1 # ********************************************************************
3 # File : $Source: /cvsroot/ijbswa/current/default.filter,v $
5 # $Id: default.filter,v 1.86 2013/02/19 11:14:47 fabiankeil Exp $
7 # Purpose : Rules to process the content of web pages
9 # Copyright : Written by and Copyright (C) 2001-2010 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 # Generally filters start with a line like "FILTER: name description".
41 # They are then referrable from the actionsfile with +filter{name}
43 # FILTER marks a filter as content filter, other filter
44 # types are CLIENT-HEADER-FILTER, CLIENT-HEADER-TAGGER,
45 # SERVER-HEADER-FILTER and SERVER-HEADER-TAGGER.
47 # Inside the filters, write one Perl-Style substitution (job) per line.
48 # Jobs that precede the first FILTER: line are ignored.
50 # For Details see the pcrs manpage contained in this distribution.
51 # (and the perlre, perlop and pcre manpages)
53 # Note that you are free to choose the delimiter as you see fit.
55 # Note2: In addition to the Perl options gimsx, the following nonstandard
56 # options are supported:
58 # 'U' turns the default to ungreedy matching. Add ? to quantifiers to
59 # switch back to greedy.
61 # 'T' (trivial) prevents parsing for backreferences in the substitute.
62 # Use if you want to include text like '$&' in your substitute without
65 # 'D' (Dynamic) allows the use of variables. Supported variables are:
66 # $host, $origin (the IP address the request came from), $path and $url.
68 # Note that '$' is a bad choice as delimiter for dynamic filters as you
69 # might end up with unintended variables if you use a variable name
70 # directly after the delimiter. Variables will be resolved without
71 # escaping anything, therefore you also have to be careful not to chose
72 # delimiters that appear in the replacement text. For example '<' should
73 # be save, while '?' will sooner or later cause conflicts with $url.
75 #################################################################################
78 #################################################################################
80 # js-annoyances: Get rid of particularly annoying JavaScript abuse.
82 #################################################################################
83 FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse.
85 # Note: Most of these jobs would be safer if restricted to a
86 # <script> context as in:
88 # s/(<script.*)nasty-item(?=.*<\/script>)/$1replacement/sigU
90 # but that would make them match only the first occurrence of
91 # nasty-item in each <script>. We need nestable jobs!
93 # Get rid of Javascript referrer tracking.
94 # Test page: http://www.javascript-page.com/referrer.html
96 s|(?:\w+\.)+referrer|"Not Your Business!"|gisU
98 # The status bar is for displaying link targets, not pointless blahblah
100 s@([\W]\s*)((?:this|window)\.(?:default)?status)\s*=\s*((['"]).*?\4)@$1$2 =\
101 (typeof(this.href) != 'undefined')?($3 + ' URL: ' + this.href):($2)@ig
103 s/(?:(?:this|window)\.(?:default)?status)\s*=\s*\w*\s*;//ig
105 # Kill OnUnload popups. Yummy.
106 # Test: http://www.zdnet.com/zdsubs/yahoo/tree/yfs.html
108 s/(<body\s+[^>]*)onunload/$1never/siU
109 s|(<script.*)window\.onunload(?=.*</script>)|$1never|sigU
111 # If we allow window.open, we want normal window features:
112 # Test: http://www.htmlgoodies.com/beyond/notitle.html
114 s/(open\s*\([^\)]+resizable=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
115 s/(open\s*\([^\)]+location=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
116 s/(open\s*\([^\)]+status=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
117 s/(open\s*\([^\)]+scroll(?:ing|bars)=)(["']?)(?:no|0)\2/$1$2auto$2/sigU
118 s/(open\s*\([^\)]+menubar=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
119 s/(open\s*\([^\)]+toolbar=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
120 s/(open\s*\([^\)]+directories=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
121 s/(open\s*\([^\)]+fullscreen=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
122 s/(open\s*\([^\)]+always(?:raised|lowered)=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
123 s/(open\s*\([^\)]+z-?lock=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
124 s/(open\s*\([^\)]+hotkeys=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
125 s/(open\s*\([^\)]+titlebar=)(["']?)(?:no|0)\2/$1$2yes$2/sigU
126 s/(open\s*\([^\)]+always(?:raised|lowered)=)(["']?)(?:yes|1)\2/$1$2no$2/sigU
129 #################################################################################
131 # js-events: Kill JavaScript event bindings and timers (Radically destructive! Only for extra nasty sites).
