curl采集封装

1.

<?php 
class cURL { 
    var $headers; 
    var $user_agent; 
    var $compression; 
    var $cookie_file; 
    var $proxy; 
    protected $refer;
    function cURL($cookies=TRUE,$cookie='cookies.txt',$compression='gzip',$proxy='') { 
        $this->headers[] = 'Accept: image/gif, image/x-bitmap, image/jpeg, image/pjpeg'; 
        $this->headers[] = 'Connection: Keep-Alive'; 
        $this->headers[] = 'CLIENT-IP:208.165.188.173'; 
        $this->headers[] = 'X-FORWARDED-FOR:208.165.188.172'; 

        $this->user_agent = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.62 Safari/537.36';
        $this->compression=$compression; 
        //$this->proxy=$proxy; 
        $this->cookies=$cookies; 
        if ($this->cookies == TRUE) $this->cookie($cookie); 
    } 
    function setHeader($headers){
        $this->headers[] = headers;
    }
    function setRefer($refer){
        $this->refer = $refer;
    }
    function setProxy($proxy){
        $this->proxy = $proxy;
    }
    function cookie($cookie_file) { 
        if (file_exists($cookie_file)) { 
            $this->cookie_file=$cookie_file; 
        } else { 
            fopen($cookie_file,'w') or $this->error('The cookie file could not be opened. Make sure this directory has the correct permissions'); 
            $this->cookie_file=$cookie_file; 
            fclose($this->cookie_file); 
        } 
    } 
    function get($url) { 
        $process = curl_init(trim($url)); 
        curl_setopt($process, CURLOPT_HTTPHEADER, $this->headers); 
        curl_setopt($process, CURLOPT_HEADER, 0); 
        curl_setopt($process, CURLOPT_USERAGENT, $this->user_agent); 
        curl_setopt($process, CURLOPT_REFERER, $this->refer); //来源
        
        curl_setopt($process,CURLOPT_ENCODING , $this->compression); 
        curl_setopt($process, CURLOPT_TIMEOUT, 30); 
        
        curl_setopt($process, CURLOPT_RETURNTRANSFER, 1); 
        curl_setopt($process, CURLOPT_FOLLOWLOCATION, 1); 
    //    curl_setopt($process, CURLOPT_CONNECTTIMEOUT, 60); 
        if ($this->cookies == TRUE) 
        {
            curl_setopt($process, CURLOPT_COOKIEFILE, $this->cookie_file);
            curl_setopt($process, CURLOPT_COOKIEJAR, $this->cookie_file);
        }
        if ($this->proxy) 
        {
            curl_setopt($process, CURLOPT_PROXY, $this->proxy); //代理IP
            curl_setopt($process, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS5); 
        }
        if(mb_substr($url, 0,5) === 'https')
        {
            //https  取消证书验证
               curl_setopt($process, CURLOPT_SSL_VERIFYPEER, false); 
            curl_setopt($process, CURLOPT_SSL_VERIFYHOST, false); 
        }
       
        $return = curl_exec($process); 
        if($return === false)
        {
            echo 'Curl error: ' . curl_error($process);
        }
        
        curl_close($process); 
        return $return; 
    } 
    function post($url,$data) { 
    
