Apache : une liste de bots à bloquer
18 avril 2015
Par le plus grand des hasards, je suis tombé sur la blacklist de bots du site Hackrepair.com, réalisé à partir du User Agent. Vous pouvez l’ajouter à votre fichier .htaccess situé à la racine de votre site WordPress, si vous êtes en hébergement mutualisé. Je vous recommande de la mettre dans un des fichiers de configuration de votre serveur Apache si vous êtes en hébergement dédié. Sous CentOS, j’ai créé pour ma part le fichier /etc/httpd/conf.d/05-hackrepair.conf dans lequel j’ai ajouté cette liste dont l’objet est de provoquer une erreur 403 pour tous ces agents :
RewriteCond %{HTTP_USER_AGENT} ^$ [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^[Ww]eb[Bb]andit [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Acunetix [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^binlar [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^BlackWidow [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Bolt\ 0 [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Bot\ mailto:craftbot\@yahoo\.com [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^BOT\ for\ JCE [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^casper [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^checkprivacy [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^ChinaClaw [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^clshttp [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^cmsworldmap [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^comodo [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Custo [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Default\ Browser\ 0 [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^diavol [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^DIIbot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^DISCo [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^dotbot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Download\ Demon [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^eCatch [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^EirGrabber [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^EmailCollector [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^EmailSiphon [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^EmailWolf [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Express\ WebPictures [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^extract [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^ExtractorPro [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^EyeNetIE [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^feedfinder [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^FHscan [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^FlashGet [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^flicky [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^GetRight [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^GetWeb! [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Go-Ahead-Got-It [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^g00g1e [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Go!Zilla [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^grab [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^GrabNet [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Grafula [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^harvest [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^HMView [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^ia_archiver [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Image\ Stripper [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Image\ Sucker [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^InterGET [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Internet\ Ninja [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^InternetSeer\.com [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^jakarta [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Java [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^JetCar [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^JOC\ Web\ Spider [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^kanagawa [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^kmccrew [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^larbin [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^LeechFTP [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^libwww [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Mass\ Downloader [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Maxthon$ [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^microsoft\.url [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^MIDown\ tool [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^miner [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Mister\ PiX [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Mozilla\.*Indy [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Mozilla\.*NEWT [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^MSFrontPage [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Navroad [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^NearSite [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Net\ Vampire [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^NetAnts [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^NetSpider [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^NetZIP [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^nutch [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Octopus [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Offline\ Explorer [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Offline\ Navigator [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^PageGrabber [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Papa\ Foto [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^pavuk [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^pcBrowser [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^PeoplePal [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^planetwork [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^psbot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^purebot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^pycurl [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^RealDownload [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^ReGet [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Rippers\ 0 [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^SeaMonkey$ [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^sitecheck\.internetseer\.com [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^SiteSnagger [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^skygrid [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^SmartDownload [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^sucker [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^SuperBot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^SuperHTTP [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Surfbot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^tAkeOut [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Teleport\ Pro [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Toata\ dragostea\ mea\ pentru\ diavola [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^turnit [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^vikspider [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^VoidEYE [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Web\ Image\ Collector [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Web\ Sucker [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^WebAuto [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^WebCopier [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^WebFetch [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^WebGo\ IS [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^WebLeacher [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^WebReaper [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^WebSauger [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^WPScan [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Website\ eXtractor [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Website\ Quester [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^WebStripper [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^WebWhacker [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^WebZIP [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Wget [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Widow [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^WWW-Mechanize [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^WWWOFFLE [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Xaldon\ WebSpider [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Yandex [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^Zeus [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ^zmeu [NC,OR]
RewriteCond %{HTTP_USER_AGENT} AhrefsBot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} CazoodleBot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} discobot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ecxi [NC,OR]
RewriteCond %{HTTP_USER_AGENT} GT::WWW [NC,OR]
RewriteCond %{HTTP_USER_AGENT} heritrix [NC,OR]
RewriteCond %{HTTP_USER_AGENT} HTTP::Lite [NC,OR]
RewriteCond %{HTTP_USER_AGENT} HTTrack [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ia_archiver [NC,OR]
RewriteCond %{HTTP_USER_AGENT} id-search [NC,OR]
RewriteCond %{HTTP_USER_AGENT} id-search\.org [NC,OR]
RewriteCond %{HTTP_USER_AGENT} IDBot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Indy\ Library [NC,OR]
RewriteCond %{HTTP_USER_AGENT} IRLbot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ISC\ Systems\ iRc\ Search\ 2\.1 [NC,OR]
RewriteCond %{HTTP_USER_AGENT} LinksManager.com_bot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} linkwalker [NC,OR]
RewriteCond %{HTTP_USER_AGENT} lwp-trivial [NC,OR]
RewriteCond %{HTTP_USER_AGENT} MFC_Tear_Sample [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Microsoft\ URL\ Control [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Missigua\ Locator [NC,OR]
RewriteCond %{HTTP_USER_AGENT} MJ12bot [NC,OR]
RewriteCond %{HTTP_USER_AGENT} panscient.com [NC,OR]
RewriteCond %{HTTP_USER_AGENT} PECL::HTTP [NC,OR]
RewriteCond %{HTTP_USER_AGENT} PHPCrawl [NC,OR]
RewriteCond %{HTTP_USER_AGENT} PleaseCrawl [NC,OR]
RewriteCond %{HTTP_USER_AGENT} SBIder [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Snoopy [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Steeler [NC,OR]
RewriteCond %{HTTP_USER_AGENT} URI::Fetch [NC,OR]
RewriteCond %{HTTP_USER_AGENT} urllib [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Web\ Sucker [NC,OR]
RewriteCond %{HTTP_USER_AGENT} webalta [NC,OR]
RewriteCond %{HTTP_USER_AGENT} WebCollage [NC,OR]
RewriteCond %{HTTP_USER_AGENT} Wells\ Search\ II [NC,OR]
RewriteCond %{HTTP_USER_AGENT} WEP\ Search [NC,OR]
RewriteCond %{HTTP_USER_AGENT} zermelo [NC,OR]
RewriteCond %{HTTP_USER_AGENT} ZyBorg [NC]
# Abuse HTTP Referrer Blocking end
RewriteRule ^.* - [F,L]