1 # ********************************************************************
3 # File : $Source: /cvsroot/ijbswa/current/default.filter,v $
5 # $Id: default.filter,v 1.8 2002/04/10 17:07:21 oes 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 # 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 # html-annoyances: Get rid of particularly annoying HTML abuse
67 #################################################################################
68 FILTER: html-annoyances Get rid of particularly annoying HTML abuse
70 # New browser windows (if allowed -- see no-popups filter below) should be
71 # resizeable and have a location and status bar
73 s/(<a\s+href[^>]+)resizable=['"]?(no|0|false)['"]?(.*>)/$1resizable="1"$3/igU
74 s/(<a\s+href[^>]+)location=['"]?(no|0)['"]?(.*>)/$1location="1"$3/igU
75 s/(<a\s+href[^>]+)status=['"]?(no|0)['"]?(.*>)/$1status="1"$3/igU
76 s/(<a\s+href[^>]+)scrolling=['"]?(no|0|auto)['"]?(.*>)/$1scrolling="no"$3/igU
77 s/(<a\s+href[^>]+)menubar=['"]?(no|0)['"]?(.*>)/$1menubar="1"$3/igU
79 # The <BLINK> tag was a crime!
81 s*<blink>|</blink>**ig
85 #s/margin(height|width)=[0-9]*//gi
86 #s/noresize/yesresize/igU
89 #################################################################################
91 # js-annoyances: Get rid of particularly annoying JavaScript abuse
93 #################################################################################
94 FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse
96 # Get rid of Javascript referrer tracking. Test page: http://www.randomoddness.com/untitled.htm
98 s|(<script.*)document\.referrer(.*</script>)|$1"Not Your Business!"$2|Usg
100 # The status bar is for displaying link targets, not pointless blahblah
102 s/window.status\s*=\s*['"].*?['"]/dUmMy=1/ig
104 # Kill OnUnload popups. Yummy. Test: http://www.zdnet.com/zdsubs/yahoo/tree/yfs.html
106 s/(<body .*)onunload(.*>)/$1never$2/iU
109 #################################################################################
111 # content-cookies: Kill cookies that come in the HTML or JS content
113 #################################################################################
114 FILTER: content-cookies Kill cookies that come in the HTML or JS content
116 # JS cookies, like found on privacy.net:
118 s|(document\.cookie)([ \t\r\n]*=)|documenZapCooky$2|g
122 s|<meta\s+http-equiv=['"]?set-cookie['"]?\s+content=[^>].*>|<!--no cookies here -->|iUT
125 ##################################################################################
127 # no-popups: Kill all popups in JS and HTML
129 #################################################################################
130 FILTER: no-popups Kill all popups in JS and HTML
132 s/window\.open\s*\(/concat(/ig # JavaScript
133 s/([ =;])open\s*\(/$1concat(/ig # JavaScript alternative
134 s/target=['"]?(_blank|_new)['"]?/notarget/ig # HTML
137 #################################################################################
139 # frameset-borders: Give frames a border, make them resizable and scrollable
141 #################################################################################
142 FILTER: frameset-borders Give frames a border and make them resizable
144 s/(<frameset [^>]+)framespacing=['"]?(no|0)['"]?(.*>)/$1$3/igU
145 s/(<frameset [^>]+)(frame)?border=['"]?(no|0)['"]?(.*>)/$1$4/igU
147 s/(<frame [^>]+)frameborder=['"]?(no|0)['"]?(.*>)/$1$3/igU
148 s/(<frame [^>]+)noresize(.*>)/$1$2/igU
149 s/(<frame [^>]+)resizable=['"]?(no)['"]?(.*>)/$1$3/igU
150 s/(<frame [^>]+)scrolling=['"]?(no)['"]?(.*>)/$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><font size="7"> WARNING: This Server is infected with <a href="http://www.cert.org/advisories/CA-2001-26.html">Nimda</a>!</font>%g
205 #################################################################################
207 # banners-by-size: Kill banners by size
209 #################################################################################
211 # Standard banner sizes taken from http://www.iab.net/iab_banner_standards/bannersizes.html
213 # Note: Use http://config.privoxy.org/send-banner?type=trans for a transparent 1x1 image
214 # Use http://config.privoxy.org/send-banner?type=pattern for a grey/white pattern image
215 # Use http://config.privoxy.org/send-banner?type=auto to auto-select.
217 #################################################################################
218 FILTER: banners-by-size Kill banners by size
220 s|<img\s+[^>]*?(width=['"]?468\D)[^>]*(height=['"]?60[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
221 s|<img\s+[^>]*?(width=['"]?234\D)[^>]*(height=['"]?60[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
222 s|<img\s+[^>]*?(width=['"]?88\D)[^>]*(height=['"]?31[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
223 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?90[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
224 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?600[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
225 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?60[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
226 s|<img\s+[^>]*?(width=['"]?160\D)[^>]*(height=['"]?600[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
227 s|<img\s+[^>]*?(width=['"]?125\D)[^>]*(height=['"]?125[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
228 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?240[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
229 s|<img\s+[^>]*?(width=['"]?180\D)[^>]*(height=['"]?150[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
230 s|<img\s+[^>]*?(width=['"]?300\D)[^>]*(height=['"]?250[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
231 s|<img\s+[^>]*?(width=['"]?250\D)[^>]*(height=['"]?250[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
232 s|<img\s+[^>]*?(width=['"]?240\D)[^>]*(height=['"]?400[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
233 s|<img\s+[^>]*?(width=['"]?336\D)[^>]*(height=['"]?280[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
235 # One more. (Where is 200x50 from?)
