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/csmonitor.com.txt | 32 +++++++++++----------- 1 file changed, 16 insertions(+), 16 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/csmonitor.com.txt (limited to 'inc/3rdparty/site_config/standard/csmonitor.com.txt') diff --git a/inc/3rdparty/site_config/standard/csmonitor.com.txt b/inc/3rdparty/site_config/standard/csmonitor.com.txt old mode 100644 new mode 100755 index d4dbc5c8..b482e34e --- a/inc/3rdparty/site_config/standard/csmonitor.com.txt +++ b/inc/3rdparty/site_config/standard/csmonitor.com.txt @@ -1,18 +1,18 @@ -title: //h1[contains(@class, 'head')] - -# standard page -body: //div[@id='mainColumn']//div[contains(@class, 'list-article-full')] -# print page -body: //div[@id='mainColumn'] - -author: //a[contains(@class, 'ui-author')] - -single_page_link: //div[@class='storyToolbar']//a[contains(@href, '/print/')] - -strip_id_or_class: storyToolbar -strip_id_or_class: promotion-tag - -tidy: no -prune: no +title: //h1[contains(@class, 'head')] + +# standard page +body: //div[@id='mainColumn']//div[contains(@class, 'list-article-full')] +# print page +body: //div[@id='mainColumn'] + +author: //a[contains(@class, 'ui-author')] + +single_page_link: //div[@class='storyToolbar']//a[contains(@href, '/print/')] + +strip_id_or_class: storyToolbar +strip_id_or_class: promotion-tag + +tidy: no +prune: no test_url: www.csmonitor.com/World/Middle-East/2011/1108/Imminent-Iran-nuclear-threat-A-timeline-of-warnings-since-1979/Earliest-warnings-1979-84 \ No newline at end of file -- cgit v1.2.3