UWP获取任意网页加载完成后的HTML

主要思想：通过后台WebView载入指定网页，再提取出WebView中的内容

关键代码：

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

有一个很简单的思路，

订阅WebView NavigationCompleted事件，然后让Navigate到指定的网址，发生事件时执行这行代码

除此之外，这里还有一个异步的方法，用到了TaskCompletionSource这个东西

首先，创建一个TaskCompletionSource：

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

因为返回的东西是string（html），所以泛型T设置成string

然后使用lambda的形式订阅Navigation事件：

 webView.NavigationCompleted += async (sender, args) =>

 {

     if (args.Uri != uri)

         return;

     await Task.Delay();

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

     webView.NavigateToString("");

     webView = null;

     completionSource.SetResult(html);

 };

Line5的延迟200ms，是为了Navigation完成之后再给页面里的其他一些元素（比如一些js脚本）一些加载的时间（讲道理订阅事件里也应该写一个的）

Line7的导航到空是为了防止WebView里的东西继续运行从而导致一些灵异事件（尤其是一些带视频的网页，咳咳）

Line9，给Task设置个Result，await就会结束

最后：

 return completionSource.Task;

封装成类：

    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>

        /// 异步实现获取Web内容

        /// </summary>

        /// <param name="Url">网址</param>

        /// <param name="TimeOut">超时时间</param>

        /// <returns>Web的Html内容</returns>

        public static Task<string> LoadWebAsync(string Url,int Timeout)

        {

            return LoadWebAsync(Url, "", Timeout);

        }

        /// <summary>

        /// 异步实现获取Web内容

        /// </summary>

        /// <param name="Url">网址</param>

        /// <param name="Referer">Header[Referer]，用以解决一些盗链效验</param>

        /// <param name="TimeOut">超时时间</param>

        /// <returns>Web的Html内容</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();

                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：

（事件订阅的方式）

        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;

            }

        }

（异步的方式）

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

巴特西

UWP获取任意网页加载完成后的HTML

最新文章

热门文章