X-Git-Url: http://www.privoxy.org/gitweb/?p=privoxy.git;a=blobdiff_plain;f=default.filter;h=111f75f2a4c058dffab2b89c366238d3ec5557fa;hp=16dfa58ad24ad4866d0116a55a55cddaba06e4a5;hb=7d0d27186d473655bc895c40515277d4e6488439;hpb=0eb9346eb1ad546b959637b92ba74b807e5a28fb diff --git a/default.filter b/default.filter index 16dfa58a..111f75f2 100644 --- a/default.filter +++ b/default.filter @@ -2,17 +2,13 @@ # # File : $Source: /cvsroot/ijbswa/current/default.filter,v $ # -# $Id: default.filter,v 1.5 2002/03/27 15:30:26 swa Exp $ +# $Id: default.filter,v 1.44 2007/07/18 11:06:56 hal9 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/ # -# Based on the Internet Junkbuster originally written -# by and Copyright (C) 1997 Anonymous Coders and -# Junkbusters Corporation. http://www.junkbusters.com -# # We value your feedback. However, to provide you with the best support, # please note: # @@ -41,8 +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. @@ -50,64 +50,113 @@ # 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 # 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. # ################################################################################# ################################################################################# # -# html-annoyances: Get rid of particularly annoying HTML abuse +# js-annoyances: Get rid of particularly annoying JavaScript abuse # ################################################################################# -FILTER: html-annoyances Get rid of particularly annoying HTML abuse +FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse -# New browser windows (if allowed -- see no-popups filter below) should be -# resizeable and have a location and status bar +# Note: Most of these jobs would be safer if restricted to a +# )|$1never|sigU + +# If we allow window.open, we want normal window features: +# Test: http://www.htmlgoodies.com/beyond/notitle.html +# +s/(open\s*\([^\)]+resizable=)(["']?)(?:no|0)\2/$1$2yes$2/sigU +s/(open\s*\([^\)]+location=)(["']?)(?:no|0)\2/$1$2yes$2/sigU +s/(open\s*\([^\)]+status=)(["']?)(?:no|0)\2/$1$2yes$2/sigU +s/(open\s*\([^\)]+scroll(?:ing|bars)=)(["']?)(?:no|0)\2/$1$2auto$2/sigU +s/(open\s*\([^\)]+menubar=)(["']?)(?:no|0)\2/$1$2yes$2/sigU +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*\([^\)]+z-?lock=)(["']?)(?:yes|1)\2/$1$2no$2/sigU +s/(open\s*\([^\)]+hotkeys=)(["']?)(?:yes|1)\2/$1$2no$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-annoyances: Get rid of particularly annoying JavaScript abuse +# js-events: Kill all JS event bindings and timers (Radically destructive! Only for extra nasty sites) # ################################################################################# -FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse +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 -# Get rid of Javascript referrer tracking. Test page: http://www.randomoddness.com/untitled.htm +################################################################################# +# +# html-annoyances: Get rid of particularly annoying HTML abuse # -s|()|$1"Not Your Business!"$2|Usg +################################################################################# +FILTER: html-annoyances Get rid of particularly annoying HTML abuse -# The status bar is for displaying link targets, not pointless blahblah +# New browser windows (if allowed -- see no-popups filter below) should be +# resizeable and have a location and status bar # -s/status='.*?';*//ig +s/(]+resizable=)(['"]?)(?:no|0)\2/$1$2yes$2/igU +s/(]+location=)(['"]?)(?:no|0)\2/$1$2yes$2/igU +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 -# Kill OnUnload popups. Yummy. Test: http://www.zdnet.com/zdsubs/yahoo/tree/yfs.html +# The and tags were crimes! # -s/()/$1never$2/iU +s---sigU ################################################################################# @@ -117,57 +166,247 @@ s/()/$1never$2/iU ################################################################################# 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]*=)|documenZapCooky$2|g +s|(\w+\.)+cookie(?=[ \t\r\n]*=)(?!='aab)|ZappedCookie|ig # HTML cookies: # -s|].*>||iUT +s|||igU + + +################################################################################# +# +# refresh-tags: Kill automatic refresh tags (for dial-on-demand setups) +# +################################################################################# +FILTER: refresh-tags Kill automatic refresh tags (for dial-on-demand setups) + +# Note: Only deactivates refreshes with more than 9 seconds delay to +# preserve monster-stupid but common redirections via meta tags. +# +s/\2]*))?