inc/3rdparty/site_config/standard/global.txt

   1 # Look for Open Graph data - http://ogp.me
   2 title: //meta[@property="og:title"]/@content
   3 date: //meta[@property="article:published_time"]/@content
   4 # article:author is someties URL, e.g. on guardian.co.uk
   5
   6 # Remove Google Publisher Tags: https://support.google.com/dfp_sb/answer/1649768?hl=en
   7 #strip_id_or_class: div-gpt-ad
   8
   9 # Strip doubleclick image ads
  10 strip_image_src: doubleclick.net
  11
  12 # If you get chunks of Javascript code appearing in the extracted output, try uncommenting the lines below.
  13 # This tries to convert script tags to hidden div elements (which Full-Text RSS removes).
  14 # If you notice issues with this approach, please let us know.
  15 #find_string: <script
  16 #replace_string: <div style="display:none"
  17 #find_string: </script>
  18 #replace_string: </div>