基于curl数据采集之正则处理函数get_matches的使用

function get_matches($pattern,$html,$err_msg,$multi=false,$flags=0,$offset=0){
     if(!$multi){
         if(!preg_match($pattern,$html,$matches,$flags,$offset)){
             echo $err_msg."! 错误信息: ".get_preg_err_msg()."\n";
             return false;
         }
     }else{
         if(!preg_match_all($pattern,$html,$matches,$flags,$offset)){
             echo $err_msg."! 错误信息: ".get_preg_err_msg()."\n";
             return false;
         }
     }
     return $matches;
 }
 function get_preg_err_msg(){
     $error_code = preg_last_error();
     switch($error_code){
         case PREG_NO_ERROR :
             $err_msg = 'PREG_NO_ERROR';
             break;
         case PREG_INTERNAL_ERROR:
             $err_msg = 'PREG_INTERNAL_ERROR';
             break;
         case PREG_BACKTRACK_LIMIT_ERROR:
             $err_msg = 'PREG_BACKTRACK_LIMIT_ERROR';
             break;
         case PREG_RECURSION_LIMIT_ERROR:
             $err_msg = 'PREG_RECURSION_LIMIT_ERROR';
             break;
         case PREG_BAD_UTF8_ERROR:
             $err_msg = 'PREG_BAD_UTF8_ERROR';
             break;
         case PREG_BAD_UTF8_OFFSET_ERROR:
             $err_msg = 'PREG_BAD_UTF8_OFFSET_ERROR';
             break;
         default:
             return '未知错误!';
     }
     return $err_msg.': '.$error_code;
 }

$url = 'http://www.baidu.com';
 $html = get_html($url);
 $matches = get_matches('!<a[^<]+</a>!',$html,'没有找到链接',true);
 if($matches){
     var_dump($matches);
 }

$urls = array('http://www.baidu.com','http://www.hao123.com');
 $htmls = get_htmls($urls);
 foreach($htmls as $html){
     $matches = get_matches('!<a[^<]+</a>!',$html,'没有找到链接',true);
     if($matches){
         var_dump($matches);
     }
 }