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 --- inc/3rdparty/site_config/standard/aljazeera.com.txt | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/aljazeera.com.txt (limited to 'inc/3rdparty/site_config/standard/aljazeera.com.txt') diff --git a/inc/3rdparty/site_config/standard/aljazeera.com.txt b/inc/3rdparty/site_config/standard/aljazeera.com.txt old mode 100644 new mode 100755 index 4f0148f4..d3bf4014 --- a/inc/3rdparty/site_config/standard/aljazeera.com.txt +++ b/inc/3rdparty/site_config/standard/aljazeera.com.txt @@ -1,8 +1,8 @@ -title: //span[@id='DetailedTitle'] -body: //td[@id='tdTextContent'] -strip_id_or_class: Skyscrapper_Body -date: //span[@id='ctl00_cphBody_lblDate'] -author: //div[@id="dvAuthorInfo"]//a/text() -strip: //table[ tbody/tr/td/object ] -prune: no +title: //span[@id='DetailedTitle'] +body: //td[@id='tdTextContent'] +strip_id_or_class: Skyscrapper_Body +date: //span[@id='ctl00_cphBody_lblDate'] +author: //div[@id="dvAuthorInfo"]//a/text() +strip: //table[ tbody/tr/td/object ] +prune: no test_url: http://www.aljazeera.com/indepth/opinion/2012/01/2012114121925380575.html \ No newline at end of file -- cgit v1.2.3