import org.ops4j.pax.carrot.html.HTMLDocument;
import org.ops4j.pax.carrot.html.HTMLParser;
import org.ops4j.pax.carrot.html.Link;
import java.io.IOException;
import java.net.URL;
public class HTMLParserExample {
public static void main(String[] args) {
try {
URL url = new URL("http://example.com");
HTMLDocument document = HTMLParser.parse(url);
for (Link link : document.getLinks()) {
System.out.println("URL: " + link.getUrl());
System.out.println("Text: " + link.getText());
}
} catch (IOException e) {
e.printStackTrace();
}
}
}
<dependency>
<groupId>org.ops4j.pax.carrot</groupId>
<artifactId>pax-carrot-html</artifactId>
<version>2.4.0</version>
</dependency>
