php 自制基于simple_html_dom的爬虫一只v1.0

<?php
/*
	*.Pho spider v1.0
	*.Written by Radish.ghost 2015.1.20
*/
//error_reporting(1); //close error report
//curl model //I will realize it in later versions
include_once("simple_html_dom.php");
$html=file_get_html('http://www.baidu.com');//The url which you want dig

$tmp=array();//Save the url in the first dig
foreach($html->find('a') as $e) 
{
	$f=$e->href;
	//if($f[10]==':')continue;
	if($f[0]=='/')$f='http://www.baidu.com'.$f;//Completion the url
	if($f[4]=='s')continue;//If the url is "https://" continue (the simple_html_dom might can't prase the https:// url)  
	if(stripos($f,"baidu")==FALSE)continue;//If the url not in this website continue
    echo $f . '<br>';
	$tmp[$cun++]=$f; //Save the urls into array
}

foreach($tmp as $r) //Dig the urls in $tmp[]
{
$html2=file_get_html($r); //Redo the step
foreach($html2->find('a') as $a)
{
	$u=$a->href;
	if($u[0]=='/')$u='http://www.baidu.com'.$u;
	if($u[4]=='s')continue;
	if(stripos($u,"baidu")==FALSE)continue;
	echo $u.'<br>';
}
$html2=null;
}
?>