1 # ********************************************************************
3 # File : $Source: /cvsroot/ijbswa/current/default.filter,v $
5 # $Id: default.filter,v 1.5 2002/03/27 15:30:26 swa Exp $
7 # Purpose : Rules to process the content of web pages
9 # Copyright : Written by and Copyright
10 # Privoxy team. http://www.privoxy.org/
12 # Based on the Internet Junkbuster originally written
13 # by and Copyright (C) 1997 Anonymous Coders and
14 # Junkbusters Corporation. http://www.junkbusters.com
16 # We value your feedback. However, to provide you with the best support,
19 # * Use the support forum to get help:
20 # http://sourceforge.net/tracker/?group_id=11118&atid=211118
21 # * Submit bugs only thru our bug forum:
22 # http://sourceforge.net/tracker/?group_id=11118&atid=111118
23 # Make sure that the bug has not already been submitted. Please try
24 # to verify that it is a Privoxy bug, and not a browser or site
25 # bug first. If you are using your own custom configuration, please
26 # try the stock configs to see if the problem is a configuration
27 # related bug. And if not using the latest development snapshot,
28 # please try the latest one. Or even better, CVS sources.
29 # * Submit feature requests only thru our feature request forum:
30 # http://sourceforge.net/tracker/?atid=361118&group_id=11118&func=browse
32 # For any other issues, feel free to use the mailing lists:
33 # http://sourceforge.net/mail/?group_id=11118
35 # Anyone interested in actively participating in development and related
36 # discussions can join the appropriate mailing list here:
37 # http://sourceforge.net/mail/?group_id=11118. Archives are available
40 #################################################################################
44 # Filters start with a line "FILTER: name description". They are then referrable
45 # from the actionsfile with +filter{name}
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 delimter as you see fit.
55 # Note2: In addidion 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.
60 # 'T' (trivial) prevents parsing for backreferences in the substitute.
61 # Use if you want to include text like '$&' in your substitute without
64 #################################################################################
67 #################################################################################
69 # html-annoyances: Get rid of particularly annoying HTML abuse
71 #################################################################################
72 FILTER: html-annoyances Get rid of particularly annoying HTML abuse
74 # New browser windows (if allowed -- see no-popups filter below) should be
75 # resizeable and have a location and status bar
77 s/(<a\s+href[^>]+)resizable=['"]?(no|0|false)['"]?(.*>)/$1resizable=1$3/igU
78 s/(<a\s+href[^>]+)location=['"]?(no|0)['"]?(.*>)/$1location=1$3/igU
79 s/(<a\s+href[^>]+)status=['"]?(no|0)['"]?(.*>)/$1status=1$3/igU
80 s/(<a\s+href[^>]+)scrolling=['"]?(no|0|auto)['"]?(.*>)/$1scrolling=no$3/igU
81 s/(<a\s+href[^>]+)menubar=['"]?(no|0)['"]?(.*>)/$1menubar=1$3/igU
83 # The <BLINK> tag was a crime!
