PHP爬虫之刷博客访问量

<?php
//只需把beginUrl改为你的博客列表首页就可以了
$beginUrl = "http://blog.csdn.net/qq_27988539?viewmode=contents";
$listpage = file_get_contents($beginUrl);

//博客列表可能有多页
//获得每一页的链接
$pattern ="/<div id=\"papelist\".*>.*<\/div>/sU";
$arr = array();
if(preg_match_all($pattern,$listpage,$arr))
{
$str = $arr[0][0];
$pattern = "/<a.*>.*<\/a>/sU";
$temp1 = array();
if(preg_match_all($pattern,$str,$temp1))
{
$temp1 = $temp1[0];
array_splice($temp1,-2);
$pages = array();

foreach ($temp1 as $key => $value)
{
$temp2 = array();
$pattern = "/\".*\"/U";
if(preg_match_all($pattern,$value,$temp2))
{
$pages[] = $temp2[0][0];
}
}
}
}
$rooturl = "http://blog.csdn.net";
$blogPage = array($beginUrl);
if(!empty($pages))
{
foreach($pages as $key => $value)
{
$pages[$key] = preg_replace("/\"/",'', $value);
$blogPage[] = $rooturl.$pages[$key];
}
}
//print_r($blogPage);
//获得所有博客的链接
$blogUrls = array();
foreach($blogPage as $key => $value)
{
$page = file_get_contents($value);
$pattern = "/<span class=\"link_title\">.*<\/span>/sU";
if(preg_match_all($pattern,$page,$arr))
{
$arr = $arr[0];
foreach($arr as $key => $value)
{
$pattern = "/<a.*<\/a>/sU";
$temp3 = array();
if(preg_match_all($pattern,$value,$temp3))
{
$pattern = "/\".*\"/U";
$str = $temp3[0][0];
$temp4 = array();
if(preg_match_all($pattern,$str,$temp4))
{
$blogUrls[] = preg_replace("/\"/","",$temp4[0][0]);
}
}
}
}
}
//var_dump($blogUrls);
//遍历访问所有的博客链接
for($i=0;$i<100;$i++)
{
foreach($blogUrls as $value)
{
$blogUrl = $rooturl.$value;
file_get_contents($blogUrl);
sleep(2);
}
}

?>