<dependency>
<groupId>net.sf.jtidy</groupId>
<artifactId>jtidy</artifactId>
<version>8.0.1</version>
</dependency>
import org.w3c.tidy.Tidy;
import java.io.*;
public class DataCleaningExample {
public static void main(String[] args) {
String html = "<html><head><title>Example</title></head><body><h1>Hello, world!</h1></body></html>";
Tidy tidy = new Tidy();
InputStream inputStream = new ByteArrayInputStream(html.getBytes());
tidy.setInputStream(inputStream);
StringWriter writer = new StringWriter();
tidy.setPrintWriter(writer);
tidy.cleanAndParse();
String cleanedHtml = writer.toString();
System.out.println(cleanedHtml);
}
}