133 #################################################################################
134 FILTER: js-events Kill JavaScript event bindings and timers (Radically destructive! Only for extra nasty sites).
136 s/(on|event\.)((mouse(over|out|down|up|move))|(un)?load|contextmenu|selectstart)/never/ig
137 # Not events, but abused on the same type of sites:
138 s/(alert|confirm)\s*\(/concat(/ig
139 s/set(timeout|interval)\(/concat(/ig
141 #################################################################################
143 # html-annoyances: Get rid of particularly annoying HTML abuse.
145 #################################################################################
146 FILTER: html-annoyances Get rid of particularly annoying HTML abuse.
148 # New browser windows (if allowed -- see no-popups filter below) should be
149 # resizeable and have a location and status bar
151 s/(<a\s+href[^>]+resizable=)(['"]?)(?:no|0)\2/$1$2yes$2/igU
152 s/(<a\s+href[^>]+location=)(['"]?)(?:no|0)\2/$1$2yes$2/igU
153 s/(<a\s+href[^>]+status=)(['"]?)(?:no|0)\2/$1$2yes1$2/igU
154 s/(<a\s+href[^>]+scrolling=)(['"]?)(?:no|0)\2/$1$2auto$2/igU
155 s/(<a\s+href[^>]+menubar=)(['"]?)(?:no|0)\2/$1$2yes$2/igU
157 # The <BLINK> and <MARQUEE> tags were crimes!
159 s-</?(blink|marquee).*>--sigU
162 #################################################################################
164 # content-cookies: Kill cookies that come in the HTML or JS content.
166 #################################################################################
167 FILTER: content-cookies Kill cookies that come in the HTML or JS content.
169 # JS cookies, except those used by antiadbuster.com to detect us:
171 s|(\w+\.)+cookie(?=[ \t\r\n]*=)(?!='aab)|ZappedCookie|ig
175 s|<meta\s+http-equiv=['"]?set-cookie.*>|<!-- ZappedCookie -->|igU
178 #################################################################################
180 # refresh-tags: Kill automatic refresh tags if refresh time is larger than 9 seconds.
182 #################################################################################
183 FILTER: refresh-tags Kill automatic refresh tags if refresh time is larger than 9 seconds.
185 # Note: Only deactivates refreshes with more than 9 seconds delay to
186 # preserve monster-stupid but common redirections via meta tags.
188 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"@ig
191 #################################################################################
193 # unsolicited-popups: Disable unsolicited pop-up windows.
195 #################################################################################
196 FILTER: unsolicited-popups Disable only unsolicited pop-up windows.
198 s+([^'"]\s*<head.*>)(?=\s*[^'"])+$1<script>function PrivoxyWindowOpen(){return(null);}</script>+isU
199 s@([^\w\s.]\s*)((?:map)?(window|this|parent)\.?)?open\s*\(@$1PrivoxyWindowOpen(@ig
200 s+([^'"]\s*</html>)(?!\s*(\\n|'|"))+$1<script>function PrivoxyWindowOpen(a, b, c){return(window.open(a, b, c));}</script>+iU
203 ##################################################################################
205 # all-popups: Kill all popups in JavaScript and HTML.
207 #################################################################################
208 FILTER: all-popups Kill all popups in JavaScript and HTML.
210 s@((\W\s*)(?:map)?(window|this|parent)\.?)open\s*\\?\(@$1concat(@ig # JavaScript
211 #s/\starget\s*=\s*(['"]?)_?(blank|new)\1?/ notarget/ig # HTML
212 s/\starget\s*=\s*(['"]?)_?(blank|new)\1?/ /ig # (X)HTML
214 ##################################################################################
216 # img-reorder: Reorder attributes in <img> tags to make the banners-by-* filters more effective.
218 #################################################################################
219 FILTER: img-reorder Reorder attributes in <img> tags to make the banners-by-* filters more effective.
221 # In the first step src is moved to the start, then width is moved to the second
222 # place to guarantee an order of src, width, height. Also does some white-space
225 # This makes banners-by-size more effective and allows both banners-by-size
226 # and banners-by-link to preserve the original image URL in the title attribute.
228 s|<img\s+?([^>]*)\ssrc\s*=\s*(['"])([^>\\\2]+)\2|<img src=$2$3$2 $1|siUg
229 s|<img\s+?([^>]*)\ssrc\s*=\s*([^'">\\\s]+)|<img src=$2 $1|sig
230 s|(<img[^>]+height)\s*=\s*|$1=|sig
232 s|<img (src=(?:(['"])[^>\\\\2]*\2\|[^'">\\\s]+?))([^>]*)\s+width\s*=\s*((["']?)\d+?\5)(?=[\s>])|<img $1 width=$4$3|siUg
235 #################################################################################
237 # banners-by-size: Kill banners by size.