85 s*<blink>|</blink>**ig
89 #s/margin(height|width)=[0-9]*//gi
90 #s/noresize/yesresize/igU
93 #################################################################################
95 # js-annoyances: Get rid of particularly annoying JavaScript abuse
97 #################################################################################
98 FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse
100 # Get rid of Javascript referrer tracking. Test page: http://www.randomoddness.com/untitled.htm
102 s|(<script.*)document\.referrer(.*</script>)|$1"Not Your Business!"$2|Usg
104 # The status bar is for displaying link targets, not pointless blahblah
108 # Kill OnUnload popups. Yummy. Test: http://www.zdnet.com/zdsubs/yahoo/tree/yfs.html
110 s/(<body .*)onunload(.*>)/$1never$2/iU
113 #################################################################################
115 # content-cookies: Kill cookies that come in the HTML or JS content
117 #################################################################################
118 FILTER: content-cookies Kill cookies that come in the HTML or JS content
120 # JS cookies, like found on privacy.net:
122 s|(document\.cookie)([ \t\r\n]*=)|documenZapCooky$2|g
126 s|<meta\s+http-equiv=['"]?set-cookie['"]?\s+content=[^>].*>|<!--no cookies here -->|iUT
129 ##################################################################################
131 # no-popups: Kill all popups in JS and HTML
133 #################################################################################
134 FILTER: no-popups Kill all popups in JS and HTML
136 s/window\.open\(/1;''\.concat\(/ig # JavaScript
137 s/target=['"]?_blank['"]?/target_crunched/ig # HTML
138 s/target=['"]?_new['"]?/target_crunched/ig # HTML
140 #################################################################################
142 # frameset-borders: Give frames a border and make them resizable
144 #################################################################################
145 FILTER: frameset-borders Give frames a border and make them resizable
147 s/(<frameset [^>]+)framespacing=['"]?(no|0)['"]?(.*>)/$1$3/igU
148 s/(<frameset [^>]+)frameborder=['"]?(no|0)['"]?(.*>)/$1$3/igU
149 s/(<frame [^>]+)border=['"]?(no|0)['"]?(.*>)/$1$3/igU
150 s/(<frame [^>]+)resizable=['"]?(no|0|false)['"]?(.*>)/$1$3/igU
152 #################################################################################
154 # webbugs: Squish WebBugs (1x1 invisible GIFs used for user tracking)
156 #################################################################################
157 FILTER: webbugs Squish WebBugs (1x1 invisible GIFs used for user tracking)
159 s/<img\s+[^>]*?(width|height)\s*=\s*['"]?1\D[^>]*?(width|height)\s*=\s*['"]?1(\D[^>]*?)?>/<!-- Squished WebBug -->/sig
162 #################################################################################
164 # no-refresh: Kill automatic refresh tags (for dial-on-demand setups)
166 #################################################################################
167 FILTER: no-refresh Kill automatic refresh tags (for dial-on-demand setups)
169 s/<meta\s+http-equiv=['"]?refresh['"]?\s+content=['"]?[0-9]*;\s+url=([^>]*)['"]?>/<link rev="x-refresh" href=$1>/iU
170 s/<meta\s+http-equiv=['"]?page-enter['"]?\s+content=[^>].*>/<!--no page enter for me-->/iU
173 #################################################################################
175 # fun: Text replacements for subversive browsing fun!
177 #################################################################################
178 FILTER: fun Text replacements for subversive browsing fun!
180 s/microsoft(?!.com)/MicroSuck/ig
182 # Buzzword Bingo (example for extended syntax)
184 s* industry[ -]leading \
186 | award[ -]winning # Comments are OK, too! \
187 | high[ -]performance \
188 | solutions[ -]based \
192 *<font color=red><b>BINGO!</b></font> \
196 #################################################################################
198 # nimda: Remove Nimda (virus) code
200 #################################################################################
201 FILTER: nimda Remove Nimda (virus) code
203 s%<script language="JavaScript">(window\.open|1;''\.concat)\("readme\.eml", null, "resizable=no,top=6000,left=6000"\)</script>%<br><hr><font size=7><b>Internet J</b></font><b><font size=6>UNK</font><font size=5 color="red"><i>BUSTER</i></font></b><font size=7> WARNING: This Server is infected with <a href="http://www.cert.org/advisories/CA-2001-26.html">Nimda</a>!</font>%g
206 #################################################################################
208 # banners-by-size: Kill banners by size
210 #################################################################################
212 # Standard banner sizes taken from http://www.iab.net/iab_banner_standards/bannersizes.html
214 # Note: Use http://config.privoxy.org/send-banner?type=trans for a transparent 1x1 image
215 # Use http://config.privoxy.org/send-banner?type=pattern for a grey/white pattern image
216 # Use http://config.privoxy.org/send-banner?type=auto to auto-select.
218 #################################################################################
219 FILTER: banners-by-size Kill banners by size
221 s|<img\s+[^>]*?(width=['"]?468\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
222 s|<img\s+[^>]*?(width=['"]?234\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
223 s|<img\s+[^>]*?(width=['"]?88\D)[^>]*(height=['"]?31[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
224 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?90[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
225 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?600[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
226 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
227 s|<img\s+[^>]*?(width=['"]?160\D)[^>]*(height=['"]?600[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
228 s|<img\s+[^>]*?(width=['"]?125\D)[^>]*(height=['"]?125[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
229 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?240[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
230 s|<img\s+[^>]*?(width=['"]?180\D)[^>]*(height=['"]?150[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
231 s|<img\s+[^>]*?(width=['"]?300\D)[^>]*(height=['"]?250[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
232 s|<img\s+[^>]*?(width=['"]?250\D)[^>]*(height=['"]?250[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
233 s|<img\s+[^>]*?(width=['"]?240\D)[^>]*(height=['"]?400[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
234 s|<img\s+[^>]*?(width=['"]?336\D)[^>]*(height=['"]?280[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
236 # One more. (Where is 200x50 from?)
