inc/3rdparty/site_config/standard/dr.dk.txt

   1 title: //meta[@property='og:title']/@content
   2 author: //div[@class='articleFunctions']//a
   3 date: //meta[@name='pubdate']/@content
   4
   5 # Can you strip elements from the body only? It is required here (`//div[@class='articleContent']/p` breaks for some reason)
   6 body: //div[@class='articleContent']
   7
   8 tidy: no
   9 test_url: http://www.dr.dk/Nyheder/Udland/2011/10/24/150115.htm