239 #################################################################################
241 # Standard banner sizes taken from http://www.iab.net/iab_banner_standards/bannersizes.html
243 # Note: Use http://config.privoxy.org/send-banner?type=trans for a transparent 1x1 image
244 # Use http://config.privoxy.org/send-banner?type=pattern for a grey/white pattern image
245 # Use http://config.privoxy.org/send-banner?type=auto to auto-select.
247 # Note2: Use img-reorder before this filter to ensure maximum matching success
249 #################################################################################
250 FILTER: banners-by-size Kill banners by size.
253 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)88\4)[^>]*?(height=(['"]?)31\6)[^>]*?(?=/?>)@\
254 <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
255 # 120*60, 120*90, 120*240, 120*600
256 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)120\4)[^>]*?(height=(['"]?)(?:600?|90|240)\6)[^>]*?(?=/?>)@\
257 <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
259 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)125\4)[^>]*?(height=(['"]?)125\6)[^>]*?(?=/?>)@\
260 <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
262 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)160\4)[^>]*?(height=(['"]?)600\6)[^>]*?(?=/?>)@\
263 <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
265 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)180\4)[^>]*?(height=(['"]?)150\6)[^>]*?(?=/?>)@\
266 <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
267 # 234*60, 468*60 (Most Banners!)
268 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:234|468)\4)[^>]*?(height=(['"]?)60\6)[^>]*?(?=/?>)@\
269 <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
271 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)240\4)[^>]*?(height=(['"]?)400\6)[^>]*?(?=/?>)@\
272 <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
274 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)(?:250|300)\4)[^>]*?(height=(['"]?)250\6)[^>]*?(?=/?>)@\
275 <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
277 s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)336\4)[^>]*?(height=(['"]?)280\6)[^>]*?(?=/?>)@\
278 <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
280 # Note: 200*50 was also proposed, but it probably causes too much collateral damage:
282 #s@<img\s+(?:src\s*=\s*(['"]?)([^>\\\1\s]+)\1)?[^>]*?(width=(['"]?)200\4)[^>]*?(height=(['"]?)50\6)[^>]*?(?=/?>)@\
283 # <img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed-$2-by-size" $3 $5@sig
286 #################################################################################
288 # banners-by-link: Kill banners by their links to known clicktrackers (Experimental).
290 #################################################################################
291 FILTER: banners-by-link Kill banners by their links to known clicktrackers.
293 # Common case with width and height attributes:
295 s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:\
296 adclick # See www.dn.se \
297 | advert # see dict.leo.org \
298 | atwola\.com/(?:link|redir) # see www.cnn.com \
299 | doubleclick\.net/jump/ # redirs for doublecklick.net ads \
301 | (?<!&type=)tracker # (&type=tracker is used in sf's project statistics) \
302 | adlog\.pl # see sf.net \
303 )[^>\1\s]*)\1[^>]*>\s*<img\s+(?:src\s*=\s*(['"]?)([^>\\\3\s]+)\3)?[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\6)[^>]*((?:width|height)\s*=\s*(['"]?)\d+?\8)[^>]*?(?=/?>)\
304 @<img $5 $7 src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed $4 by link to $2"@sigx
306 # Rare case w/o explicit dimensions:
308 s@<a\s+href\s*=\s*(['"]?)([^>\1\s]*?(?:ad(?:click|vert)|atwola\.com/(?:link|redir)|doubleclick\.net/jump/|(?<!&type=)tracker|counter|adlog\.pl)[^>\1\s]*)\1[^>]*>\s*<img\s+(?:src\s*=\s*(['"]?)([^>\\\3\s]+)\3)?[^>]*?(?=/?>)@<img src="http://config.privoxy.org/send-banner?type=auto" border="0" title="Killed $4 by link to $2"@sig
311 ################################################################################
313 # webbugs: Squish WebBugs (1x1 invisible GIFs used for user tracking).
315 #################################################################################
316 FILTER: webbugs Squish WebBugs (1x1 invisible GIFs used for user tracking).
318 s@<img[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*\s(?:width|height)\s*=\s*['"]?[01](?=\D)[^>]*?>@@siUg
321 #################################################################################
323 # tiny-textforms: Extend those tiny textareas up to 40x80 and kill the hard wrap.
325 #################################################################################
326 FILTER: tiny-textforms Extend those tiny textareas up to 40x80 and kill the hard wrap.
328 s/(<textarea[^>]*?)(?:\s*(?:rows|cols)=(['"]?)\d+\2)+/$1 rows=$2\40$2 cols=$2\80$2/ig
329 s/(<textarea[^>]*?)wrap=(['"]?)hard\2/$1/ig
332 #################################################################################
334 # jumping-windows: Prevent windows from resizing and moving themselves.
