php采集后的处理

 

 

<?php
/**
 * @name 采集后的处理.php
 * @date Sat Dec 22 02:07:45 CST 2007
 * @copyright 马永占(MyZ)
 * @author 马永占(MyZ)
 * @link http://blog.csdn.net/mayongzhan/
 */
 
//采集后的文件,然后那来进行处理.这里的东西让我抄了5本书,是哪的不方便提供,自己找找吧.
 
header(''Content-Type:text/html;charset=utf8'');
 
function writer($content,$url)
{
    $fp = fopen($url, ''ab'');
    fwrite($fp, $content);
    fclose($fp);        
}
 
//从1到136页的内容一次合并.这个是最爽的...
 
for ($i=1;$i<136;$i++) {
    $str = file_get_contents(''./myz/''.$i.''.shtml'');
    preg_match("/(<h1>)(.*?)(</h1>)(.*?)(<div class="artibody" id="artibody">)(.*?)(</div>)/s",$str,$arr);
    $arr[6] = preg_replace("/(<span[^>]+>.*?<a[^>]+>)(.*?)(</a></span>)/s","$2",preg_replace("/<p>|</p>/","rn",$arr[6]));
    $result = "rn------------------------------------------------rn------------------------------------------------rn------------------------------------------------rn".$i."----------------马永占的目录编号:".$arr[2]."rn------------------------------------------------rn------------------------------------------------rn------------------------------------------------rn".$arr[6];
    writer($result, "./myz/all.txt");
}
?> 

补充：Php教程,Php常用代码