Question

我想使用带有Selenium和ChromeDriver的C＃拍摄整页的屏幕截图。在这里：https://stackoverflow.com/a/45201692/5400125我找到了一个使用Java的示例。我正在尝试在C＃中实现这一目标，但是在第一次调用sendEvaluate时加载页面后出现了异常：

OpenQA.Selenium.WebDriverException：'没有这样的会话（驱动程序信息：chromedriver = 2.41.578737 （49da6702b16031c40d63e5618de03a32ff6c197e），platform = Windows NT 10.0.17134 x86_64）'

public class ChromeDriverEx : ChromeDriver
{
    public ChromeDriverEx(string chromeDriverDirectory, ChromeOptions options)
        : base(chromeDriverDirectory, options, RemoteWebDriver.DefaultCommandTimeout)
    {
        var addCmd = this.GetType().BaseType
            .GetMethod("AddCustomChromeCommand", BindingFlags.NonPublic | BindingFlags.Instance);
        addCmd.Invoke(this,
            new object[] {"sendCommand", "POST", "/session/:sessionId/chromium/send_command_and_get_result"});
    }

    public void GetFullScreenshot()
    {
        Object metrics = sendEvaluate(
            @"({" +
            "width: Math.max(window.innerWidth,document.body.scrollWidth,document.documentElement.scrollWidth)|0," +
            "height: Math.max(window.innerHeight,document.body.scrollHeight,document.documentElement.scrollHeight)|0," +
            "deviceScaleFactor: window.devicePixelRatio || 1," +
            "mobile: typeof window.orientation !== 'undefined'" +
            "})");
    }

    private object sendEvaluate(string script)
    {
        var response = sendCommand("Runtime.evaulate",
            new Dictionary<string, object> {{"returnByValue", true}, {"expression", script}});
        return response;
    }

    private object sendCommand(string cmd, object param)
    {
        var r = this.Execute("sendCommand", new Dictionary<string, object> {{"cmd", cmd}, {"params", param}});
        return r.Value;
    }
}

我这样称呼它：

 var opts = new ChromeOptions();
 opts.AddAdditionalCapability("useAutomationExtension", false);
 opts.AddArgument("disable-infobars");
 var driver = new ChromeDriverEx(".", opts);
 driver.Navigate().GoToUrl("https://stackoverflow.com/questions");
 driver.GetFullScreenshot();

我正在使用Chrome 68和ChromeDriver 2.41

Answer 1

此代码对我来说很好，可以创建apiVersion: v1 clusters: - cluster: api-version: v1 certificate-authority: /path/to/ca_chain.crt server: "https://my-kubernetes-cluster" ...的子类。请注意，以下代码是故意以非常非常冗长的样式编写的，以便清楚地说明解决方案的每一部分。根据一个人的编码风格和对强大错误处理的要求，可以轻松，简洁地编写它。此外，在将来的发行版中，将无需创建执行返回结果的DevTools命令的方法。这样的方法已经是.NET绑定的一部分。

v1 = client.CoreV1Api()
v1.api_client.configuration.verify_ssl = False

您将在以下代码中使用此代码：

ChromeDriver

Answer 2

这是我获得全屏截图的示例：

            string _currentPath = Path.GetDirectoryName(Assembly.GetAssembly(typeof(One of your objects)).Location) + @"\Attachs\";
            var filePath = _currentPath + sSName;

            if (!Directory.Exists(_currentPath))
                Directory.CreateDirectory(_currentPath);

            Dictionary<string, Object> metrics = new Dictionary<string, Object>();
            metrics["width"] = _driver.ExecuteScript("return Math.max(window.innerWidth,document.body.scrollWidth,document.documentElement.scrollWidth)");
            metrics["height"] = _driver.ExecuteScript("return Math.max(window.innerHeight,document.body.scrollHeight,document.documentElement.scrollHeight)");
            metrics["deviceScaleFactor"] = (double)_driver.ExecuteScript("return window.devicePixelRatio");
            metrics["mobile"] = _driver.ExecuteScript("return typeof window.orientation !== 'undefined'");
            _driver.ExecuteChromeCommand("Emulation.setDeviceMetricsOverride", metrics);

            _driver.GetScreenshot().SaveAsFile(filePath, ScreenshotImageFormat.Png);

            _driver.ExecuteChromeCommand("Emulation.clearDeviceMetricsOverride", new Dictionary<string, Object>());
            _driver.Close();

Answer 3

我更新了JimEvans解决方案，使其可以通过截取多个屏幕截图并将它们拼接在一起来处理大于8192 / 16384px的页面。

16384px的限制源于合成器使用的最大纹理尺寸。

    public class ChromeDriverEx : ChromeDriver
{
    private const string SendChromeCommandWithResult = "sendChromeCommandWithResponse";
    private const string SendChromeCommandWithResultUrlTemplate = "/session/{sessionId}/chromium/send_command_and_get_result";

    public ChromeDriverEx(ChromeDriverService service, ChromeOptions options)
        : base(service, options)
    {
        CommandInfo commandInfoToAdd = new CommandInfo(CommandInfo.PostCommand, SendChromeCommandWithResultUrlTemplate);
        this.CommandExecutor.CommandInfoRepository.TryAddCommand(SendChromeCommandWithResult, commandInfoToAdd);
    }

