#
# File : $Source: /cvsroot/ijbswa/current/default.filter,v $
#
-# $Id: default.filter,v 1.49 2007/11/03 14:29:41 fabiankeil Exp $
+# $Id: default.filter,v 1.57 2008/01/26 15:45:39 fabiankeil Exp $
#
# Purpose : Rules to process the content of web pages
#
adclick # See www.dn.se \
| advert # see dict.leo.org \
| atwola\.com/(?:link|redir) # see www.cnn.com \
-| /jump/ # redirs for doublecklick.net ads \
+| doubleclick\.net/jump/ # redirs for doublecklick.net ads \
| counter # common \
| (?<!&type=)tracker # (&type=tracker is used in sf's project statistics) \
| adlog\.pl # see sf.net \
s@</head>@\n<style type="text/css">\n\
/* Style sheet inserted by Privoxy's yahoo filter. */\n\
- \#symadbn, \#ymadbn, .yschbox, \#yschsec, .yschhd, \#yschanswr, .yschftad,\
- .yschspn, .yschspns, \#ygrp-sponsored-links, \#ks-ypn-ads {display: none !important;}\n\
- \#yschpri, \#yschweb {width: 100% !important; max-width: 100% !important;}\n\
+ \#symadbn, \#ymadbn, .yschbox, .yschhd, .bbox, \#yschsec, \#sec,\
+ \#yschanswr, .yschftad, .yschspn, .yschspns, \#ygrp-sponsored-links,\
+ \#ks-ypn-ads, .ad, \#east, \#ygrp-vital {display: none !important;}\n\
+ \#yschpri, \#yschweb, \#pri, \#web, \#main {width: 100% !important; max-width: 100% !important;}\n\
\#yschqcon, \#yschtg {width: auto !important; /* No useless horizontal scrollbar please */}\n\
</style>\n$0@
s@</head>@<style type="text/css">\n\
/* Style sheet inserted by Privoxy's msn filter. */\n\
- .msn_ads {display: none !important;}\n\
- \#results, .flank, .results_area_flank, .results_area_stroke, .SearchSection .not\
- {width: 99% /*!important*/; min-width: 99% !important;\
+ .msn_ads, \#at, \#ar {display: none !important;}\n\
+ \#results, .flank, .results_area_flank, .results_area_stroke,\n\
+ \#results_area, .SearchSection, .not, .sc_rslth1\n\
+.content, \#sw_foot, \#bf, \#sw_content, \#sidebar, \#pag\n\
+ {width: 99% !important; min-width: 99% !important;\n\
max-width: 100% !important; /* width:100% sometimes causes horizontal scrollbars */}\n\
- /* Make continue links harder to miss */\n\
- \#pagination_bottom a {padding: .3em .5em .3em .5em; border: 1px solid \#e6e6e6;}\n\
- \#pagination_bottom li, \#pagination_bottom li .selected, li .nextPage \
- {margin: 0 !important; cursor: auto; border: none; padding:.1em;}\n\
- \#pagination_bottom li .prevPage {padding-right: 1.5em !important;}\n\
- \#pagination_bottom li .selected {border: none;}\n\
- .selected a {background-color: \#d2eaf6; border: 1px solid \#b7d8ee;}\n\
/* Remove "suggestions". They are next to worthless but partly overlap with the search results */\n\
- .suggestion, \#nys_right {clear: both; display:none;}\n\
+ .suggestion, \#nys_right, \#nys {clear: both; display:none;}\n\
+ \#content {padding-right: 0;}\n\
</style>\n$0@
s@(<div[^>]*) id=(["']?)ads_[^\2]*\2@$1 class="msn_ads"@Uig
s@(<a[^>]*href=\")http://g.msn.com/.*\?(http://.*)(&&DI=.*)(\")@$1$2$4@Ug
s@(<a[^>]*)gping=\".*\"@$1 title="URL cleaned up by Privoxy's msn filter"@Ug
-s@<div id=\"ar\">(<h2>Sponsored sites</h2>)@<div class="msn_ads">$1@
-s@(</script><div) id=\"at\"@$1 class="msn_ads"@
#################################################################################
#
# appear to early or not at all and as fixing this would require a browser
# that understands background-size (CSS3), they are removed instead.
#
+# When applied to feeds, it removes comment titles that
+# only contain the beginning of the actual comment.
+#
#################################################################################
FILTER: blogspot Cleans up some Blogspot blogs. Read the fine print before using this.
s@(<div style=\"[^\"]*width:)30em@$1 100%@
s@background:url\(\"http://www.blogblog.com/rounders[^\"]*\"\).*;@/*$0*/@Ug
s@(background:\#[a-f\d]{3})( url\(\"http://www.blogblog.com/rounders[^\"]*\"\).*;)@$1 ;/*$2*/@Ug
+# Do the feed filtering magic as described above.
