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

   1 # Works with old posts too, such as http://www.joelonsoftware.com/articles/fog0000000332.html
   2
   3 author: substring-after(//div[@class="author"], 'by ')
   4 date: //div[@class="date"]
   5
   6 ## Clean stuff at top ##
   7
   8 strip: //h1[1]
   9 strip: //h2[1]
  10 strip: //div[@class="date"]
  11 strip: //div[@class="author"]
  12
  13 ## Clean stuff at bottom ##
  14
  15 strip: //blockquote[@class="textmessage"]
  16 strip: //div[@style="width:500px"]/p[last()]
  17 strip: //div[@style="width:500px"]/p[last()-1]
  18 strip: //div[@style="width:500px"]/h4[last()]
  19 strip: //div[@style="width:500px"]/h4[last()-1]
  20 strip: //div[@style="width:500px"]/div[last()]
  21 test_url: http://www.joelonsoftware.com/items/2011/09/15.html