1 # ********************************************************************
3 # File : $Source: /cvsroot/ijbswa/current/default.filter,v $
5 # Purpose : Rules to process the content of web pages
7 # Copyright : Written by and Copyright (C) 2001 the SourceForge
8 # Privoxy team. http://www.privoxy.org/
10 # This program is free software; you can redistribute it
11 # and/or modify it under the terms of the GNU General
12 # Public License as published by the Free Software
13 # Foundation; either version 2 of the License, or (at
14 # your option) any later version.
16 # This program is distributed in the hope that it will
17 # be useful, but WITHOUT ANY WARRANTY; without even the
18 # implied warranty of MERCHANTABILITY or FITNESS FOR A
19 # PARTICULAR PURPOSE. See the GNU General Public
20 # License for more details.
22 # The GNU General Public License should be included with
23 # this file. If not, you can view it at
24 # http://www.gnu.org/copyleft/gpl.html
25 # or write to the Free Software Foundation, Inc., 59
26 # Temple Place - Suite 330, Boston, MA 02111-1307, USA.
29 # $Log: default.filter,v $
30 # Revision 1.3 2002/03/24 16:08:03 jongfoster
31 # Fixing banners-by-size for new config URLs
33 # Revision 1.2 2002/03/24 13:02:18 swa
34 # name change related issues.
36 # Revision 1.1 2002/03/24 11:37:39 jongfoster
39 # Revision 1.24 2002/03/16 20:39:54 oes
40 # - Added descriptions to the filters so users will know what they select in the cgi editor
41 # - Added content-cookies filter
42 # - Bugfixed many jobs (Thanks to Al for some hints)
44 # Revision 1.22 2002/03/12 13:42:50 oes
45 # Fixing & Optimizing REs
47 # Revision 1.21 2002/03/12 11:59:20 oes
48 # Beefed up Buzzword Bingo
50 # Revision 1.20 2002/03/12 01:42:50 oes
51 # Introduced modular filters
53 # Revision 1.19 2002/03/10 19:49:24 oes
54 # Added expression to kill referer tracking in JavaScripts
56 # Revision 1.18 2002/03/08 17:14:12 oes
57 # PNG -> image in comments
59 # Revision 1.17 2002/03/07 03:50:54 oes
60 # Adapted comments to new built-in images
62 # Revision 1.16 2002/02/21 00:12:19 jongfoster
63 # Modifying the banner regexps to use long URLS and to autodetect
64 # whether to show a logo or a transparent GIF, based on actionsfile
67 # Revision 1.15 2001/12/28 23:54:20 steudten
68 # Fix for feature Req #495374: http-equiv problem
70 # Revision 1.14 2001/12/09 18:55:11 david__schmidt
71 # Updated CODE_STATUS to beta, commented out microsuck line in re_filterfile
74 # Revision 1.13 2001/10/13 13:11:20 joergs
75 # Fixed WebBug filter.
77 # Revision 1.12 2001/10/07 15:46:42 oes
78 # Followed Guy's proposal to change the document.cookie job
80 # Revision 1.11 2001/09/21 12:34:00 joergs
81 # Added filter to replace "Nimda" code by a warning.
83 # Revision 1.10 2001/07/20 11:04:26 oes
84 # Added Rodneys javascript cookie filter
86 # Revision 1.9 2001/07/13 14:03:48 oes
87 # Elimiated yet another bug in the banner-by-size jobs. Shame on me!
89 # Revision 1.8 2001/06/29 13:34:00 oes
90 # - Added explanation for U and T options
91 # - Added hint on image replacement by CGI call
92 # - Fixed bug in banner-by-size jobs
94 # Revision 1.7 2001/06/19 14:21:56 oes
95 # Fixed microsuck line
97 # Revision 1.6 2001/06/09 14:01:57 swa
98 # header. cosmetics. default: no messing ala microsuck.
103 #################################################################################
107 #################################################################################
109 # Filters start with a line "FILTER: name description". They are then referrable
110 # from the actionsfile with +filter{name}
112 # Inside the filters, write one Perl-Style substitution (job) per line.
