java爬取网页_首次java爬虫爬取特定网站

packagemain;importjava.io.ByteArrayOutputStream;importjava.io.File;importjava.io.FileOutputStream;importjava.io.IOException;importjava.io.InputStream;importjava.net.HttpURLConnection;importjava.net.URL;importjava.util.ArrayList;importjava.util.List;importjava.io.DataInputStream;importjava.io.DataOutputStream;importorg.jsoup.Jsoup;importorg.jsoup.nodes.Document;importorg.jsoup.select.Elements;public classWrom {//定义爬取网站，方便获取url所以定义两个

static String baseurl = "http://www.acgwallpaper.com";static String geturl = "http://www.acgwallpaper.com/";static String filepath = "D:\\testwrom";//定义图片存放的文件夹

static int j = 0;//计数用的变量

public static voidmain(String[] args) {

System.out.println("初始下载页面：" +geturl);

String html= getHtml(geturl); //从url解析得到html的body

List href_list = getNextUrl(html); //将href和图片所在网址构成新的url存在链表list

for