Java获取网页中的图片

原创已于 2023-12-25 15:26:15 修改 · 406 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#java #开发语言

于 2023-11-29 15:48:45 首次发布

Java 专栏收录该内容

28 篇文章

订阅专栏

本文介绍了使用Java编写的getImageByUrl4类，它通过解析网页源代码，利用正则表达式提取图片URL，并下载到本地文件夹。主要涉及了网络请求、输入输出流和正则匹配等技术。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import java.io.BufferedOutputStream;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
 
public class getImageByUrl4 {
    /**
     * @param args
     */
    private List<String> imageUrl = new ArrayList<String>();//用于存储图片的url
    private int count = 0;//图片计数器
    public static void main(String[] args) {
        String netUrl = "http://www.xxxxxx.com";//要爬的网页
        new getImageByUrl4().init(netUrl);
    }
    public void init(String netUrl){
        getPage(netUrl);
        while(imageUrl.size()!=0)
        {
            getImage(imageUrl.remove(0));
        }
    }
    //获取网页信息line中的图片url并加入到集合中
    public void getImageUrl(String line,String netUrl){
        //三种正则表达式
        //其他网站的图片,http开头如：src = "http://www.ecoc.com:8080/pic/jfjiejf.jpg
        //String searchImgReg = "(src|SRC|background|BACKGROUND|background-image|BACKGROUND-IMAGE)=('|\")(http://([\\w-]+\\.)+[\\w-]+(:[0-9]+)*(/+[\\w-]+)*(/+[\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))";
        String searchImgReg = "(src|SRC|background|BACKGROUND|background-image|BACKGROUND-IMAGE)\\w{0,2}=('|\")http(s)*://.{1,}.(jpg|JPG|png|PNG|gif|GIF)\"\\s";
        //项目中的图片，绝对路径如：src = "/ecoc/lala/jj/ooellaie.jpg
        //String searchImgReg2 = "(src|SRC|background|BACKGROUND|background-image|BACKGROUND-IMAGE)\\w{0,2}=('|\")/*(([\\w-]+/)*([\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))('\")";
        String searchImgReg2 = "(src|SRC|background|BACKGROUND|background-image|BACKGROUND-IMAGE)\\w{0,2}=('|\")/*(([\\w-]+/)*([\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))\"\\s";
        try {
            Pattern pat = Pattern.compile(searchImgReg);
            Matcher matcher=pat.matcher(line);
            String str =null;
            while(matcher.find())
            {
                str = matcher.group();
                String []sttr = str.split(" ");System.out.println(str);
                for(int i = 0;i<sttr.length;i++){
                    String s = sttr[i];
                    Integer index_denghao = s.indexOf("=")+2;
                    imageUrl.add(s.substring(index_denghao,s.length()-1));
                }
            }
            pat = Pattern.compile(searchImgReg2);
            matcher=pat.matcher(line);
            while(matcher.find())
            {
                str = matcher.group(); System.out.println(str);
                String []sttr = str.split(" ");
                for(int i = 0;i<sttr.length;i++){
                    String s = sttr[i];System.out.println(s);
                    Integer index_denghao = s.indexOf("=")+2;
                    Integer index_2 = netUrl.indexOf("/", 8);
                    if(index_2==-1)
                        index_2 = netUrl.length();
                    imageUrl.add(netUrl.substring(0, index_2)+"/"+s.substring(index_denghao,s.length()-1));
                }
            }
        } catch (Exception e) {
             
        }
    }
    //爬取网页中的信息。
    public void getPage(String netUrl){
        BufferedReader mybr = null;
        try {
            URL myurl = new URL(netUrl);
            URLConnection myconn = myurl.openConnection();
            InputStream myin = myconn.getInputStream();
            mybr = new BufferedReader(new InputStreamReader(myin,"UTF-8"));
            String line;
            while((line = mybr.readLine())!= null)
            {
                getImageUrl(line,netUrl);//判断网页中的jpg图片
            }
 
        } catch (MalformedURLException e) {
            System.out.println("getPage url异常");
        } catch (IOException e) {
            System.out.println("url连接异常");
            e.printStackTrace();
        }finally {
            if( mybr != null)
            {
                try {
                    mybr.close();
                } catch (IOException e) {
                    System.out.println("读入流关闭异常");
                }
            }
        }
    }
    //下载该图片！
    public void getImage(String imageUrl){
        InputStream myin = null;
        BufferedOutputStream myos = null;
        try {
            File file = new File("H:\\pic\\");
            File[] files = file.listFiles();
            for (File file2 : files) {
                Integer fileName = Integer.valueOf(file2.getName().substring(0, file2.getName().indexOf(".")));
                if(count<fileName){
                    count = fileName;
                }
            }
            URL myurl = new URL(imageUrl);
            URLConnection myconn = myurl.openConnection();
            myin = myconn.getInputStream();
            myos = new BufferedOutputStream(new FileOutputStream("H:\\pic\\"+(++count)+".jpg"));
            byte[] buff = new byte[1024];
            int num = 0;
            while((num = myin.read(buff))!= -1)
            {
                myos.write(buff, 0, num);
                myos.flush();
            }
        } catch (MalformedURLException e) {
            System.out.println("getImage url异常");
            e.printStackTrace();
        } catch (IOException e) {
            System.out.println("下载图片url连接异常");
            e.printStackTrace();
        }
        finally{
            if( myin != null){
                try {
                    myin.close();
                } catch (IOException e) {
                    System.out.println("读入流关闭异常");
                }
            }
            if( myos != null){
                try {
                    myos.close();
                } catch (IOException e) {
                    System.out.println("输出流关闭异常");
                }
            }
        }
    }
}