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 1.12 2001/10/07 15:46:42 oes
31 # Followed Guy's proposal to change the document.cookie job
33 # Revision 1.11 2001/09/21 12:34:00 joergs
34 # Added filter to replace "Nimda" code by a warning.
36 # Revision 1.10 2001/07/20 11:04:26 oes
37 # Added Rodneys javascript cookie filter
39 # Revision 1.9 2001/07/13 14:03:48 oes
40 # Elimiated yet another bug in the banner-by-size jobs. Shame on me!
42 # Revision 1.8 2001/06/29 13:34:00 oes
43 # - Added explanation for U and T options
44 # - Added hint on image replacement by CGI call
45 # - Fixed bug in banner-by-size jobs
47 # Revision 1.7 2001/06/19 14:21:56 oes
48 # Fixed microsuck line
50 # Revision 1.6 2001/06/09 14:01:57 swa
51 # header. cosmetics. default: no messing ala microsuck.
55 # ********************************************************************/
57 # Syntax: One Perl-Style substitution per line.
58 # For Details see the perlre, perlop and pcre manpages.
59 # Note that you are free to choose the delimter as you see fit.
61 # Note: In addidion to the Perl options egimosx, the following nonstandard
62 # options are supported:
64 # 'U' turns the default to ungreedy matching. Add ? to quantifiers to
65 # switch back to greedy.
66 # 'T' (trivial) prevents parsing for backreferences in the substitute.
67 # Use if you want to include text like '$&' in your substitute without
71 # ********************************************************************/
73 # Kill OnUnload popups. Yummy.
74 # check it out on http://www.zdnet.com/zdsubs/yahoo/tree/yfs.html
76 # ********************************************************************/
77 s/(<body .*?)onunload(.*?>)/$1never$2/i
79 # ********************************************************************/
81 # Kill refresh tags. I like to refresh myself. Manually.
82 # check it out on http://www.airport-cgn.de/ and go to the arrivals page.
84 # ********************************************************************/
85 s/<meta[^>]*http-equiv[^>]*refresh.*URL=([^>]*?)"?>/<link rev="x-refresh" href=$1>/i
86 s/<meta[^>]*http-equiv="?page-enter"?[^>]*content=[^>]*>/<!--no page enter for me-->/i
88 # ********************************************************************/
90 # If I allow popups, I want them to be resizeable and have a location
91 # and status bar: check it out on http://www.airport-cgn.de/ and go to
94 # ********************************************************************/
95 # s/resizable="?(no|0)"?/resizable=1/ig s/noresize/yesresize/ig
96 # s/location="?(no|0)"?/location=1/ig s/status="?(no|0)"?/status=1/ig
97 # s/scrolling="?(no|0|Auto)"?/scrolling=1/ig
98 # s/menubar="?(no|0)"?/menubar=1/ig #s/framespacing="?(no|0)"?//ig
99 # #s/margin(height|width)=[0-9]*//gi
101 # ********************************************************************/
103 # Remove frameborder=0 and border=0 from framesets
105 # ********************************************************************/
106 s/(<frameset[^>]+?)border=['"]?(no|0)['"]?/$1/ig
107 s/(<frameset[^>]+?)frameborder=['"]?(no|0)['"]?/$1/ig
109 # ********************************************************************/
111 # The status bar is for displaying link targets, not pointless descriptions.
112 # Again, check it out on http://www.airport-cgn.de/
114 # ********************************************************************/
117 # ********************************************************************/
119 # Get rid of Javascript cookies, like found on privacy.net:
121 # ********************************************************************/
123 s|(document\.cookie)([ \t\r\n]*=)|documenZapCooky$2|g
125 # ********************************************************************/
127 # Kill *all* popups a la popup.c. (But for *all* sites, so I wouldn't do that.)
129 # JavaScript: s/window\.open\(/who_wants_this_to.open(/ig
130 # HTML : s/target=['"]?_blank['"]?/target_who/g
132 # Kill banners by size:
133 # (Sizes from http://www.iab.net/iab_banner_standards/bannersizes.html)
134 # Note: Use http://i.j.b/send-banner?type=trans for a transparent 1x1 gif
135 # ********************************************************************/
136 s|<img\s+[^>]*?(width=['"]?468\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
137 s|<img\s+[^>]*?(width=['"]?234\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
138 s|<img\s+[^>]*?(width=['"]?88\D)[^>]*(height=['"]?31[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
139 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?90[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
140 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?600[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
141 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?60[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
142 s|<img\s+[^>]*?(width=['"]?160\D)[^>]*(height=['"]?600[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
143 s|<img\s+[^>]*?(width=['"]?125\D)[^>]*(height=['"]?125[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
144 s|<img\s+[^>]*?(width=['"]?120\D)[^>]*(height=['"]?240[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
145 s|<img\s+[^>]*?(width=['"]?180\D)[^>]*(height=['"]?150[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
146 s|<img\s+[^>]*?(width=['"]?300\D)[^>]*(height=['"]?250[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
147 s|<img\s+[^>]*?(width=['"]?250\D)[^>]*(height=['"]?250[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
148 s|<img\s+[^>]*?(width=['"]?240\D)[^>]*(height=['"]?400[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
149 s|<img\s+[^>]*?(width=['"]?336\D)[^>]*(height=['"]?280[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
151 # Where is that from?
152 s|<img\s+[^>]*?(width=['"]?200\D)[^>]*(height=['"]?50[^>]*?)>|<img src=http://i.j.b/send-banner $1 $2>|sig
154 # ********************************************************************/
158 # ********************************************************************/
159 s/<img\s+[^>]*?(width|height)\s*=\s*['"]?1\D[^>]*?(width|height)\s*=\s*['"]?1(\D[^>]*?)?>/<!-- Squished WebBug -->/sig
161 # ********************************************************************/
165 # ********************************************************************/
166 s/microsoft(?!.com)/MicroSuck/ig
168 # ********************************************************************/
170 # Crude parental filtering? (Use along with a suitable blocklist).
171 # Shows how to deny access to whole page based on a keyword.
173 # (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words)
174 # (Note #2: Is 'sex' a rude word?!)
176 #s%^.*(?<!middle)(?<!sus)(?<!es)sex.*$%<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
177 #s+^.*warez.*$+<html><head><title>No Warez</title></head><body><h3>You're not searching for illegal stuff, are you?</h3></body></html>+is
179 # ********************************************************************/
181 # http://www.farscapezone.com/wwwboard/messages/1451.html
183 # ********************************************************************/
184 s/(\w+) was tired/<b>$1 needed more coffee<\/b>/ig
186 # ********************************************************************/
190 # ********************************************************************/
191 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