在Java中读取网页中的HTML源代码时，某些字符不能正确显示

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

public class HtmlReader {
    public static void main(String[] args) throws IOException {
        URL url = new URL("http://example.com"); // 替换为你要读取的网页URL
        HttpURLConnection connection = (HttpURLConnection) url.openConnection();
        connection.setRequestMethod("GET");

        BufferedReader reader = new BufferedReader(new InputStreamReader(connection.getInputStream()));
        String line;
        StringBuilder html = new StringBuilder();
        while ((line = reader.readLine()) != null) {
            html.append(line);
        }
        reader.close();

        // 在这里对html进行处理，例如字符编码转换等
    }
}

import java.nio.charset.Charset;

// ...

// 在读取HTML源代码后，进行字符编码转换
String htmlString = html.toString();
byte[] htmlBytes = htmlString.getBytes(Charset.forName("ISO-8859-1")); // 替换为正确的字符编码
String decodedHtml = new String(htmlBytes, Charset.forName("UTF-8")); // 替换为正确的字符编码

// 现在，decodedHtml中的字符应该能够正确显示