1 # ********************************************************************
3 # File : $Source: /cvsroot/ijbswa/current/default.filter,v $
5 # $Id: default.filter,v 1.30 2006/10/18 12:36:50 fabiankeil Exp $
7 # Purpose : Rules to process the content of web pages
9 # Copyright : Written by and Copyright (C) 2001 - 2006 the
10 # Privoxy team. http://www.privoxy.org/
12 # We value your feedback. However, to provide you with the best support,
15 # * Use the support forum to get help:
16 # http://sourceforge.net/tracker/?group_id=11118&atid=211118
17 # * Submit bugs only thru our bug forum:
18 # http://sourceforge.net/tracker/?group_id=11118&atid=111118
19 # Make sure that the bug has not already been submitted. Please try
20 # to verify that it is a Privoxy bug, and not a browser or site
21 # bug first. If you are using your own custom configuration, please
22 # try the stock configs to see if the problem is a configuration
23 # related bug. And if not using the latest development snapshot,
24 # please try the latest one. Or even better, CVS sources.
25 # * Submit feature requests only thru our feature request forum:
26 # http://sourceforge.net/tracker/?atid=361118&group_id=11118&func=browse
28 # For any other issues, feel free to use the mailing lists:
29 # http://sourceforge.net/mail/?group_id=11118
31 # Anyone interested in actively participating in development and related
32 # discussions can join the appropriate mailing list here:
33 # http://sourceforge.net/mail/?group_id=11118. Archives are available
36 #################################################################################
40 # Filters start with a line "FILTER: name description". They are then referrable
41 # from the actionsfile with +filter{name}
43 # Inside the filters, write one Perl-Style substitution (job) per line.
44 # Jobs that precede the first FILTER: line are ignored.
46 # For Details see the pcrs manpage contained in this distribution.
47 # (and the perlre, perlop and pcre manpages)
49 # Note that you are free to choose the delimter as you see fit.
51 # Note2: In addidion to the Perl options gimsx, the following nonstandard
52 # options are supported:
54 # 'U' turns the default to ungreedy matching. Add ? to quantifiers to
55 # switch back to greedy.
56 # 'T' (trivial) prevents parsing for backreferences in the substitute.
57 # Use if you want to include text like '$&' in your substitute without
60 #################################################################################
63 #################################################################################
65 # js-annoyances: Get rid of particularly annoying JavaScript abuse
67 #################################################################################
68 FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse
70 # Note: Most of these jobs would be safer if restricted to a
71 # <script> context as in:
73 # s/(<script.*)nasty-item(?=.*<\/script>)/$1replacement/sigU
75 # but that would make them match only the first occurance of
76 # nasty-item in each <script>. We need nestable jobs!
78 # Get rid of Javascript referrer tracking.
79 # Test page: http://www.javascript-page.com/referrer.html
81 s|(?:\w+\.)+referrer|"Not Your Business!"|gisU
83 # The status bar is for displaying link targets, not pointless blahblah
85 s/(\W\s*)((this|window)\.(default)?status)\s*=\s*((['"]).*?(?<!\\)\6)/$1if(typeof(this.href) != 'undefined') $2 = $5 + ' URL: ' + this.href;else return false/ig
87 # Kill OnUnload popups. Yummy.
88 # Test: http://www.zdnet.com/zdsubs/yahoo/tree/yfs.html
90 s/(<body\s+[^>]*)onunload/$1never/siU
91 s|(<script.*)window\.onunload(?=.*</script>)|$1never|sigU
93 # If we allow window.open, we want normal window features:
94 # Test: http://www.htmlgoodies.com/beyond/notitle.html
96 s/(open\s*\([^\)]+resizable=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
97 s/(open\s*\([^\)]+location=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
98 s/(open\s*\([^\)]+status=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
99 s/(open\s*\([^\)]+scroll(?:ing|bars)=)(["']?)(?:no|0)\2/$1$2auto$2/sigU
100 s/(open\s*\([^\)]+menubar=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
101 s/(open\s*\([^\)]+toolbar=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
102 s/(open\s*\([^\)]+directories=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
103 s/(open\s*\([^\)]+fullscreen=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
104 s/(open\s*\([^\)]+always(?:raised|lowered)=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
105 s/(open\s*\([^\)]+z-?lock=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
106 s/(open\s*\([^\)]+hotkeys=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
107 s/(open\s*\([^\)]+titlebar=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
108 s/(open\s*\([^\)]+always(?:raised|lowered)=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
111 #################################################################################
113 # js-events: Kill all JS event bindings and timers (Radically destructive! Only for extra nasty sites)
115 #################################################################################
116 FILTER: js-events Kill all JS event bindings and timers (Radically destructive! Only for extra nasty sites)
118 s/(on|event\.)((mouse(over|out|down|up|move))|(un)?load|contextmenu|selectstart)/never/ig
119 # Not events, but abused on the same type of sites:
120 s/(alert|confirm)\s*\(/concat(/ig
121 s/settimeout\(/concat(/ig
123 #################################################################################
125 # html-annoyances: Get rid of particularly annoying HTML abuse
127 #################################################################################
128 FILTER: html-annoyances Get rid of particularly annoying HTML abuse
130 # New browser windows (if allowed -- see no-popups filter below) should be
131 # resizeable and have a location and status bar
133 s/(<a\s+href[^>]+resizable=)(['"]?)(?:no|0)\2/$1$2yes$2/igU
134 s/(<a\s+href[^>]+location=)(['"]?)(?:no|0)\2/$1$2yes$2/igU
135 s/(<a\s+href[^>]+status=)(['"]?)(?:no|0)\2/$1$2yes1$2/igU
136 s/(<a\s+href[^>]+scrolling=)(['"]?)(?:no|0)\2/$1$2auto$2/igU
137 s/(<a\s+href[^>]+menubar=)(['"]?)(?:no|0)\2/$1$2yes$2/igU
139 # The <BLINK> and <MARQUEE> tags were crimes!
