X-Git-Url: http://www.privoxy.org/gitweb/?p=privoxy.git;a=blobdiff_plain;f=default.filter;h=e8efe2e03a37473cce0b5fdf2da708a712c3792a;hp=aa9050df00cfddef4dd718ae972aba1753b837d9;hb=38f383f0e5e64f761d067594310f4c2715fe21f7;hpb=57c8513fa8cd0f05f49fea01147f056d29c34e4b

diff --git a/default.filter b/default.filter
index aa9050df..e8efe2e0 100644
--- a/default.filter
+++ b/default.filter
@@ -2,11 +2,11 @@
 # 
 #  File        :  $Source: /cvsroot/ijbswa/current/default.filter,v $
 # 
-#  $Id: default.filter,v 1.22 2006/10/04 19:17:14 fabiankeil Exp $
+#  $Id: default.filter,v 1.48 2007/10/17 18:11:32 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 - 2007 the
 #                 Privoxy team. http://www.privoxy.org/
 #
 # We value your feedback. However, to provide you with the best support,
@@ -37,8 +37,12 @@
 #
 # Syntax:
 #
-# Filters start with a line "FILTER: name description". They are then referrable
-# from the actionsfile with +filter{name}
+# Generally filters start with a line like "FILTER: name description".
+# They are then referrable from the actionsfile with +filter{name}
+#
+# FILTER marks a filter as content filter, other filter
+# types are CLIENT-HEADER-FILTER, CLIENT-HEADER-TAGGER,
+# SERVER-HEADER-FILTER and SERVER-HEADER-TAGGER.
 #
 # Inside the filters, write one Perl-Style substitution (job) per line.
 # Jobs that precede the first FILTER: line are ignored.
@@ -46,16 +50,27 @@
 # For Details see the pcrs manpage contained in this distribution.
 # (and the perlre, perlop and pcre manpages)
 #
-# Note that you are free to choose the delimter as you see fit.
+# Note that you are free to choose the delimiter as you see fit.
 #
-# Note2: In addidion to the Perl options gimsx, the following nonstandard
+# Note2: In addition to the Perl options gimsx, the following nonstandard
 # options are supported:
 # 
 # 'U' turns the default to ungreedy matching.  Add ? to quantifiers to
 #     switch back to greedy.
+#
 # 'T' (trivial) prevents parsing for backreferences in the substitute.
 #     Use if you want to include text like '$&' in your substitute without
 #     quoting.
+#
+# 'D' (Dynamic) allows the use of variables. Supported variables are:
+#     $host, $origin (the IP address the request came from), $path and $url.
+#
+#     Note that '$' is a bad choice as delimiter for dynamic filters as you
+#     might end up with unintended variables if you use a variable name
+#     directly after the delimiter. Variables will be resolved without
+#     escaping anything, therefore you also have to be careful not to chose
+#     delimiters that appear in the replacement text. For example '<' should
+#     be save, while '?' will sooner or later cause conflicts with $url.
 # 
 #################################################################################
 
@@ -72,7 +87,7 @@ FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse
 #
 # s/(<script.*)nasty-item(?=.*<\/script>)/$1replacement/sigU
 #
-# but that would make them match only the first occurance of
+# but that would make them match only the first occurrence of
 # nasty-item in each <script>. We need nestable jobs!
 
 # Get rid of Javascript referrer tracking. 
@@ -81,8 +96,11 @@ FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse
 s|(?:\w+\.)+referrer|"Not Your Business!"|gisU
 