        $process = curl_init($url); 
        $data = http_build_query($data);
        curl_setopt($process, CURLOPT_HTTPHEADER, $this->headers); 
        curl_setopt($process, CURLOPT_HEADER, 0); 
        curl_setopt($process, CURLOPT_USERAGENT, $this->user_agent);
        curl_setopt($process, CURLOPT_REFERER, $this->refer); //来源
        curl_setopt($process, CURLOPT_ENCODING , $this->compression);
        curl_setopt($process, CURLOPT_TIMEOUT, 30); 
        curl_setopt($process, CURLOPT_POSTFIELDS, $data); 
        curl_setopt($process, CURLOPT_RETURNTRANSFER, 1); 
        curl_setopt($process, CURLOPT_FOLLOWLOCATION, 1); 
        curl_setopt($process, CURLOPT_POST, 1); 
        if ($this->cookies == TRUE) 
        {
            curl_setopt($process, CURLOPT_COOKIEFILE, $this->cookie_file);
            curl_setopt($process, CURLOPT_COOKIEJAR, $this->cookie_file);
        }
        if ($this->proxy) 
        {
            curl_setopt($process, CURLOPT_PROXY, $this->proxy); //代理IP
            curl_setopt($process, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS5); 
        }
        if(mb_substr($url, 0,5) === 'https')
        {
            //https  取消证书验证
               curl_setopt($process, CURLOPT_SSL_VERIFYPEER, false); 
            curl_setopt($process, CURLOPT_SSL_VERIFYHOST, false); 
        }
        $return = curl_exec($process); 
        curl_close($process); 
        return $return; 
        //初始化
      /*  $ch = curl_init();
        //设置变量
        curl_setopt($ch, CURLOPT_URL, $url);
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, 0);//执行结果是否被返回，0是返回，1是不返回
        curl_setopt($ch, CURLOPT_HEADER, 0);//参数设置，是否显示头部信息，1为显示，0为不显示
        curl_setopt($ch, CURLOPT_REFERER, $http_url); 
        //表单数据，是正规的表单设置值为非0
        curl_setopt($ch, CURLOPT_POST, 1);
        curl_setopt($ch, CURLOPT_TIMEOUT, 1);//设置curl执行超时时间最大是多少
        //使用数组提供post数据时，CURL组件大概是为了兼容@filename这种上传文件的写法，
        //默认把content_type设为了multipart/form-data。虽然对于大多数web服务器并
        //没有影响，但是还是有少部分服务器不兼容。本文得出的结论是，在没有需要上传文件的
        //情况下，尽量对post提交的数据进行http_build_query，然后发送出去，能实现更好的兼容性，更小的请求数据包。
        curl_setopt($ch, CURLOPT_POSTFIELDS, $data);
        //执行并获取结果
        $output = curl_exec($ch);
        if($outopt === FALSE)
        {
            echo "<br/>","cUrl Error:".curl_error($ch);
        }
        //    释放cURL句柄
        curl_close($ch); */
    }
    function error($error) { 
        echo "<center><div style='width:500px;border: 3px solid #FFEEFF; padding: 3px; background-color: #FFDDFF;font-family: verdana; font-size: 10px'><b>cURL Error</b><br>$error</div></center>"; 
        die; 
    }
}


?> 

 

 

面向对象:

<?php
class mycurl { 
     protected $_useragent = 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1'; 
     protected $_url; 
     protected $_followlocation; 
     protected $_timeout; 
     protected $_maxRedirects; 
     protected $_cookieFileLocation = './cookie.txt'; 
     protected $_post; 
     protected $_postFields; 
     protected $_referer ="http://www.midnightvip.com"; 

     protected $_session; 
     protected $_webpage; 
     protected $_includeHeader; 
     protected $_noBody; 
     protected $_status; 
     protected $_binaryTransfer; 
     public    $authentication = 0; 
     public    $auth_name      = ''; 
     public    $auth_pass      = ''; 
      /**
      * @api               {public}  mycurl/__construct  01.构造函数 
      * @apiGroup          mycurl
      * @apiName           构造函数
      * @apiParam          {string}  url 请求链接
      * @apiParamExample   {string}  请求链接 
      *      https://www.baidu.com
      * @apiParam          {boolean}  followlocation TRUE要遵循 服务器作为HTTP标头一部分发送的“Location：”标题（注意这是递归的，除非设置，否则PHP将按照发送它的许多“Location：”标题执行CURLOPT_MAXREDIRS）。
      * @apiParamExample   {string}   允许抓取多重跳转
      *      true 
      * @apiParam          {string}  timeOut 请求超时时间
      * @apiParamExample   {string}  请求超时时间秒计
      *      30   
      *
      * @apiParam          {integer}  maxRedirecs 遵循的HTTP重定向的最大数量。一起使用这个选项CURLOPT_FOLLOWLOCATION。
      * @apiParamExample   {integer}  重定向的最大数量
      *      4   
      * @apiParam          {boolean}  binaryTransfer 已弃用
      * 
      * @apiParam          {boolean}  includeHeader TRUE 在输出中包含标题。
      * @apiParamExample   {boolean}  在输出中包含标题
      *      false  
      * @apiParam          {boolean}  noBody  只请求头部
      * @apiParamExample   {boolean}  只请求头部
      *      false       
      */
     public function __construct($url,$followlocation = true,$timeOut = 30,$maxRedirecs = 4,$binaryTransfer = false,$includeHeader = false,$noBody = false) 
     { 
         $this->_url = $url; 
         $this->_followlocation = $followlocation; 
         $this->_timeout = $timeOut; 
         $this->_maxRedirects = $maxRedirecs; 
         $this->_noBody = $noBody; 
         $this->_includeHeader = $includeHeader; 
         $this->_binaryTransfer = $binaryTransfer; 

         $this->_cookieFileLocation = dirname(__FILE__).'/cookie.txt'; 