336 #################################################################################
337 FILTER: jumping-windows Prevent windows from resizing and moving themselves.
339 s/(?<=[\W])(?:window|this|self)\.(?:move|resize)(?:to|by)\(/''.concat(/ig
341 #################################################################################
343 # frameset-borders: Give frames a border, make them resizable and scrollable.
345 #################################################################################
346 FILTER: frameset-borders Give frames a border and make them resizable.
348 s/(<frameset\s+[^>]*)framespacing=(['"]?)(no|0)\2/$1/igU
349 s/(<frameset\s+[^>]*)frameborder=(['"]?)(no|0)\2/$1/igU
350 s/(<frameset\s+[^>]*)border=(['"]?)(no|0)\2/$1/igU
351 s/(<frame\s+[^>]*)noresize/$1/igU
352 s/(<frame\s+[^>]*)frameborder=(['"]?)(no|0)\2/$1/igU
353 s/(<frame\s+[^>]*)scrolling=(['"]?)(no|0)\2/$1/igU
356 #################################################################################
358 # iframes: Remove all detected iframes. Should only be enabled for
359 # individual sites after testing that the iframes are optional.
361 #################################################################################
362 FILTER: iframes Removes all detected iframes. Should only be enabled for individual sites.
363 s@<iframe.*</iframe>@<!-- iframe removed by Privoxy's iframe filter -->@Uisg
366 #################################################################################
368 # demoronizer: Correct Microsoft's abuse of standardized character sets, which
369 # leave the browser to (mis)-interpret unknown characters, with
370 # sometimes bizarre results on non-MS platforms.
372 # credit: ripped from the demoroniser.pl script by:
373 # John Walker -- January 1998, http://www.fourmilab.ch/webtools/demoroniser
375 #################################################################################
376 FILTER: demoronizer Fix MS's non-standard use of standard charsets.
378 s/(&\#[0-2]\d\d)\s/$1; /g
379 # per Robert Lynch: http://slate.msn.com//?id=2067547, just a guess.
380 # Must come before x94 below.
381 s/\xE2\x80\x94/ -- /g
393 # Bullet type character.
397 #s-\x98-<sup>~</sup>-g
398 #s-\x99-<sup>TM</sup>-g
403 #################################################################################
405 # shockwave-flash: Kill embedded Shockwave Flash objects.
406 # Note: Better just block "/.*\.swf$"!
408 #################################################################################
409 FILTER: shockwave-flash Kill embedded Shockwave Flash objects.
411 s|<object [^>]*macromedia.*</object>|<!-- Squished Shockwave Object -->|sigU
412 s|<embed [^>]*(application/x-shockwave-flash\|\.swf).*>(.*</embed>)?|<!-- Squished Shockwave Flash Embed -->|sigU
415 #################################################################################
417 # quicktime-kioskmode: Make Quicktime movies saveable.
419 #################################################################################
420 FILTER: quicktime-kioskmode Make Quicktime movies saveable.
422 s/(<embed\s+[^>]*)kioskmode\s*=\s*(["']?)true\2/$1/ig
425 #################################################################################
427 # fun: Text replacements for subversive browsing fun!
429 #################################################################################
430 FILTER: fun Text replacements for subversive browsing fun!
434 s/microsoft(?!\.[^\s])/MicroSuck/ig
436 # Buzzword Bingo (example for extended regex syntax)
438 s* (?:industry|world)[ -]leading \
440 | customer[ -]focused \
442 | award[ -]winning # Comments are OK, too! \
443 | high[ -]performance \
444 | solutions[ -]based \
448 *$0<sup><font color="red"><b>Bingo!</b></font></sup> \
453 s/(M|m)edien(?![^<]*>)/$1ädchen/Ug
455 #################################################################################
457 # crude-parental: Crude parental filtering. Use with a suitable blocklist.
458 # Pages are "blocked" based on keyword matching.
460 #################################################################################
461 FILTER: crude-parental Crude parental filtering. Note that this filter doesn't work reliably.
463 # (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words)
464 # (Note #2: Is 'sex' a rude word?!)
