java 爬取网站图片

package com.atguigu.springboot.controller;

import java.io.*;
import java.net.URL;
import java.net.URLConnection;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class CrawlingImg {

    // 地址
    private static final String URL = "http://www.viwik.com/view/1814871.html";
    // 获取img标签正则
    private static final String IMGURL_REG = "<img.*src=(.*?)[^>]*?>";
    // 获取src路径的正则
    private static final String IMGSRC_REG = "[a-zA-z]+://[^\\s]*";


    public static void main(String[] args) {
        try {
            CrawlingImg cm=new CrawlingImg();
            //获得html文本内容
            String HTML = cm.getHtml(URL);
            //获取图片标签
            List<String> imgUrl = cm.getImageUrl(HTML);
            //获取图片src地址
            List<String> imgSrc = cm.getImageSrc(imgUrl);
            //下载图片
            cm.Download(imgSrc);

        }catch (Exception e){
            System.out.println("发生错误");
        }

    }

    //获取HTML内容
    private String getHtml(String url)throws Exception{
        URL url1=new URL(url);
        URLConnection connection=url1.openConnection();
        InputStream in=connection.getInputStream();
        InputStreamReader isr=new InputStreamReader(in);
        BufferedReader br=new BufferedReader(isr);

        String line;
        StringBuffer sb=new StringBuffer();
        while((line=br.readLine())!=null){
            sb.append(line,0,line.length());
            sb.append('\n');
        }
        br.close();
        isr.close();
        in.close();
        return sb.toString();
    }

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

    //获取ImageSrc地址
    private List<String> getImageSrc(List<String> listimageurl){
        List<String> listImageSrc=new ArrayList<String>();
        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;
    }

    //下载图片
    private void Download(List<String> listImgSrc) {
        try {
            for (int i = 0; i < listImgSrc.size(); i++) {
                if(listImgSrc.get(i).indexOf("jpg") == -1 && listImgSrc.get(i).indexOf("png") == -1){
                    listImgSrc.remove(i);
                    i--;
                }
            }
            //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());
                if("".equals(imageName)){
                    imageName = String.valueOf(System.currentTimeMillis());
                }
                URL uri = new URL(url);
                InputStream in = uri.openStream();
                FileOutputStream fo = new FileOutputStream(new File("src/res/"+imageName));
                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);
                }
                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");
        }
    }
}

 

  • 0
    点赞
  • 3
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值