JSOUP爬取4K高清壁纸

jsoup jar包 1.11.2

链接: https://pan.baidu.com/s/1pe3-r5_YB-pGEsosfRLbsA?pwd=41w5

提取码: 41w5

效果：

代码：

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;

public static void main(String[] args) {
try {

        String parentUrl = "XXXX"; 

        URL indexUrl = new URL("XXXX");

        Document indexHtml = Jsoup.parse(indexUrl, 10000);
        //获取分类节点
        Elements fenleis = indexHtml.getElementsByClass("classify clearfix");

        for (Element fenLei : fenleis) {
            Elements fenLeiA = fenLei.select("a");
            for (int i = 0; i < fenLeiA.size(); i++) {
                Element fenLeiA1 = fenLeiA.get(i);
                Elements a1 = fenLeiA1.select("a");
                String fenLeiHref = a1.select("a").attr("href");
                String fenLeiName = a1.select("a").attr("title");
                try {
                    //本地盘符
                    File file = new File("E:\\worm\\" + fenLeiName + "\\1.txt");
                    //创建文件夹
                    file.mkdirs();
                } catch (Exception e) {

                }

                //每个类别爬取10页
                for (int j = 1; j < 10; j++) {
                    URL fenLeiIndexUrl = new URL("https://xxxxxxx");
                    if (j != 1) {//第二页开始的url规则
                        fenLeiIndexUrl = new URL(parentUrl + fenLeiHref + "index_" + j + ".html");
                    } else {
                        fenLeiIndexUrl = new URL(parentUrl + fenLeiHref + "index.html");
                    }
                    Document doc = Jsoup.parse(fenLeiIndexUrl, 10000);
                    Elements clearfixList = doc.getElementsByClass("clearfix");
                    for (Element e : clearfixList) {
                        Elements lis = e.getElementsByTag("li");
                        for (Element li : lis) {
                            Elements a = li.select("a");
                            String href = a.select("a").attr("href");
                            URL url2 = new URL(parentUrl + href);
                            Document doc1 = Jsoup.parse(url2, 10000);
                            Elements img = doc1.getElementsByClass("photo-pic");
                            Element first = img.first();
                            Elements imgUrla = first.select("img");
                            String imgsrc = imgUrla.select("img").attr("src");
                            String title = imgUrla.select("img").attr("title");
                            title = title.replace(" ", "");
                             //文件名过滤
                            title = title.replaceAll("[*]", "");
                            title = title.replaceAll(" ", "");
                            title = title.replaceAll("[?]", "");
                            title = title.replaceAll("[|]", "");
                            download(parentUrl + imgsrc, fenLeiName, title);
                        }
                    }
                }
            }

        }


    } catch (Exception e) {
        e.printStackTrace();
    }

}

public static void download(String urlString, String dirsName, String imgName) throws Exception {

    // 构造URL

    URL url = new URL(urlString);

    // 打开连接

    URLConnection con = url.openConnection();

    // 输入流

    InputStream is = con.getInputStream();

    // 1K的数据缓冲

    byte[] bs = new byte[1024];

    // 读取到的数据长度

    int len;

    // 输出的文件流

    String filename = "E:\\worm\\" + dirsName + "\\" + imgName + ".jpg";  //下载路径及下载图片名称

    File file = new File(filename);

    FileOutputStream os = new FileOutputStream(file, true);

    // 开始读取

    while ((len = is.read(bs)) != -1) {

        os.write(bs, 0, len);

    }


    // 完毕，关闭所有链接

    os.close();

    is.close();

}