wallabag/inc/3rdparty/site_config/standard/menshealth.com.txt
2014-07-13 10:15:40 +02:00

16 lines
No EOL
592 B
Text
Executable file

# need to find a way to eliminate <span> 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