从Java中的网页中提取HTML

import java.net.*;
import java.io.*;

public class WebCrawler {
    public static void main(String[] args) throws Exception {
        String url = "https://www.example.com";
        URLConnection connection = new URL(url).openConnection();
        connection.setRequestProperty("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36");
        connection.setDoOutput(true);
        connection.getInputStream();
        BufferedReader in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
        String inputLine;
        StringBuffer response = new StringBuffer();
        while ((inputLine = in.readLine()) != null) {
            response.append(inputLine);
        }
        in.close();
        System.out.println(response.toString());
    }
}