采集css文件里面的图片采集html里面的图片

采集css文件里面的图片采集html里面的图片

<?php
/**  http://localhost/test/my/xiuwo/css2img/
 *  通过CSS采集图片. 注意：采集下来的图片 保存在和当前目录相同。



$image_path = "//images/a/c.png";
$image_path = str_replace("//","", $image_path);
$image_path = substr($image_path, 0);
$pathinfo = pathinfo($image_path);
$image_dir = $pathinfo ? $pathinfo['dirname'] : '';
echo $image_dir;

//mkdir('1/2/3', 0777,true);
//mkdir($image_dir, 0777,true);
//exit;
exit;
	*/

$spider = new spider();
//$spider->time_limiter = 1115500;
set_time_limit(0);
$spider->getAll_one();



	class spider{	
		
		public $url="http://www.a.com/templets/default/style.css";//css地址或者index.html地址
		public $url_img = "http://www.a.com/templets/default/";//源图片网址
		//匹配html里面的 img
		/*public $reg='/<img.*?src="(.*?)".*?\/?>/i';  //匹配html里面的 img  */
		/* public $reg='/url\((.*)\)/i';  //匹配html里面的 img   */

		//匹配css里面的background-image
		public $reg="|url\((.*)\)|U"; //匹配css里面的background-image 

		public $test = 0;//1测试并打印输出 0直接采集

		function __construct(){
			
		}

		function getAll_one()
		{			
			/**
			$value='http://a.a.cn/img/background/line_nav.jpg';
			$ary = explode('/', $value);
			$num = count($ary);
			echo($ary[$num-1]);
			*/
			
			$url = $this->url;			
			$reg = $this->reg;
			$data	=	@file_get_contents($url);
			preg_match_all($reg, $data, $out, PREG_PATTERN_ORDER);

			$out_1 = $out[1];
			foreach($out_1 as $k=>$img_url)
			{
				$img_url	= str_replace("../", "", $img_url);
				$img_url	= str_replace("'", "", $img_url);
				$img_url	= str_replace('"', "", $img_url);
				$out_1[$k]	= $img_url;
			}

			print_r($out_1);
			if($this->test) exit;
			$this->download_mp3_five($out_1);
		}

		function download_mp3_five($data){
				//读取 内容，并写入本地。。。
				foreach($data as $value)
				{
						//echo $value.'<br>';
						//创建目录 
						$image_path = $value;
						$image_path = str_replace("//","", $image_path);
						if(substr($image_path, 0, 1) == '/')
						{
							$image_path = substr($image_path, 1);						
						}
						$image_path = str_replace(":", "", $image_path);

						$pathinfo = pathinfo($image_path);
						$image_dir = $pathinfo ? $pathinfo['dirname'] : '';

						//echo $image_path.'--';
						//echo $image_dir.'<br><br>';exit;
						if(!is_dir($image_dir))
						{
							@mkdir($image_dir, 0777,true);
						}						
						//创建目录 END
						//exit;

						$value = $this->url_img.$value;
						//echo $value;
						//echo "\r\n\r\n<br>\r\n";

						$file = '';
						$file = @file_get_contents($value);	
						//var_dump($file);exit;


						$fp  = @fopen($image_path, 'w');
						@fwrite($fp, $file);
						@fclose($fp);
						
				}				
		}
		
		function _get_file_name($value)
		{
			$ary = explode('/', $value);
			$num = count($ary);
			return $ary[$num-1];
			//$reg = "|\/(.*)|U";
			//preg_match_all($reg, $value, $out, PREG_PATTERN_ORDER);
			//return $out[0];
		}
	
	}