<dependency> <groupId>net.htmlparser.jer</groupId> <artifactId>htmlparser</artifactId> <version>2.1</version> </dependency> Parser parser = new Parser(); NodeIterator iterator = parser.elements(); while (iterator.hasMoreNodes()) { Node node = iterator.nextNode(); if (node instanceof TextNode) { TextNode textNode = (TextNode) node; System.out.println(textNode.getText()); } } Node[] nodes = parser.extractAllNodesThatMatch(new TagNameFilter("a")).toNodeArray(); Node divNode = parser.parse(new CssSelectorNodeFilter("div.my-class")).elementAt(0); System.out.println(divNode.getText()); URL url = new URL("http://example.com"); InputStreamReader isr = new InputStreamReader(url.openStream(), "UTF-8"); parser.setInputHTML(isr); NodeList nodeList = parser.parse(null);