\2/)(?=\s*[^'"])+$1+isU +s@([^\w\s.]\s*)((?:map)?(window|this|parent)\.?)?open\s*\(@$1PrivoxyWindowOpen(@ig +s+([^'"]\s*)(?!\s*(\\n|'|"))+$1+iU ################################################################################## # -# no-popups: Kill all popups in JS and HTML +# all-popups: Kill all popups in JavaScript and HTML # ################################################################################# -FILTER: no-popups Kill all popups in JS and HTML +FILTER: all-popups Kill all popups in JavaScript and 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 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 title attribute. + +s|]*) src\s*=\s*(['"])([^>\\\2]+)\2|]*) src\s*=\s*([^'">\\\s]+)|\\\\2]*\2\|[^'">\\\s]+?))([^>]*)\s+width\s*=\s*(["']?)(\d+?)\4|\\\1\s]+)\1)?[^>]*?(width=(['"]?)88\4)[^>]*?(height=(['"]?)31\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)120\4)[^>]*?(height=(['"]?)(?:600?|90|240)\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)125\4)[^>]*?(height=(['"]?)125\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)160\4)[^>]*?(height=(['"]?)600\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)180\4)[^>]*?(height=(['"]?)150\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:234|468)\4)[^>]*?(height=(['"]?)60\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)240\4)[^>]*?(height=(['"]?)400\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:250|300)\4)[^>]*?(height=(['"]?)250\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)336\4)[^>]*?(height=(['"]?)280\6)[^>]*?(?=/?>)@\ + \\\1\s]+)\1)?[^>]*?(width=(['"]?)200\4)[^>]*?(height=(['"]?)50\6)[^>]*?(?=/?>)@\ +# ]+)framespacing=['"]?(no|0)['"]?(.*>)/$1$3/igU -s/(]+)frameborder=['"]?(no|0)['"]?(.*>)/$1$3/igU -s/(]+)border=['"]?(no|0)['"]?(.*>)/$1$3/igU -s/(]+)resizable=['"]?(no|0|false)['"]?(.*>)/$1$3/igU ################################################################################# # +# banners-by-link: Kill banners by their links to known clicktrackers (Experimental) +# +################################################################################# +FILTER: banners-by-link Kill banners by their links to known clicktrackers + +# Common case with width and height attributes: +# +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*\\\3\s]+)\3)?[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\6)[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\8)[^>]*?(?=/?>)\ +@\1\s]*?(?:ad(?:click|vert)|atwola\.com/(?:link|redir)|doubleclick\.net/jump/|tracker|counter|adlog\.pl)[^>\1\s]*)\1[^>]*>\s*\\\3\s]+)\3)?[^>]*?(?=/?>)@]*?(width|height)\s*=\s*['"]?1\D[^>]*?(width|height)\s*=\s*['"]?1(\D[^>]*?)?>//sig +s@]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*?>@@siUg ################################################################################# # -# no-refresh: Kill automatic refresh tags (for dial-on-demand setups) +# tiny-textforms: Extend those tiny textareas up to 40x80 and kill the hard wrap # ################################################################################# -FILTER: no-refresh Kill automatic refresh tags (for dial-on-demand setups) +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 -s/]*)['"]?>//iU -s/].*>//iU + +################################################################################# +# +# 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 ################################################################################# @@ -177,87 +416,589 @@ s/].*>/$1@Us +s@(
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 1.11.2.9 2002/11/08 16:39:17 oes +# Made img-reorder more cautious. Fixes bug #632715 +# +# 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 1.11.2.7 2002/09/25 15:09:39 oes +# Preserve original quoting style in tags wherever possible. Fixes Bug #605956 +# +# 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 1.11.2.4 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 1.11.2.2 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 2002/05/24 00:57:18 oes +# Made WeBugs job ungreedy; Fixes bug 559190 +# +# Revision 1.10 2002/04/18 10:14:19 oes +# renamed some filters +# +# Revision 1.9 2002/04/11 07:36:35 oes +# Generalized js-popup filter +# +# Revision 1.8 2002/04/10 17:07:21 oes +# Fixed potentially desctructive jobs, added noflash filter +# +# Revision 1.7 2002/04/09 18:34:51 oes +# Fixed HTML syntax in replacements +# +# Revision 1.6 2002/04/03 19:49:52 swa +# name change +# # Revision 1.5 2002/03/27 15:30:26 swa # have a consistent appearance # @@ -336,3 +1077,5 @@ s+^.*warez.*$+No Warez

You're not sea # # # + +