inc/3rdparty/site_config/standard/falter.at.txt

   1 title: //h2[@class='related relatedTitle']
   2 author: //a[contains(@href, 'liste.php?author_id')]
   3
   4 # can't think of a better way unfortunately, really bad markup on this site
   5 date: substring-after(//td[@style='width:85%;'], 'vom')
   6
   7 # not sure why, but instapaper seems to suck up the teaser paragraph
   8 # not solved!
   9 body: //div[contains(@class, 'teaser')]
  10 body: //div[@id='content']
  11
  12 # cleanup
  13 strip: //img[@src='http://www.falter.at/web/_pics/falterlogo_dblau.gif']
  14 strip: //div[@class='servicebox']
  15 strip: //h1
  16 strip: //br
  17 strip: //td[@id='adcol']
  18 test_url: http://www.falter.at/web/print/detail.php?id=1634