-
-
Save toptools/e0080981c12b03463239ea2d5c73d8a9 to your computer and use it in GitHub Desktop.
Bad bot blacklist nginx config file (used on Hypernodes for Magento - place in /data/web/nginx/server.blacklist)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Main list | |
if ($http_user_agent ~* (360Spider|80legs.com|Abonti|AcoonBot|Acunetix|adbeat_bot|AddThis.com|adidxbot|ADmantX|AhrefsBot|AngloINFO|Antelope|Applebot|BaiduSpider|BeetleBot|billigerbot|binlar|bitlybot|BlackWidow|BLP_bbot|BoardReader|Bolt\ 0|BOT\ for\ JCE|Bot\ mailto\:craftbot@yahoo\.com|casper|CazoodleBot|CCBot|checkprivacy|ChinaClaw|chromeframe|Clerkbot|Cliqzbot|clshttp|CommonCrawler|comodo|CPython|crawler4j|Crawlera|CRAZYWEBCRAWLER|Curious|Curl|Custo|CWS_proxy|Default\ Browser\ 0|diavol|DigExt|Digincore|DIIbot|DISCo|discobot|DoCoMo|DotBot|Download\ Demon|DTS.Agent|EasouSpider|eCatch|ecxi|EirGrabber|Elmer|EmailCollector|EmailSiphon|EmailWolf|Exabot|ExaleadCloudView|ExpertSearch|ExpertSearchSpider|Express\ WebPictures|extract|ExtractorPro|EyeNetIE|Ezooms|F2S|FastSeek|feedfinder|FeedlyBot|FHscan|finbot|Flamingo_SearchEngine|FlappyBot|FlashGet|flicky|Flipboard|g00g1e|genieo|Genieo|GetRight|GetWeb\!|GigablastOpenSource|Go\-Ahead\-Got\-It|Go\!Zilla|GozaikBot|grab|GrabNet|Grafula|GrapeshotCrawler|GT\:\:WWW|GTB5|Guzzle|harvest|heritrix|HMView|HomePageBot|HTTP\:\:Lite|HTTrack|HubSpot|ia_archiver|icarus6|id\-search|IDBot|IlseBot|Image\ Stripper|Image\ Sucker|Indigonet|Indy\ Library|integromedb|InterGET|Internet\ Ninja|InternetSeer\.com|IRLbot|ISC\ Systems\ iRc\ Search\ 2\.1|jakarta|Java|JetCar|JobdiggerSpider|JOC\ Web\ Spider|Jooblebot|Jorgee|kanagawa|KINGSpider|kmccrew|larbin|LeechFTP|libwww|Lingewoud|LinkChecker|linkdexbot|LinksCrawler|LinksManager\.com_bot|linkwalker|LinqiaRSSBot|LivelapBot|ltx71|LubbersBot|lwp\-trivial|Mail.RU_Bot|Mass\ Downloader|masscan|maverick|Maxthon$|Mediatoolkitbot|megaindex|MegaIndex|MegaIndex|MFC_Tear_Sample|Microsoft\ URL\ Control|microsoft\.url|MIDown\ tool|miner|Missigua\ Locator|Mister\ PiX|mj12bot|Mozilla.*Indy|Mozilla.*NEWT|MSFrontPage|msnbot|Navroad|NearSite|Net\ Vampire|NetAnts|netEstate|NetSpider|NetZIP|NextGenSearchBot|nutch|Octopus|Offline\ Explorer|Offline\ Navigator|OpenindexSpider|OpenWebSpider|OrangeBot|Owlin|PageGrabber|PagesInventory|panopta|panscient\.com|Papa\ Foto|pavuk|pcBrowser|PECL\:\:HTTP|PeoplePal|Photon|PHPCrawl|planetwork|PleaseCrawl|PNAMAIN.EXE|PodcastPartyBot|prijsbest|proximic|psbot|purebot|pycurl|QuerySeekerSpider|R6_CommentReader|R6_FeedFetcher|RealDownload|ReGet|Riddler|Rippers\ 0|rogerbot|RSSingBot|rv\:1.9.1|RyzeCrawler|SafeSearch|SBIder|Scrapy|Scrapy|Screaming|search_robot|search.goo.ne.jp|SearchmetricsBot|Semrush|SemrushBot|SentiBot|SEOkicks|SeznamBot|ShowyouBot|SightupBot|SISTRIX|sitecheck\.internetseer\.com|siteexplorer.info|SiteSnagger|skygrid|Slackbot|Slurp|SmartDownload|Snoopy|Sogou|Sosospider|spaumbot|Steeler|sucker|SuperBot|Superfeedr|SuperHTTP|SurdotlyBot|Surfbot|tAkeOut|Teleport\ Pro|TinEye|TinEye-bot|Toata\ dragostea\ mea\ pentru\ diavola|Toplistbot|trendictionbot|turnit|TurnitinBot|Twenga|TwengaBot|Twitterbot|URI\:\:Fetch|urllib|Vagabondo|Vagabondo|vikspider|VoidEYE|VoilaBot|WBSearchBot|Web\ Image\ Collector|Web\ Sucker|webalta|WebAuto|WebBandit|WebCollage|WebCopier|WebFetch|WebGo\ IS|WebLeacher|WebReaper|WebSauger|Website\ eXtractor|Website\ Quester|WebStripper|WebWhacker|WebZIP|Wells\ Search\ II|WEP\ Search|WeSEE|Wget|Widow|WinInet|woobot|woopingbot|worldwebheritage.org|Wotbox|WPScan|WWW\-Mechanize|WWWOFFLE|Xaldon\ WebSpider|XoviBot|yacybot|Yahoo|Yandex|YandexBot|YisouSpider|zermelo|Zeus|zh-CN|ZmEu|ZumBot|ZyBorg) ) { | |
return 410; | |
} | |
# Another list | |
if ($http_user_agent ~* (Alphabot|Baidu|BlexBot|Cliqzbot|Re-animator|Hubspot|Linguee|ltx71|mail.ru|megaindex.ru|openlinkprofiler|qwant|rogerbot|semrushbot|seokicks|seoscanners|seznam|turnitinbot|vagabondo|yandex|corpora.informatik|dotbot|tracemyfile|linkdexbot|magpie-crawler|masscan|ZEEFscraper|aiHitBot) ) { | |
return 410; | |
} | |
# Client specific list | |
if ($http_user_agent ~* (place-a-bot-identifier-here-minimum-5-chars) ) { | |
return 410; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment