#
# File : $Source: /cvsroot/ijbswa/current/default.filter,v $
#
-# $Id: default.filter,v 1.30 2006/10/18 12:36:50 fabiankeil Exp $
+# $Id: default.filter,v 1.36 2007/02/05 16:47:31 fabiankeil Exp $
#
# Purpose : Rules to process the content of web pages
#
-# Copyright : Written by and Copyright (C) 2001 - 2006 the
+# Copyright : Written by and Copyright (C) 2001 - 2007 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/(?:(?:this|window)\.(?:default)?status)\s*=\s*\w*\s*;//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.
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="0" 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="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $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="0" 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="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $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="0" 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="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $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="0" 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="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $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="0" 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="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $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="0" 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="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $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="0" 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="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $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="0" 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="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $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="0" 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="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $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="0" 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="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
#################################################################################
#
s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:\
adclick # See www.dn.se \
+| advert # see dict.leo.org \
| atwola\.com/(?:link|redir) # see www.cnn.com \
| /jump/ # redirs for doublecklick.net ads \
| 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="0" title=$1Killed $4 by link to $2$1>@sigx
+)[^>\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="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed $4 by link to $2"@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="0" title=$1Killed $4 by link to $2$1>@sig
+s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:ad(?:click|vert)|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="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed $4 by link to $2"@sig
################################################################################
#################################################################################
FILTER: webbugs Squish WebBugs (1x1 invisible GIFs used for user tracking)
-s@<img[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*?>@<!--\
- Filtered by Privoxy's webbugs filter: $0 -->@siUg
+s@<img[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*?>@@siUg
#################################################################################
# SCNR
#
-s/microsoft(?!.com)/MicroSuck/ig
+s/microsoft(?!.[^\s])/MicroSuck/ig
# Buzzword Bingo (example for extended regex syntax)
#
#################################################################################
#
-# crude-parental: Crude parental filtering? (Use along with a suitable blocklist).
-# Shows how to deny access to whole page based on a keyword.
+# crude-parental: Crude parental filtering. Use with a suitable blocklist.
+# Pages are "blocked" based on keyword matching.
#
#################################################################################
-FILTER: crude-parental Crude parental filtering (demo only)
+FILTER: crude-parental Crude parental filtering
# (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words)
# (Note #2: Is 'sex' a rude word?!)
-s%^.*(?<!middle)(?<!sus)(?<!es)sex.*$%<html><head><title>Blocked</title></head><body><h3>Blocked due to possible adult content. Please see <a href="http://dmoz.org/Kids_and_Teens/">this site</a>.</h3></body></html>%is
-s+^.*warez.*$+<html><head><title>No Warez</title></head><body><h3>You're not searching for illegal stuff, are you?</h3></body></html>+is
+# Remove by description
+s/^.*\
+(suck |lick |tounge |rub |fuck |fingering |finger |chicks? )?\
+(her |your |my |hard |with |big |wet |tight |pink |hot |moist |young |teen )+\
+(dicks?|penis|cocks?|balls?|tits?|pussy|cunt|clit|ass|mouth).*$\
+/This page has been blocked by Privoxy's crude-parental content filter\
+/is
+
+#Remove by link text
+s/^.*\
+(download|broadband|view|watch|free|get|extreem)? \
+(sex|xxx|porn|cumshot|fuck(ing|s)?|anal|ass|asian|adult|Amateur|org(y|ies)|close ups?|hand ? job|nail(ed)?)+ \
+(movies?|pics?|videos?|dvds?|dvd's|links?).*$\
+/This page has been blocked by Privoxy's crude-parental content filter\
+/is
+
+#Remove by age disclaimer
+s/^.*\
+(models?|chicks?|girls?|women|persons) \
+(who|are|were)+ (over|at least) (16|18|21) years (old|of age).*$\
+/This page has been blocked by Privoxy's crude-parental content filter\
+/is
+
+#Remove by regulations
+s/^.*(Section 2257|18 U.?S.?C.? 2257).*$\
+/This page has been blocked by Privoxy's crude-parental content filter\
+/is
#################################################################################
# no-ping: Removes non-standard ping attributes in <a> and <area> tags.
#
#################################################################################
-FILTER: no-ping Removes non-standard ping attributes in <a> and <area> tags.
