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

   1 # 2012-12-04: complete rewrite after Süddeutsche.de relaunch - carlo@...
   2
   3 single_page_link: //a[ contains( @href, "/2.220/" ) ]
   4
   5 body: //article[@id="sitecontent"]/section[@class="body"]
   6 author: //address[@class="author"]
   7 date: //div[@class="header"]//h1//span[@class="updated"]
   8 wrap_in(small): //div[@class="footer"]
   9 wrap_in(i): //figcaption/h3
  10 dissolve: //figcaption//h3
  11 dissolve: //figure/div[@class="body"]
  12 dissolve: //figure/a
  13
  14 strip: //figure[ not( contains(@class, "zoomimage" ) ) ]
  15 strip: //div[@data-onlineonly="true"]
  16 strip: //address[@class="author"]
  17
  18 test_url: http://www.sueddeutsche.de/muenchen/mietshaus-am-gaertnerplatz-alles-muss-raus-1.1556693