Nginx反爬虫： 禁止某些User Agent抓取网站

1、在/usr/local/nginx/conf目录下（因Nginx的安装区别，可能站点配置文件的路径有所不同）新建文件deny_agent.config配置文件：

#forbidden Scrapy
if ($http_user_agent ~* (Scrapy|Curl|HttpClient))
{
    return 403;
}

#forbidden UA
if ($http_user_agent ~ "Bytespider|FeedDemon|JikeSpider|Indy Library|Alexa Toolbar|AskTbFXTV|AhrefsBot|CrawlDaddy|CoolpadWebkit|Java|Feedly|UniversalFeedParser|ApacheBench|Microsoft URL Control|Swiftbot|ZmEu|oBot|jaunty|Python-urllib|lightDeckReports Bot|YYSpider|DigExt|YisouSpider|HttpClient|MJ12bot|heritrix|EasouSpider|Ezooms|^$" )
{
    return 403;
}

#forbidden not GET|HEAD|POST method access
if ($request_method !~ ^(GET|HEAD|POST)$)
{
    return 403;
}

2、在对应站点配置文件中包含deny_agent.config配置文件（注意是在server里面）：

3、重启Nginx，建议通过nginx -s reload平滑重启的方式。重启之前请先使用nginx -t命令检测配置文件是否正确。

4、通过curl命令模拟访问，看配置是否生效（返回403 Forbidden，则表示配置OK）：

附录：UA收集

FeedDemon             内容采集
BOT/0.1 (BOT for JCE) sql注入
CrawlDaddy            sql注入
Java                  内容采集
Jullo                 内容采集
Feedly                内容采集
UniversalFeedParser   内容采集
ApacheBench           cc攻击器
Swiftbot              无用爬虫
YandexBot             无用爬虫
AhrefsBot             无用爬虫
YisouSpider           无用爬虫（已被UC神马搜索收购，此蜘蛛可以放开！）
jikeSpider            无用爬虫
MJ12bot               无用爬虫
ZmEu phpmyadmin       漏洞扫描
WinHttp               采集cc攻击
EasouSpider           无用爬虫
HttpClient            tcp攻击
Microsoft URL Control 扫描
YYSpider              无用爬虫
jaunty                wordpress爆破扫描器
oBot                  无用爬虫
Python-urllib         内容采集
Indy Library          扫描
FlightDeckReports Bot 无用爬虫
Linguee Bot           无用爬虫

#添加如下内容即可防止爬虫

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;             
}

限制搜索引擎爬虫频率

#全局配置
limit_req_zone $anti_spider zone=anti_spider:10m rate=15r/m;

#某个server中
 limit_req zone=anti_spider burst=30 nodelay;
 if($http_user_agent ~ "WinHttp|WebZIP|FetchURL|node-superagent|java/|FeedDemon|Jullo|JikeSpider|Indy Library|Alexa Toolbar|AskTbFXTV|AhrefsBot|CrawlDaddy|Java|Feedly|Apache-HttpAsyncClient|UniversalFeedParser|ApacheBench|Microsoft URL Control|Swiftbot|ZmEu|oBot|jaunty|Python-urllib|lightDeckReports Bot|YYSpider|DigExt|HttpClient|MJ12bot|heritrix|EasouSpider|Ezooms|BOT/0.1|YandexBot|FlightDeckReports|Linguee Bot|^$" ) {

 set $anti_spider $http_user_agent;
}