-s@(<a(?:rea)?[^>]*?)ping=(['"]?)([^"'>]+)\2([>\s]?)@\
-<strong title="Privoxy removed ping target '$3'">PING!</strong>\n$1$4@ig
+FILTER: no-ping Removes non-standard ping attributes in <a> and <area> tags.
+s@(<a(?:rea)?[^>]*?)\sping=(['"]?)([^"'>]+)\2([>\s]?)@\
+<strong style="color:white; background-color:red;" title="Privoxy removed ping target '$3'">PING!</strong>\n$1$4@ig
#################################################################################
#
/* Style sheet inserted by Privoxy's google filter. */\n\
\#fbc, \#fbl, \#ra, .rhh {visibility: hidden !important;}\n\
\#tpa1,\#tpa2,\#tpa3,\#tpa4,\#tpa5,\#tpa5, \#spl, .ch, \#ads,\
- \#toolbar, \#google_ads_frame{display: none !important;}\n\
+ \#toolbar, \#google_ads_frame, \#mbEnd {display: none !important;}\n\
.main_body, .j {width: 100%}\n</style>\n$0@
s@<div style=\"padding-top:11px;min-width:500px\">@<div id="main_body">@
s@(<table cellspacing=0 cellpadding=0 width=25% align=right bgcolor=\#ffffff border=0\
#
#################################################################################
FILTER: yahoo CSS-based block for Yahoo text ads. Also removes a width limitation.
-s@</head>@<style type="text/css">\n\
+s@</head>@\n<style type="text/css">\n\
/* Style sheet inserted by Privoxy's yahoo filter. */\n\
- \#symadbn, \#ymadbn, \#yschsec, \#yschanswr, .yschftad,\
- .yschspn, .yschspns {display: none !important;}\n\
- \#yschpri {width: 100% }\n</style>\n$0@
+ \#symadbn, \#ymadbn, .yschbox, \#yschsec, .yschhd, \#yschanswr, .yschftad,\
+ .yschspn, .yschspns, \#ygrp-sponsored-links {display: none !important;}\n\
+ \#yschpri, \#yschweb {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, .SearchSection .not\
- {width: 100% !important; min-width: 100% !important;\
- max-width: 100% !important;}\n</style>\n$0@
+ \#results, .flank, .results_area_flank, .results_area_stroke, .SearchSection .not\
+ {width: 99% /*!important*/; min-width: 99% !important;\
+ 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\
+ </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
#
# Revisions :
# $Log: default.filter,v $
+# Revision 1.36 2007/02/05 16:47:31 fabiankeil
+# - Let banners-by-link look for "advert".
+# - Fix XML systax problems with banners-by-link
+# and banners-by-size (AF#1651570).
+#
+# Revision 1.35 2006/12/21 12:28:12 fabiankeil
+# Escaping special characters in filter descriptions is no
+# longer necessary, it's done by Privoxy now.
+#
+# Revision 1.34 2006/12/12 17:32:23 fabiankeil
+# Added id mbEnd to google filter, it's now and then
+# used for the sponsored links.
+#
+# Have js-annoyances try to prevent status bar
+# modifications where the status bar text is
+# inside another variable. Fixes 1605710.
+#
+# Revision 1.33 2006/11/16 17:10:43 fabiankeil
+# Removed webbugs debugging comment again.
+# The apostrophe could break JavaScript and
+# the comment itself could mess up existing
+# comments.
+#
+# Revision 1.32 2006/11/10 18:04:04 fabiankeil
+# Have no-ping print the ping warning in red.
+#
+# Modified yahoo to keep in sync with recent
+# CSS changes and to suppress a useless horizontal
+# scrollbar.
+#
+# msn now makes sure that the continue-link boxes
+# act as links (the original CSS just changes the cursor).
+#
+# Changed fun filter regex to leave microsoft links alone.
+# Fixes BR 1019996.
+#
+# Revision 1.31 2006/10/21 13:12:28 fabiankeil
+# Added no-ping and hide-tor-exit-notation.
+#
+# Adjusted jumping-windows to break less.
+# Fixes BR 1146134.
+#
# Revision 1.30 2006/10/18 12:36:50 fabiankeil
# google filter now cleans Google groups as well.
#
projects / privoxy.git / blobdiff