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

   1 title: //h1
   2 author: //p[contains(@class, 'author')]/a
   3 date: //p[contains(@class, 'time')]
   4 body: //div[@class='content']/div[contains(@class, 'text')]
   5
   6 # prevent "no text" errors on multi-page articles
   7 tidy: no
   8
   9 # we use a custom next-link detector instead of the print view because
  10 # it's pretty hard to strip out the unwanted parts in the print view
  11 autodetect_next_page: no
  12 next_page_link: //div[contains(@class, 'text')]/div/div[contains(@class, 'paging')]/a[@class='more ']
  13
  14 strip: //h1
  15
  16 strip_id_or_class: meta
  17 strip_id_or_class: author
  18 strip_id_or_class: paging
  19
  20 # prevent "Report an Error" from being recognized as footnote
  21 footnotes: no
  22 test_url: http://jetzt.sueddeutsche.de/texte/anzeigen/544308/Alles-flicken