 # 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*((['"]).*?\4)@$1$2 =\
+ (typeof(this.href) != 'undefined')?($3 + ' URL: ' + this.href):($2)@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
@@ -178,7 +196,7 @@ s/<meta\s+http-equiv\s*=\s*(['"]?)refresh\1\s+content\s*=\s*(['"]?)\d{2,}\s*(;\s
 FILTER: unsolicited-popups Disable only unsolicited pop-up windows
 
 s+([^'"]\s*<head.*>)(?=\s*[^'"])+$1<script>function PrivoxyWindowOpen(){return(null);}</script>+isU
-s+([^\w\s.]\s*)((window|this|parent)\.)?open\s*\(+$1PrivoxyWindowOpen(+ig
+s@([^\w\s.]\s*)((?:map)?(window|this|parent)\.?)?open\s*\(@$1PrivoxyWindowOpen(@ig
 s+([^'"]\s*</html>)(?!\s*(\\n|'|"))+$1<script>function PrivoxyWindowOpen(a, b, c){return(window.open(a, b, c));}</script>+iU     
 
 
@@ -189,16 +207,16 @@ s+([^'"]\s*</html>)(?!\s*(\\n|'|"))+$1<script>function PrivoxyWindowOpen(a, b, c
 #################################################################################
 FILTER: all-popups Kill all popups in JavaScript and HTML
 
-s/((\W\s*)(window|this|parent)\.)open\s*\\?\(/$1concat(/ig  # JavaScript
-s/\starget\s*=\s*(['"]?)_?(blank|new)\1?/ notarget/ig        # HTML
-
+s@((\W\s*)(?:map)?(window|this|parent)\.?)open\s*\\?\(@$1concat(@ig  # JavaScript
+#s/\starget\s*=\s*(['"]?)_?(blank|new)\1?/ notarget/ig        # HTML
+s/\starget\s*=\s*(['"]?)_?(blank|new)\1?/ /ig        # (X)HTML
 
 ##################################################################################
 #
 # img-reorder: Reorder attributes in <img> tags to make the banners-by-* filters more effective
 #
 #################################################################################
-FILTER: img-reorder Reorder attributes in &lt;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.
@@ -208,7 +226,7 @@ FILTER: img-reorder Reorder attributes in &lt;img> tags to make the banners-by-*
 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
 
 
 #################################################################################
@@ -229,27 +247,37 @@ s|<img (src=(?:(['"])[^>\\\\2]+\2\|[^'">\\\s]+?))([^>]*)width\s*=\s*(["']?)(\d+?
 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="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=$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="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=$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="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=$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="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=$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="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=$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="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=$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="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=$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="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=$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="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=$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="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
 
 
 #################################################################################
@@ -263,16 +291,18 @@ FILTER: banners-by-link Kill banners by their links to known clicktrackers
 #
 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 \
+| counter                             # common \
+| (?<!&type=)tracker                  # (&type=tracker is used in sf's project statistics) \
 | 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
+)[^>\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=$1\\0$1 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/|(?<!&type=)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
 
 
 ################################################################################
@@ -282,7 +312,7 @@ s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:adclick|atwola\.com/(?:link|redir)|double
 #################################################################################
 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)[^>]*?>@@siUg
 
 
 #################################################################################
@@ -303,8 +333,7 @@ s/(<textarea[^>]*?)wrap=(['"]?)hard\2/$1/ig
 #################################################################################
 FILTER: jumping-windows Prevent windows from resizing and moving themselves
 
-s/(?:window|this|self)\.(?:move|resize)(?:to|by)\(/''.concat(/ig
-
+s/(?<=[\W])(?:window|this|self)\.(?:move|resize)(?:to|by)\(/''.concat(/ig
 
 #################################################################################
 #
@@ -390,7 +419,7 @@ FILTER: fun Text replacements for subversive browsing fun!
 
 # SCNR
 #
-s/microsoft(?!.com)/MicroSuck/ig
+s/microsoft(?!.[^\s])/MicroSuck/ig
 
 # Buzzword Bingo (example for extended regex syntax)
 #
@@ -413,18 +442,48 @@ s/(M|m)edien(?![^<]*>)/$1&auml;dchen/Ug
 
 #################################################################################
 #
-# 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 that this filter doesn't work reliable.
 
