My Anti-Robot config for Apache

Started by Gregg, January 16, 2009, 05:42:16 PM

Previous topic - Next topic

Gregg

Tell the bad robots (and download managers) to go blow

[code]RewriteEngine  on
RewriteLogLevel 0

# [REMOTE_ADDR]
RewriteCond %{REMOTE_ADDR} "^63\.148\.99\.2(2[4-9]|[3-4][0-9]|5[0-5])$"  [OR]
RewriteCond %{REMOTE_ADDR} "^12\.148\.196\.(12[8-9]|1[3-9][0-9]|2[0-4][0-9]|25[0-5])$" [OR]
RewriteCond %{REMOTE_ADDR} "^12\.148\.209\.(19[2-9]|2[0-4][0-9]|25[0-5])$" [OR]
RewriteCond %{REMOTE_ADDR} "^64\.140\.49\.6([6-9])$" [OR]
RewriteCond %{REMOTE_ADDR} "^200\.63\.42\.([0-9]|[0-9][0-9]|[0-9][0-9][0-9])$" [OR]

# [REMOTE_HOST]

# [HTTP_REFERER]
RewriteCond %{HTTP_REFERER} iaea\.org [OR]
RewriteCond %{HTTP_REFERER}   phentermine-gl-pills\.com [NC,OR]
RewriteCond %{HTTP_REFERER} nogangs\.com [NC,OR]

# [FakeSearchEngine]
RewriteCond %{HTTP_USER_AGENT} ^Googlebot [NC,OR]

# [Multi-Useragent]
RewriteCond %{HTTP_USER_AGENT}  black.widow [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^e?mail.?(collector|magnet|reaper|siphon|sweeper|harvest|collect|wolf) [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^IE\ \d\.\d\ Compatible.*Browser$" [OR]
RewriteCond %{HTTP_USER_AGENT} ^net.?(ants|carta|mechanic|spider|vampire|zip) [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^site.?(searcher|snagger|valet) [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^web.?(auto|bandit|catcher|collage|collector|copier|copy|core|devil|downloader|fetch??|image|inator|hook|layers|linker|log|mole|miner|mirror|quest|reaper|sauger|site|snake|snarf|stolperer|stripper|sucker|vac|walk??|watch|whacker|weasel|zinger|zip) [NC,OR] # ODs

