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

   1 title: //meta[@property="og:title"]/@content
   2 body: //div[img[starts-with(@id, 'img_caption')]] | //div[@class="big_photo"] | //div[contains(@class, 'entry_body_text')]
   3 date: //meta[@name="publish_date"]/@content
   4 author: //a[@rel="author"]
   5 author: //meta[@name="author"]/@content
   6
   7 prune: no
   8 tidy: no
   9
  10 strip: //footer
  11 strip_id_or_class: ps-slideshow
  12 strip_id_or_class: fs-slideshow
  13 strip: //p[contains(., 'Related on HuffPost:')]
  14 strip_id_or_class: contribute-story
  15 strip_id_or_class: promo_holder
  16
  17 # end early
  18 replace_string(<div class="sbm-main): </body></html><div class="not-interested
  19
  20 test_url: http://www.huffingtonpost.com/mitch-moxley/tracking-beijings-boom-th_b_1209828.html
  21 test_url: http://www.huffingtonpost.com/2012/09/11/president-obama-iphone-throwdown_n_1873826.html