ThinkPHP6记录百度等蜘蛛的爬取日志
thinkphp6记录百度蜘蛛日志:
在控制器的父类如IndexBase中写入以下代码,所有前端控制器继承这个控制器
public function initialize() { parent::initialize(); // TODO: Change the autogenerated stub if ($this->Config['web_status'] == 0) { // 判断是否关闭网站 die('网站已经关闭'); } $this->baiduLog(); } protected function baiduLog() { $useragent = strtolower($_SERVER['HTTP_USER_AGENT']); $url = $this->request->controller() . "/" . $this->request->action(); $param = input("param.","","htmlspecialchars"); $url = (string) url($url,$param); $ip = get_real_ip(); $title = ""; if (strpos($useragent, 'googlebot') !== false){ $title = 'Google'; } elseif (strpos($useragent, 'baiduspider') !== false){ $title = 'Baidu'; } elseif (strpos($useragent, 'msnbot') !== false){ $title = 'Bing'; } elseif (strpos($useragent, 'slurp') !== false){ $title = 'Yahoo'; } elseif (strpos($useragent, 'sosospider') !== false){ $title = 'Soso'; } elseif (strpos($useragent, 'sogou spider') !== false){ $title = 'Sogou'; } elseif (strpos($useragent, 'yodaobot') !== false){ $title = 'Yodao'; } elseif (strpos($useragent, 'googlebot') !== false){ $title = 'Google'; } elseif (strpos($useragent, 'baiduspider') !== false){ $title = 'Baidu'; } else { // $title = $useragent; // 不怕数据大的话可以取消注释,记录所有访问日志 } if (!empty($title)) { BaiduLog::create(["title"=>$title,"href"=>$url,"ip"=>$ip]); } }
以上就是thinkphp6记录百度蜘蛛爬行日志的方法
get_real_ip():是获取客户真实IP的自定义函数。