php 采集函数，很好的php采集函数

<?php   
header("content-Type: text/html; charset=utf-8");
function preg_substr($start, $end, $str) // 正则截取函数      
{      
    $temp = preg_split($start, $str);      
    $content = preg_split($end, $temp[1]);      
    return $content[0];      
}   
function str_substr($start, $end, $str) // 字符串截取函数      
{      
    $temp = explode($start, $str, 2);      
    $content = explode($end, $temp[1], 2);      
    return $content[0];     
}   

// ---------------- 使用实例 ----------------   
$str = iconv("GB2312","UTF-8",  file_get_contents("http://www.037c.com/New/5.html"));    
echo ("标题: " . str_substr("<title>", "</title>", $str)); // 通过字符串提取标题   
echo ("作者: " . preg_substr("/作者：/", "/<//", $str)); // 通过正则提取作者   
echo ("内容: " . str_substr("<div class="wltg">", "</div>", $str)); //内容当然不可以少   
?>   

<?php
header("content-Type: text/html; charset=utf-8");
$html=file_get_contents("http://news.sina.com.cn/");
$html=str_replace("
","",$html);
$html=str_replace("
","",$html);
$rule="/<div class="ct_t_01".*?>(.*?)</div>/";
preg_match($rule,$html,$result);
$result=$result[1];
$rule1="/<h1 data-client="headline">(.*?)</h1>/";
preg_match_all($rule1,$result,$array);
print_r($array);

?>


<?php   
header("content-Type: text/html; charset=utf-8");
$html=file_get_contents("http://news.sina.com.cn/");
function preg_substr($start, $end, $str) // 正则截取函数        
{        
    $temp = preg_split($start, $str);        
    $content = preg_split($end, $temp[1]);        
    return $content[0];        
}   
$result=preg_substr("/<div class="ct_t_01".*?>/","/</div>/",$html);
$rule1="/<h1 data-client="headline">(.*?)</h1>/";
preg_match_all($rule1,$result,$array);
print_r($array)
?>