diff --git a/config/filter.d/apache-badbots.conf b/config/filter.d/apache-badbots.conf index 4feb70d70..a700c8639 100644 --- a/config/filter.d/apache-badbots.conf +++ b/config/filter.d/apache-badbots.conf @@ -5,18 +5,19 @@ # # Author: Yaroslav Halchenko # -# [Definition] -badbotscustom = EmailCollector|WebEMailExtrac + +badbotscustom = EmailCollector|WebEMailExtrac|TrackBack/1\.02 badbots = atSpider/1\.0|autoemailspider|China Local Browse 2\.6|ContentSmartz|DataCha0s/2\.0|DataCha0s/2\.0|DBrowse 1\.4b|DBrowse 1\.4d|Demo Bot DOT 16b|Demo Bot Z 16b|DSurf15a 01|DSurf15a 71|DSurf15a 81|DSurf15a VA|EBrowse 1\.4b|Educate Search VxB|EmailSiphon|EmailWolf 1\.00|ESurf15a 15|ExtractorPro|Franklin Locator 1\.8|FSurf15a 01|Full Web Bot 0416B|Full Web Bot 0516B|Full Web Bot 2816B|Industry Program 1\.0\.x|ISC Systems iRc Search 2\.1|IUPUI Research Bot v 1\.9a|LARBIN-EXPERIMENTAL \(efp@gmx\.net\)|LetsCrawl\.com/1\.0 +http\://letscrawl\.com/|Lincoln State Web Browser|LWP\:\:Simple/5\.803|Mac Finder 1\.0\.xx|MFC Foundation Class Library 4\.0|Microsoft URL Control - 6\.00\.8xxx|Missauga Locate 1\.0\.0|Missigua Locator 1\.9|Missouri College Browse|Mizzu Labs 2\.2|Mo College 1\.9|Mozilla/2\.0 \(compatible; NEWT ActiveX; Win32\)|Mozilla/3\.0 \(compatible; Indy Library\)|Mozilla/4\.0 \(compatible; Advanced Email Extractor v2\.xx\)|Mozilla/4\.0 \(compatible; Iplexx Spider/1\.0 http\://www\.iplexx\.at\)|Mozilla/4\.0 \(compatible; MSIE 5\.0; Windows NT; DigExt; DTS Agent|Mozilla/4\.0 efp@gmx\.net|Mozilla/5\.0 \(Version\: xxxx Type\:xx\)|MVAClient|NASA Search 1\.0|Nsauditor/1\.x|PBrowse 1\.4b|PEval 1\.4b|Poirot|Port Huron Labs|Production Bot 0116B|Production Bot 2016B|Production Bot DOT 3016B|Program Shareware 1\.0\.2|PSurf15a 11|PSurf15a 51|PSurf15a VA|psycheclone|RSurf15a 41|RSurf15a 51|RSurf15a 81|searchbot admin@google\.com|sogou spider|sohu agent|SSurf15a 11 |TSurf15a 11|Under the Rainbow 2\.2|User-Agent\: Mozilla/4\.0 \(compatible; MSIE 6\.0; Windows NT 5\.1\)|WebVulnCrawl\.blogspot\.com/1\.0 libwww-perl/5\.803|Wells Search II|WEP Search 00 # Option: failregex -# Notes.: Regexp to catch known spambots and software alike. Please verify that -# it is your intent to block IPs which were driven by abovementioned bots +# Notes.: Regexp to catch known spambots and software alike. Please verify +# that it is your intent to block IPs which were driven by +# abovementioned bots. # Values: TEXT # -failregex = ^(?P\S*) -.*"GET.*HTTP.*"(?:%(badbots)s|%(badbotscustom)s)"$ +failregex = ^ -.*"(GET|POST).*HTTP.*"(?:%(badbots)s|%(badbotscustom)s)"$ # Option: ignoreregex # Notes.: regex to ignore. If this regex matches, the line is ignored.