikel-content']/h2
  13
  14 # some authors are known and have a link, others don't
  15 author: //a[contains(@href, 'autor?')]
  16
  17 #date
  18 date: //span[@class='article-date']
  19
  20 # Strip author since we got him
  21 strip_id_or_class: author
  22
  23 #strip captions
  24 strip_id_or_class: field-name-field-image-credit
  25 strip_id_or_class: field-name-field-article-image-subtitle
  26
  27 # remove community functions
  28 strip: //div[@class='meta']
  29 strip: //div[@id='comments']
  30
  31 # remove "continue on the next page" text
  32 strip: //p[text()="[SEITE]"]
  33 test_url: http://www.cicero.de/weltbuehne/ihre-wut-ist-global-krise-jugend-revolten-aufstaende-zelte/43049