浅谈PHP封装curl采集数据函数

采集数据，也就是爬虫，对于PHP同样能够做到，通过封装curl采集数据函数，从而实现对数据的采集利用

<?php

public function g_url_contents($url, $reurl = '', $ip = '')
{
      $ch         = curl_init();
      $timeout    = 30;
      //设置你需要抓取的URL
      curl_setopt($ch, CURLOPT_URL, $url);
      //伪造来源ip
      if ($ip) {
          $header = array(
                'CLIENT-IP:' . $ip,
                'X-FORWARDED-FOR:' . $ip,
          );
          curl_setopt($ch, CURLOPT_HTTPHEADER, $header);
     }
     //随机生成一个user_agent 
     $binfo = array('Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; 
     Trident/4.0; .NET CLR 2.0.50727; InfoPath.2; AskTbPTV/5.17.0.25589; 
     Alexa Toolbar)','Mozilla/5.0 (Windows NT 5.1; rv:22.0) Gecko/20100101 
     Firefox/22.0','Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; 
     Trident/4.0; .NET4.0C; Alexa Toolbar)','Mozilla/4.0(compatible; 
     MSIE 6.0; Windows NT 5.1; SV1)',$_SERVER['HTTP_USER_AGENT']);
     $user_agent = $binfo[mt_rand(0,3)];
     
     //下面这个是单个的，有可能被监测到
     //$user_agent = $_SERVER['HTTP_USER_AGENT']
        
     //执行curl_exec是把输出做为返回值,不会输出到浏览器
     curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
     //在发起连接前等待的时间，如果设置为0，则不等待
     curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout);
     //在HTTP请求中包含一个”user-agent”头的字符串
     curl_setopt($ch, CURLOPT_USERAGENT, $user_agent);
     //设置这个选项为一个非零值(像 “Location: “)的头，服务器会把它当做
     //HTTP头的一部分发送(注意这是递归的，PHP将发送形如 “Location: “的头)
     curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
     
     //伪造来源referer
     if ($reurl) {
         curl_setopt($ch, CURLOPT_REFERER, $reurl);
     }
     @$c = curl_exec($ch);//执行请求
     curl_close($ch);//关闭url请求
     return $c;
}

---

以上完成的操作如有不正确的地方还望诸位多多指教