当前位置: 操作系统/服务器>linux
Nginx限制搜索引擎爬虫频率、禁止屏蔽网络爬虫配置示例
来源: 互联网 发布时间:2014-08-25
本文导语: 代码如下: #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 ~* "xxspider|xxbot") { set $anti_spider $http_user_agent; } 超过设置的限定频率,就会给spider一个5...
代码如下:
#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 ~* "xxspider|xxbot") {
set $anti_spider $http_user_agent;
}
超过设置的限定频率,就会给spider一个503。
上述配置详细解释请自行google下,具体的spider/bot名称请自定义。
附:nginx中禁止屏蔽网络爬虫
代码如下:
server {
listen 80;
server_name www.xxx.com;
#charset koi8-r;
#access_log logs/host.access.log main;
#location / {
# root html;
# index index.html index.htm;
#}
if ($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;
}
location ~ ^/(.*)$ {
proxy_pass http://localhost:8080;
proxy_redirect off;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
client_max_body_size 10m;
client_body_buffer_size 128k;
proxy_connect_timeout 90;
proxy_send_timeout 90;
proxy_read_timeout 90;
proxy_buffer_size 4k;
proxy_buffers 4 32k;
proxy_busy_buffers_size 64k;
proxy_temp_file_write_size 64k;
}
#error_page 404 /404.html;
# redirect server error pages to the static page /50x.html
#
error_page 500 502 503 504 /50x.html;
location = /50x.html {
root html;
}
# proxy the PHP scripts to Apache listening on 127.0.0.1:80
#
#location ~ .php$ {
# proxy_pass http://127.0.0.1;
#}
# pass the PHP scripts to FastCGI server listening on 127.0.0.1:9000
#
#location ~ .php$ {
# root html;
# fastcgi_pass 127.0.0.1:9000;
# fastcgi_index index.php;
# fastcgi_param SCRIPT_FILENAME /scripts$fastcgi_script_name;
# include fastcgi_params;
#}
# deny access to .htaccess files, if Apache's document root
# concurs with nginx's one
#
#location ~ /.ht {
# deny all;
#}
}
可以用 curl 测试一下
代码如下:
curl -I -A "qihoobot" www.xxx.com