/**
* Run this method to start the crawl.
*
* @throws IOException when the output folder cannot be created or emptied.
*/
public static void main(String[] args) throws IOException {
CrawljaxConfigurationBuilder builder = CrawljaxConfiguration.builderFor(URL);
builder.crawlRules().insertRandomDataInInputForms(false);
// We are going to use the WebScarab proxy plugin
WebScarabProxyPlugin proxyPlugin = new WebScarabProxyPlugin();
// Provide the JS file to be inserted
proxyPlugin.addPlugin(new JSInjectorProxyAddon(new File("foo.js")));
builder.addPlugin(proxyPlugin);
// Configure the proxy to use the port 8084 (you can change this of course)
builder.setProxyConfig(ProxyConfiguration.manualProxyOn("127.0.0.1", 8084));
// click these elements
builder.crawlRules().clickDefaultElements();
builder.crawlRules().click("div").withAttribute("class", "clickable");
builder.setMaximumStates(4);
// Set timeouts
builder.crawlRules().waitAfterReloadUrl(WAIT_TIME_AFTER_RELOAD, TimeUnit.MILLISECONDS);
builder.crawlRules().waitAfterEvent(WAIT_TIME_AFTER_EVENT, TimeUnit.MILLISECONDS);
builder.setBrowserConfig(new BrowserConfiguration(BrowserType.firefox, 1));
CrawljaxRunner crawljax = new CrawljaxRunner(builder.build());
crawljax.call();
}
public void stop() {
if (crawljax != null) {
crawljax.stop();
}
stopServer();
}
public void start() {
crawljax = new CrawljaxRunner(getCrawljaxBuilder());
crawljax.call();
stopServer();
}