php 读取网站页面源码的经典函数

Snoopy.class.php下载

 

include "inc/Snoopy.class.php"; 
        //读取网页,返回网页源文件内容 
function read_url($str){ 
                   $snoopy = new Snoopy;
                    $snoopy->agent = "(compatible; MSIE 4.01; MSN 2.5; AOL 4.0; Windows 98)"; 
                   //$snoopy->agent="Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.101 Safari/537.36";
                   $snoopy->rawheaders["Pragma"] = "no-cache";
                   $snoopy->maxredirs = 2; 
                   $snoopy->offsiteok = false; 
                   $snoopy->expandlinks = false;
                if($snoopy->fetch($str)) 
                   { 
                       $result=htmlspecialchars($snoopy->results); 
                   } 
               
             if ($result=="")
             {
             
                  if(function_exists("curl_init"))
                      {
                         if(!function_exists("lex_curl"))
                             {
                               function lex_curl($url)
                                 {
                                     $ch = curl_init();
                                     curl_setopt ($ch, CURLOPT_URL, $url);
                                     curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);
                                     curl_setopt ($ch, CURLOPT_CONNECTTIMEOUT, 30);
                                     curl_setopt ($ch, CURLOPT_TIMEOUT, 30);
                                     curl_setopt ($ch, CURLOPT_FOLLOWLOCATION, TRUE);
                                     curl_setopt ($ch, CURLOPT_MAXREDIRS, 2);
                                     $file_contents = curl_exec($ch);
                                     curl_close($ch);
                                      if($file_contents=="1") $file_contents="";
                                      return $file_contents;
                                  }
                              }
                           $lex_function_get="lex_curl";
                       }
                   else 
                      {$lex_function_get="file_get_contents";}
              $result=@$lex_function_get($str) or die($str.'->远程网址读取失败!');
            
             }
             
    return $result; 
}