Java hutools + jsoup 快速编写java爬虫

新建maven工程并添加依赖

<dependency>
   <groupId>cn.hutool</groupId>
   <artifactId>hutool-all</artifactId>
   <version>5.4.7</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.jsoup/jsoup -->
<dependency>
  <groupId>org.jsoup</groupId>
  <artifactId>jsoup</artifactId>
  <version>1.13.1</version>
</dependency>

确定需要爬取的页面

确定需要获取的数据（页面元素）

package com.crawler.img;


import cn.hutool.core.io.FileUtil;
import cn.hutool.http.HttpUtil;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class App {
    public static void main(String[] args) {
        String result1 = HttpUtil.get("https://www.mmonly.cc/mmtp/");

        Document document = Jsoup.parse(result1);

        Elements masonry_brick_ = document.select(".masonry_brick img");
        for (Element link : masonry_brick_) {
            String src = link.attr("src");
            System.out.println(src);
            HttpUtil.downloadFile(src, FileUtil.file(System.getProperty("user.dir")+"/src/main/resources/"));
        }

    }
}