如何使用 Java 爬取嵌入页面中的图片验证码？

import java.io.FileOutputStream;
import java.io.IOException;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class RetrieveEmbeddedImage {

    public static void main(String[] args) {
        try {
            // 解析 HTML 获取验证码 URL
            String html = getHtml();
            Pattern pattern = Pattern.compile("(/public/v4/common/control/page/image\.jsp\?date=" + ".*)");
            Matcher matcher = pattern.matcher(html);
            String imageUrl = "";
            if (matcher.find()) {
                imageUrl = matcher.group(1);
            } else {
                throw new Exception("无法找到验证码 URL");
            }

            // 获取验证码图像
            URL url = new URL("http://jx.189.cn" + imageUrl);
            HttpURLConnection connection = (HttpURLConnection) url.openConnection();
            connection.setRequestProperty("Cookie", "[YOUR_COOKIE_HERE]");  // 将 Cookie 设置为目标网站的 Cookie
            byte[] imageData = connection.getInputStream().readAllBytes();

            // 将图像保存到文件
            FileOutputStream fos = new FileOutputStream("captcha.jpg");
            fos.write(imageData);
            fos.close();

            System.out.println("验证码图像已保存为 captcha.jpg。");
        } catch (MalformedURLException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    // 获取包含验证码的页面的 HTML
    private static String getHtml() {
        // [在此处实现获取 HTML 的逻辑]
        return "";
    }
}