cairoapcampos · April 4, 2021 20:39
diff --git a/blockBadAgentsV1 b/blockBadAgentsV1
 # Criar o arquivo useragent.conf com as linhas seguintes.
 # Fazer a inclusão do arquivo no site configurado dentro do bloco server.
 # Ex: include /etc/nginx/useragent.conf

 if ($http_user_agent ~* (360Spider|80legs.com|Abonti|AcoonBot|Acunetix|adbeat_bot|AddThis.com|adidxbot|ADmantX|AhrefsBot|AngloINFO|Antelope|Applebot|BaiduSpider|BeetleBot|billigerbot|binlar|bitlybot|BlackWidow|BLP_bbot|BoardReader|Bolt\ 0|BOT\ for\ JCE|Bot\ mailto\:craftbot@yahoo\.com|casper|CazoodleBot|CCBot|checkprivacy|ChinaClaw|chromeframe|Clerkbot|Cliqzbot|clshttp|CommonCrawler|comodo|CPython|crawler4j|Crawlera|CRAZYWEBCRAWLER|Curious|Curl|Custo|CWS_proxy|Default\ Browser\ 0|diavol|DigExt|Digincore|DIIbot|discobot|DISCo|DoCoMo|DotBot|Download\ Demon|DTS.Agent|EasouSpider|eCatch|ecxi|EirGrabber|Elmer|EmailCollector|EmailSiphon|EmailWolf|Exabot|ExaleadCloudView|ExpertSearchSpider|ExpertSearch|Express\ WebPictures|ExtractorPro|extract|EyeNetIE|Ezooms|F2S|FastSeek|feedfinder|FeedlyBot|FHscan|finbot|Flamingo_SearchEngine|FlappyBot|FlashGet|flicky|Flipboard|g00g1e|Genieo|genieo|GetRight|GetWeb\!|GigablastOpenSource|GozaikBot|Go\!Zilla|Go\-Ahead\-Got\-It|GrabNet|grab|Grafula|GrapeshotCrawler|GTB5|GT\:\:WWW|Guzzle|harvest|heritrix|HMView|HomePageBot|HTTP\:\:Lite|HTTrack|HubSpot|ia_archiver|icarus6|IDBot|id\-search|IlseBot|Image\ Stripper|Image\ Sucker|Indigonet|Indy\ Library|integromedb|InterGET|InternetSeer\.com|Internet\ Ninja|IRLbot|ISC\ Systems\ iRc\ Search\ 2\.1|jakarta|Java|JetCar|JobdiggerSpider|JOC\ Web\ Spider|Jooblebot|kanagawa|KINGSpider|kmccrew|larbin|LeechFTP|libcurl|libwww|libwww-perl|Lingewoud|LinkChecker|linkdexbot|LinksCrawler|LinksManager\.com_bot|linkwalker|LinqiaRSSBot|LivelapBot|ltx71|LubbersBot|lwp\-trivial|Mail.RU_Bot|masscan|Mass\ Downloader|maverick|Maxthon$|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|NetAnts|netEstate|NetSpider|NetZIP|Net\ Vampire|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|SeaMonkey$|search.goo.ne.jp|SearchmetricsBot|search_robot|SemrushBot|Semrush|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-bot|TinEye|Toata\ dragostea\ mea\ pentru\ diavola|Toplistbot|trendictionbot|trovitBot|TurnitinBot|turnit|URI\:\:Fetch|urllib|Vagabondo|Vagabondo|vikspider|VoidEYE|VoilaBot|WBSearchBot|webalta|WebAuto|WebBandit|WebCollage|WebCopier|WebFetch|WebGo\ IS|WebLeacher|WebReaper|WebSauger|Website\ eXtractor|Website\ Quester|WebStripper|WebWhacker|WebZIP|Web\ Image\ Collector|Web\ Sucker|Wells\ Search\ II|WEP\ Search|WeSEE|Wget|Widow|WinInet|woobot|woopingbot|worldwebheritage.org|Wotbox|WPScan|WWWOFFLE|WWW\-Mechanize|Xaldon\ WebSpider|XoviBot|yacybot|YandexBot|Yandex|YisouSpider|zermelo|Zeus|zh-CN|ZmEu|ZumBot|ZyBorg) ) {
    return 403;
 }
	# Criar o arquivo useragent.conf com as linhas seguintes.
	# Fazer a inclusão do arquivo no site configurado dentro do bloco server.
	# Ex: include /etc/nginx/useragent.conf

	if ($http_user_agent ~* (360Spider\|80legs.com\|Abonti\|AcoonBot\|Acunetix\|adbeat_bot\|AddThis.com\|adidxbot\|ADmantX\|AhrefsBot\|AngloINFO\|Antelope\|Applebot\|BaiduSpider\|BeetleBot\|billigerbot\|binlar\|bitlybot\|BlackWidow\|BLP_bbot\|BoardReader\|Bolt\ 0\|BOT\ for\ JCE\|Bot\ mailto\:craftbot@yahoo\.com\|casper\|CazoodleBot\|CCBot\|checkprivacy\|ChinaClaw\|chromeframe\|Clerkbot\|Cliqzbot\|clshttp\|CommonCrawler\|comodo\|CPython\|crawler4j\|Crawlera\|CRAZYWEBCRAWLER\|Curious\|Curl\|Custo\|CWS_proxy\|Default\ Browser\ 0\|diavol\|DigExt\|Digincore\|DIIbot\|discobot\|DISCo\|DoCoMo\|DotBot\|Download\ Demon\|DTS.Agent\|EasouSpider\|eCatch\|ecxi\|EirGrabber\|Elmer\|EmailCollector\|EmailSiphon\|EmailWolf\|Exabot\|ExaleadCloudView\|ExpertSearchSpider\|ExpertSearch\|Express\ WebPictures\|ExtractorPro\|extract\|EyeNetIE\|Ezooms\|F2S\|FastSeek\|feedfinder\|FeedlyBot\|FHscan\|finbot\|Flamingo_SearchEngine\|FlappyBot\|FlashGet\|flicky\|Flipboard\|g00g1e\|Genieo\|genieo\|GetRight\|GetWeb\!\|GigablastOpenSource\|GozaikBot\|Go\!Zilla\|Go\-Ahead\-Got\-It\|GrabNet\|grab\|Grafula\|GrapeshotCrawler\|GTB5\|GT\:\:WWW\|Guzzle\|harvest\|heritrix\|HMView\|HomePageBot\|HTTP\:\:Lite\|HTTrack\|HubSpot\|ia_archiver\|icarus6\|IDBot\|id\-search\|IlseBot\|Image\ Stripper\|Image\ Sucker\|Indigonet\|Indy\ Library\|integromedb\|InterGET\|InternetSeer\.com\|Internet\ Ninja\|IRLbot\|ISC\ Systems\ iRc\ Search\ 2\.1\|jakarta\|Java\|JetCar\|JobdiggerSpider\|JOC\ Web\ Spider\|Jooblebot\|kanagawa\|KINGSpider\|kmccrew\|larbin\|LeechFTP\|libcurl\|libwww\|libwww-perl\|Lingewoud\|LinkChecker\|linkdexbot\|LinksCrawler\|LinksManager\.com_bot\|linkwalker\|LinqiaRSSBot\|LivelapBot\|ltx71\|LubbersBot\|lwp\-trivial\|Mail.RU_Bot\|masscan\|Mass\ Downloader\|maverick\|Maxthon$\|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\|NetAnts\|netEstate\|NetSpider\|NetZIP\|Net\ Vampire\|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\|SeaMonkey$\|search.goo.ne.jp\|SearchmetricsBot\|search_robot\|SemrushBot\|Semrush\|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-bot\|TinEye\|Toata\ dragostea\ mea\ pentru\ diavola\|Toplistbot\|trendictionbot\|trovitBot\|TurnitinBot\|turnit\|URI\:\:Fetch\|urllib\|Vagabondo\|Vagabondo\|vikspider\|VoidEYE\|VoilaBot\|WBSearchBot\|webalta\|WebAuto\|WebBandit\|WebCollage\|WebCopier\|WebFetch\|WebGo\ IS\|WebLeacher\|WebReaper\|WebSauger\|Website\ eXtractor\|Website\ Quester\|WebStripper\|WebWhacker\|WebZIP\|Web\ Image\ Collector\|Web\ Sucker\|Wells\ Search\ II\|WEP\ Search\|WeSEE\|Wget\|Widow\|WinInet\|woobot\|woopingbot\|worldwebheritage.org\|Wotbox\|WPScan\|WWWOFFLE\|WWW\-Mechanize\|Xaldon\ WebSpider\|XoviBot\|yacybot\|YandexBot\|Yandex\|YisouSpider\|zermelo\|Zeus\|zh-CN\|ZmEu\|ZumBot\|ZyBorg) ) {
	return 403;
	}