# ******************************************************************** # # File : $Source: /cvsroot/ijbswa/current/default.filter,v $ # # $Id: default.filter,v 1.10 2002/04/18 10:14:19 oes Exp $ # # Purpose : Rules to process the content of web pages # # Copyright : Written by and Copyright # Privoxy team. http://www.privoxy.org/ # # We value your feedback. However, to provide you with the best support, # please note: # # * Use the support forum to get help: # http://sourceforge.net/tracker/?group_id=11118&atid=211118 # * Submit bugs only thru our bug forum: # http://sourceforge.net/tracker/?group_id=11118&atid=111118 # Make sure that the bug has not already been submitted. Please try # to verify that it is a Privoxy bug, and not a browser or site # bug first. If you are using your own custom configuration, please # try the stock configs to see if the problem is a configuration # related bug. And if not using the latest development snapshot, # please try the latest one. Or even better, CVS sources. # * Submit feature requests only thru our feature request forum: # http://sourceforge.net/tracker/?atid=361118&group_id=11118&func=browse # # For any other issues, feel free to use the mailing lists: # http://sourceforge.net/mail/?group_id=11118 # # Anyone interested in actively participating in development and related # discussions can join the appropriate mailing list here: # http://sourceforge.net/mail/?group_id=11118. Archives are available # here too. # ################################################################################# # # Syntax: # # Filters start with a line "FILTER: name description". They are then referrable # from the actionsfile with +filter{name} # # Inside the filters, write one Perl-Style substitution (job) per line. # Jobs that precede the first FILTER: line are ignored. # # For Details see the pcrs manpage contained in this distribution. # (and the perlre, perlop and pcre manpages) # # Note that you are free to choose the delimter as you see fit. # # Note2: In addidion to the Perl options gimsx, the following nonstandard # options are supported: # # 'U' turns the default to ungreedy matching. Add ? to quantifiers to # switch back to greedy. # 'T' (trivial) prevents parsing for backreferences in the substitute. # Use if you want to include text like '$&' in your substitute without # quoting. # ################################################################################# ################################################################################# # # html-annoyances: Get rid of particularly annoying HTML abuse # ################################################################################# FILTER: html-annoyances Get rid of particularly annoying HTML abuse # New browser windows (if allowed -- see no-popups filter below) should be # resizeable and have a location and status bar # s/(]+)resizable=['"]?(no|0|false)['"]?(.*>)/$1resizable="1"$3/igU s/(]+)location=['"]?(no|0)['"]?(.*>)/$1location="1"$3/igU s/(]+)status=['"]?(no|0)['"]?(.*>)/$1status="1"$3/igU s/(]+)scrolling=['"]?(no|0|auto)['"]?(.*>)/$1scrolling="no"$3/igU s/(]+)menubar=['"]?(no|0)['"]?(.*>)/$1menubar="1"$3/igU # The tag was a crime! # s*|**ig ################################################################################# # # js-annoyances: Get rid of particularly annoying JavaScript abuse # ################################################################################# FILTER: js-annoyances Get rid of particularly annoying JavaScript abuse # Get rid of Javascript referrer tracking. Test page: http://www.randomoddness.com/untitled.htm # s|()|$1"Not Your Business!"$2|Usg # The status bar is for displaying link targets, not pointless blahblah # s/window.status\s*=\s*['"].*?['"]/dUmMy=1/ig # Kill OnUnload popups. Yummy. Test: http://www.zdnet.com/zdsubs/yahoo/tree/yfs.html # s/()/$1never$2/iU ################################################################################# # # content-cookies: Kill cookies that come in the HTML or JS content # ################################################################################# FILTER: content-cookies Kill cookies that come in the HTML or JS content # JS cookies, like found on privacy.net: # s|(document\.cookie)([ \t\r\n]*=)|documenZapCooky$2|g # HTML cookies: # s|].*>||iUT ################################################################################## # # popups: Kill all popups in JS and HTML # ################################################################################# FILTER: popups Kill all popups in JS and HTML s/window\.open\s*\(/concat(/ig # JavaScript s/([ =;])open\s*\(/$1concat(/ig # JavaScript alternative s/target=['"]?(_blank|_new)['"]?