java抓取页面内容，代码和详解步骤

package com.xgb.task;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;

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


/**
 * @Program: verify
 * @Description: 拉取网页内容
 * @Author: Mr.Lidong
 * @CreateDate: 2022-08-09 17:11
 **/
public class Test {

    public static void main(String[] args) {
        String url = "https://lanzhou.11467.com/xigu/pn2";
        String content = getHtml(url);//返回整个页面的数据 （String类型）
        Document doc = Jsoup.parse(content);//将字符内容解析成一个Document类（Jsoup解析html）
        Elements links=doc.select(".f_l");//找到页面带有onclick属性的a元素
        for( Element element : links ){
            System.out.println(element);//带有onclick属性的a元素
            System.out.println("==============================================");
            System.out.println("公司名称："+element.select("a").text());
            System.out.println(element.select("div>div").eq(0).text());
            System.out.println(element.select("div>div").eq(1).text());
            System.out.println(element.select("div>span").eq(0).text());
            System.out.println(element.select("div>span").eq(1).text());
            System.out.println("==============================================");

        }
    }


    public static String getHtml(String url){
        BufferedReader in = null;
        //定义字符缓冲区
        StringBuffer stringBuffer = new StringBuffer();
        try {
            //创建URL地址
            URL net = new URL(url);
            //打开URL
            URLConnection connection = net.openConnection();
            //开启输入/输出。注意：请求网络需要传参必须开启
            //connection.setDoOutput(true);
            //connection.setDoInput(true);
            //实例化字符缓冲输入流来读取数据
            in = new BufferedReader(
                    new InputStreamReader(connection.getInputStream(),"utf-8")
            );
            String line = null;
            while ((line = in.readLine())!=null) {
                //用stringBuffer拼接数据
                stringBuffer.append(line);
            }
        } catch (Exception e) {
            e.printStackTrace();
            System.out.println("网络超时");
        } finally {
            try {
                in.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        return stringBuffer.toString();
    }

}

 pom依赖：

<dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.11.2</version>
        </dependency>