宝塔-网站-设置-配置文件 解决百分之90以上的垃圾蜘蛛!

作者:大公子 时间:25-03-01 阅读数:23人阅读


#禁止Scrapy等工具的抓取

if ($http_user_agent ~* (Scrapy|HttpClient|crawl|curb|git|Wtrace)) {

宝塔-网站-设置-配置文件 解决百分之90以上的垃圾蜘蛛!


     return 403;


}


#禁止指定UA及UA为空的访问

if ($http_user_agent ~* "CheckMarkNetwork|Synapse|Nimbostratus-Bot|Dark|scraper|LMAO|Hakai|Gemini|Wappalyzer|masscan|crawler4j|Mappy|Center|eright|aiohttp|MauiBot|Crawler|researchscan|Dispatch|AlphaBot|Census|ips-agent|NetcraftSurveyAgent|ToutiaoSpider|EasyHttp|Iframely|sysscan|fasthttp|muhstik|DeuSu|mstshash|HTTP_Request|ExtLinksBot|package|SafeDNSBot|CPython|SiteExplorer|SSH|MegaIndex|BUbiNG|CCBot|NetTrack|Digincore|aiHitBot|SurdotlyBot|null|SemrushBot|Test|Copied|ltx71|Nmap|DotBot|AdsBot|InetURL|Pcore-HTTP|PocketParser|Wotbox|newspaper|DnyzBot|redback|PiplBot|SMTBot|WinHTTP|Auto Spider 1.0|GrabNet|TurnitinBot|Go-Ahead-Got-It|Download Demon|Go!Zilla|GetWeb!|GetRight|libwww-perl|Cliqzbot|MailChimp|SMTBot|Dataprovider|XoviBot|linkdexbot|SeznamBot|Qwantify|spbot|evc-batch|zgrab|Go-http-client|FeedDemon|Jullo|Feedly|YandexBot|oBot|FlightDeckReports|Linguee Bot|JikeSpider|Indy Library|Alexa Toolbar|AskTbFXTV|AhrefsBot|CrawlDaddy|CoolpadWebkit|Java|UniversalFeedParser|ApacheBench|Microsoft URL Control|Swiftbot|ZmEu|jaunty|Python-urllib|lightDeckReports Bot|YYSpider|DigExt|HttpClient|MJ12bot|EasouSpider|LinkpadBot|Ezooms|^[        DISCUZ_CODE_0        ]quot; ) {

 

     return 403;

 

}


#禁止非GET|HEAD|POST方式的抓取

if ($request_method !~ ^(GET|HEAD|POST)$) {


    return 403;


}



    #屏蔽垃圾蜘蛛

    if ($request_method ~ ^(HEAD)$ ) {

                return 444 "FUCK U";

    }

    if ($http_range ~ "\d(9,)") {

                return 444;

    }

    if ($http_user_agent ~* (Amazonbot|SemrushBot|python|Linespider|crawler|DingTalkBot|simplecrawler|ZoominfoBot|zoombot|Neevabot|coccocbot|Facebot|YandexBot|Adsbot|DotBot|Applebot|DataForSeoBot|MJ12bot|BLEXBot|trendictionbot0|trendictionbot|AhrefsBot|hubspot|opensiteexplorer|leiki|webmeup|TinyTestBot|Symfony|PetalBot|proximic|GrapeshotCrawler|YaoSouBot|serpstatbot|Scrapy|Go-http-client|CCBot|CensysInspect|facebookexternalhit|GPTBot|ClaudeBot|Python-urllib|meta-externalagent|Yisouspider)) { return 444;

     }


    #禁止访问的文件或目录

    location ~ ^/(\.user.ini|\.htaccess|\.git|\.env|\.svn|\.project|LICENSE|README.md)

    {

        return 404;

    }