From ac4d114214d820b20e18518a2dbc809337e39043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 6 Dec 2013 10:13:03 +0100 Subject: [add] new specific configuration files --- inc/3rdparty/site_config/standard/menshealth.com.txt | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 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 new file mode 100644 index 00000000..e7e1e269 --- /dev/null +++ b/inc/3rdparty/site_config/standard/menshealth.com.txt @@ -0,0 +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')] +test_url: http://www.menshealth.com/mhlists/pursuit_of_happiness/index.php \ No newline at end of file -- cgit v1.2.3