     } 
     /**
      * @api               {public}  mycurl/useAuth     02.是否需要登录
      * @apiGroup          mycurl
      * @apiName           是否需要登录
      * @apiParam          {boolean}  use 是否需要登录
      * @apiParamExample   {boolean}  需要登录 
      *        true
      */
     public function useAuth($use){ 
       $this->authentication = 0; 
       if($use == true) $this->authentication = 1; 
     }
     /**
      * @api               {public}  mycurl/setName     03.设置登录用户名
      * @apiGroup          mycurl
      * @apiName           设置登录用户名
      * @apiParam          {string}  name 用户名
      * @apiParamExample   {string}  用户名 
      *      admin    
      */
     public function setName($name){ 
       $this->auth_name = $name; 
     }
     /**
      * @api               {public}  mycurl/setPass  04.设置登录用户密码 
      * @apiGroup          mycurl
      * @apiName           设置登录用户密码        
      * @apiParam          {string}  name 密码
      * @apiParamExample   {string}  密码 
      *      123456    
      */
     public function setPass($pass){ 
       $this->auth_pass = $pass; 
     } 
    /**
      * @api               {public}  mycurl/setReferer  05.设置http “Referer：”标头的内容
      * @apiGroup          mycurl
      * @apiName           设置http “Referer：”标头的内容        
      * @apiParam          {string}  referer 来源
      * @apiParamExample   {string}  来源 
      *      www.baidu.com    
      */
     public function setReferer($referer){ 
       $this->_referer = $referer; 
     } 

      /**
      * @api               {public}  mycurl/setCookiFileLocation  06.保存所有内部cookie到文件的名称
      * @apiGroup          mycurl
      * @apiName           保存所有内部cookie到文件的名称，例如在curl_close调用之后。       
      * @apiParam          {string}  path 存储位置
      * @apiParamExample   {path}  存储位置 
      *      e://cookie.txt   
      */
     public function setCookiFileLocation($path) 
     { 
         $this->_cookieFileLocation = $path; 
     } 
    /**
      * @api               {public}  mycurl/setPost  07.设置post发送请求数据
      * @apiGroup          mycurl
      * @apiName           设置post发送请求数据。       
      * @apiParam          {array}  postFields 发送请求数据
      * @apiParamExample   {array}  发送请求数据
      *      array(
      *        'username'=>'123',
      *        'password'=>'123456'
      *      )
      */
     public function setPost ($postFields) 
     { 
        $this->_post = true; 
        $this->_postFields = $postFields; 
     } 
     
     public function setUserAgent($userAgent) 
     { 
         $this->_useragent = $userAgent; 
     } 

     public function createCurl($url = 'nul') 
     { 
        if($url != 'nul'){ 
          $this->_url = $url; 
        } 

         $s = curl_init(); 

         curl_setopt($s,CURLOPT_URL,$this->_url); 
         curl_setopt($s,CURLOPT_HTTPHEADER,array('Expect:')); 
         curl_setopt($s,CURLOPT_TIMEOUT,$this->_timeout); 
         curl_setopt($s,CURLOPT_MAXREDIRS,$this->_maxRedirects); 
         curl_setopt($s,CURLOPT_RETURNTRANSFER,true); 
         curl_setopt($s,CURLOPT_FOLLOWLOCATION,$this->_followlocation); 
         curl_setopt($s,CURLOPT_COOKIEJAR,$this->_cookieFileLocation); 
         curl_setopt($s,CURLOPT_COOKIEFILE,$this->_cookieFileLocation); 

         if($this->authentication == 1){ 
           curl_setopt($s, CURLOPT_USERPWD, $this->auth_name.':'.$this->auth_pass); 
         } 
         if($this->_post) 
         { 
             curl_setopt($s,CURLOPT_POST,true); 
             curl_setopt($s,CURLOPT_POSTFIELDS,$this->_postFields); 

         } 

         if($this->_includeHeader) 
         { 
               curl_setopt($s,CURLOPT_HEADER,true); 
         } 

         if($this->_noBody) 
         { 
             curl_setopt($s,CURLOPT_NOBODY,true); 
         } 
         /* 
         if($this->_binary) 
         { 
             curl_setopt($s,CURLOPT_BINARYTRANSFER,true); 
         } 
         */ 
         curl_setopt($s,CURLOPT_USERAGENT,$this->_useragent); 
         curl_setopt($s,CURLOPT_REFERER,$this->_referer); 

         $this->_webpage = curl_exec($s); 
                   $this->_status = curl_getinfo($s,CURLINFO_HTTP_CODE); 
         curl_close($s); 

     } 

   public function getHttpStatus() 
   { 
       return $this->_status; 
   } 

   public function __tostring(){ 
      return $this->_webpage; 
   } 
}