wallabag/inc/3rdparty/site_config/standard/redtape.msnbc.msn.com.txt
2013-12-06 10:13:03 +01:00

20 lines
No EOL
825 B
Text

# Think there might be something up with your parser that it strips out 'print' from the title :)
title: //meta[@name='title']/@content
author: //meta[@name='author']/@content
date: //meta[@name='date']/@content
body: //div[@class='articleText']
strip: //div[contains(@class, 'day')]
strip: //div[contains(@class, 'month')]
strip: //div[contains(@class, 'year')]
strip: //div[contains(@class, 'time')]
strip: //h1[@class='gl_headline']
strip: //div[@class='byline']
strip: //div[@id='left_ear']
strip: //div[@id='right_ear']
strip: //div[contains(@class, 'PopularPosts')]
strip ://div[@class='discuss_page_break']
strip ://div[contains(@class, 'p-content_TagList')]
test_url: http://redtape.msnbc.msn.com/_news/2011/09/28/8020661-sprint-raises-fee-but-wont-free-users-from-two-year-contracts?preview=true