#
# File : $Source: /cvsroot/ijbswa/current/default.filter,v $
#
-# $Id: default.filter,v 1.20 2006/10/01 21:00:22 fabiankeil Exp $
+# $Id: default.filter,v 1.28 2006/10/11 13:31:13 fabiankeil Exp $
#
# Purpose : Rules to process the content of web pages
#
-# Copyright : Written by and Copyright (C) 2001 - 2004 the
+# Copyright : Written by and Copyright (C) 2001 - 2006 the
# Privoxy team. http://www.privoxy.org/
#
# We value your feedback. However, to provide you with the best support,
# The status bar is for displaying link targets, not pointless blahblah
#
-s/(\W\s*)((this|window)\.(default)?status)\s*=\s*((['"]).*?\6)/$1if(typeof(this.href) != 'undefined') $2 = $5 + ' URL: ' + this.href;else return false/ig
+s/(\W\s*)((this|window)\.(default)?status)\s*=\s*((['"]).*?(?<!\\)\6)/$1if(typeof(this.href) != 'undefined') $2 = $5 + ' URL: ' + this.href;else return false/ig
# Kill OnUnload popups. Yummy.
# Test: http://www.zdnet.com/zdsubs/yahoo/tree/yfs.html
# img-reorder: Reorder attributes in <img> tags to make the banners-by-* filters more effective
#
#################################################################################
-FILTER: img-reorder Reorder attributes in <img> tags to make the banners-by-* filters more effective
+FILTER: img-reorder Reorder attributes in <img> tags to make the banners-by-* filters more effective
# In the first step src is moved to the start, then width is moved to the second
# place to guarantee an order of src, width, height.
s|<img\s+?([^>]*) src\s*=\s*(['"])([^>\\\2]+)\2|<img src=$2$3$2 $1|siUg
s|<img\s+?([^>]*) src\s*=\s*([^'">\\\s]+)|<img src=$2 $1|sig
-s|<img (src=(?:(['"])[^>\\\\2]
+\2\|[^'">\\\s]+?))([^>]*)width\s*=\s*(["']?)(\d+?)\4|<img $1 width=$4$5$4$3|siUg
+s|<img (src=(?:(['"])[^>\\\\2]
*\2\|[^'">\\\s]+?))([^>]*)\s+width\s*=\s*(["']?)(\d+?)\4|<img $1 width=$4$5$4$3|siUg
#################################################################################
FILTER: banners-by-size Kill banners by size
# 88*31
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)88\4)[^>]*?(height=(['"]?)31\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border=$1\\0$1 title=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)88\4)[^>]*?(height=(['"]?)31\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
# 120*60, 120*90, 120*240, 120*600
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)120\4)[^>]*?(height=(['"]?)(?:600?|90|240)\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border=$1\\0$1 title=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)120\4)[^>]*?(height=(['"]?)(?:600?|90|240)\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
# 125*125
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)125\4)[^>]*?(height=(['"]?)125\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border=$1\\0$1 title=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)125\4)[^>]*?(height=(['"]?)125\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
# 160*600
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)160\4)[^>]*?(height=(['"]?)600\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border=$1\\0$1 title=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)160\4)[^>]*?(height=(['"]?)600\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
# 180*150
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)180\4)[^>]*?(height=(['"]?)150\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border=$1\\0$1 title=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)180\4)[^>]*?(height=(['"]?)150\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
# 234*60, 468*60 (Most Banners!)
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:234|468)\4)[^>]*?(height=(['"]?)60\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border=$1\\0$1 title=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:234|468)\4)[^>]*?(height=(['"]?)60\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
# 240*400
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)240\4)[^>]*?(height=(['"]?)400\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border=$1\\0$1 title=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)240\4)[^>]*?(height=(['"]?)400\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
# 250*250, 300*250
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:250|300)\4)[^>]*?(height=(['"]?)250\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border=$1\\0$1 title=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:250|300)\4)[^>]*?(height=(['"]?)250\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
# 336*280
-s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)336\4)[^>]*?(height=(['"]?)280\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border=$1\\0$1 title=$1Killed-$2-by-size$1 $3 $5>@sig
+s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)336\4)[^>]*?(height=(['"]?)280\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
# Note: 200*50 was also proposed, but it probably causes too much collateral damage:
#
-#s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)200\4)[^>]*?(height=(['"]?)50\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border=$1\\0$1 title=$1Killed-$2-by-size$1 $3 $5>@sig
+#s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)200\4)[^>]*?(height=(['"]?)50\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
#################################################################################
| tracker | counter # common \
| adlog\.pl # see sf.net \
)[^>\1\s]*)\1[^>]*>\s*<img\s+(?:src\s*=\s*(['"]?)([^>\\\3\s]+)\3)?[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\6)[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\8)[^>]*>\
-@<img $5 $7 src=$1http://config.privoxy.org/send-banner?type=auto$1 border=$1\\0$1 title=$1Killed $4 by link to $2$1>@sigx
+@<img $5 $7 src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed $4 by link to $2$1>@sigx
# Rare case w/o explicit dimensions:
#
-s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:adclick|atwola\.com/(?:link|redir)|doubleclick\.net/jump/|tracker|counter|adlog\.pl)[^>\1\s]*)\1[^>]*>\s*<img\s+(?:src\s*=\s*(['"]?)([^>\\\3\s]+)\3)?[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border=$1\\0$1 title=$1Killed $4 by link to $2$1>@sig
+s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:adclick|atwola\.com/(?:link|redir)|doubleclick\.net/jump/|tracker|counter|adlog\.pl)[^>\1\s]*)\1[^>]*>\s*<img\s+(?:src\s*=\s*(['"]?)([^>\\\3\s]+)\3)?[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed $4 by link to $2$1>@sig
################################################################################
#################################################################################
FILTER: webbugs Squish WebBugs (1x1 invisible GIFs used for user tracking)
-s/<img\s+[^>]*(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*?>//siUg
+s@<img[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*?>@<!--\
+ Filtered by Privoxy's webbugs filter: $0 -->@siUg
#################################################################################
# Address bar spoofing (http://www.secunia.com/advisories/10395/):
#
-s/(<a[^>]*href[^>]*)(\x01|\x02|\x03|%0[012])/$1MALICIOUS-LINK/ig
+s/(<a[^>]*href[^>]*)(?:\x01|\x02|\x03|%0[012])@/$1MALICIOUS-LINK@/ig
# Nimda:
#
FILTER: msn CSS-based block for MSN text ads. Also removes tracking URLs and a width limitation.
