blob: d8ec1acf1bc15f58c110fdff508a2df4f3d2fc36 (
plain) (
tree)
|
|
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
|