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

   1 body: //div[@class='blogbody']
   2 strip: //h3[@class='title']
   3 date: //h2[@class='date']
   4 #Should Atwood just be a literal?
   5 author: substring-before( substring-after(//div[@class='posted'], 'y'), 'V')
   6
   7 # tim.kingman@... 2011-07-26
   8 # Prune:no to retain all-link ULs that are part of the body content like
   9 # http://www.codinghorror.com/blog/2011/07/building-a-pc-part-vii-rebooting.html
  10 # Then explicitly strip the "Posted By" and prev/next links that Prune:yes would have removed.
  11
  12 prune: no
  13 strip: //div[@class='posted']/following-sibling::*
  14 strip: //div[@class='posted']
  15 test_url: http://www.codinghorror.com/blog/2011/07/building-a-pc-part-vii-rebooting.html