sfeed

commit affe5b6b64d57e56eb14132fa67c8f9e3800af6c
parent 1b14e601434435f48dfe1027a117c2af3dac325b
Author: Hiltjo Posthuma <hiltjo@codemadness.org>
Date:   Thu, 25 Jun 2020 19:50:43 +0200

README: small tweaks and a filter example improvement

This is a "quick&dirty" regex to block some of the typical 1px width or height
tracking pixels.

Diffstat:
M
README
 | 
7
+++++--

1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/README b/README
@@ -115,7 +115,7 @@ OS tested
 - DragonFlyBSD
 - Windows (cygwin gcc, mingw).
 - HaikuOS (using libbsd).
-- FreeDOS (djgpp)
+- FreeDOS (djgpp).
 
 
 Architectures tested
@@ -140,7 +140,7 @@ sfeed_plain       - Format feed data (TSV) to a plain-text list.
 sfeed_twtxt       - Format feed data (TSV) to a twtxt feed.
 sfeed_update      - Update feeds and merge items.
 sfeed_web         - Find urls to RSS/Atom feed from a webpage.
-sfeed_xmlenc      - Detect character-set encoding from XML stream.
+sfeed_xmlenc      - Detect character-set encoding from a XML stream.
 sfeedrc.example   - Example config file. Can be copied to $HOME/.sfeed/sfeedrc.
 style.css         - Example stylesheet to use with sfeed_html(1) and
                     sfeed_frames(1).
@@ -303,6 +303,9 @@ advertisements, strip tracking parameters and more.
 				$3 = filterlink($3); # link
 				$8 = filterlink($8); # enclosure
 
+				# try to remove tracking pixels: <img/> tags with 1px width or height.
+				gsub("<img[^>]*(width|height)[\s]*=[\s]*[\"'"'"' ]?1[\"'"'"' ]?[^0-9>]+[^>]*>", "", $4);
+
 				print $0;
 			}'
 	}