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/msnbc.msn.com.txt | 38 +++++++++++----------- 1 file changed, 19 insertions(+), 19 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/msnbc.msn.com.txt (limited to 'inc/3rdparty/site_config/standard/msnbc.msn.com.txt') diff --git a/inc/3rdparty/site_config/standard/msnbc.msn.com.txt b/inc/3rdparty/site_config/standard/msnbc.msn.com.txt old mode 100644 new mode 100755 index ad89cda8..f008d2d1 --- a/inc/3rdparty/site_config/standard/msnbc.msn.com.txt +++ b/inc/3rdparty/site_config/standard/msnbc.msn.com.txt @@ -1,21 +1,21 @@ -title: //title -author: //div[@id='byline'] - -date: //div[contains(@class,'timestamp')]/abbr/text() - -body: //div[@id='intellitTXT'] - -strip: //div[@id='byline'] -strip: //div[contains(@class,'timestamp')] -strip: //div[contains(@class, 'ad-label')] -strip: //div[contains(@class, 'ad-break')] -strip: //span[contains(@class, 'x-video')] -strip: //span[contains(@class, 'inline')] -strip: //div[contains(@class, 'video')] -strip: //div[contains(@class, 'discuss')] -strip: //div[@id='most-popular'] -strip: //div[contains(@class,'drawer')] -strip: //*[contains(@class, 'hide')] - +title: //title +author: //div[@id='byline'] + +date: //div[contains(@class,'timestamp')]/abbr/text() + +body: //div[@id='intellitTXT'] + +strip: //div[@id='byline'] +strip: //div[contains(@class,'timestamp')] +strip: //div[contains(@class, 'ad-label')] +strip: //div[contains(@class, 'ad-break')] +strip: //span[contains(@class, 'x-video')] +strip: //span[contains(@class, 'inline')] +strip: //div[contains(@class, 'video')] +strip: //div[contains(@class, 'discuss')] +strip: //div[@id='most-popular'] +strip: //div[contains(@class,'drawer')] +strip: //*[contains(@class, 'hide')] + footnotes: no test_url: http://www.msnbc.msn.com/id/44748412/ns/business-world_business/#.TolUv-vfDbE \ No newline at end of file -- cgit v1.2.3