s@</head>@<style type="text/css">\n\
/* Style sheet inserted by Privoxy's msn filter. */\n\
- \#msn_ads, \#ads_rightC {display: none !important;}\n\
+ .msn_ads {display: none !important;}\n\
\#results, .flank, .SearchSection .not\
{width: 100% !important; min-width: 100% !important;\
max-width: 100% !important;}\n</style>\n$0@
-s@(<div id=)\"ads_[^\"]*\"@$0msn_ads@Uig
+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
\#content {width: 98% }\n\
\#main {width: 70% }\n\
\#sidebar {width: 29% }\n\
- .blogComments {width: 100%; overflow: scroll;}\n</style>\n$0@
-s@<body.*(<div id="(content|wrap4|wrapper))@<body><!-- Privoxy's\
- blogspot filter ditched some garbage here -->$1@Us
+ .post-body {overflow: auto;}\n\
+ .blogComments {width: 100%; overflow: auto;}\n</style>\n$0@
+s@<body.*(?:<div id="space-for-ie"></div>|(<div id="(?:content|wrap4|wrapper)))@<body>\
+ <!-- Privoxy's blogspot filter ditched some garbage here -->$1@Us
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
+#################################################################################
+#
+# x-httpd-php-to-html: Header filter to change the Content-Type from
+# x-httpd-php to html. "Content-Type: x-httpd-php"
+# is set by clueless PHP users and causes many
+# browsers do open a download menu instead of
+# rendering the page.
+#
+#################################################################################
+FILTER: x-httpd-php-to-html Header filter to change the Content-Type from x-httpd-php to html.
+s@^(Content-Type:) application/x-httpd-php@$1 text/html@
+
#################################################################################
#
# html-to-xml: Header filter to change the Content-Type from html to xml.
#
# Revisions :
# $Log: default.filter,v $
+# Revision 1.28 2006/10/11 13:31:13 fabiankeil
+# Added Anduin Withers' js-annoyances fix
+# for not messing up escaped quotes. Fixes BR 999765.
+#
+# Improved blogspot filter to make it less likely that
+# the blogspot banner at the top of the page is missed.
+#
+# Revision 1.27 2006/10/08 17:00:51 fabiankeil
+# Modified webbugs filter to create a comment around the offending
+# image instead of removing it entirely.
+#
+# Adjusted regex to only match if there's at least one whitespace
+# before the width and height attributes. Makes it more likely that
+# they are indeed attributes, and not part of the value of another attribute.
+# Solves BR 1035587.
+#
+# Thanks to Martin Thomas for diagnosing the cause of the problem.
+#
+# Revision 1.26 2006/10/06 18:06:16 fabiankeil
+# Added header filter x-httpd-php-to-html
+# and reverted another img-reorder whitespace
+# problem.
+#
+# Revision 1.25 2006/10/06 15:26:09 fabiankeil
+# Bumped copyright year.
+#
+# Reverted parts of the last img-reorder change
+# which were intended to remove superfluous whitespace
+# but had the side effect to mess up some tags.
+#
+# Modified banners-by-size and banners-by-link to
+# use border value "0" instead of "\0". Fixes BR 1100065.
+#
+# Revision 1.24 2006/10/06 11:25:31 fabiankeil
+# Taught img-reorder not to break img tags
+# with empty src attributes. Fixes BR 1089474.
+# Thanks to Raphael Moll for reporting.
+#
+# Revision 1.23 2006/10/05 14:46:28 fabiankeil
+# Replaced "<" in img-reorder's description with "<".
+#
+# Modified msn filter to tag ads with classes instead
+# of ids. There may be more than one ad per page,
+# but ids are required to be unique.
+#
+# Revision 1.22 2006/10/04 19:17:14 fabiankeil
+# Incorportated Frédéric Crozat's ie-exploits
+# modification to make it less trigger-happy.
+#
+# Modified blogspot filter to make .post-body
+# scrollable if necessary.
+#
+# Revision 1.21 2006/10/02 16:21:14 fabiankeil
+# Adjusted yahoo filter to hide .yschspns as well.
+# Added header filters: html-to-xml and xml-to-html.
+#
# Revision 1.20 2006/10/01 21:00:22 fabiankeil
# New site-specific filters: google, yahoo, msn and blogspot.
#
projects / privoxy.git / blobdiff