java爬虫爬图片

/**
 * 爬图片
 * Created by gz on 2017/11/29.
 */
public class GetImage {
    // 获取img标签正则
    private static final String IMGURL_REG = "]*?>";
    // 获取src路径的正则
    private static final String IMGSRC_REG = "[a-zA-z]+://[^\\s]*";

    public String getHtml(String url) throws Exception {
        URL url1 = new URL(url);//使用java.net.URL
        URLConnection connection = url1.openConnection();//打开链接
        InputStream in = connection.getInputStream();//获取输入流
        InputStreamReader isr = new InputStreamReader(in);//流的包装
        BufferedReader br = new BufferedReader(isr);

        String line;
        StringBuffer sb = new StringBuffer();
        while ((line = br.readLine()) != null) {//整行读取
            sb.append(line, 0, line.length());//添加到StringBuffer中
            sb.append('\n');//添加换行符
        }
        //关闭各种流，先声明的后关闭
        br.close();
        isr.close();
        in.close();
        return sb.toString();
    }

    //获取ImageUrl地址
    public List getImageUrl(String html) {
        Matcher matcher = Pattern.compile(IMGURL_REG).matcher(html);
        List listimgurl = new ArrayList();
        while (matcher.find()) {
            listimgurl.add(matcher.group());
        }
        return listimgurl;
    }

    //获取ImageSrc地址
    public List getImageSrc(List listimageurl) {
        List listImageSrc = new ArrayList();
        for (String image : listimageurl) {
            Matcher matcher = Pattern.compile(IMGSRC_REG).matcher(image);
            while (matcher.find()) {
                listImageSrc.add(matcher.group().substring(0, matcher.group().length() - 1));
            }
        }
        return listImageSrc;
    }
    public void Download(List listImgSrc) {
        try {
            //开始时间
            Date begindate = new Date();
            for (String url : listImgSrc) {
                //开始时间
                Date begindate2 = new Date();
                String imageName = url.substring(url.lastIndexOf("/") + 1, url.length());
                URL uri = new URL(url);
                InputStream in = uri.openStream();
                FileOutputStream fo = new FileOutputStream(new File("D:\\Html\\image\\"+imageName));//文件输出流
                byte[] buf = new byte[1024];
                int length = 0;
                System.out.println("开始下载:" + url);
                while ((length = in.read(buf, 0, buf.length)) != -1) {
                    fo.write(buf, 0, length);
                }
                //关闭流
                in.close();
                fo.close();
                System.out.println(imageName + "下载完成");
                //结束时间
                Date overdate2 = new Date();
                double time = overdate2.getTime() - begindate2.getTime();
                System.out.println("耗时：" + time / 1000 + "s");
            }
            Date overdate = new Date();
            double time = overdate.getTime() - begindate.getTime();
            System.out.println("总耗时：" + time / 1000 + "s");
        } catch (Exception e) {
            System.out.println("下载失败");
        }
    }
}