237 s|<img\s+[^>]*?(width=['"]?200\D)[^>]*(height=['"]?50[^>]*?)>|<img src="http://config.privoxy.org/send-banner?type=auto" $1 $2>|sig
240 #################################################################################
242 # noflash: Kill embedded Shockwave Flash objects
244 #################################################################################
245 FILTER: noflash Kill embedded Shockwave Flash objects
247 s|<embed [^>]*application/x-shockwave-flash.*</embed>|<!-- Squished Shockwave Flash Embed -->|sigU
250 #################################################################################
252 # crude-parental: Crude parental filtering? (Use along with a suitable blocklist).
253 # Shows how to deny access to whole page based on a keyword.
255 #################################################################################
257 # (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words)
258 # (Note #2: Is 'sex' a rude word?!)
260 #################################################################################
261 FILTER: crude-parental Crude parental filtering (demo only)
263 s%^.*(?<!middle)(?<!sus)(?<!es)sex.*$%<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
264 s+^.*warez.*$+<html><head><title>No Warez</title></head><body><h3>You're not searching for illegal stuff, are you?</h3></body></html>+is
266 ##############################################################################
269 # $Log: default.filter,v $
270 # Revision 1.8 2002/04/10 17:07:21 oes
271 # Fixed potentially desctructive jobs, added noflash filter
273 # Revision 1.7 2002/04/09 18:34:51 oes
274 # Fixed HTML syntax in replacements
276 # Revision 1.6 2002/04/03 19:49:52 swa
279 # Revision 1.5 2002/03/27 15:30:26 swa
280 # have a consistent appearance
282 # Revision 1.4 2002/03/26 22:29:54 swa
283 # we have a new homepage!
285 # Revision 1.3 2002/03/24 16:08:03 jongfoster
286 # Fixing banners-by-size for new config URLs
288 # Revision 1.2 2002/03/24 13:02:18 swa
289 # name change related issues.
291 # Revision 1.1 2002/03/24 11:37:39 jongfoster
294 # Revision 1.24 2002/03/16 20:39:54 oes
295 # - Added descriptions to the filters so users will know what they select in the cgi editor
296 # - Added content-cookies filter
297 # - Bugfixed many jobs (Thanks to Al for some hints)
299 # Revision 1.22 2002/03/12 13:42:50 oes
300 # Fixing & Optimizing REs
302 # Revision 1.21 2002/03/12 11:59:20 oes
303 # Beefed up Buzzword Bingo
305 # Revision 1.20 2002/03/12 01:42:50 oes
306 # Introduced modular filters
308 # Revision 1.19 2002/03/10 19:49:24 oes
309 # Added expression to kill referer tracking in JavaScripts
311 # Revision 1.18 2002/03/08 17:14:12 oes
312 # PNG -> image in comments
314 # Revision 1.17 2002/03/07 03:50:54 oes
315 # Adapted comments to new built-in images
317 # Revision 1.16 2002/02/21 00:12:19 jongfoster
318 # Modifying the banner regexps to use long URLS and to autodetect
319 # whether to show a logo or a transparent GIF, based on actionsfile
322 # Revision 1.15 2001/12/28 23:54:20 steudten
323 # Fix for feature Req #495374: http-equiv problem
325 # Revision 1.14 2001/12/09 18:55:11 david__schmidt
326 # Updated CODE_STATUS to beta, commented out microsuck line in re_filterfile
329 # Revision 1.13 2001/10/13 13:11:20 joergs
330 # Fixed WebBug filter.
332 # Revision 1.12 2001/10/07 15:46:42 oes
333 # Followed Guy's proposal to change the document.cookie job
335 # Revision 1.11 2001/09/21 12:34:00 joergs
336 # Added filter to replace "Nimda" code by a warning.
338 # Revision 1.10 2001/07/20 11:04:26 oes
339 # Added Rodneys javascript cookie filter
341 # Revision 1.9 2001/07/13 14:03:48 oes
342 # Elimiated yet another bug in the banner-by-size jobs. Shame on me!
344 # Revision 1.8 2001/06/29 13:34:00 oes
345 # - Added explanation for U and T options
346 # - Added hint on image replacement by CGI call
347 # - Fixed bug in banner-by-size jobs
349 # Revision 1.7 2001/06/19 14:21:56 oes
350 # Fixed microsuck line
352 # Revision 1.6 2001/06/09 14:01:57 swa
353 # header. cosmetics. default: no messing ala microsuck.