c# - 使用IPersistStreamInit从WPF-WebBrowser-Control获取HTML源

我正在尝试获取已加载到WPF WebBrowser控件中的网页的HTML源。做到这一点的唯一方法似乎是将WebBrowser.Document的实例转换为IPersistStreamInit（我必须定义自己，因为它是一个COM接口），然后调用IPersistStreamInit.Save方法，并传递一个
IStream的实现（同样是COM接口），它将持久保存
文档到流。好吧，有点：我总是得到流的前4 KB，而不是整个文档，我也不知道为什么。

这是IPersistStreamInit的代码：

using System;
using System.Runtime.InteropServices;
using System.Runtime.InteropServices.ComTypes;
using System.Security;

namespace PayPal.SkyNet.BpiTool.Interop
{
    [ComImport, InterfaceType(ComInterfaceType.InterfaceIsIUnknown),
        SuppressUnmanagedCodeSecurity,
        Guid("7FD52380-4E07-101B-AE2D-08002B2EC713")]
    public interface IPersistStreamInit
    {
        void GetClassID(out Guid pClassID);
        [PreserveSig]
        int IsDirty();
        void Load([In, MarshalAs(UnmanagedType.Interface)] IStream pstm);
        void Save([In, MarshalAs(UnmanagedType.Interface)] IStream pstm, [In, MarshalAs(UnmanagedType.Bool)] bool fClearDirty);
        void GetSizeMax([Out, MarshalAs(UnmanagedType.LPArray)] long pcbSize);
        void InitNew();
    }
}

这是IStream-Implementation的代码：

using System;
using System.IO;
using System.Runtime.InteropServices.ComTypes;

namespace PayPal.SkyNet.BpiTool.Interop
{
    public class ComStream : IStream
    {
        private Stream _stream;

        public ComStream(Stream stream)
        {
            this._stream = stream;
        }

        public void Commit(int grfCommitFlags)
        {
        }

        public void CopyTo(IStream pstm, long cb, IntPtr pcbRead, IntPtr pcbWritten)
        {
        }

        public void LockRegion(long libOffset, long cb, int dwLockType)
        {
        }

        public void Read(byte[] pv, int cb, IntPtr pcbRead)
        {
            this._stream.Read(pv, (int)this._stream.Position, cb);
        }

        public void Revert()
        {
        }

        public void SetSize(long libNewSize)
        {
            this._stream.SetLength(libNewSize);
        }

        public void Stat(out System.Runtime.InteropServices.ComTypes.STATSTG pstatstg, int grfStatFlag)
        {
            pstatstg = new System.Runtime.InteropServices.ComTypes.STATSTG();
        }

        public void UnlockRegion(long libOffset, long cb, int dwLockType)
        {
        }

        public void Write(byte[] pv, int cb, IntPtr pcbWritten)
        {
            this._stream.Write(pv, 0, cb);
        }

        public void Clone(out IStream outputStream)
        {
            outputStream = null;
        }

        public void Seek(long dlibMove, int dwOrigin, IntPtr plibNewPosition)
        {
            this._stream.Seek(dlibMove, (SeekOrigin)dwOrigin);
        }
    }
}

现在，我有一个课程来包装所有内容。由于我不想重新分发mshtml-interop-assembly，因此选择了后期绑定-由于在VB中后期绑定比较容易，所以我在VB中做到了。这是代码：

Option Strict Off
Option Explicit Off

Imports System.IO

Public Class HtmlDocumentWrapper : Implements IDisposable

    Private htmlDoc As Object

    Public Sub New(ByVal htmlDoc As Object)
        Me.htmlDoc = htmlDoc
    End Sub

    Public Property Document As Object
        Get
            Return Me.htmlDoc
        End Get
        Set(value As Object)
            Me.htmlDoc = Nothing
            Me.htmlDoc = value
        End Set
    End Property

    Public ReadOnly Property DocumentStream As Stream
        Get
            Dim str As Stream = Nothing
            Dim psi As IPersistStreamInit = CType(Me.htmlDoc, IPersistStreamInit)
            If psi IsNot Nothing Then
                str = New MemoryStream
                Dim cStream As New ComStream(str)
                psi.Save(cStream, False)
                str.Position = 0
            End If
            Return str
        End Get
    End Property
End Class

现在我应该可以使用所有这些：

private void Browser_Navigated(object sender, NavigationEventArgs e)
{
    HtmlDocumentWrapper doc = new HtmlDocumentWrapper();
    doc.Document = Browser.Document;
    using (StreamReader sr = new StreamReader(doc.DocumentStream))
    {
        using (StreamWriter sw = new StreamWriter("test.txt"))
        {
            //BOOM! Only 4kb of HTML source
            sw.WriteLine(sr.ReadToEnd());
            sw.Flush();
        }
    }
}

谁知道，为什么我没有得到整个HTML资源？任何帮助是极大的赞赏。

问候

Arne

最佳答案

将您的代码从Browser.Navigated移至Browser.LoadCompleted，因为升江正确地在上面进行了注释，并且可以正常工作

关于c# - 使用IPersistStreamInit从WPF-WebBrowser-Control获取HTML源，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/7516747/