采集源代码示范

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;
$reg='#
.*#isU'; preg_match($reg,$str,$arr); //var_dump($arr); //标题 $reg2='#

(.*)

#isU'; preg_match_all($reg2,$arr[0],$data1); //var_dump($data1); //内容 $reg3='#

(.*); 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 $reg4='#NBA#isU'; preg_match_all($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); }

你可能感兴趣的:(采集源代码示范)