.NET ? WebBrowser ?? mshtml.HTMLDocument? ???? ???? HTML ??? ???? ??

??

.NET? ???? HTML ??? ???? ???? ? ??? ???? ?? ???? ?? ??? ?????. ? ????? ?? HTML ??? ???? ?? ? ?? ?? ??, ? System.Windows.Forms? WebBrowser ???? ???? Microsoft HTML ?? ????? ????? COM ????? mshtml.HTMLDocument? ???? ??? ?????.

?? ?? 1: ?? WebBrowser

WebBrowser ???? ? ???? ???? ?? ???? ????? ? ??? ?????. ?? ??? WebBrowser DocumentCompleted ???? ???? ???? ???? HTML? ???? ??? ?????.

<code class="csharp">WebBrowser wb = new WebBrowser();
wb.Navigate("https://www.google.com/#q=where+am+i");

wb.DocumentCompleted += delegate(object sender, WebBrowserDocumentCompletedEventArgs e)
{
    mshtml.IHTMLDocument2 doc = (mshtml.IHTMLDocument2)wb.Document.DomDocument;
    foreach (IHTMLElement element in doc.all)
    {
        System.Diagnostics.Debug.WriteLine(element.outerHTML);
    }     
};</code>

?? ?? 2: mshtml.HTMLDocument ??

mshtml. HTMLDocument ?????? HTML ??? ?? ???? ???? ??? ?????. ?? ???? ????? HTML? ???? ???? ? ????.

<code class="csharp">mshtml.IHTMLDocument2 doc = (mshtml.IHTMLDocument2)new mshtml.HTMLDocument();
doc.write(new System.Net.WebClient().DownloadString("https://www.google.com/#q=where+am+i"));

foreach (IHTMLElement e in doc.all)
{
    System.Diagnostics.Debug.WriteLine(e.outerHTML);
}</code>

WebBrowser ? mshtml.HTMLDocument? ?? ??

WebBrowser ? mshtml.HTMLDocument ?? ?? ?? ??? ????. ?? ??? ???? HTML ??? ???? ?? ????. ? ??? ???? ?? ???/?? ? ?? ??? ???? ??? ?? ??? ?? ???? ??? ???? ?????. ? ?? ??? HTML ?? ??? ???? ?????? ??? ????? ???? ?????.

?? ??

?? ???? ??? ??? ?? ??? ?????.

<code class="csharp">using Microsoft.Win32;
using System;
using System.ComponentModel;
using System.Diagnostics;
using System.Threading;
using System.Threading.Tasks;
using System.Windows.Forms;

namespace WbFetchPage
{
    public partial class MainForm : Form
    {
        public MainForm()
        {
            SetFeatureBrowserEmulation();
            InitializeComponent();
            this.Load += MainForm_Load;
        }

        async void MainForm_Load(object sender, EventArgs e)
        {
            try
            {
                var cts = new CancellationTokenSource(10000); // cancel in 10s
                var html = await LoadDynamicPage("https://www.google.com/#q=where+am+i", cts.Token);
                MessageBox.Show(html.Substring(0, 1024) + "..." ); // it's too long!
            }
            catch (Exception ex)
            {
                MessageBox.Show(ex.Message);
            }
        }

        async Task<string> LoadDynamicPage(string url, CancellationToken token)
        {
            var tcs = new TaskCompletionSource<bool>();
            WebBrowserDocumentCompletedEventHandler handler = (s, arg) => tcs.TrySetResult(true);

            using (token.Register(() => tcs.TrySetCanceled(), useSynchronizationContext: true))
            {
                this.webBrowser.DocumentCompleted += handler;
                try 
                {           
                    this.webBrowser.Navigate(url);
                    await tcs.Task; // wait for DocumentCompleted
                }
                finally
                {
                    this.webBrowser.DocumentCompleted -= handler;
                }
            }

            var documentElement = this.webBrowser.Document.GetElementsByTagName("html")[0];

            var html = documentElement.OuterHtml;
            while (true)
            {
                await Task.Delay(500, token); 

                if (this.webBrowser.IsBusy)
                    continue; 

                var htmlNow = documentElement.OuterHtml;
                if (html == htmlNow)
                    break; 

                html = htmlNow;
            }

            token.ThrowIfCancellationRequested();
            return html;
        }

        static void SetFeatureBrowserEmulation()
        {
            if (LicenseManager.UsageMode != LicenseUsageMode.Runtime)
                return;
            var appName = System.IO.Path.GetFileName(System.Diagnostics.Process.GetCurrentProcess().MainModule.FileName);
            Registry.SetValue(@"HKEY_CURRENT_USER\Software\Microsoft\Internet Explorer\Main\FeatureControl\FEATURE_BROWSER_EMULATION",
                appName, 10000, RegistryValueKind.DWord);
        }
    }
}</code>

? ??? HTML ???? ???? ?? ???? ??? ?????? ???? ? ???? ???? ??? ?????.

? ??? .NET? ???? HTML ??? ???? ???? ?? ??? ??????? ?? ?????. ??? ??? PHP ??? ????? ?? ?? ??? ?????!