Nginx gfw.conf

允许指定浏览器访问
if ($http_user_agent !~ "^((.UCWEB.)|(.WAP.)|(.Mini.)|(.iPhone.)|(.Android.)|(.Chrome.)|(.Safari.)|(.MSIE.)|(.Firefox.)|(.mobile.)|(java.)|(.BlackBerry.*))$" ){
             return 403;
 }

禁止各类蜘蛛
if ($http_user_agent ~* "qihoobot|Baiduspider|Googlebot|Googlebot-Mobile|Googlebot-Image|Mediapartners-Google|Adsbot-Google|Feedfetcher-Google|Yahoo! Slurp|Yahoo! Slurp China|YoudaoBot|Sosospider|Sogou spider|Sogou web spider|MSNBot|ia_archiver|Tomato Bot") { 
             return 403; 
 }

禁止Scrapy等工具的抓取
if ($http_user_agent ~* (Scrapy|Curl|HttpClient)) {
             return 403;
 }

禁止指定UA及UA为空的访问
if ($http_user_agent ~ "WinHttp|WebZIP|FetchURL|node-superagent|java/|FeedDemon|Jullo|JikeSpider|Indy Library|Alexa Toolbar|AskTbFXTV|AhrefsBot|CrawlDaddy|Java|Feedly|Apache-HttpAsyncClient|UniversalFeedParser|ApacheBench|Microsoft URL Control|Swiftbot|ZmEu|oBot|jaunty|Python-urllib|lightDeckReports Bot|YYSpider|DigExt|HttpClient|MJ12bot|heritrix|EasouSpider|Ezooms|BOT/0.1|YandexBot|FlightDeckReports|Linguee Bot|^$" ) {
             return 403;             
 }

禁止非GET|HEAD|POST方式的抓取
if ($request_method !~ ^(GET|HEAD|POST)$) {
             return 403;
 }

发表评论