nginx规则整理

很多情况下会用到的Nginx规则，找时麻烦的一批，记录一下，方便你我他，持续补充！

#请求这些敏感词时跳转下载10g文件
if ($request_uri ~* "(\.gz)|(")|(\.tar)|(admin)|(\.zip)|(\.sql)|(\.asp)|(\.rar)|(function)|($_GET)|(eval)|(\?php)|(config)|(\')|(\.bak)") {
            return 301 http://lg-dene.fdcservers.net/10GBtest.zip;
        }


#禁止下载以 XXX 后缀的文件
location ~ \.(zip|rar|sql|bak|gz|7z)$
{
   return 444;
  }


#访问链接里含有 test 直接跳转到公安网
if ($request_uri ~* test=) {
  return 301 https://www.mps.gov.cn;
}


#防止SB爬虫
if ($http_user_agent ~* (SemrushBot|python|MJ12bot|AhrefsBot|AhrefsBot|hubspot|opensiteexplorer|leiki|webmeup)) {
      return 444;
    }


#屏蔽非常见蜘蛛爬虫配置
if ($http_user_agent ~* (SemrushBot|python|MJ12bot|AhrefsBot|AhrefsBot|hubspot|opensiteexplorer|leiki|webmeup)) {
     return 444;
  }


#禁止某个目录执行脚本
#uploads|templets|data 这些目录禁止执行PHP
location ~* ^/(uploads|templets|data)/.*.(php|php5)$ {
    return 444;
  }

#防止SB爬虫
if ($http_user_agent ~* (SemrushBot|python|MJ12bot|AhrefsBot|AhrefsBot|hubspot|opensiteexplorer|leiki|webmeup)) {
      return 444;
    }

#禁止爬虫
        if ($http_user_agent ~* "qihoobot|Censys|Baiduspider|Googlebot|Googlebot-Mobile|Googlebot-Image|Mediapartners-Google|Adsbot-Google|Feedfetcher-Google|Yahoo! Slurp|Yahoo! Slurp China|YoudaoBot|Sosospider|Sogou spider|Sogou web spider|MSNBot|ia_archiver|Tomato Bot|FeedDemon|JikeSpider|Indy Library|Alexa Toolbar|AskTbFXTV|AhrefsBot|CrawlDaddy|CoolpadWebkit|Java|Feedly|UniversalFeedParser|ApacheBench|Microsoft URL Control|Swiftbot|ZmEu|oBot|jaunty|Python-urllib|lightDeckReports Bot|YYSpider|DigExt|YisouSpider|Scrapy|HttpClient|MJ12bot|heritrix|EasouSpider|LinkpadBot|Ezooms|^$") {  
        return 404; #禁止爬虫返回404
        }

#非指定域名访问403
        if ($host != 'XX.XX.XX'){
    return 403; #非指定域名访问返回403
        }

#仅允许特定IP访问并加上帐号密码验证
 root /opt/hostloc/www;
 allow  xx.xx.xx.xx; 
 allow  2xx.xx.x.xx; 
 deny  all;
 auth_basic “test”;
 auth_basic_user_file htpasswd;

#禁止访问多个目录
 location ~ ^/(cron|templates)/
 {
 deny all;
 break;
 }

#隐藏nginx版本号 http块添加
http {
...
server_tokens off;
...
}

#禁止非浏览器访问
if ($http_user_agent ~ ^$) {
        return 412;
}