1 # ********************************************************************
3 # File : $Source: /cvsroot/ijbswa/current/re_filterfile,v $
5 # Purpose : Rules to process the content of web pages
7 # Copyright : Written by and Copyright (C) 2001 the SourceForge
8 # IJBSWA team. http://ijbswa.sourceforge.net
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: re_filterfile,v $
30 # Revision 1.24 2002/03/16 20:39:54 oes
31 # - Added descriptions to the filters so users will know what they select in the cgi editor
32 # - Added content-cookies filter
33 # - Bugfixed many jobs (Thanks to Al for some hints)
35 # Revision 1.22 2002/03/12 13:42:50 oes
36 # Fixing & Optimizing REs
38 # Revision 1.21 2002/03/12 11:59:20 oes
39 # Beefed up Buzzword Bingo
41 # Revision 1.20 2002/03/12 01:42:50 oes
42 # Introduced modular filters
44 # Revision 1.19 2002/03/10 19:49:24 oes
45 # Added expression to kill referer tracking in JavaScripts
47 # Revision 1.18 2002/03/08 17:14:12 oes
48 # PNG -> image in comments
50 # Revision 1.17 2002/03/07 03:50:54 oes
51 # Adapted comments to new built-in images
53 # Revision 1.16 2002/02/21 00:12:19 jongfoster
54 # Modifying the banner regexps to use long URLS and to autodetect
55 # whether to show a logo or a transparent GIF, based on actionsfile
58 # Revision 1.15 2001/12/28 23:54:20 steudten
59 # Fix for feature Req #495374: http-equiv problem
61 # Revision 1.14 2001/12/09 18:55:11 david__schmidt
62 # Updated CODE_STATUS to beta, commented out microsuck line in re_filterfile
65 # Revision 1.13 2001/10/13 13:11:20 joergs
66 # Fixed WebBug filter.
68 # Revision 1.12 2001/10/07 15:46:42 oes
69 # Followed Guy's proposal to change the document.cookie job
71 # Revision 1.11 2001/09/21 12:34:00 joergs
72 # Added filter to replace "Nimda" code by a warning.
74 # Revision 1.10 2001/07/20 11:04:26 oes
75 # Added Rodneys javascript cookie filter
77 # Revision 1.9 2001/07/13 14:03:48 oes
78 # Elimiated yet another bug in the banner-by-size jobs. Shame on me!
80 # Revision 1.8 2001/06/29 13:34:00 oes
81 # - Added explanation for U and T options
82 # - Added hint on image replacement by CGI call
83 # - Fixed bug in banner-by-size jobs
85 # Revision 1.7 2001/06/19 14:21:56 oes
86 # Fixed microsuck line
88 # Revision 1.6 2001/06/09 14:01:57 swa
89 # header. cosmetics. default: no messing ala microsuck.
94 #################################################################################
98 #################################################################################
100 # Filters start with a line "FILTER: name description". They are then referrable
101 # from the actionsfile with +filter{name}
103 # Inside the filters, write one Perl-Style substitution (job) per line.
104 # Jobs that precede the first FILTER: line are ignored.
106 # For Details see the pcrs manpage contained in this distribution.
107 # (and the perlre, perlop and pcre manpages)
109 # Note that you are free to choose the delimter as you see fit.
111 # Note2: In addidion to the Perl options gimsx, the following nonstandard
112 # options are supported:
114 # 'U' turns the default to ungreedy matching. Add ? to quantifiers to
115 # switch back to greedy.
116 # 'T' (trivial) prevents parsing for backreferences in the substitute.
117 # Use if you want to include text like '$&' in your substitute without
120 #################################################################################
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|false)['"]?(.*>)/$1resizable=1$3/igU
134 s/(<a\s+href[^>]+)location=['"]?(no|0)['"]?(.*>)/$1location=1$3/igU
135 s/(<a\s+href[^>]+)status=['"]?(no|0)['"]?(.*>)/$1status=1$3/igU
136 s/(<a\s+href[^>]+)scrolling=['"]?(no|0|auto)['"]?(.*>)/$1scrolling=no$3/igU
137 s/(<a\s+href[^>]+)menubar=['"]?(no|0)['"]?(.*>)/$1menubar=1$3/igU
139 # The <BLINK> tag was a crime!
141 s*<blink>|</blink>**ig
145 #s/margin(height|width)=[0-9]*//gi
146 #s/noresize/yesresize/igU
149 #################################################################################
151 # js-annoyances: Get rid of particularly annoying JavaScript abuse
153 #################################################################################
154 FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse
156 # Get rid of Javascript referrer tracking. Test page: http://www.randomoddness.com/untitled.htm
158 s|(<script.*)document\.referrer(.*</script>)|$1"Not Your Business!"$2|Usg
160 # The status bar is for displaying link targets, not pointless blahblah
164 # Kill OnUnload popups. Yummy. Test: http://www.zdnet.com/zdsubs/yahoo/tree/yfs.html
166 s/(<body .*)onunload(.*>)/$1never$2/iU
169 #################################################################################
171 # content-cookies: Kill cookies that come in the HTML or JS content
173 #################################################################################
174 FILTER: content-cookies Kill cookies that come in the HTML or JS content
176 # JS cookies, like found on privacy.net:
178 s|(document\.cookie)([ \t\r\n]*=)|documenZapCooky$2|g
182 s|<meta\s+http-equiv=['"]?set-cookie['"]?\s+content=[^>].*>|<!--no cookies here -->|iUT
185 ##################################################################################
187 # no-popups: Kill all popups in JS and HTML
189 #################################################################################
190 FILTER: no-popups Kill all popups in JS and HTML
192 s/window\.open\(/1;''\.concat\(/ig # JavaScript
193 s/target=['"]?_blank['"]?/target_crunched/ig # HTML
194 s/target=['"]?_new['"]?/target_crunched/ig # HTML
196 #################################################################################
198 # frameset-borders: Give frames a border and make them resizable
200 #################################################################################
201 FILTER: frameset-borders Give frames a border and make them resizable
203 s/(<frameset [^>]+)framespacing=['"]?(no|0)['"]?(.*>)/$1$3/igU
204 s/(<frameset [^>]+)frameborder=['"]?(no|0)['"]?(.*>)/$1$3/igU
205 s/(<frame [^>]+)border=['"]?(no|0)['"]?(.*>)/$1$3/igU
206 s/(<frame [^>]+)resizable=['"]?(no|0|false)['"]?(.*>)/$1$3/igU
208 #################################################################################
210 # webbugs: Squish WebBugs (1x1 invisible GIFs used for user tracking)
212 #################################################################################
213 FILTER: webbugs Squish WebBugs (1x1 invisible GIFs used for user tracking)
215 s/<img\s+[^>]*?(width|height)\s*=\s*['"]?1\D[^>]*?(width|height)\s*=\s*['"]?1(\D[^>]*?)?>/<!-- Squished WebBug -->/sig
218 #################################################################################
220 # no-refresh: Kill automatic refresh tags (for dial-on-demand setups)
222 #################################################################################
223 FILTER: no-refresh Kill automatic refresh tags (for dial-on-demand setups)
225 s/<meta\s+http-equiv=['"]?refresh['"]?\s+content=['"]?[0-9]*;\s+url=([^>]*)['"]?>/<link rev="x-refresh" href=$1>/iU
226 s/<meta\s+http-equiv=['"]?page-enter['"]?\s+content=[^>].*>/<!--no page enter for me-->/iU
229 #################################################################################
231 # fun: Text replacements for subversive browsing fun!
233 #################################################################################
234 FILTER: fun Text replacements for subversive browsing fun!
236 s/microsoft(?!.com)/MicroSuck/ig
238 # Buzzword Bingo (example for extended syntax)
240 s* industry[ -]leading \
242 | award[ -]winning # Comments are OK, too! \
243 | high[ -]performance \
244 | solutions[ -]based \
248 *<font color=red><b>BINGO!</b></font> \
252 #################################################################################
254 # nimda: Remove Nimda (virus) code
256 #################################################################################
257 FILTER: nimda Remove Nimda (virus) code
259 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
262 #################################################################################
264 # banners-by-size: Kill banners by size
266 #################################################################################
268 # Standard banner sizes taken from http://www.iab.net/iab_banner_standards/bannersizes.html
270 # Note: Use http://ijbswa.sourceforge.net/config/send-banner?type=trans for a transparent 1x1 image
271 # Use http://ijbswa.sourceforge.net/config/send-banner?type=logo for the logo image
272 # Use http://ijbswa.sourceforge.net/config/send-banner?type=logo for a grey/white pattern image
273 # Use http://ijbswa.sourceforge.net/config/send-banner?type=auto to auto-select.
275 #################################################################################
276 FILTER: banners-by-size Kill banners by size
278 s|<img\s+[^>]*?(width=['"]?468\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
279 s|<img\s+[^>]*?(width=['"]?234\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
280 s|<img\s+[^>]*?(width=['"]?88\D)[^>]*(height=['"]?31[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
281 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?90[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
282 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?600[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
283 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
284 s|<img\s+[^>]*?(width=['"]?160\D)[^>]*(height=['"]?600[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
285 s|<img\s+[^>]*?(width=['"]?125\D)[^>]*(height=['"]?125[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
286 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?240[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
287 s|<img\s+[^>]*?(width=['"]?180\D)[^>]*(height=['"]?150[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
288 s|<img\s+[^>]*?(width=['"]?300\D)[^>]*(height=['"]?250[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
289 s|<img\s+[^>]*?(width=['"]?250\D)[^>]*(height=['"]?250[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
290 s|<img\s+[^>]*?(width=['"]?240\D)[^>]*(height=['"]?400[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
291 s|<img\s+[^>]*?(width=['"]?336\D)[^>]*(height=['"]?280[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
293 # One more. (Where is 200x50 from?)
295 s|<img\s+[^>]*?(width=['"]?200\D)[^>]*(height=['"]?50[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
298 #################################################################################
300 # crude-parental: Crude parental filtering? (Use along with a suitable blocklist).
301 # Shows how to deny access to whole page based on a keyword.
303 #################################################################################
305 # (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words)
306 # (Note #2: Is 'sex' a rude word?!)
308 #################################################################################
309 FILTER: crude-parental Crude parental filtering (demo only)
311 s%^.*(?<!middle)(?<!sus)(?<!es)sex.*$%<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
312 s+^.*warez.*$+<html><head><title>No Warez</title></head><body><h3>You're not searching for illegal stuff, are you?</h3></body></html>+is