import org.ccil.cowan.tagsoup.Parser;
import org.w3c.dom.Document;
import org.xml.sax.InputSource;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
public class TagSoupExample {
public static void main(String[] args) throws Exception {
Parser parser = new Parser();
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
DocumentBuilder builder = factory.newDocumentBuilder();
Document doc = builder.parse(new InputSource(parser.getStream("http://example.com")));
System.out.println("Title: " + doc.getElementsByTagName("title").item(0).getTextContent());
NodeList links = doc.getElementsByTagName("a");
for (int i = 0; i < links.getLength(); i++) {
Element link = (Element) links.item(i);
System.out.println("Link: " + link.getAttribute("href"));
}
}
}
<dependencies>
<dependency>
<groupId>org.ccil.cowan.tagsoup</groupId>
<artifactId>tagsoup</artifactId>
<version>1.2</version>
</dependency>
</dependencies>