/notarget/ig # HTML ################################################################################# # # frameset-borders: Give frames a border, make them resizable and scrollable # ################################################################################# FILTER: frameset-borders Give frames a border and make them resizable s/(]+)framespacing=['"]?(no|0)['"]?(.*>)/$1$3/igU s/(]+)(frame)?border=['"]?(no|0)['"]?(.*>)/$1$4/igU s/(]+)frameborder=['"]?(no|0)['"]?(.*>)/$1$3/igU s/(]+)noresize(.*>)/$1$2/igU s/(]+)resizable=['"]?(no)['"]?(.*>)/$1$3/igU s/(]+)scrolling=['"]?(no)['"]?(.*>)/$1$3/igU ################################################################################# # # webbugs: Squish WebBugs (1x1 invisible GIFs used for user tracking) # ################################################################################# FILTER: webbugs Squish WebBugs (1x1 invisible GIFs used for user tracking) s/]*?(width|height)\s*=\s*['"]?1\D[^>]*?(width|height)\s*=\s*['"]?1(\D[^>]*?)?>//siUg ################################################################################# # # refresh-tags: Kill automatic refresh tags (for dial-on-demand setups) # ################################################################################# FILTER: refresh-tags Kill automatic refresh tags (for dial-on-demand setups) s/]*)['"]?>//iU s/].*>//iU ################################################################################# # # fun: Text replacements for subversive browsing fun! # ################################################################################# FILTER: fun Text replacements for subversive browsing fun! s/microsoft(?!.com)/MicroSuck/ig # Buzzword Bingo (example for extended regex syntax) # s* industry[ -]leading \ | cutting[ -]edge \ | award[ -]winning # Comments are OK, too! \ | high[ -]performance \ | solutions[ -]based \ | unmatched \ | unparalleled \ | unrivalled \ *BINGO! \ *igx ################################################################################# # # nimda: Remove Nimda (virus) code # ################################################################################# FILTER: nimda Remove Nimda (virus) code s%%
WARNING: This Server is infected with Nimda!%g ################################################################################# # # banners-by-size: Kill banners by size # ################################################################################# # # Standard banner sizes taken from http://www.iab.net/iab_banner_standards/bannersizes.html # # Note: Use http://config.privoxy.org/send-banner?type=trans for a transparent 1x1 image # Use http://config.privoxy.org/send-banner?type=pattern for a grey/white pattern image # Use http://config.privoxy.org/send-banner?type=auto to auto-select. # ################################################################################# FILTER: banners-by-size Kill banners by size s|]*?(width=['"]?468\D)[^>]*(height=['"]?60[^>]*?)>||sig s|]*?(width=['"]?234\D)[^>]*(height=['"]?60[^>]*?)>||sig s|]*?(width=['"]?88\D)[^>]*(height=['"]?31[^>]*?)>||sig s|]*?(width=['"]?120\D)[^>]*(height=['"]?90[^>]*?)>||sig s|]*?(width=['"]?120\D)[^>]*(height=['"]?600[^>]*?)>||sig s|]*?(width=['"]?120\D)[^>]*(height=['"]?60[^>]*?)>||sig s|]*?(width=['"]?160\D)[^>]*(height=['"]?600[^>]*?)>||sig s|]*?(width=['"]?125\D)[^>]*(height=['"]?125[^>]*?)>||sig s|]*?(width=['"]?120\D)[^>]*(height=['"]?240[^>]*?)>||sig s|]*?(width=['"]?180\D)[^>]*(height=['"]?150[^>]*?)>||sig s|]*?(width=['"]?300\D)[^>]*(height=['"]?250[^>]*?)>||sig s|]*?(width=['"]?250\D)[^>]*(height=['"]?250[^>]*?)>||sig s|]*?(width=['"]?240\D)[^>]*(height=['"]?400[^>]*?)>||sig s|]*?(width=['"]?336\D)[^>]*(height=['"]?280[^>]*?)>||sig # One more. (Where is 200x50 from?) # s|]*?(width=['"]?200\D)[^>]*(height=['"]?50[^>]*?)>||sig ################################################################################# # # shockwave-flash: Kill embedded Shockwave Flash objects # ################################################################################# FILTER: shockwave-flash Kill embedded Shockwave Flash objects s|]*application/x-shockwave-flash.*||sigU ################################################################################# # # crude-parental: Crude parental filtering? (Use along with a suitable blocklist). # Shows how to deny access to whole page based on a keyword. # ################################################################################# # # (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words) # (Note #2: Is 'sex' a rude word?!) # ################################################################################# FILTER: crude-parental Crude parental filtering (demo only) s%^.*(?Blocked

Blocked due to possible adult content. Please see this site.