 # (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.*$%<html><head><title>Blocked</title></head><body><h3>Blocked due to possible adult content. Please see <a href="http://dmoz.org/Kids_and_Teens/">this site</a>.</h3></body></html>%is
+s%^.*(?<!middle)(?<!sus)(?<!es)sex.*$%<html><head><title>Blocked</title></head><body>\
+<h3>Blocked by Privoxy's crude-parental filter due to possible adult content.</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?)\s*)?\
+(?:(her|your|my|hard|with|big|wet|tight|pink|hot|moist|young|teen)\s*)+\
+(dicks?|penis|cocks?|balls?|tits?|pussy|cunt|clit|ass|mouth).*$\
+/This page has been blocked by Privoxy's crude-parental content filter\
+/is
+
+#Remove by link text
+s/^.*\
+(download|broadband|view|watch|free|get|extreem)?\s*\
+(sex|xxx|porn|cumshot|fuck(ing|s)?|anal|ass|asian|adult|Amateur|org(y|ies)|close ups?|hand?job|nail(ed)?)+\s*\
+(movies?|pics?|videos?|dvds?|dvd's|links?).*$\
+/This page has been blocked by Privoxy's crude-parental content filter\
+/is
+
+#Remove by age disclaimer
+s/^.*\
+(models?|chicks?|girls?|women|persons)\s*\
+(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 
+
 
 #################################################################################
 #
@@ -496,6 +555,15 @@ s|(<img [^>]*)onload|$1never|sig
 s|(<INPUT name="\d{2,4}" type="RADIO" value="0") CHECKED |$1|g
 s|<INPUT name="\d{2,4}" type="RADIO" value="3" |$0 checked|g
 
+#################################################################################
+#
+# 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)?[^>]*?)\sping=(['"]?)([^"'>]+)\2([>\s]?)@\
+<strong style="color:white; background-color:red;" title="Privoxy removed ping target '$3'">PING!</strong>\n$1$4@ig
+
 #################################################################################
 #
 # google: CSS-based block for Google text ads. Also removes
@@ -506,12 +574,15 @@ FILTER: google CSS-based block for Google text ads. Also removes a width limitat
 s@</head>@<style type="text/css">\n\
  /* 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\
+ \#tpa1,\#tpa2,\#tpa3,\#tpa4,\#tpa5,\#tpa5, \#spl, .ch, \#ads,\
+ \#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\
 |</font></td></tr></tbody></table><table align=\"right\" bgcolor=\"\#ffffff\"\
-|<table cellspacing=0 cellpadding=0 align=right bgcolor=\#ffffff border=0)@$0 id="ads"@
+|<table cellspacing=0 cellpadding=0 align=right bgcolor=\#ffffff border=0\
+|<table style=\"clear:both\" align=right width=25% cellspacing=\"0\" cellpadding=\"0\"\
+ border=\"0\" bgcolor=\"\#ffffff\")@$0 id="ads"@
 s@(<br clear=all><table)( border=0 cellpadding=9><tr><td)@$1 id="toolbar"$2@
 
 #################################################################################
@@ -520,11 +591,13 @@ s@(<br clear=all><table)( border=0 cellpadding=9><tr><td)@$1 id="toolbar"$2@
 #
 #################################################################################
 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, \#ks-ypn-ads {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@
 
 #################################################################################
 #
@@ -536,12 +609,24 @@ FILTER: msn CSS-based block for MSN text ads. Also removes tracking URLs and a w
 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://.*)(&amp;&amp;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"@
 
 #################################################################################
 #
@@ -564,32 +649,265 @@ s@</head>@<style type="text/css">\n\
  \#sidebar {width: 29% }\n\
  .post-body {overflow: auto;}\n\
  .blogComments {width: 100%; overflow: auto;}\n</style>\n$0@
-s@<body.*(<div id="(content|wrap4|wrapper))@<body><!-- Privoxy's\
- blogspot filter ditched some garbage here -->$1@Us
+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
 