113 # Jobs that precede the first FILTER: line are ignored.
115 # For Details see the pcrs manpage contained in this distribution.
116 # (and the perlre, perlop and pcre manpages)
118 # Note that you are free to choose the delimter as you see fit.
120 # Note2: In addidion to the Perl options gimsx, the following nonstandard
121 # options are supported:
123 # 'U' turns the default to ungreedy matching. Add ? to quantifiers to
124 # switch back to greedy.
125 # 'T' (trivial) prevents parsing for backreferences in the substitute.
126 # Use if you want to include text like '$&' in your substitute without
129 #################################################################################
132 #################################################################################
134 # html-annoyances: Get rid of particularly annoying HTML abuse
136 #################################################################################
137 FILTER: html-annoyances Get rid of particularly annoying HTML abuse
139 # New browser windows (if allowed -- see no-popups filter below) should be
140 # resizeable and have a location and status bar
142 s/(<a\s+href[^>]+)resizable=['"]?(no|0|false)['"]?(.*>)/$1resizable=1$3/igU
143 s/(<a\s+href[^>]+)location=['"]?(no|0)['"]?(.*>)/$1location=1$3/igU
144 s/(<a\s+href[^>]+)status=['"]?(no|0)['"]?(.*>)/$1status=1$3/igU
145 s/(<a\s+href[^>]+)scrolling=['"]?(no|0|auto)['"]?(.*>)/$1scrolling=no$3/igU
146 s/(<a\s+href[^>]+)menubar=['"]?(no|0)['"]?(.*>)/$1menubar=1$3/igU
148 # The <BLINK> tag was a crime!
150 s*<blink>|</blink>**ig
154 #s/margin(height|width)=[0-9]*//gi
155 #s/noresize/yesresize/igU
158 #################################################################################
160 # js-annoyances: Get rid of particularly annoying JavaScript abuse
162 #################################################################################
163 FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse
165 # Get rid of Javascript referrer tracking. Test page: http://www.randomoddness.com/untitled.htm
167 s|(<script.*)document\.referrer(.*</script>)|$1"Not Your Business!"$2|Usg
169 # The status bar is for displaying link targets, not pointless blahblah
173 # Kill OnUnload popups. Yummy. Test: http://www.zdnet.com/zdsubs/yahoo/tree/yfs.html
175 s/(<body .*)onunload(.*>)/$1never$2/iU
178 #################################################################################
180 # content-cookies: Kill cookies that come in the HTML or JS content
182 #################################################################################
183 FILTER: content-cookies Kill cookies that come in the HTML or JS content
185 # JS cookies, like found on privacy.net:
187 s|(document\.cookie)([ \t\r\n]*=)|documenZapCooky$2|g
191 s|<meta\s+http-equiv=['"]?set-cookie['"]?\s+content=[^>].*>|<!--no cookies here -->|iUT
194 ##################################################################################
196 # no-popups: Kill all popups in JS and HTML
198 #################################################################################
199 FILTER: no-popups Kill all popups in JS and HTML
201 s/window\.open\(/1;''\.concat\(/ig # JavaScript
202 s/target=['"]?_blank['"]?/target_crunched/ig # HTML
203 s/target=['"]?_new['"]?/target_crunched/ig # HTML
205 #################################################################################
207 # frameset-borders: Give frames a border and make them resizable
209 #################################################################################
210 FILTER: frameset-borders Give frames a border and make them resizable
212 s/(<frameset [^>]+)framespacing=['"]?(no|0)['"]?(.*>)/$1$3/igU
213 s/(<frameset [^>]+)frameborder=['"]?(no|0)['"]?(.*>)/$1$3/igU
214 s/(<frame [^>]+)border=['"]?(no|0)['"]?(.*>)/$1$3/igU
215 s/(<frame [^>]+)resizable=['"]?(no|0|false)['"]?(.*>)/$1$3/igU
217 #################################################################################
219 # webbugs: Squish WebBugs (1x1 invisible GIFs used for user tracking)
221 #################################################################################
222 FILTER: webbugs Squish WebBugs (1x1 invisible GIFs used for user tracking)
224 s/<img\s+[^>]*?(width|height)\s*=\s*['"]?1\D[^>]*?(width|height)\s*=\s*['"]?1(\D[^>]*?)?>/<!-- Squished WebBug -->/sig
227 #################################################################################
229 # no-refresh: Kill automatic refresh tags (for dial-on-demand setups)
231 #################################################################################
232 FILTER: no-refresh Kill automatic refresh tags (for dial-on-demand setups)
234 s/<meta\s+http-equiv=['"]?refresh['"]?\s+content=['"]?[0-9]*;\s+url=([^>]*)['"]?>/<link rev="x-refresh" href=$1>/iU
235 s/<meta\s+http-equiv=['"]?page-enter['"]?\s+content=[^>].*>/<!--no page enter for me-->/iU
238 #################################################################################
240 # fun: Text replacements for subversive browsing fun!
