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

   1 # 2014-10-21 [Marmo] added stripping of inline ads and appropriate test_url
   2 # 2013.10.30 [rezor92] fixed single_page_link
   3 # 2012-12-23 [carlo@...] fixed half-assed headlines in articles, removed inline author profiles, adjusted picture captions
   4 # 2012-03-17 [dkless@...] Cut metadata parts in the beginning and the ends of the content block; copyright entries for pictures removed; Author fixed, not sure if old entries still valid (I left them); Weird problems with some pages addressed (see last section for removing hidden section)
   5 # 2011-12-09 [carlo@...] Removed "related articles" block
   6 # 2011-08-23 [carlo@...] changed single page link to use print version: page works better, less ambiguity. Related cleanups and simplifications.
   7 # 2011-08-20 [carlo@...] added author, fixed date
   8
   9
  10 single_page_link: //a[@title='Auf einer Seite']
  11 tidy: no
  12
  13 title: //title
  14 date: substring-before( //li[@class="date"], " " )
  15 author: //li[@class="author"]/a/text() | //li[@class="author first"]/a/text()
  16 author: substring-after(//li[@class='source first '], 'Quelle: ')
  17
  18 strip_id_or_class: articleheader
  19 strip: //div[@id="comments"] | //div[@class="pagination block"] | //p[@class="ressortbacklink"] | //div[@id="relatedArticles"]  |  // div[@class="inline portrait"]
  20 #Remove inline ads
  21 strip: //div[@class="innerad"]
  22
  23 #Removes author and date from the start
  24 strip: //ul[@class="tools"]
  25 #Removes copyright statement - often disturb as first line of the news
  26 strip: //p[@class="copyright"]
  27 strip: //div[@class="copyright"]
  28 #Removes pagination links at the end
  29 strip: //div[@class="pagination"]
  30
  31 # Fix picture captions
  32 wrap_in(small): //p[@class="caption"]/text()
  33
  34 # Fix sub-headlines
  35 wrap_in(h2): //p/strong
  36 dissolve: //h2/strong
  37
  38 #Sometimes things are embedded in the print version that are not displayed on the web, but will be displayed in the mobilized versions and lead even to problems. These sections are removed here.
  39 strip_id_or_class:"informatives"
  40 strip_id_or_class:"bottom"
  41 strip_id_or_class:"teasermosaic"
  42 strip_id_or_class:"comments"
  43 strip_id_or_class:"articlefooter af"
  44 strip_id_or_class:"relateds"
  45 strip_id_or_class:"pagination"
  46
  47 footnotes: no
  48 test_url: http://www.zeit.de/kultur/film/2012-12/Kurzfilmtag
  49 test_url: http://www.zeit.de/wissen/2014-10/ebola-nigeria-who