X-Git-Url: http://www.privoxy.org/gitweb/?p=privoxy.git;a=blobdiff_plain;f=default.filter;h=508b7f49e2c2cbc26ab76bd81fd1f806461b16d4;hp=ce4a3f454d17c0dae924fedf7945686675e0e901;hb=11d4d86d90ca075d52a87bb95af11de1b0c5ac1a;hpb=64b1b3aca3ba360e69fc762605da378bd5fa8b52 diff --git a/default.filter b/default.filter index ce4a3f45..508b7f49 100644 --- a/default.filter +++ b/default.filter @@ -2,11 +2,11 @@ # # File : $Source: /cvsroot/ijbswa/current/default.filter,v $ # -# $Id: default.filter,v 1.16 2002/11/11 13:40:38 oes Exp $ +# $Id: default.filter,v 1.57 2008/01/26 15:45:39 fabiankeil Exp $ # # Purpose : Rules to process the content of web pages # -# Copyright : Written by and Copyright +# 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. @@ -46,48 +50,62 @@ # 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. # ################################################################################# ################################################################################# # -# js-annoyances: Get rid of particularly annoying JavaScript abuse +# js-annoyances: Get rid of particularly annoying JavaScript abuse. # ################################################################################# -FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse +FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse. # Note: Most of these jobs would be safer if restricted to a # )|$1never|sigU # If we allow window.open, we want normal window features: @@ -102,17 +120,30 @@ s/(open\s*\([^\)]+toolbar=)(["']?)(?:no|0)\2/$1$2yes$2/sigU s/(open\s*\([^\)]+directories=)(["']?)(?:no|0)\2/$1$2yes$2/sigU s/(open\s*\([^\)]+fullscreen=)(["']?)(?:yes|1)\2/$1$2no$2/sigU s/(open\s*\([^\)]+always(?:raised|lowered)=)(["']?)(?:yes|1)\2/$1$2no$2/sigU -s/(open\s*\([^\)]+zlock=)(["']?)(?:yes|1)\2/$1$2no$2/sigU +s/(open\s*\([^\)]+z-?lock=)(["']?)(?:yes|1)\2/$1$2no$2/sigU s/(open\s*\([^\)]+hotkeys=)(["']?)(?:yes|1)\2/$1$2no$2/sigU -s/(open\s*\([^\)]+titlebar=)(["']?)(?:yes|1)\2/$1$2yes$2/sigU +s/(open\s*\([^\)]+titlebar=)(["']?)(?:no|0)\2/$1$2yes$2/sigU +s/(open\s*\([^\)]+always(?:raised|lowered)=)(["']?)(?:yes|1)\2/$1$2no$2/sigU + + +################################################################################# +# +# js-events: Kill all JS event bindings and timers (Radically destructive! Only for extra nasty sites). +# +################################################################################# +FILTER: js-events Kill all JS event bindings and timers (Radically destructive! Only for extra nasty sites). +s/(on|event\.)((mouse(over|out|down|up|move))|(un)?load|contextmenu|selectstart)/never/ig +# Not events, but abused on the same type of sites: +s/(alert|confirm)\s*\(/concat(/ig +s/settimeout\(/concat(/ig ################################################################################# # -# html-annoyances: Get rid of particularly annoying HTML abuse +# html-annoyances: Get rid of particularly annoying HTML abuse. # ################################################################################# -FILTER: html-annoyances Get rid of particularly annoying HTML abuse +FILTER: html-annoyances Get rid of particularly annoying HTML abuse. # New browser windows (if allowed -- see no-popups filter below) should be # resizeable and have a location and status bar @@ -123,21 +154,21 @@ s/(]+status=)(['"]?)(?:no|0)\2/$1$2yes1$2/igU s/(]+scrolling=)(['"]?)(?:no|0)\2/$1$2auto$2/igU s/(]+menubar=)(['"]?)