使用Java将HTML文件读取到DOM树

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

implementation 'org.jsoup:jsoup:1.14.3'

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;

public class JsoupExample {
    public static void main(String[] args) {
        String url = "https://example.com";
        try {
            Document document = Jsoup.connect(url).get();
            System.out.println(document.toString());
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}