466 s%^.*(?<!middle)(?<!sus)(?<!es)sex.*$%<html><head><title>Blocked</title></head><body>\
467 <h3>Blocked by Privoxy's crude-parental filter due to possible adult content.</h3></body></html>%is
469 s+^.*warez.*$+<html><head><title>No Warez</title></head><body><h3>You're not searching for illegal stuff, are you?</h3></body></html>+is
471 # Remove by description
473 (?:(suck|lick|tongue|rub|fuck|fingering|finger|chicks?)\s*)?\
474 (?:(her|your|my|hard|with|big|wet|tight|pink|hot|moist|young|teen)\s*)+\
475 (dicks?|penis|cocks?|balls?|tits?|pussy|cunt|clit|ass|mouth).*$\
476 /This page has been blocked by Privoxy's crude-parental content filter\
481 (download|broadband|view|watch|free|get|extreem)?\s*\
482 (sex|xxx|porn|cumshot|fuck(ing|s)?|anal|ass|asian|adult|Amateur|org(y|ies)|close ups?|hand?job|nail(ed)?)+\s*\
483 (movies?|pics?|videos?|dvds?|dvd's|links?).*$\
484 /This page has been blocked by Privoxy's crude-parental content filter\
487 #Remove by age disclaimer
489 (models?|chicks?|girls?|women|persons)\s*\
490 (who|are|were)+ (over|at least) (16|18|21) years (old|of age).*$\
491 /This page has been blocked by Privoxy's crude-parental content filter\
494 #Remove by regulations
495 s/^.*(Section 2257|18 U.?S.?C.? 2257).*$\
496 /This page has been blocked by Privoxy's crude-parental content filter\
500 #################################################################################
502 # IE-Exploits: Disable some known Internet Explorer bug exploits.
504 #################################################################################
505 FILTER: ie-exploits Disable some known Internet Explorer bug exploits.
507 # Note: This is basically a demo and waits for someone more interested in IE
508 # security (sic!) to take over.
510 # Cross-site-scripting:
512 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
514 # Address bar spoofing (http://www.secunia.com/advisories/10395/):
516 s/(<a[^>]*href[^>]*)(?:\x01|\x02|\x03|%0[012])@/$1MALICIOUS-LINK@/ig
520 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
523 #################################################################################
526 # site-specifics: Cure for site-specific problems. Don't apply generally!
528 # Note: The fixes contained here are so specific to the problems of the
529 # particular web sites they are designed for that they would be a
530 # waste of CPU cycles (or even destructive!) on 99.9% of the web
531 # sites where they don't apply.
533 #################################################################################
534 FILTER: site-specifics Cure for site-specific problems. Don't apply generally!
536 # www.spiegel.de excludes X11 users from viewing Flash5 objects - shame.
537 # Apply to: www.spiegel.de/static/js/flash-plugin.js
539 s/indexOf\("x11"\)/indexOf("x13")/
541 # www.quelle-bausparkasse.de uses a very stupid redirect mechanism that
542 # relies on a webbug being present. Can we tolerate that? No!
543 # Apply to: www.quelle-bausparkasse.de/$
547 # groups.yahoo.com has splash pages that one needs to click through in
548 # order to access the actual messages. Let the browser do that. Thanks
549 # to Paul Jobson for this one:
551 s|<a href="(.+?)">(?:Continue to message\|Weiter zu Nachricht)</a>|<meta http-equiv="refresh" content="0; URL=$1">|ig
553 # monster.com has two very similar gimmicks:
555 s|<input type="hidden" name="REDIRECT" value="(.+?)">|<meta http-equiv="refresh" content="0; URL=$1">|i
557 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
559 # nytimes.com triggers popups through the onload handler of dummy images
560 # to fool popup-blockers.
562 s|(<img [^>]*)onload|$1never|sig
564 # Pre-check all the "Discard" buttons in GNU Mailman's web interface.
565 # (This saves a lot of mouse aiming practice when flushing spamtraps)
567 s|(<INPUT name="\d{2,4}" type="RADIO" value="0") CHECKED |$1|g
568 s|<INPUT name="\d{2,4}" type="RADIO" value="3" |$0 checked|g
570 #################################################################################
572 # no-ping: Removes non-standard ping attributes in <a> and <area> tags.
574 #################################################################################
575 FILTER: no-ping Removes non-standard ping attributes in <a> and <area> tags.
576 s@(<a(?:rea)?[^>]*?)\sping=(['"]?)([^"'>]+)\2([>\s]?)@\
577 <strong style="color:white; background-color:red;" title="Privoxy removed ping target '$3'">PING!</strong>\n$1$4@ig
579 #################################################################################
581 # google: CSS-based block for Google text ads. Also removes
582 # a width limitation and the toolbar advertisement.
