<dependency> <groupId>org.ops4j.pax.swissbox</groupId> <artifactId>pax-swissbox-core</artifactId> <version>1.8.1</version> </dependency> import org.ops4j.pax.carrot.maven.CarrotRunner; import org.ops4j.pax.carrot.runner.CarrotRunnerFactory; import org.w3c.dom.Element; import org.w3c.dom.NodeList; public class HTMLParserExample { public static void main(String[] args) { CarrotRunner runner = CarrotRunnerFactory.create("/path/to/html/document.html"); Element rootElement = runner.getDomDocument().getDocumentElement(); NodeList links = rootElement.getElementsByTagName("a"); for (int i = 0; i < links.getLength(); i++) { Element linkElement = (Element) links.item(i); String href = linkElement.getAttribute("href"); System.out.println(href); } } }


上一篇:
下一篇:
切换中文