Skip to content

Can not load web page completely #485

Description

@pangzhaiwei

Hi, when I use htmlunit to load this url
https://view.inews.qq.com/a/20220607A09ES500?tbkt=D&uid=
It throw an exception, and I can not get the full web page html. the exception is below :

Exception class=[net.sourceforge.htmlunit.corejs.javascript.JavaScriptException]
com.gargoylesoftware.htmlunit.ScriptException: Error: Minified React error #327; visit https://reactjs.org/docs/error-decoder.html?invariant=327 for the full message or use the non-minified dev environment for full errors and additional helpful warnings. (https://mat1.gtimg.com/qqcdn/news-share/js/react.production.min.js#22)
	at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$HtmlUnitContextAction.run(JavaScriptEngine.java:996)
	at net.sourceforge.htmlunit.corejs.javascript.Context.call(Context.java:590)
	at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.call(ContextFactory.java:484)
	at com.gargoylesoftware.htmlunit.javascript.HtmlUnitContextFactory.callSecured(HtmlUnitContextFactory.java:349)
	at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.callFunction(JavaScriptEngine.java:923)
	at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.callFunction(JavaScriptEngine.java:895)
	at com.gargoylesoftware.htmlunit.html.HtmlPage.executeJavaScriptFunction(HtmlPage.java:2613)
	at com.gargoylesoftware.htmlunit.html.HtmlPage.executeJavaScriptFunction(HtmlPage.java:2606)
	at com.gargoylesoftware.htmlunit.javascript.host.event.EventListenersContainer.executeEventListeners(EventListenersContainer.java:342)
	at com.gargoylesoftware.htmlunit.javascript.host.event.EventListenersContainer.executeAtTargetListeners(EventListenersContainer.java:379)
	at com.gargoylesoftware.htmlunit.javascript.host.event.EventTarget.fireEvent(EventTarget.java:173)
	at com.gargoylesoftware.htmlunit.javascript.host.event.EventTarget.dispatchEvent(EventTarget.java:277)
	at com.gargoylesoftware.htmlunit.javascript.host.MessagePort$1.lambda$execute$0(MessagePort.java:115)
	at net.sourceforge.htmlunit.corejs.javascript.Context.call(Context.java:590)
	at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.call(ContextFactory.java:484)
	at com.gargoylesoftware.htmlunit.javascript.host.MessagePort$1.execute(MessagePort.java:115)
	at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.doProcessPostponedActions(JavaScriptEngine.java:1044)
	at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$HtmlUnitContextAction.run(JavaScriptEngine.java:991)
	at net.sourceforge.htmlunit.corejs.javascript.Context.call(Context.java:590)
	at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.call(ContextFactory.java:484)
	at com.gargoylesoftware.htmlunit.javascript.HtmlUnitContextFactory.callSecured(HtmlUnitContextFactory.java:349)
	at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.callFunction(JavaScriptEngine.java:923)
	at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.callFunction(JavaScriptEngine.java:895)
	at com.gargoylesoftware.htmlunit.html.HtmlPage.executeJavaScriptFunction(HtmlPage.java:2613)
	at com.gargoylesoftware.htmlunit.html.HtmlPage.executeJavaScriptFunction(HtmlPage.java:2606)
	at com.gargoylesoftware.htmlunit.javascript.host.event.EventListenersContainer.executeEventListeners(EventListenersContainer.java:342)
	at com.gargoylesoftware.htmlunit.javascript.host.event.EventListenersContainer.executeAtTargetListeners(EventListenersContainer.java:379)
	at com.gargoylesoftware.htmlunit.javascript.host.event.EventTarget.fireEvent(EventTarget.java:173)
	at com.gargoylesoftware.htmlunit.html.DomElement.lambda$fireEvent$0(DomElement.java:1490)
	at net.sourceforge.htmlunit.corejs.javascript.Context.call(Context.java:590)
	at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.call(ContextFactory.java:484)
	at com.gargoylesoftware.htmlunit.javascript.HtmlUnitContextFactory.callSecured(HtmlUnitContextFactory.java:349)
	at com.gargoylesoftware.htmlunit.html.DomElement.fireEvent(DomElement.java:1490)
	at com.gargoylesoftware.htmlunit.html.HtmlImage.fireEvent(HtmlImage.java:949)
	at com.gargoylesoftware.htmlunit.html.HtmlImage.doOnLoad(HtmlImage.java:319)
	at com.gargoylesoftware.htmlunit.html.HtmlImage.setAttributeNS(HtmlImage.java:171)
	at com.gargoylesoftware.htmlunit.html.DomElement.setAttributeNS(DomElement.java:498)
	at com.gargoylesoftware.htmlunit.html.DomElement.setAttribute(DomElement.java:485)
	at com.gargoylesoftware.htmlunit.javascript.host.html.HTMLElement.setAttribute(HTMLElement.java:552)
	at sun.reflect.GeneratedMethodAccessor14.invoke(Unknown Source)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at net.sourceforge.htmlunit.corejs.javascript.MemberBox.invoke(MemberBox.java:215)
	at net.sourceforge.htmlunit.corejs.javascript.FunctionObject.call(FunctionObject.java:405)
	at net.sourceforge.htmlunit.corejs.javascript.Interpreter.interpretLoop(Interpreter.java:1876)
	at net.sourceforge.htmlunit.corejs.javascript.Interpreter.interpret(Interpreter.java:1053)
	at net.sourceforge.htmlunit.corejs.javascript.InterpretedFunction.call(InterpretedFunction.java:89)
	at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.doTopCall(ContextFactory.java:392)
