header("content-type:text/html;charset=utf-8"); set_time_limit(0); $url='http://sports.sohu.com/nba.shtml'; $str=file_get_contents($url); $str=iconv("GBK","utf-8",$str); //echo $str; $reg='#<div style="HEIGHT: 290px; OVERFLOW: hidden" id="columnID" class="heavyColumn">.*<a onFocus="undefined" href="http://sports.sohu.com/s2016/7265/s460940033/" target="_blank">#isU'; preg_match($reg,$str,$arr); //var_dump($arr); //标题 $reg2='#<h4><a onFocus="undefined" title="" href="http://sports.sohu.com/s2016/7265/.*/" target="_blank">(.*)</a></h4>#isU'; preg_match_all($reg2,$arr[0],$data1); //var_dump($data1); //内容 $reg3='#<p>(.*)<a#isU'; preg_match_all($reg3,$arr[0],$data2); //var_dump($data2); $pdo=new PDO('mysql:host=localhost;dbname=test','root','root'); $pdo->exec("set names utf8"); for($i=0;$i<count($data1[1]);$i++){ $title=$data1[1][$i]; $content=$data2[1][$i]; $sql="insert into nba (title,content) VALUES ('$title','$content')"; $pdo->exec($sql); } //图片 $reg4='#<img alt="NBA" src="(.*)" border="0" height="100" width="100"></a>#isU'; preg_match_all($reg4,$arr[0],$data3); //var_dump($data3); foreach($data3[1] as $v){ $path=file_get_contents($v); $ext=substr($v,strrpos($v,'.')); $file_name='img/'.time().rand(1000,9999).$ext; file_put_contents($file_name,$path); }