<dependency>
<groupId>org.ops4j.pax.carrot</groupId>
<artifactId>pax-carrot-html-parser</artifactId>
<version>1.3.0</version>
</dependency>
import org.ops4j.pax.carrot.api.Interpreter;
import org.ops4j.pax.carrot.api.ParserResult;
import org.ops4j.pax.carrot.html.parser.HtmlDomInterpreter;
import org.ops4j.pax.carrot.html.parser.HtmlParser;
import java.io.IOException;
import java.io.StringReader;
public class WebPageScraper {
public static void main(String[] args) {
String html = "<html><head><title>Example</title></head><body><h1>My Web Page</h1><p>Welcome to my website!</p></body></html>";
HtmlParser htmlParser = new HtmlParser();
Interpreter interpreter = new HtmlDomInterpreter();
try (ParserResult result = htmlParser.parse(htmlParser.createContext(), new StringReader(html), interpreter)) {
String title = result.getPath("head > title").getText();
String paragraph = result.getPath("body > p").getText();
System.out.println("Title: " + title);
System.out.println("Paragraph: " + paragraph);
} catch (IOException e) {
e.printStackTrace();
}
}
}