# [HTTP_USER_AGENT]
# ::ELNSB50  EmailHarvesting & GuestbookSpamming
RewriteCond %{HTTP_USER_AGENT} ^::ELNSB50 [NC,OR]

RewriteCond %{HTTP_USER_AGENT} ^Acrobat  [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^anarchie [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ASPSimply [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Atomz [OR]
RewriteCond %{HTTP_USER_AGENT} ^cherry.?picker [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "compatible ; MSIE 6.0?" [OR]
RewriteCond %{HTTP_USER_AGENT} crescent [NC,OR] # OD
RewriteCond %{HTTP_USER_AGENT} "^DA \d\.\d+" [OR] # OD
RewriteCond %{HTTP_USER_AGENT} "^DTS Agent" [OR] # OD
RewriteCond %{HTTP_USER_AGENT} ^Download [OR] # OD
RewriteCond %{HTTP_USER_AGENT} ^EasyDL/\d\.\d+ [OR] # OD
RewriteCond %{HTTP_USER_AGENT} "^ABCdatos BotLink" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Acme.Spider [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Ahoy [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Alkaline [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^ananzi [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Anthill [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Arachnophilia [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Arale [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Araneo [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^AraybOt [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^ArchitextSpider [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Aretha [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^ARIADNE [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^arks [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^ASpider [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^ATN Worldwide" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^attach [OR]
RewriteCond %{HTTP_USER_AGENT} ^AURESYS [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^BackRub [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^BackWeb [OR]
RewriteCond %{HTTP_USER_AGENT} ^Bandit [OR]
RewriteCond %{HTTP_USER_AGENT} ^BatchFTP [OR]
RewriteCond %{HTTP_USER_AGENT} "^Bay Spider" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^BBot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^Big Brother" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Bjaaland [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^BlackWidow [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Bloodhound [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Borg-Bot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^Bot\ mailto:[email protected]" [OR]
RewriteCond %{HTTP_USER_AGENT} ^BoxSeaBot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^bright.net [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^BSpider [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Buddy [OR]
RewriteCond %{HTTP_USER_AGENT} ^CACTVS [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Calif [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Cassandra [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Checkbot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^ChinaClaw [OR]
RewriteCond %{HTTP_USER_AGENT} ^ChristCrawler.com [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^churl [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^cIeNcIaFiCcIoN.nEt [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^CMC/0.01 [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Collective [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Collector [OR]
RewriteCond %{HTTP_USER_AGENT} "^Combine System" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^ComputingSite Robi/1.0" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Conceptbot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^ConfuzzledBot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^CoolBot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Copier [OR]
RewriteCond %{HTTP_USER_AGENT} ^crawlpaper  [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Cusco [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^CyberSpyder [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^CydralSpider [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^DA [OR]
RewriteCond %{HTTP_USER_AGENT} "^Desert Realm " [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^DeWeb(c) [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^Die Blinde Kuh" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^DienstSpider [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Digger [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^Digimarc MarcSpider" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^Digimarc Marcspider/CGI" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^Digital Integrity Robot" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^Direct Hit Grabber" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^DISCo\ Pump" [OR]
RewriteCond %{HTTP_USER_AGENT} ^DNAbot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^DownLoad Express" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^Download\ Demon" [OR]
RewriteCond %{HTTP_USER_AGENT} "^Download\ Wonder" [OR]
RewriteCond %{HTTP_USER_AGENT} ^Downloader [OR]
RewriteCond %{HTTP_USER_AGENT} ^DragonBot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Drip [OR]
RewriteCond %{HTTP_USER_AGENT} ^DWCP [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^EbiNess [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^eCatch [OR]
RewriteCond %{HTTP_USER_AGENT} ^e-collector [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^EirGrabber [OR]
RewriteCond %{HTTP_USER_AGENT} "^EIT Link Verifier Robot" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^ELFINBOT [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^Emacs-w3 Search Engine" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^esculapio [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Esther [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^Evliya Celebi" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^Express\ WebPictures" [OR]
RewriteCond %{HTTP_USER_AGENT} ^ExtractorPro [OR]
RewriteCond %{HTTP_USER_AGENT} ^EyeNetIE [OR]
RewriteCond %{HTTP_USER_AGENT} ^FastCrawler [NC,OR]
RewriteCond %{HTTP_USER_AGENT} "^Felix IDE" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^FetchRover [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^fido [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^FileHound [OR]
RewriteCond %{HTTP_USER_AGENT} "^Fish search" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^FlashGet [OR]
RewriteCond %{HTTP_USER_AGENT} "^Fluid Dynamics Search Engine" [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Fouineur [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Freecrawl [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^FunnelWeb [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^gammaSpider [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^gazz [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^GCreep [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^GetBot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^GetRight [OR]
RewriteCond %{HTTP_USER_AGENT} ^GetSmart [OR]
RewriteCond %{HTTP_USER_AGENT} ^GetterroboPlus [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^GetURL [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Go!Zilla [OR]
RewriteCond %{HTTP_USER_AGENT} ^Go-Ahead-Got-It [OR]
RewriteCond %{HTTP_USER_AGENT} ^Golem [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^gotit [OR]
RewriteCond %{HTTP_USER_AGENT} ^Grabber [OR]
RewriteCond %{HTTP_USER_AGENT} ^GrabNet [OR]
RewriteCond %{HTTP_USER_AGENT} ^Grafula [OR]
RewriteCond %{HTTP_USER_AGENT} ^Grapnel/0.01 [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Griffon [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Gromit [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Gulper [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^H

mario

#1
I addition to that I have a PHP script checking for most robots

which can be found here https://forum.apachehaus.com/index.php?topic=11.0