How can i convert a JAVAFX Webvie to Parsing JSOUP? - javafx

Question

I want to convert a Webseite loaded by javaFX to JSOUP.
p
ublic class database {
public static ArrayList<String> database = new ArrayList<String>();
public static ArrayList<Integer> laenge = new ArrayList<Integer>();
public static ArrayList<Integer> tiefe = new ArrayList<Integer>();
public static void main(String[] args) throws IOException, JSONException {
// TODO Auto-generated method stub
WebView browser = new WebView();
WebEngine webEngine = browser.getEngine();
String url = "http://www.google.com";
webEngine.load(url);
//get w3c document from webEngine
org.w3c.dom.Document w3cDocument = webEngine.getDocument();
// use jsoup helper methods to convert it to string
String htm = new org.jsoup.helper.W3CDom().asString(webEngine.getDocument());
// create jsoup document by parsing html
Document doc = Jsoup.parse(url, htm);
//Document doc = Jsoup.connect("http://ttp-schreiber.de/Mathematik/index2.html").get();
Element title = doc.body();
/*WebView browser = new WebView();
WebEngine webEngine = browser.getEngine();
webEngine.load("http://ttp-schreiber.de/Mathematik/index2.html");
*/
Elements html = doc.select("html");
Controller(html);
// System.out.println("+--+"+deeper(next(html,html.last()))[0][0]);
databasesafe();
}
I get these Error Message:
Exception in thread "main" java.lang.ExceptionInInitializerError
How is the misttage?
ETC I have the example from here:
How to parse html from javafx webview and transfer this data to Jsoup Document?
In these line ist .get wrong: String html = new org.jsoup.helper.W3CDom().asString(webEngine.get);

Answer 1

This duplicate is probably your best bet. After a page is loaded in WebView, use a Transformer to get its HTML. Then use that HTML string in Jsoup. I am not sure if you will get your expected outcome.
import java.io.File;
import java.nio.file.Files;
import javafx.application.Application;
import javafx.concurrent.Worker;
import javafx.scene.Scene;
import javafx.scene.layout.StackPane;
import javafx.scene.web.WebEngine;
import javafx.scene.web.WebView;
import javafx.stage.Stage;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import org.jsoup.Jsoup;
import org.w3c.dom.Document;
//import org.jsoup.nodes.Document;
public class App extends Application
{
org.jsoup.nodes.Document jsoupDocument;
#Override
public void start(Stage stage)
{
String url = "http://www.google.com";
WebView webview = new WebView();
final WebEngine webengine = webview.getEngine();
webengine.getLoadWorker().stateProperty().addListener((ov, oldState, newState) ->
{
if (newState == Worker.State.SUCCEEDED) {
Document doc = webengine.getDocument();
try {
Transformer transformer = TransformerFactory.newInstance().newTransformer();
transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "no");
transformer.setOutputProperty(OutputKeys.METHOD, "xml");
transformer.setOutputProperty(OutputKeys.INDENT, "yes");
transformer.setOutputProperty(OutputKeys.ENCODING, "UTF-8");
transformer.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "4");
File file = new File("results.txt");
file.createNewFile();
StreamResult results = new StreamResult(file);
transformer.transform(new DOMSource(doc), results);
String fileContent = Files.readString(file.toPath());
jsoupDocument = Jsoup.parse(fileContent);
System.out.println(jsoupDocument.toString());
} catch (Exception ex) {
ex.printStackTrace();
}
}
});
webengine.load("http://stackoverflow.com");
StackPane root = new StackPane(webview);
stage.setTitle("Hello Drag And Drop");
Scene scene = new Scene(root, 400, 200);
stage.setScene(scene);
stage.show();
}
public static void main(String[] args)
{
Application.launch(args);
}
}