(?:no|0)\2/$1$2yes$2/igU -# The tag was a crime! +# The and tags were crimes! # -s*|**ig +s---sigU ################################################################################# # -# content-cookies: Kill cookies that come in the HTML or JS content +# content-cookies: Kill cookies that come in the HTML or JS content. # ################################################################################# -FILTER: content-cookies Kill cookies that come in the HTML or JS content +FILTER: content-cookies Kill cookies that come in the HTML or JS content. -# JS cookies, like found on privacy.net: +# JS cookies, except those used by antiadbuster.com to detect us: # -s|document\.cookie(?=[ \t\r\n]*=)|ZappedCookie|ig +s|(\w+\.)+cookie(?=[ \t\r\n]*=)(?!='aab)|ZappedCookie|ig # HTML cookies: # @@ -146,73 +177,61 @@ s|||igU ################################################################################# # -# webbugs: Squish WebBugs (1x1 invisible GIFs used for user tracking) +# refresh-tags: Kill automatic refresh tags (for dial-on-demand setups). # ################################################################################# -FILTER: webbugs Squish WebBugs (1x1 invisible GIFs used for user tracking) - -s/]*(?:width|height)\s*=\s*['"]?1(?=\D)[^>]*(?:width|height)\s*=\s*['"]?1(?=\D)[^>]*?>//siUg - +FILTER: refresh-tags Kill automatic refresh tags (for dial-on-demand setups). -################################################################################## -# -# popups: Kill all popups in JS and HTML +# Note: Only deactivates refreshes with more than 9 seconds delay to +# preserve monster-stupid but common redirections via meta tags. # -################################################################################# -FILTER: popups Kill all popups in JS and HTML - -s/([\n =;{}]|window\.)open\s*\\?\(/$1concat(/ig # JavaScript -s/ target\s*=\s*(['"]?)(_blank|_new)\1?/ notarget/ig # HTML +s/\2]*))?\2/]*)framespacing=(['"]?)(no|0)\2/$1/igU -s/(]*)frameborder=(['"]?)(no|0)\2/$1/igU -s/(]*)border=(['"]?)(no|0)\2/$1/igU -s/(]*)noresize/$1/igU -s/(]*)frameborder=(['"]?)(no|0)\2/$1/igU -s/(]*)scrolling=(['"]?)(no|0)\2/$1/igU +s+([^'"]\s*)(?=\s*[^'"])+$1+isU +s@([^\w\s.]\s*)((?:map)?(window|this|parent)\.?)?open\s*\(@$1PrivoxyWindowOpen(@ig +s+([^'"]\s*)(?!\s*(\\n|'|"))+$1+iU -################################################################################# +################################################################################## # -# refresh-tags: Kill automatic refresh tags (for dial-on-demand setups) +# all-popups: Kill all popups in JavaScript and HTML. # ################################################################################# -FILTER: refresh-tags Kill automatic refresh tags (for dial-on-demand setups) +FILTER: all-popups Kill all popups in JavaScript and HTML. -# Note: Only deactivates refreshes with more than 9 seconds delay to -# preserve monster-stupid but common redirections via meta tags. -# -s/\2]*))?\2/ tags to make the banners-by-* filters more effective +# img-reorder: Reorder attributes in tags to make the banners-by-* filters more effective. # ################################################################################# -FILTER: img-reorder Reorder attributes in tags to make the banners-by-* filters more effective +FILTER: img-reorder Reorder attributes in 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. # This makes banners-by-size more effective and allows both banners-by-size -# and banners-by-link to preserve the original image URL in the alt attribute. +# and banners-by-link to preserve the original image URL in the title attribute. s|]*) src\s*=\s*(['"])([^>\\\2]+)\2|]*) src\s*=\s*([^'">\\\s]+)|\\\\2]+\2\|[^'">\\\s]+?))([^>]*)width\s*=\s*(["']?)(\d+?)|\\\\2]*\2\|[^'">\\\s]+?))([^>]*)\s+width\s*=\s*(["']?)(\d+?)\4|\\\\2]+\2\|[^'">\\\s]+?))([^>]*)width\s*=\s*(["']?)