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

   1 title://div[@class="article-title"]/h1[@class="title"]
   2 date: //p[@class="article-date"]
   3 body://div[contains(@class, "article-body")]
   4 # Trim out related posts at bottom of article
   5 strip://blockquote[@class="memo"]
   6
   7 tidy: no
   8
   9 # Yup, no idea why author won't work...
  10 author://div[@class="page-header article-header clearfix"]/p[@class="title"]
  11 # [Marco:] Author won't work here because the page defines the "home" link under the author's name as rel="author", which always gets priority if the page has defined it.
  12 test_url: http://allthingsd.com/20120513/exclusive-yahoos-thompson-out-levinsohn-in-board-settlement-with-loeb-nears-completion/
  13 test_url: http://allthingsd.com/20131010/google-cio-ben-fried-on-how-google-works/