141 s-</?(blink|marquee).*>--sigU
144 #################################################################################
146 # content-cookies: Kill cookies that come in the HTML or JS content
148 #################################################################################
149 FILTER: content-cookies Kill cookies that come in the HTML or JS content
151 # JS cookies, except those used by antiadbuster.com to detect us:
153 s|(\w+\.)+cookie(?=[ \t\r\n]*=)(?!='aab)|ZappedCookie|ig
157 s|<meta\s+http-equiv=['"]?set-cookie.*>|<!-- ZappedCookie -->|igU
160 #################################################################################
162 # refresh-tags: Kill automatic refresh tags (for dial-on-demand setups)
164 #################################################################################
165 FILTER: refresh-tags Kill automatic refresh tags (for dial-on-demand setups)
167 # Note: Only deactivates refreshes with more than 9 seconds delay to
168 # preserve monster-stupid but common redirections via meta tags.
170 s/<meta\s+http-equiv\s*=\s*(['"]?)refresh\1\s+content\s*=\s*(['"]?)\d{2,}\s*(;\s*url\s*=\s*([^>\2]*))?\2/<link rev="x-refresh" href="$4"/iU
173 #################################################################################
175 # unsolicited-popups: Disable unsolicited pop-up windows
177 #################################################################################
178 FILTER: unsolicited-popups Disable only unsolicited pop-up windows
180 s+([^'"]\s*<head.*>)(?=\s*[^'"])+$1<script>function PrivoxyWindowOpen(){return(null);}</script>+isU
181 s+([^\w\s.]\s*)((window|this|parent)\.)?open\s*\(+$1PrivoxyWindowOpen(+ig
182 s+([^'"]\s*</html>)(?!\s*(\\n|'|"))+$1<script>function PrivoxyWindowOpen(a, b, c){return(window.open(a, b, c));}</script>+iU
185 ##################################################################################
187 # all-popups: Kill all popups in JavaScript and HTML
189 #################################################################################
190 FILTER: all-popups Kill all popups in JavaScript and HTML
192 s/((\W\s*)(window|this|parent)\.)open\s*\\?\(/$1concat(/ig # JavaScript
193 s/\starget\s*=\s*(['"]?)_?(blank|new)\1?/ notarget/ig # HTML
196 ##################################################################################
198 # img-reorder: Reorder attributes in <img> tags to make the banners-by-* filters more effective
200 #################################################################################
201 FILTER: img-reorder Reorder attributes in <img> tags to make the banners-by-* filters more effective
203 # In the first step src is moved to the start, then width is moved to the second
204 # place to guarantee an order of src, width, height.
205 # This makes banners-by-size more effective and allows both banners-by-size
206 # and banners-by-link to preserve the original image URL in the title attribute.
208 s|<img\s+?([^>]*) src\s*=\s*(['"])([^>\\\2]+)\2|<img src=$2$3$2 $1|siUg
209 s|<img\s+?([^>]*) src\s*=\s*([^'">\\\s]+)|<img src=$2 $1|sig
211 s|<img (src=(?:(['"])[^>\\\\2]*\2\|[^'">\\\s]+?))([^>]*)\s+width\s*=\s*(["']?)(\d+?)\4|<img $1 width=$4$5$4$3|siUg
214 #################################################################################
216 # banners-by-size: Kill banners by size
218 #################################################################################
220 # Standard banner sizes taken from http://www.iab.net/iab_banner_standards/bannersizes.html
222 # Note: Use http://config.privoxy.org/send-banner?type=trans for a transparent 1x1 image
223 # Use http://config.privoxy.org/send-banner?type=pattern for a grey/white pattern image
224 # Use http://config.privoxy.org/send-banner?type=auto to auto-select.