(\d+? # Note2: Use img-reorder before this filter to ensure maximum matching success # ################################################################################# -FILTER: banners-by-size Kill banners by size +FILTER: banners-by-size Kill banners by size. # 88*31 -s@\\\1\s]+)\1)?[^>]*?(width=(['"]?)88\4)[^>]*?(height=(['"]?)31\6)[^>]*>@$1Killed-$2-by-size$1@sig +s@\\\1\s]+)\1)?[^>]*?(width=(['"]?)88\4)[^>]*?(height=(['"]?)31\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)120\4)[^>]*?(height=(['"]?)(?:600?|90|240)\6)[^>]*>@$1Killed-$2-by-size$1@sig +s@\\\1\s]+)\1)?[^>]*?(width=(['"]?)120\4)[^>]*?(height=(['"]?)(?:600?|90|240)\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)125\4)[^>]*?(height=(['"]?)125\6)[^>]*>@$1Killed-$2-by-size$1@sig +s@\\\1\s]+)\1)?[^>]*?(width=(['"]?)125\4)[^>]*?(height=(['"]?)125\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)160\4)[^>]*?(height=(['"]?)600\6)[^>]*>@$1Killed-$2-by-size$1@sig +s@\\\1\s]+)\1)?[^>]*?(width=(['"]?)160\4)[^>]*?(height=(['"]?)600\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)180\4)[^>]*?(height=(['"]?)150\6)[^>]*>@$1Killed-$2-by-size$1@sig +s@\\\1\s]+)\1)?[^>]*?(width=(['"]?)180\4)[^>]*?(height=(['"]?)150\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:234|468)\4)[^>]*?(height=(['"]?)60\6)[^>]*>@$1Killed-$2-by-size$1@sig +s@\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:234|468)\4)[^>]*?(height=(['"]?)60\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)240\4)[^>]*?(height=(['"]?)400\6)[^>]*>@$1Killed-$2-by-size$1@sig +s@\\\1\s]+)\1)?[^>]*?(width=(['"]?)240\4)[^>]*?(height=(['"]?)400\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:250|300)\4)[^>]*?(height=(['"]?)250\6)[^>]*>@$1Killed-$2-by-size$1@sig +s@\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:250|300)\4)[^>]*?(height=(['"]?)250\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)336\4)[^>]*?(height=(['"]?)280\6)[^>]*>@$1Killed-$2-by-size$1@sig +s@\\\1\s]+)\1)?[^>]*?(width=(['"]?)336\4)[^>]*?(height=(['"]?)280\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)200\4)[^>]*?(height=(['"]?)50\6)[^>]*>@$1Killed-$2-by-size$1@sig +#s@\\\1\s]+)\1)?[^>]*?(width=(['"]?)200\4)[^>]*?(height=(['"]?)50\6)[^>]*?(?=/?>)@\ +# \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 \ +| doubleclick\.net/jump/ # redirs for doublecklick.net ads \ +| counter # common \ +| (?\1\s]*)\1[^>]*>\s*\\\3\s]+)\3)?[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\6)[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\8)[^>]*>\ -@$1Killed@sigx +)[^>\1\s]*)\1[^>]*>\s*\\\3\s]+)\3)?[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\6)[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\8)[^>]*?(?=/?>)\ +@\1\s]*?(?:adclick|atwola\.com/(?:link|redir)|doubleclick\.net/jump/|tracker|counter|adlog\.pl)[^>\1\s]*)\1[^>]*>\s*\\\3\s]+)\3)?[^>]*>@$1Killed@sig +s@\1\s]*?(?:ad(?:click|vert)|atwola\.com/(?:link|redir)|doubleclick\.net/jump/|(?\1\s]*)\1[^>]*>\s*\\\3\s]+)\3)?[^>]*?(?=/?>)@]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*?>@@siUg + + +################################################################################# +# +# tiny-textforms: Extend those tiny textareas up to 40x80 and kill the hard wrap. +# +################################################################################# +FILTER: tiny-textforms Extend those tiny textareas up to 40x80 and kill the hard wrap. + +s/(]*?)(?:\s*(?:rows|cols)=(['"]?)\d+\2)+/$1 rows=$2\40$2 cols=$2\80$2/ig +s/(]*?)wrap=(['"]?)hard\2/$1/ig + + +################################################################################# +# +# jumping-windows: Prevent windows from resizing and moving themselves. +# +################################################################################# +FILTER: jumping-windows Prevent windows from resizing and moving themselves. + +s/(?