Get the on-screen location of web page with Selenium WebDriver

Question

Is there a way to get the on-screen coordinates of HTML window (page body) with Selenium WebDriver?

Answer 1

The posted code by Zechtitus is amazing, I tried it under IE11 and Chrome Version 39.0.2171.95 m and it worked like a charm. Although I had to pass the real object of IWebDriver instead of using WrappedDriver because it doesn't work with Chrome. Just for your info, I have Win 7 ultimate x64 and using Selenium WebDriver 2.44. this is the code that I took it from Zechtitus and modified it:

    public static Rectangle GetAbsCoordinates(IWebDriver driver, IWebElement element)
    {
        var handle = GetIntPtrHandle(driver);
        var ae = AutomationElement.FromHandle(handle);
        AutomationElement doc = null;
        var caps = ((RemoteWebDriver)driver).Capabilities;
        var browserName = caps.BrowserName;
        switch (browserName)
        {
            case "safari":
                var conditions = (new AndCondition(new PropertyCondition(AutomationElement.ControlTypeProperty, ControlType.Pane),
                    new PropertyCondition(AutomationElement.ClassNameProperty, "SearchableWebView")));
                doc = ae.FindFirst(TreeScope.Descendants, conditions);
                break;
            case "firefox":
                doc = ae.FindFirst(TreeScope.Descendants, new PropertyCondition(AutomationElement.ControlTypeProperty, ControlType.Document));
                break;
            case "chrome":
                doc = ae.FindFirst(TreeScope.Descendants, new PropertyCondition(AutomationElement.NameProperty, "Chrome Legacy Window"));
                if (doc == null)
                {
                    doc = ae.FindFirst(TreeScope.Descendants, new PropertyCondition(AutomationElement.NameProperty, "Google Chrome"));
                    if (doc == null)
                        throw new Exception("unable to find element containing browser window");
                    doc = doc.FindFirst(TreeScope.Descendants, new PropertyCondition(AutomationElement.ControlTypeProperty, ControlType.Document));
                }
                break;
            case "internet explorer":
                doc = ae.FindFirst(TreeScope.Descendants, new AndCondition(new PropertyCondition(AutomationElement.ControlTypeProperty, ControlType.Pane),
                    new PropertyCondition(AutomationElement.ClassNameProperty, "TabWindowClass")));
                break;
        }

        if (doc == null)
            throw new Exception("unable to find element containing browser window");

        var iWinLeft = (int)doc.Current.BoundingRectangle.Left;
        var iWinTop = (int)doc.Current.BoundingRectangle.Top;

        var coords = ((ILocatable)element).Coordinates;
        var rect = new Rectangle(iWinLeft + coords.LocationInDom.X, iWinTop + coords.LocationInDom.Y, element.Size.Width, element.Size.Height);
        return rect;
    }

    public static IntPtr GetIntPtrHandle(this IWebDriver driver, int timeoutSeconds = 20)
    {
        var end = DateTime.Now.AddSeconds(timeoutSeconds);
        while (DateTime.Now < end)
        {
            // Searching by AutomationElement is a bit faster (can filter by children only)
            var ele = AutomationElement.RootElement;
            foreach (AutomationElement child in ele.FindAll(TreeScope.Children, Condition.TrueCondition))
            {
                if (!child.Current.Name.Contains(driver.Title)) continue;
                return new IntPtr(child.Current.NativeWindowHandle); ;
            }
        }
        return IntPtr.Zero;
    }

and I used it like this:

Rectangle recView = GetAbsCoordinates(MyWebDriverObj, myIWebElementObj);

the correct X, Y are then stored in recView.X and recView.Y As I said, it's working for me for both IE11 and Chrome. Good luck