采集实例

来源:互联网 发布:避孕套 知乎 编辑:程序博客网 时间:2024/05/18 02:00
/**
* 采集
* @author [zhao]
*/
public function actionTitle()
{
//采集标题
header("content-type:text/html;charset=utf-8");
for($i=1;$i<=10;$i++){
$url="http://bj.5i5j.com/rent/n".$i;
$content=file_get_contents($url);
$reg1='#<h2><a href=".*" target=".*">(.*)</a></h2>[\n\s\t\r]*.* </div>#isU';
preg_match_all($reg1, $content,$result1);
//print_r($result1); die;
$reg2='#<li class="font-balck"><span>(.*)</span><span>(.*)</span><span>(.*)</span><span>(.*)</span></li>#';
preg_match_all($reg2, $content,$result2);
//unset($result2[0]);//print_r($result2); die;
//拼接数组
$file=array();
foreach ($result1 as $key => $value){
$file['title']=$value;
$file['area']=$result2[1];
$file['area1']=$result2[2];
$file['direction']=$result2[3];
$file['floor']=$result2[4];
/*print_r($file);die;*/
}
//print_r($file);die;
$data=array();
foreach($file['title'] as $k=>$v)
{

$data[$k]['title']=$v;
$data[$k]['area']=$file['area'][$k];
$data[$k]['area1']=$file['area1'][$k];
$data[$k]['direction']=$file['direction'][$k];
$data[$k]['floor']=$file['floor'][$k];
}
//print_r($data);die;
$str="";//定义入库字符串

foreach($data as $key=> $val){
$str.="(null,'$val[title]','$val[area]','$val[area1]','$val[direction]','$val[floor]')".",";
}

$str=trim($str,","); //去除最后逗号
Yii::$app->db->createCommand('TRUNCATE houses');
$res=Yii::$app->db->createCommand("insert into `houses` values $str")->execute();

echo $res;
}

}
0 0
原创粉丝点击