226 # Note2: Use img-reorder before this filter to ensure maximum matching success
228 #################################################################################
229 FILTER: banners-by-size Kill banners by size
232 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)88\4)[^>]*?(height=(['"]?)31\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
233 # 120*60, 120*90, 120*240, 120*600
234 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)120\4)[^>]*?(height=(['"]?)(?:600?|90|240)\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
236 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)125\4)[^>]*?(height=(['"]?)125\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
238 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)160\4)[^>]*?(height=(['"]?)600\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
240 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)180\4)[^>]*?(height=(['"]?)150\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
241 # 234*60, 468*60 (Most Banners!)
242 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:234|468)\4)[^>]*?(height=(['"]?)60\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
244 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)240\4)[^>]*?(height=(['"]?)400\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
246 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:250|300)\4)[^>]*?(height=(['"]?)250\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
248 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)336\4)[^>]*?(height=(['"]?)280\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
250 # Note: 200*50 was also proposed, but it probably causes too much collateral damage:
252 #s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)200\4)[^>]*?(height=(['"]?)50\6)[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed-$2-by-size$1 $3 $5>@sig
255 #################################################################################
257 # banners-by-link: Kill banners by their links to known clicktrackers (Experimental)
259 #################################################################################
260 FILTER: banners-by-link Kill banners by their links to known clicktrackers
262 # Common case with width and height attributes:
264 s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:\
265 adclick # See www.dn.se \
266 | atwola\.com/(?:link|redir) # see www.cnn.com \
267 | /jump/ # redirs for doublecklick.net ads \
268 | tracker | counter # common \
269 | adlog\.pl # see sf.net \
270 )[^>\1\s]*)\1[^>]*>\s*<img\s+(?:src\s*=\s*(['"]?)([^>\\\3\s]+)\3)?[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\6)[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\8)[^>]*>\
271 @<img $5 $7 src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed $4 by link to $2$1>@sigx
273 # Rare case w/o explicit dimensions:
275 s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:adclick|atwola\.com/(?:link|redir)|doubleclick\.net/jump/|tracker|counter|adlog\.pl)[^>\1\s]*)\1[^>]*>\s*<img\s+(?:src\s*=\s*(['"]?)([^>\\\3\s]+)\3)?[^>]*>@<img src=$1http://config.privoxy.org/send-banner?type=auto$1 border="0" title=$1Killed $4 by link to $2$1>@sig
278 ################################################################################
280 # webbugs: Squish WebBugs (1x1 invisible GIFs used for user tracking)
282 #################################################################################
283 FILTER: webbugs Squish WebBugs (1x1 invisible GIFs used for user tracking)
285 s@<img[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*?>@<!--\
286 Filtered by Privoxy's webbugs filter: $0 -->@siUg
289 #################################################################################
291 # tiny-textforms: Extend those tiny textareas up to 40x80 and kill the hard wrap
293 #################################################################################
294 FILTER: tiny-textforms Extend those tiny textareas up to 40x80 and kill the hard wrap
296 s/(<textarea[^>]*?)(?:\s*(?:rows|cols)=(['"]?)\d+\2)+/$1 rows=$2\40$2 cols=$2\80$2/ig
297 s/(<textarea[^>]*?)wrap=(['"]?)hard\2/$1/ig
300 #################################################################################
302 # jumping-windows: Prevent windows from resizing and moving themselves
304 #################################################################################
305 FILTER: jumping-windows Prevent windows from resizing and moving themselves
307 s/(?<=[\W])(?:window|this|self)\.(?:move|resize)(?:to|by)\(/''.concat(/ig
309 #################################################################################
311 # frameset-borders: Give frames a border, make them resizable and scrollable
313 #################################################################################
314 FILTER: frameset-borders Give frames a border and make them resizable
316 s/(<frameset\s+[^>]*)framespacing=(['"]?)(no|0)\2/$1/igU
317 s/(<frameset\s+[^>]*)frameborder=(['"]?)(no|0)\2/$1/igU
318 s/(<frameset\s+[^>]*)border=(['"]?)(no|0)\2/$1/igU
319 s/(<frame\s+[^>]*)noresize/$1/igU
320 s/(<frame\s+[^>]*)frameborder=(['"]?)(no|0)\2/$1/igU
321 s/(<frame\s+[^>]*)scrolling=(['"]?)(no|0)\2/$1/igU
325 #################################################################################
327 # demoronizer: Correct Microsoft's abuse of standardized character sets, which
328 # leave the browser to (mis)-interpret unknown characters, with
329 # sometimes bizarre results on non-MS platforms.
331 # credit: ripped from the demoroniser.pl script by:
332 # John Walker -- January 1998, http://www.fourmilab.ch/webtools/demoroniser
334 #################################################################################
335 FILTER: demoronizer Fix MS's non-standard use of standard charsets
337 s/(&\#[0-2]\d\d)\s/$1; /g
338 # per Robert Lynch: http://slate.msn.com//?id=2067547, just a guess.
339 # Must come before x94 below.
340 s/\xE2\x80\x94/ -- /g
352 # Bullet type character.
356 #s-\x98-<sup>~</sup>-g
357 #s-\x99-<sup>TM</sup>-g
362 #################################################################################
364 # shockwave-flash: Kill embedded Shockwave Flash objects
365 # Note: Better just block "/.*\.swf$"!
367 #################################################################################
368 FILTER: shockwave-flash Kill embedded Shockwave Flash objects
370 s|<object [^>]*macromedia.*</object>|<!-- Squished Shockwave Object -->|sigU
371 s|<embed [^>]*(application/x-shockwave-flash\|\.swf).*>(.*</embed>)?|<!-- Squished Shockwave Flash Embed -->|sigU
374 #################################################################################
376 # quicktime-kioskmode: Make Quicktime movies saveable
378 #################################################################################
379 FILTER: quicktime-kioskmode Make Quicktime movies saveable
381 s/(<embed\s+[^>]*)kioskmode\s*=\s*(["']?)true\2/$1/ig
384 #################################################################################
386 # fun: Text replacements for subversive browsing fun!
388 #################################################################################
389 FILTER: fun Text replacements for subversive browsing fun!
393 s/microsoft(?!.com)/MicroSuck/ig
395 # Buzzword Bingo (example for extended regex syntax)
397 s* (?:industry|world)[ -]leading \
399 | customer[ -]focused \
401 | award[ -]winning # Comments are OK, too! \
402 | high[ -]performance \
403 | solutions[ -]based \
407 *$0<sup><font color="red"><b>Bingo!</b></font></sup> \
412 s/(M|m)edien(?![^<]*>)/$1ädchen/Ug
414 #################################################################################
416 # crude-parental: Crude parental filtering? (Use along with a suitable blocklist).
417 # Shows how to deny access to whole page based on a keyword.
419 #################################################################################
420 FILTER: crude-parental Crude parental filtering (demo only)
422 # (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words)
423 # (Note #2: Is 'sex' a rude word?!)
425 s%^.*(?<!middle)(?<!sus)(?<!es)sex.*$%<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
426 s+^.*warez.*$+<html><head><title>No Warez</title></head><body><h3>You're not searching for illegal stuff, are you?</h3></body></html>+is
429 #################################################################################
431 # IE-Exploits: Disable some known Internet Explorer bug exploits
433 #################################################################################
434 FILTER: ie-exploits Disable some known Internet Explorer bug exploits
436 # Note: This is basically a demo and waits for someone more interested in IE
437 # security (sic!) to take over.
439 # Cross-site-scripting:
441 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
443 # Address bar spoofing (http://www.secunia.com/advisories/10395/):
445 s/(<a[^>]*href[^>]*)(?:\x01|\x02|\x03|%0[012])@/$1MALICIOUS-LINK@/ig
449 s%<script language="JavaScript">(window\.open|1;''\.concat)\("readme\.eml", null, "resizable=no,top=6000,left=6000"\)</script>%<br><font size="7"> WARNING: This Server is infected with <a href="http://www.cert.org/advisories/CA-2001-26.html">Nimda</a>!</font>%g
452 #################################################################################
455 # site-specifics: Cure for site-specific problems. Don't apply generally!
457 # Note: The fixes contained here are so specific to the problems of the
458 # particular web sites they are designed for that they would be a
459 # waste of CPU cycles (or even destructive!) on 99.9% of the web
460 # sites where they don't apply.
462 #################################################################################
463 FILTER: site-specifics Cure for site-specific problems. Don't apply generally!
465 # www.spiegel.de excludes X11 users from viewing Flash5 objects - shame.
466 # Apply to: www.spiegel.de/static/js/flash-plugin.js
468 s/indexOf\("x11"\)/indexOf("x13")/
470 # www.quelle-bausparkasse.de uses a very stupid redirect mechanism that
471 # relies on a webbug being present. Can we tolerate that? No!
472 # Apply to: www.quelle-bausparkasse.de/$
476 # groups.yahoo.com has splash pages that one needs to click through in
477 # order to access the actual messages. Let the browser do that. Thanks
478 # to Paul Jobson for this one:
480 s|<a href="(.+?)">(?:Continue to message\|Weiter zu Nachricht)</a>|<meta http-equiv="refresh" content="0; URL=$1">|ig
482 # monster.com has two very similar gimmicks:
484 s|<input type="hidden" name="REDIRECT" value="(.+?)">|<meta http-equiv="refresh" content="0; URL=$1">|i
486 s|<IMG SRC="http://media.monster.com/mm/usen/my/no_thanks_211x40.gif".+?>|<meta http-equiv="refresh" content="0; URL=http://my.monster.com/resume.asp">|i
488 # nytimes.com triggers popups through the onload handler of dummy images
489 # to fool popup-blockers.