584 #################################################################################
585 FILTER: google CSS-based block for Google text ads. Also removes a width limitation and the toolbar advertisement.
587 s@</head>[^\\]@<style type="text/css">\n\
588 /* Style sheet inserted by Privoxy's google filter. */\n\
589 \#fbc, \#fbl, \#ra, .rhh {visibility: hidden !important;}\n\
590 \#tpa1,\#tpa2,\#tpa3,\#tpa4,\#tpa5,\#tpa5, \#spl, .ch, \#ads,\
591 \#toolbar, \#google_ads_frame, \#mbEnd {display: none !important;}\n\
592 .main_body, .j, \#res, .med, .hd, .g, .s\n\
593 {width: 99%; max-width: 100%; margin-left: 0; margin-right: 0;}\n\
595 s@<div style=\"padding-top:11px;min-width:500px\">@<div id="main_body">@
596 s@(<table cellspacing=0 cellpadding=0 width=25% align=right bgcolor=\#ffffff border=0\
597 |</font></td></tr></tbody></table><table align=\"right\" bgcolor=\"\#ffffff\"\
598 |<table cellspacing=0 cellpadding=0 align=right bgcolor=\#ffffff border=0\
599 |<table style=\"clear:both\" align=right width=25% cellspacing=\"0\" cellpadding=\"0\"\
600 border=\"0\" bgcolor=\"\#ffffff\")@$0 id="ads"@
601 s@(<br clear=all><table)( border=0 cellpadding=9><tr><td)@$1 id="toolbar"$2@
603 #################################################################################
605 # yahoo: CSS-based block for Yahoo text ads. Also removes a width limitation.
607 #################################################################################
608 FILTER: yahoo CSS-based block for Yahoo text ads. Also removes a width limitation.
610 s@</head>@\n<style type="text/css">\n\
611 /* Style sheet inserted by Privoxy's yahoo filter. */\n\
612 \#symadbn, \#ymadbn, .yschbox, .yschhd, .bbox, \#yschsec, \#sec,\
613 \#yschanswr, .yschftad, .yschspn, .yschspns, \#ygrp-sponsored-links,\
614 \#nwad, \#MWA2, \#MSCM, \#yregad, \#sponsored-links,\
615 \#ks-ypn-ads, .ad, \#east, \#ygrp-vital, .ads {display: none !important;}\n\
616 \#yschpri, \#yschweb, \#pri, \#web, \#main, .yschttl, .abstr, .res \n\
617 {width: 99% !important; max-width: 100% !important;}\n\
618 .yschttl, .res, .res.indent, \#web {padding: 0px; margin: 0px !important;}\n\
619 \#web {padding-left: 0.5em}\n\
620 \#yschqcon, \#yschtg {width: auto !important; /* No useless horizontal scrollbar please */}\n\
621 \#composebox \#compose_editorArea {width: 70% !important; /* reasonably sized reply textarea please */\n\
624 s@(<textarea\s+id="composeArea"[^>]*)width:545px;@$1width:70%;@isU
626 #################################################################################
628 # msn: CSS-based block for MSN text ads. Also removes tracking URLs
629 # and a width limitation.
631 #################################################################################
632 FILTER: msn CSS-based block for MSN text ads. Also removes tracking URLs and a width limitation.
634 s@</head>@<style type="text/css">\n\
635 /* Style sheet inserted by Privoxy's msn filter. */\n\
636 .msn_ads, \#at, \#ar, .mktmsg {display: none !important;}\n\
637 \#results, .flank, .results_area_flank, .results_area_stroke,\n\
638 \#results_area, \#content, .sb_tlst, .sa_cc, .sb_ph, \#sw_main,\n\
639 .content, \#sw_foot, \#bf, \#sw_content, \#sidebar, \#pag\n\
640 {width: 99% !important; min-width: 99% !important;\n\
641 max-width: 100% !important; /* width:100% sometimes causes horizontal scrollbars */}\n\
642 /* Remove "suggestions". They are next to worthless but partly overlap with the search results */\n\
643 .suggestion, \#nys_right, \#nys {clear: both; display:none;}\n\
645 /* Overlay ads to enable Facebook 'likes' in search results. */\n\
646 .sn_container {display:none !important;}\n\
647 \#content {padding-right: 0;}\n\
649 # Are these ids still in use?
650 s@(<div[^>]*) id=(["']?)ads_[^\2]*\2@$1 class="msn_ads"@Uig
651 s@(<div[^>]*) class=(["']?)sb_ads[^\2]*\2@$1 class="msn_ads"@Uig
652 s@(<a[^>]*href=\")http://g.msn.com/.*\?(http://.*)(&&DI=.*)(\")@$1$2$4@Ug
653 s@(<a[^>]*)gping=\".*\"@$1 title="URL cleaned up by Privoxy's msn filter"@Ug
655 #################################################################################
657 # blogspot: Cleans up some Blogspot blogs. Read the fine print before using this.
