From 835b3ff483b0b62af6c48fdab3aff23730849d48 Mon Sep 17 00:00:00 2001 From: Edward Beckett Date: Sat, 5 Sep 2015 00:12:28 -0400 Subject: [PATCH 1/3] Update apache-badbots.conf Useragent strings including `+http` need to be escaped to be valid. --- config/filter.d/apache-badbots.conf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/config/filter.d/apache-badbots.conf b/config/filter.d/apache-badbots.conf index 75c0de03..48b30666 100644 --- a/config/filter.d/apache-badbots.conf +++ b/config/filter.d/apache-badbots.conf @@ -8,7 +8,7 @@ [Definition] badbotscustom = EmailCollector|WebEMailExtrac|TrackBack/1\.02|sogou music spider -badbots = Atomic_Email_Hunter/4\.0|atSpider/1\.0|autoemailspider|bwh3_user_agent|China Local Browse 2\.6|ContactBot/0\.2|ContentSmartz|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|EmailSpider|EmailWolf 1\.00|ESurf15a 15|ExtractorPro|Franklin Locator 1\.8|FSurf15a 01|Full Web Bot 0416B|Full Web Bot 0516B|Full Web Bot 2816B|Guestbook Auto Submitter|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|LMQueueBot/0\.2|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|MVAClient|Mozilla/2\.0 \(compatible; NEWT ActiveX; Win32\)|Mozilla/3\.0 \(compatible; Indy Library\)|Mozilla/3\.0 \(compatible; scan4mail \(advanced version\) http\://www\.peterspages\.net/?scan4mail\)|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 \(Version\: xxxx Type\:xx\)|NameOfAgent \(CMS Spider\)|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|ShablastBot 1\.0|snap\.com beta crawler v0|Snapbot/1\.0|Snapbot/1\.0 \(Snap Shots, +http\://www\.snap\.com\)|sogou develop spider|Sogou Orion spider/3\.0\(+http\://www\.sogou\.com/docs/help/webmasters\.htm#07\)|sogou spider|Sogou web spider/3\.0\(+http\://www\.sogou\.com/docs/help/webmasters\.htm#07\)|sohu agent|SSurf15a 11 |TSurf15a 11|Under the Rainbow 2\.2|User-Agent\: Mozilla/4\.0 \(compatible; MSIE 6\.0; Windows NT 5\.1\)|VadixBot|WebVulnCrawl\.unknown/1\.0 libwww-perl/5\.803|Wells Search II|WEP Search 00 +badbots = Atomic_Email_Hunter/4\.0|atSpider/1\.0|autoemailspider|bwh3_user_agent|China Local Browse 2\.6|ContactBot/0\.2|ContentSmartz|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|EmailSpider|EmailWolf 1\.00|ESurf15a 15|ExtractorPro|Franklin Locator 1\.8|FSurf15a 01|Full Web Bot 0416B|Full Web Bot 0516B|Full Web Bot 2816B|Guestbook Auto Submitter|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|LMQueueBot/0\.2|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|MVAClient|Mozilla/2\.0 \(compatible; NEWT ActiveX; Win32\)|Mozilla/3\.0 \(compatible; Indy Library\)|Mozilla/3\.0 \(compatible; scan4mail \(advanced version\) http\://www\.peterspages\.net/?scan4mail\)|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 \(Version\: xxxx Type\:xx\)|NameOfAgent \(CMS Spider\)|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|ShablastBot 1\.0|snap\.com beta crawler v0|Snapbot/1\.0|Snapbot/1\.0 \(Snap Shots, \+http\://www\.snap\.com\)|sogou develop spider|Sogou Orion spider/3\.0\(\+http\://www\.sogou\.com/docs/help/webmasters\.htm#07\)|sogou spider|Sogou web spider/3\.0\(\+http\://www\.sogou\.com/docs/help/webmasters\.htm#07\)|sohu agent|SSurf15a 11 |TSurf15a 11|Under the Rainbow 2\.2|User-Agent\: Mozilla/4\.0 \(compatible; MSIE 6\.0; Windows NT 5\.1\)|VadixBot|WebVulnCrawl\.unknown/1\.0 libwww-perl/5\.803|Wells Search II|WEP Search 00 failregex = ^ -.*"(GET|POST|HEAD).*HTTP.*"(?:%(badbots)s|%(badbotscustom)s)"$ From 03460d5ed0be3f6b22fd396710ac71f731e1a830 Mon Sep 17 00:00:00 2001 From: Edward Beckett Date: Sun, 6 Sep 2015 01:05:52 -0400 Subject: [PATCH 2/3] Update gen_badbots Added plus char to the regex for escaping user-agent strings. --- files/gen_badbots | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/files/gen_badbots b/files/gen_badbots index 278058f7..52732317 100755 --- a/files/gen_badbots +++ b/files/gen_badbots @@ -42,7 +42,7 @@ done \ | grep -h -B4 'S '\ | sed -e 's/ //g' \ | awk '/^--/{getline; gsub(" ",""); print $0}' \ -| sed -e 's/\([.\:|()]\)/\\\1/g' \ +| sed -e 's/\([.\:|()+]\)/\\\1/g' \ | uniq \ | tr '\n' '|' \ | sed -e 's/|$//g' From 4bd7991573c266f8d674706b27c816f137676c0d Mon Sep 17 00:00:00 2001 From: Edward Beckett Date: Sun, 6 Sep 2015 01:12:19 -0400 Subject: [PATCH 3/3] Added apache-badbots.conf --- ChangeLog | 2 ++ 1 file changed, 2 insertions(+) diff --git a/ChangeLog b/ChangeLog index 4fe225da..f27e7dfc 100644 --- a/ChangeLog +++ b/ChangeLog @@ -44,6 +44,8 @@ ver. 0.9.3 (2015/08/01) - lets-all-stay-friends * filter.d/roundcube-auth.conf - Updated regex to work with 'errors' log (1.0.5 and 1.1.1) - Added regex to work with 'userlogins' log + * filter.d/apache-badbots.conf + - Updated useragent string regex * action.d/sendmail*.conf - use LC_ALL (superseeding LC_TIME) to override locale on systems with customized LC_ALL * performance fix: minimizes connection overhead, close socket only at