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/truthdig.com.txt | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/truthdig.com.txt (limited to 'inc/3rdparty/site_config/standard/truthdig.com.txt') diff --git a/inc/3rdparty/site_config/standard/truthdig.com.txt b/inc/3rdparty/site_config/standard/truthdig.com.txt old mode 100644 new mode 100755 index e7c1a4bc..9e0663b0 --- a/inc/3rdparty/site_config/standard/truthdig.com.txt +++ b/inc/3rdparty/site_config/standard/truthdig.com.txt @@ -1,10 +1,12 @@ -title: //div[@class='printbody']/h1 -body: //div[@class='printbody'] -prune: no - -strip: //div[@class='printbody']/a[@href='http://www.truthdig.com/'] -strip: //table[@class='footer'] - -single_page_link: //div[@class='article_tools']//a[contains(@href, '/print/')] - -test_url: http://www.truthdig.com/report/item/the_election_march_of_the_trolls_20110829/ \ No newline at end of file +title: //div[@class='printbody']/h1 +body: //div[@class='printbody'] +prune: no + +strip: //div[@class='printbody']/a[@href='http://www.truthdig.com/'] +strip: //table[@class='footer'] +strip: //h6[contains(., 'http://')] + +single_page_link: //a[contains(@href, '/print/')] + +test_url: http://www.truthdig.com/report/item/the_election_march_of_the_trolls_20110829/ +test_url: http://www.truthdig.com/dig/item/the_death_of_truth_20130505/ \ No newline at end of file -- cgit v1.2.3