659 # This filter also intentionally removes some navigation stuff and
660 # sets the page width to 100%. As a result, some rounded "corners" would
661 # appear to early or not at all and as fixing this would require a browser
662 # that understands background-size (CSS3), they are removed instead.
664 # When applied to feeds, it removes comment titles that
665 # only contain the beginning of the actual comment.
667 #################################################################################
668 FILTER: blogspot Cleans up some Blogspot blogs. Read the fine print before using this.
670 s@</head>@<style type="text/css">\n\
671 /* Style sheet inserted by Privoxy's blogspot filter. */\n\
672 \#powered-by {display: none !important;}\n\
673 \#wrap4, \#wrapper {margin-top: 0px }\n\
674 \#blogheader, \#header {margin-top: 0.5em !important}\n\
675 \#content {width: 98% }\n\
676 \#main {width: 70% }\n\
677 \#sidebar {width: 29% }\n\
678 .post-body {overflow: auto;}\n\
679 .blogComments {width: 100%; overflow: auto;}\n</style>\n$0@
680 s@<body.*(?:<div id="space-for-ie"></div>|(<div id="(?:content|wrap4|wrapper)))@<body>\
681 <!-- Privoxy's blogspot filter ditched some garbage here -->$1@Us
682 s@(<div style=\"[^\"]*width:)30em@$1 100%@
683 s@background:url\(\"http://www.blogblog.com/rounders[^\"]*\"\).*;@/*$0*/@Ug
684 s@(background:\#[a-f\d]{3})( url\(\"http://www.blogblog.com/rounders[^\"]*\"\).*;)@$1 ;/*$2*/@Ug
685 # Do the feed filtering magic as described above.
686 s@<title(?:\s+type=\'text\')?>([^<]*)(?:\.\.\.)?\s*</title>\s*\
687 (<content(?:\s+type=\'(?:html|text)\')?>\s*\1)@<title></title>$2@ig
689 #################################################################################
691 # x-httpd-php-to-html: Changes the Content-Type header from
692 # x-httpd-php to html. "Content-Type: x-httpd-php"
693 # is set by clueless PHP users and causes many
694 # browsers do open a download menu instead of
695 # rendering the page.
697 #################################################################################
698 SERVER-HEADER-FILTER: x-httpd-php-to-html Changes the Content-Type header from x-httpd-php to html.
700 s@^(Content-Type:)\s*application/x-httpd-php@$1 text/html@i
702 #################################################################################
704 # html-to-xml: Changes the Content-Type header from html to xml.
706 #################################################################################
707 SERVER-HEADER-FILTER: html-to-xml Changes the Content-Type header from html to xml.
709 s@^(Content-Type:)\s*text/html(;.*)?$@$1 application/xhtml+xml$2@i
711 #################################################################################
713 # xml-to-html: Changes the Content-Type header from xml to html.
715 #################################################################################
716 SERVER-HEADER-FILTER: xml-to-html Changes the Content-Type header from xml to html.
718 s@^(Content-Type:)\s*(?:application|text)/(?:xhtml\+)?xml(;.*)?$@$1 text/html$2@i
720 #################################################################################
722 # hide-tor-exit-notation: Remove the Tor exit node notation in Host and Referer headers.
724 # Note: If Privoxy and Tor are chained and Privoxy is configured to
725 # use socks4a, one can use http://www.example.org.foobar.exit/
726 # to access the host www.example.org through Tor exit node foobar.
728 # As the HTTP client isn't aware of this notation, it treats the
729 # whole string "www.example.org.foobar.exit" as host and uses it
730 # for the "Host" and "Referer" headers. From the server's point of
731 # view the resulting headers are invalid and can cause problems.
733 # An invalid "Referer" header can trigger "hot-linking" protections,
734 # an invalid "Host" header will make it impossible for the server to
735 # find the right vhost (several domains hosted on the same IP address).
737 # This filter removes the "foo.exit" part in those headers
738 # to prevent the mentioned problems. Note that it only modifies
739 # the HTTP headers, it doesn't make it impossible for the server
740 # to detect your Tor exit node based on the IP address the request is
743 #################################################################################
744 CLIENT-HEADER-FILTER: hide-tor-exit-notation Removes the Tor exit node notation in Host and Referer headers.
746 s@^((?:Referer|Host):\s*(?:https?://)?[^/]*)\.[^\./]*?\.exit@$1@i
748 #################################################################################
750 # less-download-windows: Prevents annoying download windows for content types
751 # the browser can handle itself.
753 #################################################################################
754 SERVER-HEADER-FILTER: less-download-windows Prevent annoying download windows for content types the browser can handle itself.