<=[\W])(?:window|this|self)\.(?:move|resize)(?:to|by)\(/''.concat(/ig + +################################################################################# +# +# frameset-borders: Give frames a border, make them resizable and scrollable. +# +################################################################################# +FILTER: frameset-borders Give frames a border and make them resizable. + +s/(]*)framespacing=(['"]?)(no|0)\2/$1/igU +s/(]*)frameborder=(['"]?)(no|0)\2/$1/igU +s/(]*)border=(['"]?)(no|0)\2/$1/igU +s/(]*)noresize/$1/igU +s/(]*)frameborder=(['"]?)(no|0)\2/$1/igU +s/(]*)scrolling=(['"]?)(no|0)\2/$1/igU + + + +################################################################################# +# +# demoronizer: Correct Microsoft's abuse of standardized character sets, which +# leave the browser to (mis)-interpret unknown characters, with +# sometimes bizarre results on non-MS platforms. +# +# credit: ripped from the demoroniser.pl script by: +# John Walker -- January 1998, http://www.fourmilab.ch/webtools/demoroniser +# +################################################################################# +FILTER: demoronizer Fix MS's non-standard use of standard charsets. + +s/(&\#[0-2]\d\d)\s/$1; /g +# per Robert Lynch: http://slate.msn.com//?id=2067547, just a guess. +# Must come before x94 below. +s/\xE2\x80\x94/ -- /g +s/\x82/,/g +#s-\x83-f-g +s/\x84/,,/g +s/\x85/.../g +#s/\x88/^/g +#s-\x89- °/°°-g +s/\x8B/~-g +#s-\x99-TM-g +# per Robert Lynch. +s/\x9B/>/g # 155 + + +################################################################################# +# +# shockwave-flash: Kill embedded Shockwave Flash objects. +# Note: Better just block "/.*\.swf$"! +# +################################################################################# +FILTER: shockwave-flash Kill embedded Shockwave Flash objects. + +s|]*macromedia.*||sigU +s|]*(application/x-shockwave-flash\|\.swf).*>(.*)?||sigU + + +################################################################################# +# +# quicktime-kioskmode: Make Quicktime movies saveable. +# +################################################################################# +FILTER: quicktime-kioskmode Make Quicktime movies saveable. + +s/(]*)kioskmode\s*=\s*(["']?)true\2/$1/ig + ################################################################################# # @@ -280,11 +417,13 @@ s@\1\s]*?(?:adclick|atwola\.com/(?:link|redir)|double ################################################################################# FILTER: fun Text replacements for subversive browsing fun! -s/microsoft(?!.com)/MicroSuck/ig +# SCNR +# +s/microsoft(?!.[^\s])/MicroSuck/ig # Buzzword Bingo (example for extended regex syntax) # -s* industry[ -]leading \ +s* (?:industry|world)[ -]leading \ | cutting[ -]edge \ | customer[ -]focused \ | market[ -]driven \ @@ -294,141 +433,700 @@ s* industry[ -]leading \ | unmatched \ | unparalleled \ | unrivalled \ -*BINGO! \ +*$0Bingo! \ *igx +# For Germans only +# +s/(M|m)edien(?![^<]*>)/$1ädchen/Ug ################################################################################# # -# nimda: Remove Nimda (virus) code +# crude-parental: Crude parental filtering. Use with a suitable blocklist. +# Pages are "blocked" based on keyword matching. # ################################################################################# -FILTER: nimda Remove Nimda (virus) code +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%^.*(?Blocked\ +

Blocked by Privoxy's crude-parental filter due to possible adult content.

%is +s+^.*warez.*$+No Warez

You're not searching for illegal stuff, are you?

