Java爬虫Jsoup+正则表达式爬取必应壁纸

Java爬虫Jsoup+正则表达式爬取必应壁纸

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import java.io.File;
import java.io.FileOutputStream;
import java.util.Scanner;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class DIYMain2 {
    public static void main(String[] args) throws Exception {
        int page = 1;//起始页
        Scanner scanner = new Scanner(System.in);
        System.out.println("请输入你要下载多少页");
        int howMuchPage = scanner.nextInt();//输入下载的页数
        while (page <= howMuchPage) {
            Document document = Jsoup.connect("https://bing.ioliu.cn/?p=" + page + "").get();//请求链接
            Matcher matcher = Pattern.compile("<a class=\"mark\" href=\"(.*?)\"></a>").matcher(document.toString());//正则表达式匹配略缩图网址
            int i = 1;
            while (matcher.find()) {
                String newURL = "https://bing.ioliu.cn/" + matcher.group(1) + "";//拼接成完整的略缩图网址
                String regex = "<img class=\"target progressive__img progressive--not-loaded\" src=\".*?\" data-progressive=\"(.*?)\">";//匹配规则
                Matcher matcher1 = Pattern.compile(regex).matcher(Jsoup.connect(newURL).get().toString());//正则表达式匹配提取高清大图网址
                while (matcher1.find()) {//匹配到高清大图网址
                    try {
                        byte[] bytes = Jsoup.connect(matcher1.group(1)).ignoreContentType(true).execute().bodyAsBytes();//将大图图片转为字节数组
                        File filePath = new File("C://bring//");//创建文件路径
                        if (!filePath.exists())//文件路径不存在
                            filePath.mkdir();//则创建此抽象文件路径
                     FileOutputStream fileOutputStream = new FileOutputStream(""+filePath+"/第" + page + "页-第" + i + "张.jpg");
                        fileOutputStream.write(bytes);//从字节数组中写出此流,生成高清大图图片
                    } catch (Exception e) {//异常处理
                        continue;//不在往下,跳过异常或不存在的高清大图网址
                    }
                    System.out.println("第" + page + "页-第" + i + "张.jpg正在下载.......");
                    i++;
                }
            }
            page++;//页数递增
        }
        System.out.println("下载完成!");
    }
}