491 s|(<img [^>]*)onload|$1never|sig
493 # Pre-check all the "Discard" buttons in GNU Mailman's web interface.
494 # (This saves a lot of mouse aiming practice when flushing spamtraps)
496 s|(<INPUT name="\d{2,4}" type="RADIO" value="0") CHECKED |$1|g
497 s|<INPUT name="\d{2,4}" type="RADIO" value="3" |$0 checked|g
499 #################################################################################
501 # no-ping: Removes non-standard ping attributes in <a> and <area> tags.
503 #################################################################################
504 FILTER: no-ping Removes non-standard ping attributes in <a> and <area> tags.
505 s@(<a(?:rea)?[^>]*?)ping=(['"]?)([^"'>]+)\2([>\s]?)@\
506 <strong title="Privoxy removed ping target '$3'">PING!</strong>\n$1$4@ig
508 #################################################################################
510 # google: CSS-based block for Google text ads. Also removes
511 # a width limitation and the toolbar advertisement.
513 #################################################################################
514 FILTER: google CSS-based block for Google text ads. Also removes a width limitation and the toolbar advertisement.
515 s@</head>@<style type="text/css">\n\
516 /* Style sheet inserted by Privoxy's google filter. */\n\
517 \#fbc, \#fbl, \#ra, .rhh {visibility: hidden !important;}\n\
518 \#tpa1,\#tpa2,\#tpa3,\#tpa4,\#tpa5,\#tpa5, \#spl, .ch, \#ads,\
519 \#toolbar, \#google_ads_frame{display: none !important;}\n\
520 .main_body, .j {width: 100%}\n</style>\n$0@
521 s@<div style=\"padding-top:11px;min-width:500px\">@<div id="main_body">@
522 s@(<table cellspacing=0 cellpadding=0 width=25% align=right bgcolor=\#ffffff border=0\
523 |</font></td></tr></tbody></table><table align=\"right\" bgcolor=\"\#ffffff\"\
524 |<table cellspacing=0 cellpadding=0 align=right bgcolor=\#ffffff border=0\
525 |<table style=\"clear:both\" align=right width=25% cellspacing=\"0\" cellpadding=\"0\"\
526 border=\"0\" bgcolor=\"\#ffffff\")@$0 id="ads"@
527 s@(<br clear=all><table)( border=0 cellpadding=9><tr><td)@$1 id="toolbar"$2@
529 #################################################################################
531 # yahoo: CSS-based block for Yahoo text ads. Also removes a width limitation.
533 #################################################################################
534 FILTER: yahoo CSS-based block for Yahoo text ads. Also removes a width limitation.
535 s@</head>@<style type="text/css">\n\
536 /* Style sheet inserted by Privoxy's yahoo filter. */\n\
537 \#symadbn, \#ymadbn, \#yschsec, \#yschanswr, .yschftad,\
538 .yschspn, .yschspns {display: none !important;}\n\
539 \#yschpri {width: 100% }\n</style>\n$0@
541 #################################################################################
543 # msn: CSS-based block for MSN text ads. Also removes tracking URLs
544 # and a width limitation.
546 #################################################################################
547 FILTER: msn CSS-based block for MSN text ads. Also removes tracking URLs and a width limitation.
548 s@</head>@<style type="text/css">\n\
549 /* Style sheet inserted by Privoxy's msn filter. */\n\
550 .msn_ads {display: none !important;}\n\
551 \#results, .flank, .SearchSection .not\
552 {width: 100% !important; min-width: 100% !important;\
553 max-width: 100% !important;}\n</style>\n$0@
554 s@(<div[^>]*) id=(["']?)ads_[^\2]*\2@$1 class="msn_ads"@Uig
555 s@(<a[^>]*href=\")http://g.msn.com/.*\?(http://.*)(&&DI=.*)(\")@$1$2$4@Ug
556 s@(<a[^>]*)gping=\".*\"@$1 title="URL cleaned up by Privoxy's msn filter"@Ug
558 #################################################################################
560 # blogspot: Cleans up some Blogspot blogs. Read the fine print before using this.
562 # This filter also intentionally removes some navigation stuff and
563 # sets the page width to 100%. As a result, some rounded "corners" would
564 # appear to early or not at all and as fixing this would require a browser
565 # that understands background-size (CSS3), they are removed instead.
