import java.io.IOException;
import java.net.MalformedURLException;
import java.util.List;
import com.gargoylesoftware.htmlunit.FailingHttpStatusCodeException;
import com.gargoylesoftware.htmlunit.WebClient;
import com.gargoylesoftware.htmlunit.html.HtmlAnchor;
import com.gargoylesoftware.htmlunit.html.HtmlButton;
import com.gargoylesoftware.htmlunit.html.HtmlForm;
import com.gargoylesoftware.htmlunit.html.HtmlPage;
import com.gargoylesoftware.htmlunit.html.HtmlTextInput;
public class YoutubeBot {
private static final String YOUTUBE = "http://www.youtube.com";
public static void main(String[] args) throws FailingHttpStatusCodeException, MalformedURLException, IOException {
WebClient webClient = new WebClient();
webClient.setThrowExceptionOnScriptError(false);
// This is equivalent to typing youtube.com to the adress bar of browser
HtmlPage currentPage = webClient.getPage("http://www.youtube.com/results?search_type=videos&search_query=official+music+video&search_sort=video_date_uploaded&suggested_categories=10%2C24&uni=3");
// Get form where submit button is located
HtmlForm searchForm = (HtmlForm) currentPage.getElementById("masthead-search");
// Get the input field.
HtmlTextInput searchInput = (HtmlTextInput) currentPage.getElementById("masthead-search-term");
// Insert the search term.
searchInput.setText("java");
// Workaround: create a 'fake' button and add it to the form.
HtmlButton submitButton = (HtmlButton) currentPage.createElement("button");
submitButton.setAttribute("type", "submit");
searchForm.appendChild(submitButton);
//Workaround: use the reference to the button to submit the form.
HtmlPage newPage = submitButton.click();
//Find all links on page with given class
final List<HtmlAnchor> listLinks = (List<HtmlAnchor>) currentPage.getByXPath("//a[@class='ux-thumb-wrap result-item-thumb']");
//Print all links to console
for (int i=0; i<listLinks.size(); i++)
System.out.println(YOUTUBE + listLinks.get(i).getAttribute("href"));
}
}
This code is working but I just want to sort youtube clips for example by upload date. How to do this with HtmlUnit? I have to click on filter, this should load content by ajax request and then I should click on "Upload date" link. I just don't know this first step, to load ajax content. Is this possible with HtmlUnit?
This worked for me. Set this
webClient.setAjaxController(new NicelyResynchronizingAjaxController());
This would cause all ajax calls to be synchronous.
This is how I setup my WebClient object
WebClient webClient = new WebClient(BrowserVersion.CHROME);
webClient.getOptions().setJavaScriptEnabled(true);
webClient.getOptions().setCssEnabled(false);
webClient.getOptions().setUseInsecureSSL(true);
webClient.getOptions().setThrowExceptionOnFailingStatusCode(false);
webClient.getCookieManager().setCookiesEnabled(true);
webClient.setAjaxController(new NicelyResynchronizingAjaxController());
webClient.getOptions().setThrowExceptionOnScriptError(false);
webClient.getCookieManager().setCookiesEnabled(true);