 #################################################################################
 #
-# html-to-xml: Header filter to change the Content-Type from html to xml.
+# x-httpd-php-to-html: Changes the Content-Type header 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.
+#
+#################################################################################
+SERVER-HEADER-FILTER: x-httpd-php-to-html Changes the Content-Type header from x-httpd-php to html.
+s@^(Content-Type:)\s*application/x-httpd-php@$1 text/html@i
+
+#################################################################################
+#
+# html-to-xml: Changes the Content-Type header from html to xml.
+#
+#################################################################################
+SERVER-HEADER-FILTER: html-to-xml Changes the Content-Type header from html to xml.
+s@^(Content-Type:)\s*text/html(;.*)?$@$1 application/xhtml+xml$2@i
+
+#################################################################################
+#
+# xml-to-html: Changes the Content-Type header from xml to html.
+#
+#################################################################################
+SERVER-HEADER-FILTER: xml-to-html Changes the Content-Type header from xml to html.
+s@^(Content-Type:)\s*(?:application|text)/(?:xhtml\+)?xml(;.*)?$@$1 text/html$2@i
+
+#################################################################################
+#
+# hide-tor-exit-notation: Remove the Tor exit node notation in Host and Referer headers.
+#
+#   Note: If Privoxy and Tor are chained and Privoxy is configured to
+#         use socks4a, one can use http://www.example.org.foobar.exit/
+#         to access the host www.example.org through Tor exit node foobar.
+#
+#         As the HTTP client isn't aware of this notation, it treats the
+#         whole string "www.example.org.foobar.exit" as host and uses it
+#         for the "Host" and "Referer" headers. From the server's point of
+#         view the resulting headers are invalid and can cause problems.
+#
+#         An invalid "Referer" header can trigger "hot-linking" protections,
+#         an invalid "Host" header will make it impossible for the server to
+#         find the right vhost (several domains hosted on the same IP address).
+#
+#         This filter removes the "foo.exit" part in those headers
+#         to prevent the mentioned problems. Note that it only modifies
+#         the HTTP headers, it doesn't make it impossible for the server
+#         to detect your Tor exit node based on the IP address the request is
+#         coming from.
 #
 #################################################################################
-FILTER: html-to-xml Header filter to change the Content-Type from html to xml.
-s@^(Content-Type:) text/html(;.*)?$@$1 application/xhtml+xml$2@
+CLIENT-HEADER-FILTER: hide-tor-exit-notation Removes the Tor exit node notation in Host and Referer headers.
+s@^((?:Referer|Host):\s*(?:https?://)?[^/]*)\.[^\./]*?\.exit@$1@i
 
 #################################################################################
 #
-# xml-to-html: Header filter to change the Content-Type from xml to html.
+# less-download-windows: Prevents annoying download windows for content types
+#                        the browser can handle itself.
 #
 #################################################################################
-FILTER: xml-to-html Header filter to change the Content-Type from xml to html.
-s@^(Content-Type:) (?:application|text)/(?:xhtml\+)?xml(;.*)?$@$1 text/html$2@
+SERVER-HEADER-FILTER: less-download-windows Prevent annoying download windows for content types the browser can handle itself
+s@^Content-Disposition:.*filename=(["']?).*\.(png|gif|jpe?g|diff?|d?patch|c|h|pl|shar)\1.*$@@i
+s@^(Content-Type:)\s*(?:message/(?:news|rfc822)|text/x-.*|application/x-sh)\s*@$1 text/plain@i
+
+#################################################################################
+#
+# image-requests: Tags detected image requests as "IMAGE-REQUEST". Whether
+#                 or not the detection actually works depends on the browser.
+#
+#################################################################################
+CLIENT-HEADER-TAGGER: image-requests Tags detected image requests as "IMAGE-REQUEST".
+s@Accept:\s*image/.*@IMAGE-REQUEST@i
+
+#################################################################################
+#
+# css-requests:  Tags detected CSS requests as "CSS-REQUEST". Whether
+#                or not the detection actually works depends on the browser.
+#
+#################################################################################
+CLIENT-HEADER-TAGGER: css-requests Tags detected CSS requests as "CSS-REQUEST".
+s@Accept:\s*text/css.*@CSS-REQUEST@i
+
+#################################################################################
+#
+# privoxy-control: The taggers create tags with the content of X-Privoxy-Control
+#                  headers, the filters remove said headers.
+#
+#################################################################################
+CLIENT-HEADER-TAGGER: privoxy-control Creates tags with the content\
+ of X-Privoxy-Control headers
+s@^X-Privoxy-Control:\s*@@i
+
+CLIENT-HEADER-FILTER: privoxy-control Removes X-Privoxy-Control headers
+s@^X-Privoxy-Control:.*@@i
+
+SERVER-HEADER-TAGGER: privoxy-control Creates tags with the content\
+ of X-Privoxy-Control headers
+s@^X-Privoxy-Control:\s*@@i
+
+SERVER-HEADER-FILTER: privoxy-control Removes X-Privoxy-Control headers
+s@^X-Privoxy-Control:.*@@i
+
 
 ############################################################################## 
 #
 #  Revisions   :
 #     $Log: default.filter,v $
+#     Revision 1.48  2007/10/17 18:11:32  fabiankeil
+#     Add privoxy-control header filters and taggers.
+#
+#     Revision 1.47  2007/10/06 15:45:25  fabiankeil
+#     Let msn hide sponsored links in #at divs.
+#
+#     Revision 1.46  2007/10/06 09:54:13  fabiankeil
+#     - Let msn hide sponsored links in #ar divs.
+#     - Teach banners-by-link not to block the graphs for sf's tracker statistics.
+#
+#     Revision 1.45  2007/08/11 16:54:12  fabiankeil
+#     - Complete the changes from r1.42.
+#     - Make crude-parental less sensitive to the amount of white-space,
+#       add the note that it doesn't work too well again and replace the
+#       DMOZ link with a less confusing explanation.
+#
+#     Revision 1.44  2007/07/18 11:06:56  hal9
+#     Replace notarget with '' in all popups filter to keep from breaking xhmtl per
+#     report from Siegfried Gipp.
+#
+#     Revision 1.43  2007/06/01 14:17:04  fabiankeil
+#     Mention possible delimiter conflicts with variables in dynamic pcrs commands.
+#
+#     Revision 1.42  2007/05/17 15:55:36  fabiankeil
+#     Undo an improperly tested last-minute change
+#     and turn "text-requests" back into "css-requests".
+#
+#     Revision 1.41  2007/05/17 15:45:41  fabiankeil
+#     - Mention new filter types and the 'D' option.
+#     - Header filters are now case-insensitive and accept a
+#       varying amount of whitespace after the colon.
+#     - Add another selector for yahoo ads.
+#     - New server-header filter: less-download-windows
+#     - New client-header taggers: text-requests and image-requests.
+#
+#     Revision 1.40  2007/03/20 15:40:00  fabiankeil
+#     Adjust to new world order with dedicated header-filter actions.
+#
+#     Revision 1.39  2007/02/21 14:10:23  fabiankeil
+#     - Fix a js-annoyances pcrs command that broke
+#       evaluated code. (BR #1124071, thanks to Bor Gergely)
+#     - Have unsolicited-popups and all-popups catch the
+#       wheather.com popup reported in in AF #1640173.
+#
+#     Revision 1.38  2007/02/19 11:22:48  hal9
+#     Adding back the orginal filter content to offset problems found by Fabian.
+#
+#     Revision 1.37  2007/02/17 13:29:44  hal9
+#     Updates to the crude parental filter per Feature Requests item #1648657.
+#
+#     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.
+#
+#     Revision 1.29  2006/10/11 14:03:17  fabiankeil
+#     Changed img-reorder regex to only move width
+#     attributes if they are following at least one
+#     whitespace. Fixes BR 1328455.
+#
+#     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 "&lt;".
+#
+#     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.