+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 + + +################################################################################# +# +# IE-Exploits: Disable some known Internet Explorer bug exploits. +# +################################################################################# +FILTER: ie-exploits Disable some known Internet Explorer bug exploits. + +# Note: This is basically a demo and waits for someone more interested in IE +# security (sic!) to take over. + +# Cross-site-scripting: +# +s%f\("javascript:location.replace\('mk:@MSITStore:C:'\)"\);%alert\("This page looks like it tries to use a vulnerability described here:\n http://online.securityfocus.com/archive/1/298748/2002-11-02/2002-11-08/2"\);%siU + +# Address bar spoofing (http://www.secunia.com/advisories/10395/): +# +s/(]*href[^>]*)(?:\x01|\x02|\x03|%0[012])@/$1MALICIOUS-LINK@/ig + +# Nimda: +# s%%
WARNING: This Server is infected with Nimda!%g ################################################################################# # -# shockwave-flash: Kill embedded Shockwave Flash objects +# +# site-specifics: Cure for site-specific problems. Don't apply generally! +# +# Note: The fixes contained here are so specific to the problems of the +# particular web sites they are designed for that they would be a +# waste of CPU cycles (or even destructive!) on 99.9% of the web +# sites where they don't apply. # ################################################################################# -FILTER: shockwave-flash Kill embedded Shockwave Flash objects +FILTER: site-specifics Cure for site-specific problems. Don't apply generally! + +# www.spiegel.de excludes X11 users from viewing Flash5 objects - shame. +# Apply to: www.spiegel.de/static/js/flash-plugin.js +# +s/indexOf\("x11"\)/indexOf("x13")/ + +# www.quelle-bausparkasse.de uses a very stupid redirect mechanism that +# relies on a webbug being present. Can we tolerate that? No! +# Apply to: www.quelle-bausparkasse.de/$ +# +s/mylogfunc()//g -s|]*application/x-shockwave-flash.*||sigU +# groups.yahoo.com has splash pages that one needs to click through in +# order to access the actual messages. Let the browser do that. Thanks +# to Paul Jobson for this one: +# +s|(?:Continue to message\|Weiter zu Nachricht)||ig +# monster.com has two very similar gimmicks: +# +s|||i + +s|||i + +# nytimes.com triggers popups through the onload handler of dummy images +# to fool popup-blockers. +# +s|(]*)onload|$1never|sig + +# Pre-check all the "Discard" buttons in GNU Mailman's web interface. +# (This saves a lot of mouse aiming practice when flushing spamtraps) +# +s|( and tags. +# +################################################################################# +FILTER: no-ping Removes non-standard ping attributes in and tags. +s@(]*?)\sping=(['"]?)([^"'>]+)\2([>\s]?)@\ +PING!\n$1$4@ig + +################################################################################# +# +# google: CSS-based block for Google text ads. Also removes +# a width limitation and the toolbar advertisement. # ################################################################################# -FILTER: quicktime-kioskmode Make Quicktime movies saveable +FILTER: google CSS-based block for Google text ads. Also removes a width limitation and the toolbar advertisement. -s/(]*)kioskmode\s*=\s*(["']?)true\2/$1/ig +s@@\n$0@ +s@
@
@ +s@(
@\n\n$0@ ################################################################################# # -# js-events: Kill all JS event bindings (Radically destructive! Only for extra nasty sites) +# msn: CSS-based block for MSN text ads. Also removes tracking URLs +# and a width limitation. # ################################################################################# -FILTER: js-events Kill all JS event bindings (Radically destructive! Only for extra nasty sites) +FILTER: msn CSS-based block for MSN text ads. Also removes tracking URLs and a width limitation. -s/(on|event\.)((mouse(over|out|down|up|move))|(un)?load|contextmenu|selectstart)/never/ig -# Not events, but abused on the same type of sites: -s/(alert|confirm)\s*\(/concat(/ig +s@@\n$0@ +s@(]*) id=(["']?)ads_[^\2]*\2@$1 class="msn_ads"@Uig +s@(]*href=\")http://g.msn.com/.*\?(http://.*)(&&DI=.*)(\")@$1$2$4@Ug +s@(]*)gping=\".*\"@$1 title="URL cleaned up by Privoxy's msn filter"@Ug +################################################################################# +# +# blogspot: Cleans up some Blogspot blogs. Read the fine print before using this. +# +# This filter also intentionally removes some navigation stuff and +# sets the page width to 100%. As a result, some rounded "corners" would +# 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@@\n$0@ +s@|(
([^\s]*).*?\.\.\.\s*(\1)@$2@ig ################################################################################# # -# crude-parental: Crude parental filtering? (Use along with a suitable blocklist). -# Shows how to deny access to whole page based on a keyword. +# 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. # ################################################################################# -FILTER: crude-parental Crude parental filtering (demo only) +SERVER-HEADER-FILTER: x-httpd-php-to-html Changes the Content-Type header from x-httpd-php to html. -# (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words) -# (Note #2: Is 'sex' a rude word?!) +s@^(Content-Type:)\s*application/x-httpd-php@$1 text/html@i -s%^.*(?Blocked

Blocked due to possible adult content. Please see this site.

%is -s+^.*warez.*$+No Warez

You're not searching for illegal stuff, are you?

+is +################################################################################# +# +# 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$2@i ################################################################################# # -# demoronizer: Correct Microsoft's abuse of standardized character sets, which -# leave the browser to (mis)-interpret unknown characters, with -# sometimes bizarre results on non-MS platforms. +# xml-to-html: Changes the Content-Type header from xml to html. # -# credit: ripped from the demoroniser.pl script by: -# John Walker -- January 1998, http://www.fourmilab.ch/webtools/demoroniser +################################################################################# +SERVER-HEADER-FILTER: xml-to-html Changes the Content-Type header from xml to html. + +s@^(Content-Type:)\s*(?:application|text)/(?:xhtml\+)?xml(;.*)?$@$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: demoronizer fixing MS's non-standard use of std charsets. +CLIENT-HEADER-FILTER: hide-tor-exit-notation Removes the Tor exit node notation in Host and Referer headers. + +s@^((?:Referer|Host):\s*(?:https?://)?[^/]*)\.[^\./]*?\.exit@$1@i + +################################################################################# +# +# less-download-windows: Prevents annoying download windows for content types +# the browser can handle itself. +# +################################################################################# +SERVER-HEADER-FILTER: less-download-windows Prevent annoying download windows for content types the browser can handle itself. + +s@^Content-Disposition:.*filename=(["']?).*\.(png|gif|jpe?g|diff?|d?patch|c|h|pl|shar)\1.*$@@i +s@^(Content-Type:)\s*(?:message/(?:news|rfc822)|text/x-.*|application/x-sh(?:\s|$))\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 + +################################################################################# +# +# 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 +# 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 -s/(&\#[0-2]\d\d)\s/$1; /g -# per Robert Lynch: http://slate.msn.com//?id=2067547, just a guess. -# Must come before x94 below. -s/\xE2\x80\x94/ -- /g -s/\x82/,/g -#s-\x83-f-g -s/\x84/,,/g -s/\x85/.../g -#s/\x88/^/g -#s-\x89- °/°°-g -s/\x8B/~-g -#s-\x99-TM-g -# per Robert Lynch. -s/\x9B/>/g # 155 ############################################################################## # # Revisions : # $Log: default.filter,v $ -# Revision 1.16 2002/11/11 13:40:38 oes +# 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. +# +# 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 "<". +# +# 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. +# +# Revision 1.19 2006/07/18 14:48:45 david__schmidt +# Reorganizing the repository: swapping out what was HEAD (the old 3.1 branch) +# with what was really the latest development (the v_3_0_branch branch) +# +# Revision 1.11.2.23 2004/02/17 13:34:01 oes +# - Beefed up the protection of the unsolicited-popups +# filter against matching in JavaScript string constants. +# - Extended the fun filter with a German joke +# - Extended the site-specifics filter with a convenience +# reeplacement for managing mailing lists at SourceForge +# +# Revision 1.11.2.22 2004/01/30 15:29:29 oes +# Updated the copyright note +# +# Revision 1.11.2.21 2004/01/20 15:15:01 oes +# Detail enhancement in all-popups +# +# Revision 1.11.2.20 2004/01/06 16:46:14 oes +# Fixed a JS syntax problem in jumping-windows +# +# Revision 1.11.2.19 2003/12/17 17:09:25 oes +# Added remedy against IE address bar spoofing +# +# Revision 1.11.2.18 2003/12/02 11:25:27 oes +# Fixed a line trashed in previous commit +# +# Revision 1.11.2.17 2003/12/01 21:58:46 oes +# Assorted tuning: +# +# - unsolicited-popups no longer matches at start or end of quoted +# strings, and is now activated earlier and deactivated later in +# the page. +# - replacement images in banners-by-* now without border +# - more effective shockwave flash flattening +# - Custom annoyance filtering for Yahoo Groups, Monster.com, NY Times. +# +# Revision 1.11.2.16 2003/05/08 09:44:56 oes +# Allow extra parameters in blink,marquee tags. Fixes bug #734012 +# +# Revision 1.11.2.15 2003/03/30 13:57:08 oes +# Making unsolicited-popups safe for use on tags enclosed in JS strings +# +# Revision 1.11.2.14 2003/03/19 13:17:50 oes +# - Added filter "site-specifics" to address site specific problems +# - Fixed a small problem in the img-reorder filter +# +# Revision 1.11.2.13 2003/03/18 19:28:59 oes +# Fixed a minor problem in the img-reorder filter +# +# Revision 1.11.2.12 2003/03/15 14:06:58 oes +# - Assorted refinements, optimizations and fixes in the js-annoyances, +# img-reorder, banners-by-size, banners-by-link, webbugs, refresh-tags, +# html-annoyances, content-cookies and fun filters +# - Replaced filter "popups" by choice between two modes: +# - "unsolicited-popups" tries to catch only the unsolicited ones +# - "all-popups" tries to kill them all (as before) +# - New filter "tiny-textforms" Help those tiny or hard-wrap textareas. +# - New filter "jumping-windows" that prevents windows from resizing +# and moving themselves +# - Replaced "nimda" with more general "ie-exploits" filter in which +# all filters for exploits shall be collected +# +# Revision 1.11.2.11 2002/11/12 16:14:43 oes +# Exchanged js-annoyance filter against status bar rewrites with improved version by Don Libes +# +# Revision 1.11.2.10 2002/11/11 13:39:47 oes # Make refresh-tags filter work even on incorrect refresh tags like found on usatoday.com # -# Revision 1.15 2002/11/08 16:40:56 oes +# Revision 1.11.2.9 2002/11/08 16:39:17 oes # Made img-reorder more cautious. Fixes bug #632715 # -# Revision 1.14 2002/10/13 21:58:20 hal9 -# Add demoronizer filter to sync with 3.0.1. +# Revision 1.11.2.8 2002/10/13 21:56:52 hal9 +# Adding demoronizer filter. This should include all the common abuses. I have +# left a few of the rare cases commented out (never found these in the wild). # -# Revision 1.13 2002/09/11 16:04:20 oes +# Revision 1.11.2.7 2002/09/25 15:09:39 oes # Preserve original quoting style in tags wherever possible. Fixes Bug #605956 # -# Revision 1.12 2002/09/05 14:55:38 oes -# Synced with the stable branch: -# Revision 1.11.2.6 2002/08/23 14:12:26 oes -# Proofed frameset-borders against "fremaborder=0 border=0" +# Revision 1.11.2.6 2002/08/23 14:12:26 oes +# Proofed frameset-borders against "fremaborder=0 border=0" # -# Revision 1.11.2.5 2002/08/22 15:05:20 oes -# Added Filter to make Quicktime movies saveable (thanks to aaron@linville.org for the idea) +# Revision 1.11.2.5 2002/08/22 15:05:20 oes +# Added Filter to make Quicktime movies saveable (thanks to aaron@linville.org for the idea) # -# Revision 1.11.2.4 2002/08/10 11:32:29 oes -# Attribute values in replacement tags of banners-by-size filter now undelimited. (Fixes bug #592493) +# Revision 1.11.2.4 2002/08/10 11:32:29 oes +# Attribute values in replacement tags of banners-by-size filter now undelimited. (Fixes bug #592493) # -# Revision 1.11.2.3 2002/08/05 11:43:56 oes -# Fixed a bug in the popups filter that was introduced with the last fix :-( +# Revision 1.11.2.3 2002/08/05 11:43:56 oes +# Fixed a bug in the popups filter that was introduced with the last fix :-( # -# Revision 1.11.2.2 2002/08/01 11:20:13 oes -# Fixed bugs 587802, 577802 and an unreported one +# Revision 1.11.2.2 2002/08/01 11:20:13 oes +# Fixed bugs 587802, 577802 and an unreported one # -# Revision 1.11.2.1 2002/07/26 15:18:26 oes -# - All filters reviewed and many shorcomings fixed -# - New filters: img-reorder, banners-by-link and js-events -# - Jobs reorderd because they are now executed in order of -# appearance +# Revision 1.11.2.1 2002/07/26 15:18:26 oes +# - All filters reviewed and many shorcomings fixed +# - New filters: img-reorder, banners-by-link and js-events +# - Jobs reorderd because they are now executed in order of +# appearance # # Revision 1.11 2002/05/24 00:57:18 oes # Made WeBugs job ungreedy; Fixes bug 559190 @@ -526,3 +1224,5 @@ s/\x9B/>/g # 155 # # # + +