updated specific configuration for parsing

1 files changed, 18 insertions, 4 deletions

diff --git a/inc/3rdparty/site_config/standard/global.txt b/inc/3rdparty/site_config/standard/global.txt
index 135ed500..71fbc934 100644..100755
--- a/inc/3rdparty/site_config/standard/global.txt
+++ b/inc/3rdparty/site_config/standard/global.txt
@@ -1,4 +1,18 @@
-# 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
\ No newline at end of file
+# 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>
\ No newline at end of file