在conf下 vi 一个文件agent_deny.conf
添加如下内容
#禁止Scrapy|curl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 ~ "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|^$" )
{
return 403;
}
#禁止非GET|HEAD|POST方式的抓取
if ($request_method !~ ^(GET|HEAD|POST)$)
{
return 403;
}
最后在 server 下的location里面添加 include agent_deny.conf;