242 #################################################################################
243 FILTER: fun Text replacements for subversive browsing fun!
245 s/microsoft(?!.com)/MicroSuck/ig
247 # Buzzword Bingo (example for extended syntax)
249 s* industry[ -]leading \
251 | award[ -]winning # Comments are OK, too! \
252 | high[ -]performance \
253 | solutions[ -]based \
257 *<font color=red><b>BINGO!</b></font> \
261 #################################################################################
263 # nimda: Remove Nimda (virus) code
265 #################################################################################
266 FILTER: nimda Remove Nimda (virus) code
268 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
271 #################################################################################
273 # banners-by-size: Kill banners by size
275 #################################################################################
277 # Standard banner sizes taken from http://www.iab.net/iab_banner_standards/bannersizes.html
279 # Note: Use http://config.privoxy.org/send-banner?type=trans for a transparent 1x1 image
280 # Use http://config.privoxy.org/send-banner?type=pattern for a grey/white pattern image
281 # Use http://config.privoxy.org/send-banner?type=auto to auto-select.
283 #################################################################################
284 FILTER: banners-by-size Kill banners by size
286 s|<img\s+[^>]*?(width=['"]?468\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
287 s|<img\s+[^>]*?(width=['"]?234\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
288 s|<img\s+[^>]*?(width=['"]?88\D)[^>]*(height=['"]?31[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
289 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?90[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
290 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?600[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
291 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
292 s|<img\s+[^>]*?(width=['"]?160\D)[^>]*(height=['"]?600[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
293 s|<img\s+[^>]*?(width=['"]?125\D)[^>]*(height=['"]?125[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
294 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?240[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
295 s|<img\s+[^>]*?(width=['"]?180\D)[^>]*(height=['"]?150[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
296 s|<img\s+[^>]*?(width=['"]?300\D)[^>]*(height=['"]?250[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
297 s|<img\s+[^>]*?(width=['"]?250\D)[^>]*(height=['"]?250[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
298 s|<img\s+[^>]*?(width=['"]?240\D)[^>]*(height=['"]?400[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
299 s|<img\s+[^>]*?(width=['"]?336\D)[^>]*(height=['"]?280[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
301 # One more. (Where is 200x50 from?)
303 s|<img\s+[^>]*?(width=['"]?200\D)[^>]*(height=['"]?50[^>]*?)>|<img src=http://config.privoxy.org/send-banner?type=auto $1 $2>|sig
306 #################################################################################
308 # crude-parental: Crude parental filtering? (Use along with a suitable blocklist).
309 # Shows how to deny access to whole page based on a keyword.
311 #################################################################################
313 # (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words)
314 # (Note #2: Is 'sex' a rude word?!)
316 #################################################################################
317 FILTER: crude-parental Crude parental filtering (demo only)
319 s%^.*(?<!middle)(?<!sus)(?<!es)sex.*$%<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
320 s+^.*warez.*$+<html><head><title>No Warez</title></head><body><h3>You're not searching for illegal stuff, are you?</h3></body></html>+is