inc/3rdparty/site_config/standard/menshealth.com.txt

   1 # need to find a way to eliminate <span> content for "related content" without eliminating important content
   2
   3 convert_double_br_tags: [yes]
   4 #body: //div[@id='leftside']
   5 title: //h1
   6 title: //h2
   7 Author: substring-after(//h4, 'By ')
   8 Author: substring-after(//h4, 'By: ')
   9 #Strip: //span
  10 strip_id_or_class: morefromcat
  11 strip_id_or_class: mostpopular
  12 strip_id_or_class: articlepagination
  13 strip_id_or_class: toolbar
  14 body: //div[@id='zmodcontent']
  15 single_page_link: //li[@class='onepage'] //a[contains (@href, 'printer.php')]
  16 test_url: http://www.menshealth.com/mhlists/pursuit_of_happiness/index.php