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 1.16 2002/02/21 00:12:19 jongfoster
31 # Modifying the banner regexps to use long URLS and to autodetect
32 # whether to show a logo or a transparent GIF, based on actionsfile
35 # Revision 1.15 2001/12/28 23:54:20 steudten
36 # Fix for feature Req #495374: http-equiv problem
38 # Revision 1.14 2001/12/09 18:55:11 david__schmidt
39 # Updated CODE_STATUS to beta, commented out microsuck line in re_filterfile
42 # Revision 1.13 2001/10/13 13:11:20 joergs
43 # Fixed WebBug filter.
45 # Revision 1.12 2001/10/07 15:46:42 oes
46 # Followed Guy's proposal to change the document.cookie job
48 # Revision 1.11 2001/09/21 12:34:00 joergs
49 # Added filter to replace "Nimda" code by a warning.
51 # Revision 1.10 2001/07/20 11:04:26 oes
52 # Added Rodneys javascript cookie filter
54 # Revision 1.9 2001/07/13 14:03:48 oes
55 # Elimiated yet another bug in the banner-by-size jobs. Shame on me!
57 # Revision 1.8 2001/06/29 13:34:00 oes
58 # - Added explanation for U and T options
59 # - Added hint on image replacement by CGI call
60 # - Fixed bug in banner-by-size jobs
62 # Revision 1.7 2001/06/19 14:21:56 oes
63 # Fixed microsuck line
65 # Revision 1.6 2001/06/09 14:01:57 swa
66 # header. cosmetics. default: no messing ala microsuck.
70 # ********************************************************************/
72 # Syntax: One Perl-Style substitution per line.
73 # For Details see the perlre, perlop and pcre manpages.
74 # Note that you are free to choose the delimter as you see fit.
76 # Note: In addidion to the Perl options egimosx, the following nonstandard
77 # options are supported:
79 # 'U' turns the default to ungreedy matching. Add ? to quantifiers to
80 # switch back to greedy.
81 # 'T' (trivial) prevents parsing for backreferences in the substitute.
82 # Use if you want to include text like '$&' in your substitute without
86 # ********************************************************************/
88 # Kill OnUnload popups. Yummy.
89 # check it out on http://www.zdnet.com/zdsubs/yahoo/tree/yfs.html
91 # ********************************************************************/
92 s/(<body .*?)onunload(.*?>)/$1never$2/i
94 # ********************************************************************/
96 # Kill refresh tags. I like to refresh myself. Manually.
97 # check it out on http://www.airport-cgn.de/ and go to the arrivals page.
99 # ********************************************************************/
100 # only if content value isn't 0..1
101 # FIXME: second line like first line for content value
102 s/<meta[^>]*http-equiv[^>]*refresh.*([0-9]+[0-9]|"[2-9]);URL=([^>]*?)"?>/<link rev="x-refresh" href=$2>/i
103 s/<meta[^>]*http-equiv="?page-enter"?[^>]*content=[^>]*>/<!--no page enter for me-->/i
105 # ********************************************************************/
107 # If I allow popups, I want them to be resizeable and have a location
108 # and status bar: check it out on http://www.airport-cgn.de/ and go to
111 # ********************************************************************/
112 # s/resizable="?(no|0)"?/resizable=1/ig s/noresize/yesresize/ig
113 # s/location="?(no|0)"?/location=1/ig s/status="?(no|0)"?/status=1/ig
114 # s/scrolling="?(no|0|Auto)"?/scrolling=1/ig
115 # s/menubar="?(no|0)"?/menubar=1/ig #s/framespacing="?(no|0)"?//ig
116 # #s/margin(height|width)=[0-9]*//gi
118 # ********************************************************************/
120 # Remove frameborder=0 and border=0 from framesets
122 # ********************************************************************/
123 s/(<frameset[^>]+?)border=['"]?(no|0)['"]?/$1/ig
124 s/(<frameset[^>]+?)frameborder=['"]?(no|0)['"]?/$1/ig
126 # ********************************************************************/
128 # The status bar is for displaying link targets, not pointless descriptions.
129 # Again, check it out on http://www.airport-cgn.de/
131 # ********************************************************************/
134 # ********************************************************************/
136 # Get rid of Javascript cookies, like found on privacy.net:
138 # ********************************************************************/
140 s|(document\.cookie)([ \t\r\n]*=)|documenZapCooky$2|g
142 # ********************************************************************/
144 # Kill *all* popups a la popup.c. (But for *all* sites, so I wouldn't do that.)
146 # JavaScript: s/window\.open\(/1;''\.concat\(/ig
147 # HTML : s/target=['"]?_blank['"]?/target_who/g
149 # Kill banners by size:
150 # (Sizes from http://www.iab.net/iab_banner_standards/bannersizes.html)
151 # Note: Use http://ijbswa.sourceforge.net/config/send-banner?type=trans for a transparent 1x1 PNG
152 # Use http://ijbswa.sourceforge.net/config/send-banner?type=logo for the logo PNG
153 # Use http://ijbswa.sourceforge.net/config/send-banner?type=logo for a grey/white pattern PNG
154 # Use http://ijbswa.sourceforge.net/config/send-banner?type=auto to auto-select.
155 # ********************************************************************/
156 s|<img\s+[^>]*?(width=['"]?468\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
157 s|<img\s+[^>]*?(width=['"]?234\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
158 s|<img\s+[^>]*?(width=['"]?88\D)[^>]*(height=['"]?31[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
159 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?90[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
160 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?600[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
161 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
162 s|<img\s+[^>]*?(width=['"]?160\D)[^>]*(height=['"]?600[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
163 s|<img\s+[^>]*?(width=['"]?125\D)[^>]*(height=['"]?125[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
164 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?240[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
165 s|<img\s+[^>]*?(width=['"]?180\D)[^>]*(height=['"]?150[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
166 s|<img\s+[^>]*?(width=['"]?300\D)[^>]*(height=['"]?250[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
167 s|<img\s+[^>]*?(width=['"]?250\D)[^>]*(height=['"]?250[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
168 s|<img\s+[^>]*?(width=['"]?240\D)[^>]*(height=['"]?400[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
169 s|<img\s+[^>]*?(width=['"]?336\D)[^>]*(height=['"]?280[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
171 # Where is that from?
172 s|<img\s+[^>]*?(width=['"]?200\D)[^>]*(height=['"]?50[^>]*?)>|<img src=http://ijbswa.sourceforge.net/config/send-banner?type=auto $1 $2>|sig
174 # ********************************************************************/
178 # ********************************************************************/
179 s/<img\s+[^>]*?(width|height)\s*=\s*['"]?1\D[^>]*?(width|height)\s*=\s*['"]?1(\D[^>]*?)?>/<!-- Squished WebBug -->/sig
181 # ********************************************************************/
185 # ********************************************************************/
186 #s/microsoft(?!.com)/MicroSuck/ig
188 # ********************************************************************/
190 # Crude parental filtering? (Use along with a suitable blocklist).
191 # Shows how to deny access to whole page based on a keyword.
193 # (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words)
194 # (Note #2: Is 'sex' a rude word?!)
196 #s%^.*(?<!middle)(?<!sus)(?<!es)sex.*$%<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
197 #s+^.*warez.*$+<html><head><title>No Warez</title></head><body><h3>You're not searching for illegal stuff, are you?</h3></body></html>+is
199 # ********************************************************************/
203 # ********************************************************************/
204 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