	at com.gargoylesoftware.htmlunit.javascript.HtmlUnitContextFactory.doTopCall(HtmlUnitContextFactory.java:335)
	at net.sourceforge.htmlunit.corejs.javascript.ScriptRuntime.doTopCall(ScriptRuntime.java:3916)
	at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$3.doRun(JavaScriptEngine.java:916)
	at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$HtmlUnitContextAction.run(JavaScriptEngine.java:979)
	at net.sourceforge.htmlunit.corejs.javascript.Context.call(Context.java:590)
	at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.call(ContextFactory.java:484)
	at com.gargoylesoftware.htmlunit.javascript.HtmlUnitContextFactory.callSecured(HtmlUnitContextFactory.java:349)
	at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.callFunction(JavaScriptEngine.java:923)
	at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine.callFunction(JavaScriptEngine.java:895)
	at com.gargoylesoftware.htmlunit.html.HtmlPage.executeJavaScriptFunction(HtmlPage.java:2613)
	at com.gargoylesoftware.htmlunit.html.HtmlPage.executeJavaScriptFunction(HtmlPage.java:2606)
	at com.gargoylesoftware.htmlunit.javascript.host.event.EventListenersContainer.executeEventListeners(EventListenersContainer.java:342)
	at com.gargoylesoftware.htmlunit.javascript.host.event.EventListenersContainer.executeAtTargetListeners(EventListenersContainer.java:379)
	at com.gargoylesoftware.htmlunit.javascript.host.event.EventTarget.fireEvent(EventTarget.java:173)
	at com.gargoylesoftware.htmlunit.html.HtmlPage.lambda$executeEventHandlersIfNeeded$1(HtmlPage.java:1292)
	at net.sourceforge.htmlunit.corejs.javascript.Context.call(Context.java:590)
	at net.sourceforge.htmlunit.corejs.javascript.ContextFactory.call(ContextFactory.java:484)
	at com.gargoylesoftware.htmlunit.javascript.HtmlUnitContextFactory.callSecured(HtmlUnitContextFactory.java:349)
	at com.gargoylesoftware.htmlunit.html.HtmlPage.executeEventHandlersIfNeeded(HtmlPage.java:1292)
	at com.gargoylesoftware.htmlunit.html.HtmlPage.initialize(HtmlPage.java:322)
	at com.gargoylesoftware.htmlunit.WebClient.loadWebResponseInto(WebClient.java:708)
	at com.gargoylesoftware.htmlunit.WebClient.loadWebResponseInto(WebClient.java:590)
	at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:508)
	at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:415)
	at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:553)
	at com.gargoylesoftware.htmlunit.WebClient.getPage(WebClient.java:535)
	at org.example.Main.main(Main.java:10)
Caused by: net.sourceforge.htmlunit.corejs.javascript.JavaScriptException: Error: Minified React error #327; visit https://reactjs.org/docs/error-decoder.html?invariant=327 for the full message or use the non-minified dev environment for full errors and additional helpful warnings. (https://mat1.gtimg.com/qqcdn/news-share/js/react.production.min.js#22)
	at net.sourceforge.htmlunit.corejs.javascript.Interpreter.interpretLoop(Interpreter.java:1300)
	at net.sourceforge.htmlunit.corejs.javascript.Interpreter.interpret(Interpreter.java:1053)
	at net.sourceforge.htmlunit.corejs.javascript.InterpretedFunction.call(InterpretedFunction.java:89)
	at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$3.doRun(JavaScriptEngine.java:914)
	at com.gargoylesoftware.htmlunit.javascript.JavaScriptEngine$HtmlUnitContextAction.run(JavaScriptEngine.java:979)
	... 74 more
JavaScriptException value = Error: Minified React error #327; visit https://reactjs.org/docs/error-decoder.html?invariant=327 for the full message or use the non-minified dev environment for full errors and additional helpful warnings.
== CALLING JAVASCRIPT ==
  function () {
      if (null !== J) {
          var a = t();
          ta = a + sa;
          try {
              J(!0, a) ? X.postMessage(null) : (I = !1, J = null);
          }
          catch (b) {
              throw X.postMessage(null), b;
          }
      } else {
          I = !1;
      }
  }
======= EXCEPTION END ========

And the version of htmlunit which I use is 2.62.0. My test source code is below:

public class Main {

    public static void main(String[] args) throws Exception {
        WebClient webClient = webClient();
        HtmlPage page = webClient.getPage("https://view.inews.qq.com/a/20220607A09ES500?tbkt=D&uid=");
        synchronized (page) {
            page.wait(5000);
        }
        System.out.println(page.asXml());
    }

    private static WebClient webClient() {
        WebClient webClient = new WebClient(BrowserVersion.CHROME);
        webClient.getOptions().setTimeout(50000);
        webClient.getOptions().setRedirectEnabled(true);
        webClient.getOptions().setThrowExceptionOnScriptError(false);
        webClient.getOptions().setThrowExceptionOnFailingStatusCode(false);
        webClient.getOptions().setUseInsecureSSL(true);
        webClient.getOptions().setJavaScriptEnabled(true);
        webClient.getOptions().setCssEnabled(false);
        webClient.getCookieManager().setCookiesEnabled(true);
        webClient.waitForBackgroundJavaScript(30000);
        webClient.setAjaxController(new NicelyResynchronizingAjaxController());
        return webClient;
    }
}

Has anyone encountered a similar problem?

No activity

Activity on this issue will appear here.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions