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/menshealth.com.txt | 30 +++++++++++----------- 1 file changed, 15 insertions(+), 15 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/menshealth.com.txt (limited to 'inc/3rdparty/site_config/standard/menshealth.com.txt') diff --git a/inc/3rdparty/site_config/standard/menshealth.com.txt b/inc/3rdparty/site_config/standard/menshealth.com.txt old mode 100644 new mode 100755 index e7e1e269..a1a46f63 --- a/inc/3rdparty/site_config/standard/menshealth.com.txt +++ b/inc/3rdparty/site_config/standard/menshealth.com.txt @@ -1,16 +1,16 @@ -# need to find a way to eliminate content for "related content" without eliminating important content - -convert_double_br_tags: [yes] -#body: //div[@id='leftside'] -title: //h1 -title: //h2 -Author: substring-after(//h4, 'By ') -Author: substring-after(//h4, 'By: ') -#Strip: //span -strip_id_or_class: morefromcat -strip_id_or_class: mostpopular -strip_id_or_class: articlepagination -strip_id_or_class: toolbar -body: //div[@id='zmodcontent'] -single_page_link: //li[@class='onepage'] //a[contains (@href, 'printer.php')] +# need to find a way to eliminate content for "related content" without eliminating important content + +convert_double_br_tags: [yes] +#body: //div[@id='leftside'] +title: //h1 +title: //h2 +Author: substring-after(//h4, 'By ') +Author: substring-after(//h4, 'By: ') +#Strip: //span +strip_id_or_class: morefromcat +strip_id_or_class: mostpopular +strip_id_or_class: articlepagination +strip_id_or_class: toolbar +body: //div[@id='zmodcontent'] +single_page_link: //li[@class='onepage'] //a[contains (@href, 'printer.php')] test_url: http://www.menshealth.com/mhlists/pursuit_of_happiness/index.php \ No newline at end of file -- cgit v1.2.3