    public OpenQA.Selenium.Screenshot GetFullPageScreenshot()
    {
        // Evaluate this only to get the object that the
        // Emulation.setDeviceMetricsOverride command will expect.
        // Note that we can use the already existing ExecuteChromeCommand
        // method to set and clear the device metrics, because there's no
        // return value that we care about.
        string metricsScript = @"({
        width: Math.max(window.innerWidth,document.body.scrollWidth,document.documentElement.scrollWidth)|0,
        height: Math.max(window.innerHeight,document.body.scrollHeight,document.documentElement.scrollHeight)|0,
        deviceScaleFactor: window.devicePixelRatio || 1,,
        mobile: typeof window.orientation !== 'undefined'
        })";
        Dictionary<string, object> metrics = this.EvaluateDevToolsScript(metricsScript);
        this.ExecuteChromeCommand("Emulation.setDeviceMetricsOverride", metrics);
        Thread.Sleep(1000);
        Dictionary<string, object> parameters = new Dictionary<string, object>
        {
            ["format"] = "png",
            ["fromSurface"] = true
        };
        var fullHeight = int.Parse(metrics["height"]?.ToString() ?? "0");
        var splitSSAt = 8192;

        if (fullHeight > splitSSAt)
        {
            var currentHeight = splitSSAt;
            var startHeight = 0;
            List<Bitmap> bitmaps = new List<Bitmap>();

            while (fullHeight > 0)
            {
                if (currentHeight > fullHeight)
                {
                    currentHeight = fullHeight;
                }
                parameters["clip"] = new Dictionary<string, object>
                {
                    ["x"] = 0,
                    ["y"] = startHeight,
                    ["width"] = metrics["width"],
                    ["height"] = currentHeight,
                    ["scale"] = 1,
                };

                object splitScreenshotObject = this.ExecuteChromeCommandWithResult("Page.captureScreenshot", parameters);
                Dictionary<string, object> splitScreenshotResult = splitScreenshotObject as Dictionary<string, object>;
                Byte[] bitmapData = Convert.FromBase64String(FixBase64ForImage(splitScreenshotResult["data"] as string));
                MemoryStream streamBitmap = new System.IO.MemoryStream(bitmapData);
                bitmaps.Add(new Bitmap((Bitmap)Image.FromStream(streamBitmap)));
                fullHeight -= splitSSAt;
                startHeight += splitSSAt;
            }

            using var ms = new MemoryStream();
            using var bitmap = new Bitmap(MergeImages(bitmaps));
            bitmap.Save(ms, System.Drawing.Imaging.ImageFormat.Png);
            var base64 = Convert.ToBase64String(ms.GetBuffer()); //Get Base64
            return new OpenQA.Selenium.Screenshot(base64);
        }
        object screenshotObject = this.ExecuteChromeCommandWithResult("Page.captureScreenshot", parameters);
        Dictionary<string, object> screenshotResult = screenshotObject as Dictionary<string, object>;
        string screenshotData = screenshotResult["data"] as string;

        this.ExecuteChromeCommand("Emulation.clearDeviceMetricsOverride", new Dictionary<string, object>());

        var screenshot = new OpenQA.Selenium.Screenshot(screenshotData);
        return screenshot;
    }

    public string FixBase64ForImage(string image)
    {
        StringBuilder sbText = new StringBuilder(image, image.Length);
        sbText.Replace("\r\n", String.Empty); sbText.Replace(" ", string.Empty);
        return sbText.ToString();
    }

    private Bitmap MergeImages(IEnumerable<Bitmap> images)
    {
        var enumerable = images as IList<Bitmap> ?? images.ToList();

        var width = 0;
        var height = 0;

        foreach (var image in enumerable)
        {
            width = image.Width;
            height += image.Height;
        }

        var bitmap = new Bitmap(width, height);
        using (var g = Graphics.FromImage(bitmap))
        {
            var localHeight = 0;
            foreach (var image in enumerable)
            {
                g.DrawImage(image, 0, localHeight);
                localHeight += image.Height;
            }
        }
        return bitmap;
    }


    public object ExecuteChromeCommandWithResult(string commandName, Dictionary<string, object> commandParameters)
    {
        if (commandName == null)
        {
            throw new ArgumentNullException("commandName", "commandName must not be null");
        }

        Dictionary<string, object> parameters = new Dictionary<string, object>();
        parameters["cmd"] = commandName;
        parameters["params"] = commandParameters;
        Response response = this.Execute(SendChromeCommandWithResult, parameters);
        return response.Value;
    }

    private Dictionary<string, object> EvaluateDevToolsScript(string scriptToEvaluate)
    {
        // This code is predicated on knowing the structure of the returned
        // object as the result. In this case, we know that the object returned
        // has a "result" property which contains the actual value of the evaluated
        // script, and we expect the value of that "result" property to be an object
        // with a "value" property. Moreover, we are assuming the result will be
        // an "object" type (which translates to a C# Dictionary<string, object>).
        Dictionary<string, object> parameters = new Dictionary<string, object>();
        parameters["returnByValue"] = true;
        parameters["expression"] = scriptToEvaluate;
        object evaluateResultObject = this.ExecuteChromeCommandWithResult("Runtime.evaluate", parameters);
        Dictionary<string, object> evaluateResultDictionary = evaluateResultObject as Dictionary<string, object>;
        Dictionary<string, object> evaluateResult = evaluateResultDictionary["result"] as Dictionary<string, object>;

        // If we wanted to make this actually robust, we'd check the "type" property
        // of the result object before blindly casting to a dictionary.
        Dictionary<string, object> evaluateValue = evaluateResult["value"] as Dictionary<string, object>;
        return evaluateValue;
    }
}

C＃-硒整页截图

3 个答案: