<dependency>
<groupId>org.ops4j.pax.carrot</groupId>
<artifactId>pax-carrot-html</artifactId>
<version>1.0.0</version>
</dependency>
CarrotEngine engine = new CarrotEngine();
engine.start();
HTMLParser parser = new HTMLParser();
HTMLDocument document = parser.parse(new File("example.html"));
List<HTMLLink> links = document.getLinks();
for (HTMLLink link : links) {
System.out.println(link.getHref());
}
try {
} catch (CarrotException e) {
e.printStackTrace();
}
CarrotConfiguration config = new CarrotConfiguration();
config.setOption(CarrotOptions.IGNORE_CASE, true);
config.setOption(CarrotOptions.MAX_ERRORS, 100);
config.setOption(CarrotOptions.USE_XHTML_MODE, false);
CarrotEngine engine = new CarrotEngine(config);
