From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- .../site_config/standard/redtape.msnbc.msn.com.txt | 36 +++++++++++----------- 1 file changed, 18 insertions(+), 18 deletions(-) mode change 100644 => 100755 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 old mode 100644 new mode 100755 index 4f195a06..8541a0d4 --- a/inc/3rdparty/site_config/standard/redtape.msnbc.msn.com.txt +++ b/inc/3rdparty/site_config/standard/redtape.msnbc.msn.com.txt @@ -1,20 +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'] +# 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