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

??

HTML ??? ???? ?? ? ????? ???? ?? ? ??? ? ???? ?????? ???? ?????. .NET??? ?? ???? ?? System.Windows.Forms.WebBrowser ???? mshtml.HTMLDocument ??????? ? ?? ??? ?????. ??? ????? ???? ?? ??? ? ????.

WebBrowser ???

System.Windows.Forms.WebBrowser ???? ?????? ?? ? ???? ????? ???????. ??? ?? ?? ? ?? ???? ????? ???? ??? HTML? ???? ??? ???? ????.

?? ?? ??? WebBrowser ??? ?????.

<code class="csharp">using System.Windows.Forms;
using mshtml;

namespace WebBrowserTest
{
    public class Program
    {
        public static void Main()
        {
            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);
                }
            };
            Form f = new Form();
            f.Controls.Add(wb);
            Application.Run(f);
        }
    }
}</code>

mshtml.HTMLDocument ?????

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

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

<code class="csharp">using mshtml;

namespace HTMLDocumentTest
{
    public class Program
    {
        public static void Main()
        {
            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? ??? ????? ?? ?? ??? ??? ? ????.

1. WebBrowser ???? ????.
2. ?? URL? ???? DocumentCompleted ???? ???? ?? mshtml.HTMLDocument2 ??? ????.
3. ??? WebBrowser.IsBusy ??? ?? ???? ??? ???? ??? ??? ?????.
4. ?? ???? ??? ??? ??? OuterHtml ??? ?????.

?? ??

?? C# ??? ? ?? ??? ?????.

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

namespace DynamicHTMLFetcher
{
    public partial class MainForm : Form
    {
        public MainForm()
        {
            InitializeComponent();
            this.webBrowser.DocumentCompleted += WebBrowser_DocumentCompleted;
            this.Load += MainForm_Load;
        }

        private 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);
            }
        }

        private 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; // no changes detected, end the poll loop
                html = htmlNow;
            }

            token.ThrowIfCancellationRequested();
            return html;
        }

        private void WebBrowser_DocumentCompleted(object sender, WebBrowserDocumentCompletedEventArgs e)
        {
            // Intentional no-op handler, we receive the DocumentCompleted event in the calling method.
        }
    }
}</code>

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

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