inc/3rdparty/site_config/standard/echo-online.de.txt

   1 # Author: Marvin Dickhaus <github@marvindickhaus.de>
   2 # 2014-10-08
   3
   4 #Tidy just messes up the DOM
   5 tidy: no
   6
   7 title: //h1
   8 body: //h2 | //div[@id='artikelteaser'] | //div[@id='artikeltext']
   9
  10 #Strip
  11 strip_image_src: artikel_a_merken.gif
  12 strip: //div[@class='zusatzinfo']
  13
  14 #Author: substring is used to remove the " Von " prefix.
  15 author: substring(//li[@class='artikelautor'], 5)
  16
  17 date: //li[@class='artikeldatum']
  18
  19 #The first two URLs will at some point no longer show
  20 #the full article. There is a time-based paywall
  21 #installed. Using the feed should present valid output
  22 test_url: http://www.echo-online.de/art1231,5503063
  23 test_url: http://www.echo-online.de/art1168,5502598
  24 test_url: http://www.echo-online.de/rss/darmstadt.xml