inc/3rdparty/site_config/standard/benoitmaison.org.txt

   1 body: //div[@class="entry-content"]
   2
   3 # Remove text &lsquo;Tweet&rsquo;
   4 strip: //div[@class="entry-content"]/div[last()]
   5
   6 title: h1[@class="entry-title"]
   7
   8 # If the Instapaper text parser worked with HTML5 tags, we would use:
   9 date: //time[@class="entry-date"]
  10
  11 # But since it does not, use this more complicated rule:
  12 date: //div[@class="entry-meta"]/a[@rel="bookmark"]
  13
  14 # Unfortunately, the following rule is overridden by the automatically found author.
  15 author: ("Benoit Maison")
  16 test_url: http://www.benoitmaison.org/2011/12/06/why-siri-had-to-start-in-beta/