php抓取图片

function actionGetimg(){
ob_end_clean();
ob_implicit_flush(1);
//13050
for($a=1;$a<13074;$a++){
echo $a.'+';
echo '<br/>';
$url = "http://www.jtyxzz.com/portal.php?mod=view&aid=".$a;
$arr = $this->file_from_url_content($url);
$regex4 = "/<img src=\"data\/[\s\S]*?\">/";//标题
preg_match_all($regex4, $arr, $result1);
//var_dump($result1);
//var_dump(empty($result1[0]));exit;
if (!empty($result1[0])) {
foreach ($result1 as $key => $val) {
$first = str_replace('<img src="', '', $val);
$second = str_replace('">', '', $first);
}
//dump($second);exit;
foreach ($second as $key => $val) {
//var_dump($val);
//echo '<br/>';
$zuihou=strrpos($val,'/');
$mulu=substr($val,0,$zuihou);
//$ming=substr($val,$zuihou+1);
//dump($ming);exit;
if(is_dir($mulu)){
//echo 'cunzai';
}else{//目录不存在创建目录
//echo 'bucunzai';exit;
mkdir($mulu,0777,true);
}


$image =@file_get_contents('http://www.jtyxzz.com/' . $val);
if($image){
file_put_contents($val, $image);
//echo $val;exit;
}else{
file_put_contents('images/diushi.txt',$a.'/'.$val.'图片丢失<br/>',FILE_APPEND);
                        echo $a.'/'.$val.'图片丢失';
echo '<br/>';
}


}
}else {
                echo $a.'no img or no permission';
echo '<br/>';
}
$sleep=$a/100;
if(is_int($sleep)){
echo $sleep;
echo '<br/>';
echo $a;
sleep(rand(40,50));
}
}
echo '图片采集完毕';
//var_dump($second);exit;
       exit;

}


/**
* 异步将远程链接上的内容
* @param unknown $url 远程地址
* @param unknown $saveName 保存在服务器上的文件名
* @param unknown $path 保存路径
* @return boolean
*/
function file_from_url_content($url) {
// 设置运行时间为无限制
set_time_limit ( 0 );
$url = trim ( $url );
$curl = curl_init ();
// 设置你需要抓取的URL
curl_setopt ( $curl, CURLOPT_URL, $url );
// 设置header
curl_setopt ( $curl, CURLOPT_HEADER, 0 );
// 设置cURL 参数,要求结果保存到字符串中还是输出到屏幕上。
curl_setopt ( $curl, CURLOPT_RETURNTRANSFER, 1 );
// 运行cURL,请求网页
$file = curl_exec ( $curl );
// 关闭URL请求
curl_close ( $curl );
return $file;
}





猜你喜欢

转载自blog.csdn.net/qq_40872870/article/details/79936944
今日推荐