nginx 代理防止403
proxy_store off;
proxy_redirect off
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header Referer $remote_addr;
proxy_set_header User-Agent "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36";
proxy_connect_timeout 600;
proxy_redirect off
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header Referer $remote_addr;
proxy_set_header User-Agent "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36";
proxy_connect_timeout 600;
主要是加上这个 User-Agent "", 如果没有这个，很大可能性判定为爬虫什么的，就被ban掉了。
# 防止网络爬虫
#forbid spider
if ($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;
}阅读量: 63
发布于:
修改于:
发布于:
修改于: