inc/3rdparty/site_config/standard/uni-watch.com.txt

   1 author: substring-before(substring-after(//div[@class='post-byline'], 'By '), ', on')
   2 date: substring-after(//div[@class='post-byline'], ', on')
   3
   4 # for some reason, the following is producing a "no text [48]" error
   5 #title: //div[@class='post-headline']
   6
   7 # for some reason, the following doesn't appear to isolate just the body copy
   8 body: //div[@class='post-bodycopy']
   9
  10 # we solve the above issue by stripping out everything else we don't want
  11 # these can probably all be removed if the body: command above worked
  12 strip_id_or_class: reply
  13 strip_id_or_class: left
  14 strip_id_or_class: post-headline
  15 strip_id_or_class: post-byline
  16 strip_id_or_class: footer
  17 test_url: http://www.uni-watch.com/2011/10/18/the-curious-case-of-steve-debergs-microphone-and-speaker/