Skip to content

Instantly share code, notes, and snippets.

@luchaninov
Created October 5, 2016 17:34
Show Gist options
  • Save luchaninov/4bdfbcaba1bc0222ad5decb31eedcd3e to your computer and use it in GitHub Desktop.
Save luchaninov/4bdfbcaba1bc0222ad5decb31eedcd3e to your computer and use it in GitHub Desktop.
if ($http_user_agent ~* "Java\/|^1C$|SemrushBot|Sitemap|intelium_bot|sqlmap|SiteTruth|openwebspider|Microsoft\sURL|URLChecker|Abonti|integromedb|CommentReader|findlinks|icjobs|PagesInventory|Wotbox|spray-can|spbot|Add\sCatalog|LinksCrawler|ePochta|LSSRocketCrawler|Sogou|SEOENGBot|searchmetrics|BlogPulseLive|gooblog|start.exe|YesupBot|Snoopy|BDP\sReferral|SmartCJ|GSLFbot|Jigsaw|AcoonBot|Influencebot|Lipperhey|coccoc|CCBot|fastbot|cctld.ru|Plesk|Sparrow|swebot|Gigabot|JoeDog|EC2LinkFinder|Exabot|GoScraper|SeznamBot|discobot|cmscrawler|Asynchronous\sWinHTTP|Purebot|netEstate|Referrer\sKarma|^Mozilla\/4\.0$|sistrix|AhrefsBot|Lunasys|SearchBot|Aboundex|RTS\/|yacybot|MLBot|nerdbynature|Parking\sDomains|OffByOne|Sosospider|WebIndex|ZumBot|Ezooms|SiteIntel|Zend_Http_Client|rganalytics|Synapse|pirst|FreeWebMonitoring|MJ12bot|ABBYY|Morfeus|dragostea|multi_get|^oBot$|C-T\sbot|python|nikto|wkito|pikto|scan|acunetix|HTTrack|clshttp|harvest|loadimpact|Mozilla\s\/\s4\.0|nutch|Gootkit|DomainCrawler|curl|ZmEu|Solomono|DomainWatcher|wget|Indy|URLDBCleaner|urllib|2ip.ru|Ruby|Anonymouse|scritch|xpymep|libwww|HttpClient|rgspider|WordPress|Xenu|DLE_Spider|Funnelback|^Mozilla/5.0$|^spider$|naver\.com|Mozilla\/4\.0\s\(compatible\;\)|RankFlex|VoilaBot|YoudaoBot")
{
return 444;
}
if ($http_user_agent ~* "statdom|psbot|ip-web-crawler|Screenshot|UserAgent:|^Mozilla$|Admin\ssearch\ssystem|linguee|NING|SiteExplorer|proximic|EMail\sExractor|MetaURI|UnwindFetchor|Crowsnest|Butterfly|ShowyouBot|JS-Kit|PaperLiBot|BLEXBot|exb.de|YisouSpider|Lunalys|PHP|radian6|MonTools|siclab|ColdFusion|200PleaseBot|GeliyooBot|JikeSpider|ltbot|Whois365|aboutthedomain|Skywalker|BLEXBot|lufsbot|NETCRAFT|Qualidator|redirectchecker|Web-Monitoring|openstat.ru|MAUI\sWAP\sBrowser|itrack\.ru|AraBot|BOT\/\d\.\d\s\(BOT\sfor\sJCE\)|Miami\sStyle|LinkpadBot|updown_tester|EasouSpider|BeetleBot|Ryobot|Seon")
{
return 444;
}
if ($http_user_agent ~* "Mechanize|rootlink|\\x22M|TppRFbot|nutch|httpunit|SEOlyzer|WebCopier|Phantom|SimplePie|ContextAd|wesee|ICC-Crawler|InternetSeer|A6-Indexer|mbot|panscient|niki-bot|WebBot|TurnitinBot|trendictionbot|Vedma|UnisterBot|aiHitBot|SurveyBot|CrawlDaddy|cognitiveseo|filterdb|ScreenerBot|hrbot|AntBot|meanpathbot|Nekstbot|Cliqzbot|SBL-BOT|rogerbot|KomodiaBot|CompSpyBot|WordChampBot|chlooe|ZemlyaCrawl|socialbm_bot|Prlog|LoadTimeBot|BDCbot|emefgebot|Rootlebot|MJ12bot|scrapy|adnorm|IstellaBot|NerdyBot|ShoppnetUptimeBot|heritrix")
{
return 444;
}
if ($http_user_agent ~* "^111$|^CBot|SputnikBot|fr-crawler|Riddler|SEOstats|isitup|Pingfinity|\[EX\]|wscheck|startmebot|Bazinga|wwwtype|IstellaBot|URLAppendBot|TurnitinBot|trendictionbot|seokicks|WebBot-FindUrl|MixBot|niki-bot|Vedma|XoviBot|Insitesbot|PiplBot|UnisterBot|seplinkbot|NerdyBot|aiHitBot|wesee.com|getdownload|u12Bot|Facebot|downloaflare|overx50|inload|DownloadBot|Livelapbot|ScreenerBot|Diffbot|gimme60bot|comodorobot|meanpathbot|semalt")
{
return 444;
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment