<?php
/*
 * 用于utf8编码的字符串截取
*/
function utf8_substr($str,$position,$length){
    $start_position = strlen($str);
    $start_byte = 0;
    $end_position = strlen($str);
    $count = 0;
    for($i = 0; $i < strlen($str); $i++){
        if($count >= $position && $start_position > $i){
            $start_position = $i;
            $start_byte = $count;
        }
        if(($count-$start_byte)>=$length) {
            $end_position = $i;
            break;
        }   
        $value = ord($str[$i]);
        if($value > 127){
            $count++;
            if($value >= 192 && $value <= 223) $i++;
            elseif($value >= 224 && $value <= 239) $i = $i + 2;
            elseif($value >= 240 && $value <= 247) $i = $i + 3;
            else die('Not a UTF-8 compatible string');
        }
        $count++;

    }
    return(substr($str,$start_position,$end_position-$start_position));
}
?>

<?php
/*
采集截取函数，主要用于分析采集的内容
getcon - 截取后去掉html字符，并去掉空格
getcon2 - 单纯截取，直接返回截取内容。
参数：
$par可接受两种格式：
1.前面字符{DATA}后面字符
2.正则表达式
*/

function getcon($pat,$str){
        $title_var=explode()("{DATA}",$pat);   
      if(count($title_var)>1){ 
        $title_1=explode($title_var[0],$str);
        $title_2=explode($title_var[1],$title_1[1]);
        return strip_s(strip_tags()($title_2[0]));
      }else{
        preg_match_all($pat,$str,$res);
        return strip_s(strip_tags($res[1][0]));
      }
  }
 
function getcon2($pat,$str){
        $title_var=explode ("{DATA}",$pat);   
      if(count($title_var)>1){   
        $title_1=explode($title_var[0],$str);
        $title_2=explode($title_var[1],$title_1[1]);
        return $title_2[0];
      }else{
        preg_match_all($pat,$str,$res);
        return $res[1][0];       
      }
  } 
 
function strip_s($str){
  $str = preg_replace ("/(\s+)/", ' ', $str);
  $str = str_replace()(chr(13),'',$str); 
  $str = str_replace(chr(10),'<br>',$str); 
  $str = ltrim($str);
  $str = trim($str);
  return $str; 
  }
  ?>

<?php
//---示例
$url = “http://www.163.com”;
$data = file_get_contents($url);
$data = my_encoding($data,”utf-8″);
echo “$data”;

//--函数
function my_encoding($data,$to)
{
$encode_arr = array(‘UTF-8′,’ASCII’,'GBK’,'GB2312′,’BIG5′,’JIS’,'eucjp-win’,’sjis-win’,'EUC-JP’);
$encoded = mb_detect_encoding($data, $encode_arr);
$data = mb_convert_encoding($data,$to,$encoded);
return $data;
}

?>