+s@<title\s+type=\'text\'>([^\s]*).*?\.\.\.</title>\s*(<content type=\'html\'>\1)@$2@ig
#################################################################################
#
SERVER-HEADER-FILTER: less-download-windows Prevent annoying download windows for content types the browser can handle itself.
s@^Content-Disposition:.*filename=(["']?).*\.(png|gif|jpe?g|diff?|d?patch|c|h|pl|shar)\1.*$@@i
-s@^(Content-Type:)\s*(?:message/(?:news|rfc822)|text/x-.*|application/x-sh)\s*@$1 text/plain@i
+s@^(Content-Type:)\s*(?:message/(?:news|rfc822)|text/x-.*|application/x-sh(?:\s|$))\s*@$1 text/plain@i
#################################################################################
#
s@Accept:\s*text/css.*@CSS-REQUEST@i
+#################################################################################
+#
+# client-ip-address: Tags the request with the client's IP address.
+#
+#################################################################################
+CLIENT-HEADER-TAGGER: client-ip-address Tags the request with the client's IP address.
+
+s@^\w*\s+.*\s+HTTP/\d\.\d\s*@IP-ADDRESS: $origin@D
+
+#################################################################################
+#
+# http-method: Tags the request with its HTTP method.
+#
+#################################################################################
+CLIENT-HEADER-TAGGER: http-method Tags the request with its HTTP method.
+
+s@^(\w*).*HTTP/\d\.\d\s*$@$1@i
+
+#################################################################################
+#
+# allow-post: Tags POST requests as "ALLOWED-POST".
+#
+#################################################################################
+CLIENT-HEADER-TAGGER: allow-post Tags POST requests as "ALLOWED-POST".
+
+s@^(?:POST)\s+.*\s+HTTP/\d\.\d\s*@ALLOWED-POST@i
+
+#################################################################################
+#
+# complete-url: Tags the request with the whole request URL.
+#
+#################################################################################
+CLIENT-HEADER-TAGGER: complete-url Tags the request with the whole request URL.
+
+s@^\w*\s+(.*)\s+HTTP/\d\.\d\s*$@$1@i
+
+#################################################################################
+#
+# user-agent: Tags the request with the complete User-Agent header.
+#
+#################################################################################
+CLIENT-HEADER-TAGGER: user-agent Tags the request with the complete User-Agent header.
+
+s@^User-Agent:.*@$0@i
+
+#################################################################################
+#
+# content-type: Tags the request with the content type declarded by the server.
+#
+#################################################################################
+SERVER-HEADER-TAGGER: content-type Tags the request with the content type declarded by the server.
+
+s@^Content-Type:\s*([^;]*).*@$1@i
+
#################################################################################
#
# privoxy-control: The taggers create tags with the content of X-Privoxy-Control
#
# Revisions :
# $Log: default.filter,v $
+# Revision 1.57 2008/01/26 15:45:39 fabiankeil
+# Don't let the less-download-windows filter mess up
+# "Content-Type: application/x-shockwave-flash" headers.
+#
+# Revision 1.56 2008/01/25 19:12:40 fabiankeil
+# - Add yet another new yahoo ad id.
+# - Don't let the first banners-by-link job punish URLs for merely
+# containing the pattern "/jump/" when it should really look for
+# "doubleclick\.net/jump/".
+#
+# Revision 1.55 2007/12/31 19:53:59 fabiankeil
+# Let the msn filter remove the width limitation again.
+#
+# Revision 1.54 2007/12/31 19:11:31 fabiankeil
+# - Let the yahoo filter remove the width limitation again.
+# - Teach the blogspot filter to remove useless feed comment
+# titles that only contain the beginning of the actual comment.
+#
+# Revision 1.53 2007/12/23 15:48:12 fabiankeil
+# - Lo and behold, the CSS fix for the MSN buttons is no longer necessary.
+# - Add some new selectors the msn filter should hide.
+# - Add the two yahoo selectors Lee reported in #1856574.
+# - Add comments that the width limitation fixes stopped
+# working for the msn and yahoo filter.
+#
+# Revision 1.52 2007/11/27 18:35:48 fabiankeil
+# Update CSS for the yahoo filter.
+#
+# Revision 1.51 2007/11/04 16:15:11 fabiankeil
+# - Add client-header taggers: client-ip-address,
+# http-method, allow-post, complete-url and user-agent.
+# - Add server-header tagger: content-type.
+#
+# Revision 1.50 2007/11/03 15:05:30 fabiankeil
+# Consistently use an empty line between the description and the PCRS code
+# and end descriptions with dots. Patch submitted by Simon Ruderich.
+#
# Revision 1.49 2007/11/03 14:29:41 fabiankeil
# Spelling fixes mostly submitted by Simon Ruderich.
#