wallabag/inc/3rdparty/site_config/standard/dr.dk.txt
2013-12-06 10:13:03 +01:00

9 lines
No EOL
371 B
Text

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