简单的图片爬取【php】

因为做项目，需要拿一些图片来处理测试，就写了个简单的爬取壁纸网站，代码如下：

<?php


function dump($data)
{
	if(is_array($data) || is_object($data)){
		echo '<pre>';
		print_r($data);
		echo '</pre>';
	}else{
		echo $data;
	}
	echo "<hr>";
}

function download($url, $pronames,$path = 'images/')
{
	$ch = curl_init();
	curl_setopt($ch, CURLOPT_URL, $url);
	curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
	curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 30);
	$file = curl_exec($ch);
	curl_close($ch);
	$filename = pathinfo($url, PATHINFO_BASENAME);

	if(!is_dir($path . $pronames)){
		mkdir('images/'.$pronames);
	}

	$resource = fopen($path . $pronames . '/' . $filename, 'a');
	fwrite($resource, $file);
	fclose($resource);
}

//$subject = "1aotfyyjzj3aa4bdkxvg78457zmfxdngrxwyta3qb7nh1jpvotmlwv9o4e6lwzeg";

//$subject = file_get_contents('./pro/t1.html');
//
set_time_limit(0);

$pattern = "/[a-zA-z]+:\/\/[^\s]*?jpg/";
$arr = array();
$matches = null;

//每一页的重复图片  
$shieldUrl = array(
		'http://img.netbian.com/file/2018/1218/5174f6bd57412ee0d66bcff52629cf5e.jpg',
		'http://img.netbian.com/file/2018/1218/2c953b94fcb487c210cb8816f7146148.jpg',
		'http://img.netbian.com/file/2018/1225/604a688cd6f79161236e6250189bc25b.jpg',
		'http://img.netbian.com/file/2019/0304/d7718c988ae353a6531742bb92d97e91.jpg'

	);

for ($i=2; $i < 100; $i++) {
	# code...
	$subject = file_get_contents('http://www.netbian.com/index_'.$i.'.htm');

	$t2 = preg_match_all($pattern,$subject,$matches);
	$arr[] = $matches[0];

	foreach ($matches[0] as $key => $value) {
		if (!in_array($value, $shieldUrl)) {
			download($value,$i);  //下载
		}
	}
}


dump($arr);








?>