%is s+^.*warez.*$+No Warez

You're not searching for illegal stuff, are you?

+is ############################################################################## # # Revisions : # $Log: default.filter,v $ # Revision 1.10 2002/04/18 10:14:19 oes # renamed some filters # # Revision 1.9 2002/04/11 07:36:35 oes # Generalized js-popup filter # # Revision 1.8 2002/04/10 17:07:21 oes # Fixed potentially desctructive jobs, added noflash filter # # Revision 1.7 2002/04/09 18:34:51 oes # Fixed HTML syntax in replacements # # Revision 1.6 2002/04/03 19:49:52 swa # name change # # Revision 1.5 2002/03/27 15:30:26 swa # have a consistent appearance # # Revision 1.4 2002/03/26 22:29:54 swa # we have a new homepage! # # Revision 1.3 2002/03/24 16:08:03 jongfoster # Fixing banners-by-size for new config URLs # # Revision 1.2 2002/03/24 13:02:18 swa # name change related issues. # # Revision 1.1 2002/03/24 11:37:39 jongfoster # Name change # # Revision 1.24 2002/03/16 20:39:54 oes # - Added descriptions to the filters so users will know what they select in the cgi editor # - Added content-cookies filter # - Bugfixed many jobs (Thanks to Al for some hints) # # Revision 1.22 2002/03/12 13:42:50 oes # Fixing & Optimizing REs # # Revision 1.21 2002/03/12 11:59:20 oes # Beefed up Buzzword Bingo # # Revision 1.20 2002/03/12 01:42:50 oes # Introduced modular filters # # Revision 1.19 2002/03/10 19:49:24 oes # Added expression to kill referer tracking in JavaScripts # # Revision 1.18 2002/03/08 17:14:12 oes # PNG -> image in comments # # Revision 1.17 2002/03/07 03:50:54 oes # Adapted comments to new built-in images # # Revision 1.16 2002/02/21 00:12:19 jongfoster # Modifying the banner regexps to use long URLS and to autodetect # whether to show a logo or a transparent GIF, based on actionsfile # setting. # # Revision 1.15 2001/12/28 23:54:20 steudten # Fix for feature Req #495374: http-equiv problem # # Revision 1.14 2001/12/09 18:55:11 david__schmidt # Updated CODE_STATUS to beta, commented out microsuck line in re_filterfile # for 2.9.10 beta # # Revision 1.13 2001/10/13 13:11:20 joergs # Fixed WebBug filter. # # Revision 1.12 2001/10/07 15:46:42 oes # Followed Guy's proposal to change the document.cookie job # # Revision 1.11 2001/09/21 12:34:00 joergs # Added filter to replace "Nimda" code by a warning. # # Revision 1.10 2001/07/20 11:04:26 oes # Added Rodneys javascript cookie filter # # Revision 1.9 2001/07/13 14:03:48 oes # Elimiated yet another bug in the banner-by-size jobs. Shame on me! # # Revision 1.8 2001/06/29 13:34:00 oes # - Added explanation for U and T options # - Added hint on image replacement by CGI call # - Fixed bug in banner-by-size jobs # # Revision 1.7 2001/06/19 14:21:56 oes # Fixed microsuck line # # Revision 1.6 2001/06/09 14:01:57 swa # header. cosmetics. default: no messing ala microsuck. # # #