238 s|<img\s+[^>]*?(width=['"]?200\D)[^>]*(height=['"]?50[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
241 #################################################################################
243 # crude-parental: Crude parental filtering? (Use along with a suitable blocklist).
244 # Shows how to deny access to whole page based on a keyword.
246 #################################################################################
248 # (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words)
249 # (Note #2: Is 'sex' a rude word?!)
251 #################################################################################
252 FILTER: crude-parental Crude parental filtering (demo only)
254 s%^.*(?<!middle)(?<!sus)(?<!es)sex.*$%<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
255 s+^.*warez.*$+<html><head><title>No Warez</title></head><body><h3>You're not searching for illegal stuff, are you?</h3></body></html>+is
257 ##############################################################################
260 # $Log: default.filter,v $
261 # Revision 1.5 2002/03/27 15:30:26 swa
262 # have a consistent appearance
264 # Revision 1.4 2002/03/26 22:29:54 swa
265 # we have a new homepage!
267 # Revision 1.3 2002/03/24 16:08:03 jongfoster
268 # Fixing banners-by-size for new config URLs
270 # Revision 1.2 2002/03/24 13:02:18 swa
271 # name change related issues.
273 # Revision 1.1 2002/03/24 11:37:39 jongfoster
276 # Revision 1.24 2002/03/16 20:39:54 oes
277 # - Added descriptions to the filters so users will know what they select in the cgi editor
278 # - Added content-cookies filter
279 # - Bugfixed many jobs (Thanks to Al for some hints)
281 # Revision 1.22 2002/03/12 13:42:50 oes
282 # Fixing & Optimizing REs
284 # Revision 1.21 2002/03/12 11:59:20 oes
285 # Beefed up Buzzword Bingo
287 # Revision 1.20 2002/03/12 01:42:50 oes
288 # Introduced modular filters
290 # Revision 1.19 2002/03/10 19:49:24 oes
291 # Added expression to kill referer tracking in JavaScripts
293 # Revision 1.18 2002/03/08 17:14:12 oes
294 # PNG -> image in comments
296 # Revision 1.17 2002/03/07 03:50:54 oes
297 # Adapted comments to new built-in images
299 # Revision 1.16 2002/02/21 00:12:19 jongfoster
300 # Modifying the banner regexps to use long URLS and to autodetect
301 # whether to show a logo or a transparent GIF, based on actionsfile
304 # Revision 1.15 2001/12/28 23:54:20 steudten
305 # Fix for feature Req #495374: http-equiv problem
307 # Revision 1.14 2001/12/09 18:55:11 david__schmidt
308 # Updated CODE_STATUS to beta, commented out microsuck line in re_filterfile
311 # Revision 1.13 2001/10/13 13:11:20 joergs
312 # Fixed WebBug filter.
314 # Revision 1.12 2001/10/07 15:46:42 oes
315 # Followed Guy's proposal to change the document.cookie job
317 # Revision 1.11 2001/09/21 12:34:00 joergs
318 # Added filter to replace "Nimda" code by a warning.
320 # Revision 1.10 2001/07/20 11:04:26 oes
321 # Added Rodneys javascript cookie filter
323 # Revision 1.9 2001/07/13 14:03:48 oes
324 # Elimiated yet another bug in the banner-by-size jobs. Shame on me!
326 # Revision 1.8 2001/06/29 13:34:00 oes
327 # - Added explanation for U and T options
328 # - Added hint on image replacement by CGI call
329 # - Fixed bug in banner-by-size jobs
331 # Revision 1.7 2001/06/19 14:21:56 oes
332 # Fixed microsuck line
334 # Revision 1.6 2001/06/09 14:01:57 swa
335 # header. cosmetics. default: no messing ala microsuck.