网页抓图

header('Content-Type:text/html;charset=utf-8');

/**
 * 一个用于抓去图片的类
 * @author tangpan
 */
class download_image {
    public $_save_path = NULL; //图片保存路劲
    public $_limit_size = NULL; //图片限制大小
    public static $_img_url_old = array();  //存储已抓取过的图片链接地址
    public static $_a_page_url = array();    //存储抓取过的页面
    public function __construct( $_save_path, $_limit_size) {
        $this->_save_path = $_save_path;
        $this->_limit_size = $_limit_size;
    }

    public function get_all_page_image( $site_url ) {
        if ( $site_url == '' ) {
            return false;
        }
        if ( ! in_array( $site_url, self::$_a_page_url ) ) {  //判断当前页面是否抓取过
            self::$_a_page_url[] = $site_url;   //将超链接存入静态数组中
        } else {
            return;     //若抓取过则跳出
        }
        $this->download_the_page_image( $site_url );
        $content = @file_get_contents($site_url);
        $a_page_url = "|]+href=['\" ]?([^ '\"?]+)['\" >]|U";
        $all_url = array();