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/appleinsider.com.txt | 34 +++++++++++++++------- 1 file changed, 23 insertions(+), 11 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/appleinsider.com.txt (limited to 'inc/3rdparty/site_config/standard/appleinsider.com.txt') diff --git a/inc/3rdparty/site_config/standard/appleinsider.com.txt b/inc/3rdparty/site_config/standard/appleinsider.com.txt old mode 100644 new mode 100755 index 279fbce1..5ae1050b --- a/inc/3rdparty/site_config/standard/appleinsider.com.txt +++ b/inc/3rdparty/site_config/standard/appleinsider.com.txt @@ -1,11 +1,23 @@ -title: //p[@class='title'] - -author: //p[text() = 'By ']/a/text() -strip: //p[text() = 'By '] - -body: //td[@class='bod'] -strip_id_or_class: title -strip_id_or_class: minor - -strip_id_or_class: multipagefooter -test_url: http://www.appleinsider.com/articles/12/02/29/inside_os_x_108_mountain_lion_safari_52_gets_a_simplified_user_interface_with_new_sharing_features.html \ No newline at end of file +title: //h1[@class="art-head"] + +author: //p[contains(@class, 'byline')]/a +#author: //p[text() = 'By ']/a/text() +#strip: //p[text() = 'By '] + +date: //p[contains(@class, 'date-header')] + +body: //div[@class="article"] +strip_id_or_class: lazy +#strip_id_or_class: minor +strip_id_or_class: multipagefooter +strip_id_or_class: date-header +strip_id_or_class: byline + +find_string: