2014-07-13 08:15:40 +00:00
|
|
|
# Look for Open Graph data - http://ogp.me
|
|
|
|
|
title: //meta[@property="og:title"]/@content
|
|
|
|
|
date: //meta[@property="article:published_time"]/@content
|
|
|
|
|
# article:author is someties URL, e.g. on guardian.co.uk
|
|
|
|
|
|
|
|
|
|
# Remove Google Publisher Tags: https://support.google.com/dfp_sb/answer/1649768?hl=en
|
|
|
|
|
#strip_id_or_class: div-gpt-ad
|
|
|
|
|
|
|
|
|
|
# Strip doubleclick image ads
|
|
|
|
|
strip_image_src: doubleclick.net
|
|
|
|
|
|
|
|
|
|
# If you get chunks of Javascript code appearing in the extracted output, try uncommenting the lines below.
|
|
|
|
|
# This tries to convert script tags to hidden div elements (which Full-Text RSS removes).
|
|
|
|
|
# If you notice issues with this approach, please let us know.
|
|
|
|
|
#find_string: <script
|
|
|
|
|
#replace_string: <div style="display:none"
|
|
|
|
|
#find_string: </script>
|
|
|
|
|
#replace_string: </div>
|
