Java获取html页面的动态响应数据

引入依赖

<dependency>
	<groupId>org.jsoup</groupId>
	<artifactId>jsoup</artifactId>
	<version>1.14.3</version>
</dependency>

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;

try {
    URL url = new URL("html地址url");
    URLConnection connection =url.openConnection();
    connection.setRequestProperty("User-Agent","Mozilla/5.0");
    connection.setConnectTimeout(5000);
    connection.setReadTimeout(5000);

    InputStream inputStream = connection.getInputStream();
    BufferedReader reader = new BufferedReader(new
    InputStreamReader(inputStream));
    String line;
    StringBuilder htmlContent = new StringBuilder();
    System.out.println("----------"+url);
    while((line =reader.readLine())!= null) {
        htmlContent.append(line);
    }
    Document doc = Jsoup.parse(htmlContent.toString());
    // 假设要获取id为aaa的div元素下数据，根据 id 定位指定的 div 元素
    Element unitInfoDiv = doc.getElementById("aaa");

    // 如果找到了对应 id 的 div 元素
    if (unitInfoDiv != null) {
        // 获取 div 元素下的所有文本内容（包括子元素）
        String divContent = unitInfoDiv.text();
        // 切分数据
        String[] parts = divContent.split("\\s+");

        // 提取所需信息
        String label1 = "";
        String label2 = "";
        String label3 = "";

        for (int i = 0; i < parts.length - 1; i++) {
            if (parts[i].equals("label1")) {
                label1 = parts[i + 1];
            } else if (parts[i].equals("label2")) {
                label2 = parts[i + 1];
            } else if (parts[i].equals("label3")) {
                label3 = parts[i + 1];
            }
        }
        // 输出提取的信息
        System.out.println("label1: " + label1);
        System.out.println("label2: " + label2);
        System.out.println("label3: " + label3);
    }
    reader.close();
}catch(Exception e){
    e.printStackTrace();
}