<dependency> <groupId>org.ops4j.pax.carrot</groupId> <artifactId>pax-carrot-htmlparser</artifactId> <version>1.0.0</version> </dependency> HTMLParser parser = new HTMLParser(); File file = new File("path/to/html/file.html"); HTMLDocument document = parser.parse(file); HTMLDocument document = parser.parse(htmlSource); HTMLElement element = document.getElementById("elementId"); String tagName = element.getTagName(); String attributeValue = element.getAttribute("attributeName"); String textContent = element.getTextContent(); ElementSelector selector = new XPathElementSelector("//div[@class='content']"); List<HTMLElement> elements = selector.selectElements(document); for (HTMLElement element : elements) { }