756 s@^Content-Disposition:.*filename=(["']?).*\.(png|gif|jpe?g|diff?|d?patch|c|h|pl|shar)\1.*$@@i
757 s@^(Content-Type:)\s*(?:message/(?:news|rfc822)|text/x-.*|application/x-sh(?:\s|$))\s*@$1 text/plain@i
759 #################################################################################
761 # image-requests: Tags detected image requests as "IMAGE-REQUEST". Whether
762 # or not the detection actually works depends on the browser.
764 #################################################################################
765 CLIENT-HEADER-TAGGER: image-requests Tags detected image requests as "IMAGE-REQUEST".
767 s@^Accept:\s*image/.*@IMAGE-REQUEST@i
769 #################################################################################
771 # css-requests: Tags detected CSS requests as "CSS-REQUEST". Whether
772 # or not the detection actually works depends on the browser.
774 #################################################################################
775 CLIENT-HEADER-TAGGER: css-requests Tags detected CSS requests as "CSS-REQUEST".
777 s@^Accept:\s*text/css.*@CSS-REQUEST@i
779 #################################################################################
781 # range-requests: Tags range requests as "RANGE-REQUEST".
783 # By default Privoxy removes Range headers for requests to
784 # ressources that will be filtered to make sure the filters
785 # get the whole picture. Otherwise Range requests could be
786 # intentionally used to circumvent filters or, less likely,
787 # filtering a partial response may damage it because it matched
788 # a pattern that the ressource as a whole wouldn't.
790 # Range requests can be useful and save bandwidth so instead
791 # of removing Range headers for requests to ressources that
792 # will be filtered, you may prefer to simply disable filtering
793 # for those requests.
795 # That's what this tagger is all about. After enabling it,
796 # you can disable filtering for range requests using the following
799 # {-filter -deanimate-gifs}
802 #################################################################################
803 CLIENT-HEADER-TAGGER: range-requests Tags range requests as "RANGE-REQUEST".
805 s@^Range:.*@RANGE-REQUEST@i
807 #################################################################################
809 # client-ip-address: Tags the request with the client's IP address.
811 #################################################################################
812 CLIENT-HEADER-TAGGER: client-ip-address Tags the request with the client's IP address.
814 s@^\w*\s+.*\s+HTTP/\d\.\d\s*@IP-ADDRESS: $origin@D
816 #################################################################################
818 # http-method: Tags the request with its HTTP method.
820 #################################################################################
821 CLIENT-HEADER-TAGGER: http-method Tags the request with its HTTP method.
823 s@^(\w*).*HTTP/\d\.\d\s*$@$1@i
825 #################################################################################
827 # allow-post: Tags POST requests as "ALLOWED-POST".
829 #################################################################################
830 CLIENT-HEADER-TAGGER: allow-post Tags POST requests as "ALLOWED-POST".
832 s@^(?:POST)\s+.*\s+HTTP/\d\.\d\s*@ALLOWED-POST@i
834 #################################################################################
836 # complete-url: Tags the request with the whole request URL.
838 #################################################################################
839 CLIENT-HEADER-TAGGER: complete-url Tags the request with the whole request URL.
841 s@^\w*\s+(.*)\s+HTTP/\d\.\d\s*$@$1@i
843 #################################################################################
845 # user-agent: Tags the request with the complete User-Agent header.
847 #################################################################################
848 CLIENT-HEADER-TAGGER: user-agent Tags the request with the complete User-Agent header.
850 s@^User-Agent:.*@$0@i
852 #################################################################################
854 # referer: Tags the request with the complete Referer header.
856 #################################################################################
857 CLIENT-HEADER-TAGGER: referer Tags the request with the complete Referer header.
861 #################################################################################
863 # content-type: Tags the request with the content type declared by the server.
865 #################################################################################
866 SERVER-HEADER-TAGGER: content-type Tags the request with the content type declared by the server.
868 s@^Content-Type:\s*([^;]+).*@$1@i
870 #################################################################################
872 # privoxy-control: The taggers create tags with the content of X-Privoxy-Control
873 # headers, the filters remove said headers.
875 #################################################################################
876 CLIENT-HEADER-TAGGER: privoxy-control Creates tags with the content of X-Privoxy-Control headers.
878 s@^X-Privoxy-Control:\s*@@i
880 CLIENT-HEADER-FILTER: privoxy-control Removes X-Privoxy-Control headers.
882 s@^X-Privoxy-Control:.*@@i
884 SERVER-HEADER-TAGGER: privoxy-control Creates tags with the content of X-Privoxy-Control headers.
886 s@^X-Privoxy-Control:\s*@@i
888 SERVER-HEADER-FILTER: privoxy-control Removes X-Privoxy-Control headers.
890 s@^X-Privoxy-Control:.*@@i