From ac4d114214d820b20e18518a2dbc809337e39043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 6 Dec 2013 10:13:03 +0100 Subject: [add] new specific configuration files --- .../site_config/standard/redtape.msnbc.msn.com.txt | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/redtape.msnbc.msn.com.txt (limited to 'inc/3rdparty/site_config/standard/redtape.msnbc.msn.com.txt') diff --git a/inc/3rdparty/site_config/standard/redtape.msnbc.msn.com.txt b/inc/3rdparty/site_config/standard/redtape.msnbc.msn.com.txt new file mode 100644 index 00000000..4f195a06 --- /dev/null +++ b/inc/3rdparty/site_config/standard/redtape.msnbc.msn.com.txt @@ -0,0 +1,20 @@ +# 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 \ No newline at end of file -- cgit v1.2.3