<dependency>
<groupId>org.htmlparser</groupId>
<artifactId>htmlparser</artifactId>
<version>2.1</version>
</dependency>
import org.htmlparser.Node;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.util.NodeList;
public class HTMLParserExample {
public static void main(String[] args) {
try {
Parser parser = new Parser("http://example.com/page.html");
NodeClassFilter filter = new NodeClassFilter(ElementTag.class);
NodeList nodeList = parser.extractAllNodesThatMatch(filter);
for (int i = 0; i < nodeList.size(); i++) {
Node node = nodeList.elementAt(i);
System.out.println(node.getText());
}
} catch (Exception e) {
e.printStackTrace();
}
}
}
