简单数据采集（http://blog.jobbole.com/tag/php/）

<?php
for($i=1;$i<=4;$i++){
$url="http://blog.jobbole.com/tag/php/page/$i/";
$str=file_get_contents($url);
$reg='#<div class="post floated-thumb">.*<div id="sidebar" class="grid-4">#isU';
preg_match($reg,$str,$arr);
//var_dump($arr);die();
$reg2='#<img src="(.*)" alt="" .* />.*<a target="_blank" class="archive-title" href=".*" title=".*">(.*)</a><br />(.*) · <a href=".*" rel="category tag">.*<span class="excerpt"><p>(.*)</p>.*<span class="read-more">#isU';
preg_match_all($reg2,$arr[0],$data);
//var_dump($data);die();
$dsn = "mysql:host=127.0.0.1;dbname=cjlianxi";
$db = new PDO($dsn, 'root', 'root');
foreach($data[1] as $k1=>$v1){
$str=file_get_contents($v1);//获取图片内容
$ext=substr($v1,strrpos($v1,"."));//截取后缀
$filename="images/".time().rand(1000,9999).$ext;
file_put_contents($filename,$str);//移入缓存
$sql="insert into exam902(title,content,img,addtime)VALUES ('".$data[2][$k1]."','".$data[4][$k1]."','".$filename."','".$data[3][$k1]."')";
$db->exec($sql);
}
}