diff options
Diffstat (limited to 'ruwiki/tags/release-0.9.3/data/agents.banned')
-rw-r--r-- | ruwiki/tags/release-0.9.3/data/agents.banned | 60 |
1 files changed, 0 insertions, 60 deletions
diff --git a/ruwiki/tags/release-0.9.3/data/agents.banned b/ruwiki/tags/release-0.9.3/data/agents.banned deleted file mode 100644 index 93500d9..0000000 --- a/ruwiki/tags/release-0.9.3/data/agents.banned +++ /dev/null @@ -1,60 +0,0 @@ -#-- -# Ruwiki -# Copyright © 2002 - 2004, Digikata and HaloStatue -# Alan Chen (alan@digikata.com) -# Austin Ziegler (ruwiki@halostatue.ca) -# -# Licensed under the same terms as Ruby. -# -# $Id$ -# -# This file contains the list of User Agent strings which will be greeted -# with "403 Forbidden" responses by Ruwiki. These are generally known email -# harvesters or link directory builders for reciprocal link partners. These -# may also be robots that routinely ignore the robots.txt file. -# -# This list is generated from a wide variety of sources including: -# * http://www.clockwatchers.com/robots_list.html -# * http://searchenginewatch.com/webmasters/article.php/2167991 -# * http://www.neilgunton.com/spambot_trap/ -# * http://www.robotstxt.org/wc/active/all.txt -# -# This file is in "extended" regular expression format, one optional -# expression to a line. Spaces are not significant and comments are -# allowed. If you want to recognise a space in your regular expression, do -# so either with a character class ([ ]) or the whitespace meta-character -# (\s). Hash marks must be escaped (\#) or they will be treated as comment -# markers. Blank or comment-only lines are ignored. All other lines will -# be joined together: -# -# foo -# bar -# -# becomes: -# -# %r{foo|bar}x -#++ - - # Known email harvesters -(?i:^nicerspro) -(?i:^teleport) -^CherryPicker -^Crescent # Crescent Internet ToolPak -^EmailCollector -^EmailSiphon -^EmailWolf -^ExtractorPro -^Microsoft\sURL -^WebEMailExtrac - - # Link directory builders. -^LinkWalker -^Zeus.*Webster - - # Strongly suspected spoofed user agents from spam harvesters. These user - # agents have been reported patterns by other antispam fighters. -^[A-Z]+$ -^Internet\sExplore\s5.x -^Mozilla.*NEWT -^Mozilla\/4.0$ -MSIECrawler |