UWP獲取任意網頁加載完成后的HTML

主要思想：通過后台WebView載入指定網頁，再提取出WebView中的內容

關鍵代碼：

var html = await webView.InvokeScriptAsync("eval", new string[] { "document.documentElement.outerHTML;" });

有一個很簡單的思路，

訂閱WebView NavigationCompleted事件，然后讓Navigate到指定的網址，發生事件時執行這行代碼

 

 

除此之外，這里還有一個異步的方法，用到了TaskCompletionSource這個東西

首先，創建一個TaskCompletionSource：

TaskCompletionSource<string> completionSource = new TaskCompletionSource<string>();

因為返回的東西是string（html），所以泛型T設置成string

然后使用lambda的形式訂閱Navigation事件：

webView.NavigationCompleted += async (sender, args) =>
{
    if (args.Uri != uri)
        return;
    await Task.Delay(200);
    var html = await sender.InvokeScriptAsync("eval", new string[] { "document.documentElement.outerHTML;" });
    webView.NavigateToString("");
    webView = null;
    completionSource.SetResult(html);
};

Line5的延遲200ms，是為了Navigation完成之后再給頁面里的其他一些元素（比如一些js腳本）一些加載的時間（講道理訂閱事件里也應該寫一個的）

Line7的導航到空是為了防止WebView里的東西繼續運行從而導致一些靈異事件（尤其是一些帶視頻的網頁，咳咳）

Line9，給Task設置個Result，await就會結束

 

最后：

return completionSource.Task;

 

封裝成類：

    public class WebHelper
    {
        public class WebLoadedArgs:EventArgs
        {
            public bool Success { get; private set; }
            public WebErrorStatus WebErrorStatus { get; private set; }
            public string Html { get; private set; }

            public WebLoadedArgs(WebErrorStatus webErrorStatus)
            {
                WebErrorStatus = webErrorStatus;
                Success = false;
            }

            public WebLoadedArgs(string Html,WebErrorStatus webErrorStatus)
            {
                this.Html = Html;
                WebErrorStatus = webErrorStatus;
                Success = true;
            }
        }

        public string Url { get; private set; }
        public event EventHandler<WebLoadedArgs> WebLoaded;
        private WebView webView;

        public WebHelper(string Url)
        {
            this.Url = Url;
            webView = new WebView(WebViewExecutionMode.SeparateThread);
            webView.Navigate(new Uri(Url));
            webView.NavigationCompleted += WebView_NavigationCompleted;
            webView.NavigationFailed += WebView_NavigationFailed;
        }

        private void WebView_NavigationFailed(object sender, WebViewNavigationFailedEventArgs e)
        {
            WebLoaded(this, new WebLoadedArgs(e.WebErrorStatus));
        }

        private async void WebView_NavigationCompleted(WebView sender, WebViewNavigationCompletedEventArgs args)
        {
            
            var html = await sender.InvokeScriptAsync("eval", new string[] { "document.documentElement.outerHTML;" });
            webView = null;
            WebLoaded(this, new WebLoadedArgs(html,args.WebErrorStatus));
        }

        /// <summary>
        /// 異步實現獲取Web內容
        /// </summary>
        /// <param name="Url">網址</param>
        /// <param name="TimeOut">超時時間</param>
        /// <returns>Web的Html內容</returns>
        public static Task<string> LoadWebAsync(string Url,int Timeout)
        {
            return LoadWebAsync(Url, "", Timeout);
        }


        /// <summary>
        /// 異步實現獲取Web內容
        /// </summary>
        /// <param name="Url">網址</param>
        /// <param name="Referer">Header[Referer]，用以解決一些盜鏈效驗</param>
        /// <param name="TimeOut">超時時間</param>
        /// <returns>Web的Html內容</returns>
        public static Task<string> LoadWebAsync(string Url,string Referer, int TimeOut)
        {
            
            WebView webView = new WebView(WebViewExecutionMode.SeparateThread);
            Uri uri = new Uri(Url);
            HttpRequestMessage requestMessage = new HttpRequestMessage(HttpMethod.Get, uri);
            requestMessage.Headers.Add("Referer", Referer);
            webView.NavigateWithHttpRequestMessage(requestMessage);

            TaskCompletionSource<string> completionSource = new TaskCompletionSource<string>();
            webView.NavigationCompleted += async (sender, args) =>
            {
                if (args.Uri != uri)
                    return;
                await Task.Delay(200);
                var html = await sender.InvokeScriptAsync("eval", new string[] { "document.documentElement.outerHTML;" });
                webView.NavigateToString("");
                webView = null;
                completionSource.SetResult(html);
            };
            webView.NavigationFailed += (sender, args) =>
            {
                webView = null;
                completionSource.SetException(new WebException("", (WebExceptionStatus)args.WebErrorStatus));
            };
            DispatcherTimer timer = new DispatcherTimer();
            timer.Interval = TimeSpan.FromSeconds(TimeOut);
            timer.Tick += (sender, args) =>
            {
                timer = null;
                webView.NavigateToString("");
                webView = null;
                completionSource.SetException(new TimeoutException());
            };
            timer.Start();

            return completionSource.Task;
        }
    }

 

使用方法：

（事件訂閱的方式）

        WebHelper webHelper = new WebHelper("http://www.baidu.com/");
        webHelper.WebLoaded += WebHelper_WebLoaded;

        private void WebHelper_WebLoaded(object sender, WebHelper.WebLoadedArgs e)
        {
            if(e.Success)
            {
                var html = e.Html;
            }
        }

 

（異步的方式）

var html = await WebHelper.LoadWebAsync("http://www.baidu.com", 120);