567 #################################################################################
568 FILTER: blogspot Cleans up some Blogspot blogs. Read the fine print before using this.
569 s@</head>@<style type="text/css">\n\
570 /* Style sheet inserted by Privoxy's blogspot filter. */\n\
571 \#powered-by {display: none !important;}\n\
572 \#wrap4, \#wrapper {margin-top: 0px }\n\
573 \#blogheader, \#header {margin-top: 0.5em !important}\n\
574 \#content {width: 98% }\n\
575 \#main {width: 70% }\n\
576 \#sidebar {width: 29% }\n\
577 .post-body {overflow: auto;}\n\
578 .blogComments {width: 100%; overflow: auto;}\n</style>\n$0@
579 s@<body.*(?:<div id="space-for-ie"></div>|(<div id="(?:content|wrap4|wrapper)))@<body>\
580 <!-- Privoxy's blogspot filter ditched some garbage here -->$1@Us
581 s@(<div style=\"[^\"]*width:)30em@$1 100%@
582 s@background:url\(\"http://www.blogblog.com/rounders[^\"]*\"\).*;@/*$0*/@Ug
583 s@(background:\#[a-f\d]{3})( url\(\"http://www.blogblog.com/rounders[^\"]*\"\).*;)@$1 ;/*$2*/@Ug
585 #################################################################################
587 # x-httpd-php-to-html: Header filter to change the Content-Type from
588 # x-httpd-php to html. "Content-Type: x-httpd-php"
589 # is set by clueless PHP users and causes many
590 # browsers do open a download menu instead of
591 # rendering the page.
593 #################################################################################
594 FILTER: x-httpd-php-to-html Header filter to change the Content-Type from x-httpd-php to html.
595 s@^(Content-Type:) application/x-httpd-php@$1 text/html@
597 #################################################################################
599 # html-to-xml: Header filter to change the Content-Type from html to xml.
601 #################################################################################
602 FILTER: html-to-xml Header filter to change the Content-Type from html to xml.
603 s@^(Content-Type:) text/html(;.*)?$@$1 application/xhtml+xml$2@
605 #################################################################################
607 # xml-to-html: Header filter to change the Content-Type from xml to html.
609 #################################################################################
610 FILTER: xml-to-html Header filter to change the Content-Type from xml to html.
611 s@^(Content-Type:) (?:application|text)/(?:xhtml\+)?xml(;.*)?$@$1 text/html$2@
613 #################################################################################
615 # hide-tor-exit-notation: Header filter to remove the Tor exit node notation
616 # in Host and Referer headers.
618 # Note: If Privoxy and Tor are chained and Privoxy is configured to
619 # use socks4a, one can use http://www.example.org.foobar.exit/
620 # to access the host www.example.org through Tor exit node foobar.
622 # As the HTTP client isn't aware of this notation, it treats the
623 # whole string "www.example.org.foobar.exit" as host and uses it
624 # for the "Host" and "Referer" headers. From the server's point of
625 # view the resulting headers are invalid and can cause problems.
627 # An invalid "Referer" header can trigger "hot-linking" protections,
628 # an invalid "Host" header will make it impossible for the server to
629 # find the right vhost (several domains hosted on the same IP address).
631 # This filter removes the "foo.exit" part in those headers
632 # to prevent the mentioned problems. Note that it only modifies
633 # the HTTP headers, it doesn't make it impossible for the server
634 # to detect your Tor exit node based on the IP address the request is
637 #################################################################################
638 FILTER: hide-tor-exit-notation Header filter to remove the Tor exit node notation in Host and Referer headers.
639 s@^((?:Referer|Host):\s*(?:https?://)?[^/]*)\.[^\./]*?\.exit@$1@i
642 ##############################################################################
645 # $Log: default.filter,v $
646 # Revision 1.30 2006/10/18 12:36:50 fabiankeil
647 # google filter now cleans Google groups as well.
649 # Revision 1.29 2006/10/11 14:03:17 fabiankeil
650 # Changed img-reorder regex to only move width
651 # attributes if they are following at least one
652 # whitespace. Fixes BR 1328455.
654 # Revision 1.28 2006/10/11 13:31:13 fabiankeil
655 # Added Anduin Withers' js-annoyances fix
656 # for not messing up escaped quotes. Fixes BR 999765.
658 # Improved blogspot filter to make it less likely that
659 # the blogspot banner at the top of the page is missed.
661 # Revision 1.27 2006/10/08 17:00:51 fabiankeil
662 # Modified webbugs filter to create a comment around the offending
663 # image instead of removing it entirely.
665 # Adjusted regex to only match if there's at least one whitespace
666 # before the width and height attributes. Makes it more likely that
667 # they are indeed attributes, and not part of the value of another attribute.
670 # Thanks to Martin Thomas for diagnosing the cause of the problem.
672 # Revision 1.26 2006/10/06 18:06:16 fabiankeil
673 # Added header filter x-httpd-php-to-html
674 # and reverted another img-reorder whitespace
677 # Revision 1.25 2006/10/06 15:26:09 fabiankeil
678 # Bumped copyright year.
680 # Reverted parts of the last img-reorder change
681 # which were intended to remove superfluous whitespace
682 # but had the side effect to mess up some tags.
684 # Modified banners-by-size and banners-by-link to
685 # use border value "0" instead of "\0". Fixes BR 1100065.
687 # Revision 1.24 2006/10/06 11:25:31 fabiankeil
688 # Taught img-reorder not to break img tags
689 # with empty src attributes. Fixes BR 1089474.
690 # Thanks to Raphael Moll for reporting.
692 # Revision 1.23 2006/10/05 14:46:28 fabiankeil
693 # Replaced "<" in img-reorder's description with "<".
695 # Modified msn filter to tag ads with classes instead
696 # of ids. There may be more than one ad per page,
697 # but ids are required to be unique.
699 # Revision 1.22 2006/10/04 19:17:14 fabiankeil
700 # Incorportated Frédéric Crozat's ie-exploits
701 # modification to make it less trigger-happy.
703 # Modified blogspot filter to make .post-body
704 # scrollable if necessary.
706 # Revision 1.21 2006/10/02 16:21:14 fabiankeil
707 # Adjusted yahoo filter to hide .yschspns as well.
708 # Added header filters: html-to-xml and xml-to-html.
710 # Revision 1.20 2006/10/01 21:00:22 fabiankeil
711 # New site-specific filters: google, yahoo, msn and blogspot.
713 # Revision 1.19 2006/07/18 14:48:45 david__schmidt
714 # Reorganizing the repository: swapping out what was HEAD (the old 3.1 branch)
715 # with what was really the latest development (the v_3_0_branch branch)
717 # Revision 1.11.2.23 2004/02/17 13:34:01 oes
718 # - Beefed up the protection of the unsolicited-popups
719 # filter against matching in JavaScript string constants.
720 # - Extended the fun filter with a German joke
721 # - Extended the site-specifics filter with a convenience
722 # reeplacement for managing mailing lists at SourceForge
724 # Revision 1.11.2.22 2004/01/30 15:29:29 oes
725 # Updated the copyright note
727 # Revision 1.11.2.21 2004/01/20 15:15:01 oes
728 # Detail enhancement in all-popups
730 # Revision 1.11.2.20 2004/01/06 16:46:14 oes
731 # Fixed a JS syntax problem in jumping-windows
733 # Revision 1.11.2.19 2003/12/17 17:09:25 oes
734 # Added remedy against IE address bar spoofing
736 # Revision 1.11.2.18 2003/12/02 11:25:27 oes
737 # Fixed a line trashed in previous commit
739 # Revision 1.11.2.17 2003/12/01 21:58:46 oes
742 # - unsolicited-popups no longer matches at start or end of quoted
743 # strings, and is now activated earlier and deactivated later in
745 # - replacement images in banners-by-* now without border
746 # - more effective shockwave flash flattening
747 # - Custom annoyance filtering for Yahoo Groups, Monster.com, NY Times.
749 # Revision 1.11.2.16 2003/05/08 09:44:56 oes
750 # Allow extra parameters in blink,marquee tags. Fixes bug #734012
752 # Revision 1.11.2.15 2003/03/30 13:57:08 oes
753 # Making unsolicited-popups safe for use on <html> tags enclosed in JS strings
755 # Revision 1.11.2.14 2003/03/19 13:17:50 oes
756 # - Added filter "site-specifics" to address site specific problems
757 # - Fixed a small problem in the img-reorder filter
759 # Revision 1.11.2.13 2003/03/18 19:28:59 oes
760 # Fixed a minor problem in the img-reorder filter
762 # Revision 1.11.2.12 2003/03/15 14:06:58 oes
763 # - Assorted refinements, optimizations and fixes in the js-annoyances,
764 # img-reorder, banners-by-size, banners-by-link, webbugs, refresh-tags,
765 # html-annoyances, content-cookies and fun filters
766 # - Replaced filter "popups" by choice between two modes:
767 # - "unsolicited-popups" tries to catch only the unsolicited ones
768 # - "all-popups" tries to kill them all (as before)
769 # - New filter "tiny-textforms" Help those tiny or hard-wrap textareas.
770 # - New filter "jumping-windows" that prevents windows from resizing
771 # and moving themselves
772 # - Replaced "nimda" with more general "ie-exploits" filter in which
773 # all filters for exploits shall be collected
775 # Revision 1.11.2.11 2002/11/12 16:14:43 oes
776 # Exchanged js-annoyance filter against status bar rewrites with improved version by Don Libes
778 # Revision 1.11.2.10 2002/11/11 13:39:47 oes
779 # Make refresh-tags filter work even on incorrect refresh tags like found on usatoday.com
781 # Revision 1.11.2.9 2002/11/08 16:39:17 oes
782 # Made img-reorder more cautious. Fixes bug #632715
784 # Revision 1.11.2.8 2002/10/13 21:56:52 hal9
785 # Adding demoronizer filter. This should include all the common abuses. I have
786 # left a few of the rare cases commented out (never found these in the wild).
788 # Revision 1.11.2.7 2002/09/25 15:09:39 oes
789 # Preserve original quoting style in <img> tags wherever possible. Fixes Bug #605956
791 # Revision 1.11.2.6 2002/08/23 14:12:26 oes
792 # Proofed frameset-borders against "fremaborder=0 border=0"
794 # Revision 1.11.2.5 2002/08/22 15:05:20 oes
795 # Added Filter to make Quicktime movies saveable (thanks to aaron@linville.org for the idea)
797 # Revision 1.11.2.4 2002/08/10 11:32:29 oes
798 # Attribute values in replacement tags of banners-by-size filter now undelimited. (Fixes bug #592493)
800 # Revision 1.11.2.3 2002/08/05 11:43:56 oes
801 # Fixed a bug in the popups filter that was introduced with the last fix :-(
803 # Revision 1.11.2.2 2002/08/01 11:20:13 oes
804 # Fixed bugs 587802, 577802 and an unreported one
806 # Revision 1.11.2.1 2002/07/26 15:18:26 oes
807 # - All filters reviewed and many shorcomings fixed
808 # - New filters: img-reorder, banners-by-link and js-events
809 # - Jobs reorderd because they are now executed in order of
812 # Revision 1.11 2002/05/24 00:57:18 oes
813 # Made WeBugs job ungreedy; Fixes bug 559190
815 # Revision 1.10 2002/04/18 10:14:19 oes
816 # renamed some filters
818 # Revision 1.9 2002/04/11 07:36:35 oes
819 # Generalized js-popup filter
821 # Revision 1.8 2002/04/10 17:07:21 oes
822 # Fixed potentially desctructive jobs, added noflash filter
824 # Revision 1.7 2002/04/09 18:34:51 oes
825 # Fixed HTML syntax in replacements
827 # Revision 1.6 2002/04/03 19:49:52 swa
830 # Revision 1.5 2002/03/27 15:30:26 swa
831 # have a consistent appearance
833 # Revision 1.4 2002/03/26 22:29:54 swa
834 # we have a new homepage!
836 # Revision 1.3 2002/03/24 16:08:03 jongfoster
837 # Fixing banners-by-size for new config URLs
839 # Revision 1.2 2002/03/24 13:02:18 swa
840 # name change related issues.
842 # Revision 1.1 2002/03/24 11:37:39 jongfoster
845 # Revision 1.24 2002/03/16 20:39:54 oes
846 # - Added descriptions to the filters so users will know what they select in the cgi editor
847 # - Added content-cookies filter
848 # - Bugfixed many jobs (Thanks to Al for some hints)
850 # Revision 1.22 2002/03/12 13:42:50 oes
851 # Fixing & Optimizing REs
853 # Revision 1.21 2002/03/12 11:59:20 oes
854 # Beefed up Buzzword Bingo
856 # Revision 1.20 2002/03/12 01:42:50 oes
857 # Introduced modular filters
859 # Revision 1.19 2002/03/10 19:49:24 oes
860 # Added expression to kill referer tracking in JavaScripts
862 # Revision 1.18 2002/03/08 17:14:12 oes
863 # PNG -> image in comments
865 # Revision 1.17 2002/03/07 03:50:54 oes
866 # Adapted comments to new built-in images
868 # Revision 1.16 2002/02/21 00:12:19 jongfoster
869 # Modifying the banner regexps to use long URLS and to autodetect
870 # whether to show a logo or a transparent GIF, based on actionsfile
873 # Revision 1.15 2001/12/28 23:54:20 steudten
874 # Fix for feature Req #495374: http-equiv problem
876 # Revision 1.14 2001/12/09 18:55:11 david__schmidt
877 # Updated CODE_STATUS to beta, commented out microsuck line in re_filterfile
880 # Revision 1.13 2001/10/13 13:11:20 joergs
881 # Fixed WebBug filter.
883 # Revision 1.12 2001/10/07 15:46:42 oes
884 # Followed Guy's proposal to change the document.cookie job
886 # Revision 1.11 2001/09/21 12:34:00 joergs
887 # Added filter to replace "Nimda" code by a warning.
889 # Revision 1.10 2001/07/20 11:04:26 oes
890 # Added Rodneys javascript cookie filter
892 # Revision 1.9 2001/07/13 14:03:48 oes
893 # Elimiated yet another bug in the banner-by-size jobs. Shame on me!
895 # Revision 1.8 2001/06/29 13:34:00 oes
896 # - Added explanation for U and T options
897 # - Added hint on image replacement by CGI call
898 # - Fixed bug in banner-by-size jobs
900 # Revision 1.7 2001/06/19 14:21:56 oes
901 # Fixed microsuck line
903 # Revision 1.6 2001/06/09 14:01:57 swa
904 # header. cosmetics. default: no messing ala microsuck.