使用带有 x-emf 图像的 OpenXMLPowerTools 失败将 docx 转换为 html

Question

我正在使用 OpenXMLPowerTools 将文档 (docx) 转换为 html 文件的功能，但我遇到了 .emf 图像。

文档中的所有图片都是 .emf 图片，无法转换为 html。

我进行了研究，似乎 OpenXMLPowerTools 不支持此扩展？我说的对吗？

是否有人在使用此工具时遇到此问题？

这是我当前的代码（VB.NET）：

Sub Main()

    Dim objSource As Object = Nothing
    Dim wdDoc As WordprocessingDocument
    Dim fi As FileInfo
    Dim destFileName As FileInfo
    Dim di As DirectoryInfo
    Dim strImageDirectoryName As String = String.Empty
    Dim iImageCounter As Integer = 0
    Dim part As CoreFilePropertiesPart
    Dim strPageTitle As String = String.Empty
    Dim HtmlSettings As WmlToHtmlConverterSettings
    Dim strExtension As String = String.Empty
    Dim imageFormat As ImageFormat = Nothing
    Dim strBase64 As String = String.Empty
    Dim strMimeType As String = String.Empty
    Dim format As ImageFormat
    Dim codec As ImageCodecInfo
    Dim strImageSource As String = String.Empty
    Dim img As XElement
    Dim arrByte As Byte()
    Dim htmlElement As XElement
    Dim html As XDocument
    Dim strHtml As String = String.Empty
    Dim strFilePath As String = String.Empty
    Dim strOutputDirectory As String = String.Empty
    Dim objWriter As Object = Nothing
    Dim localDirInfo As DirectoryInfo

    strFilePath = "FilePath"
    strOutputDirectory = "OutputPath"

    fi = New FileInfo(strFilePath)
    destFileName = New FileInfo(fi.Name.Replace(".docx", ".html"))

    If strOutputDirectory IsNot Nothing AndAlso strOutputDirectory <> String.Empty Then
        di = New DirectoryInfo(strOutputDirectory)
        If Not di.Exists Then
            Throw New OpenXmlPowerToolsException("Output directory does not exist")
        End If
        destFileName = New FileInfo(Path.Combine(di.FullName, destFileName.Name))
    End If

    objSource = Packaging.Package.Open(strFilePath)
    wdDoc = WordprocessingDocument.Open(objSource)

    strImageDirectoryName = destFileName.FullName.Substring(0, destFileName.FullName.Length - 5) & "_files"
    part = wdDoc.CoreFilePropertiesPart
    strPageTitle = fi.FullName

    If part IsNot Nothing Then
        strPageTitle = If(CStr(part.GetXDocument().Descendants(DC.title).FirstOrDefault()), fi.FullName)
    End If

    strImageDirectoryName = destFileName.FullName.Substring(0, destFileName.FullName.Length - 5) & "_files"

    HtmlSettings = New WmlToHtmlConverterSettings
    Dim imgPart = wdDoc.MainDocumentPart.ImageParts

    With HtmlSettings

        .PageTitle = strPageTitle
        .FabricateCssClasses = True
        .CssClassPrefix = "pt-"
        .RestrictToSupportedLanguages = False
        .RestrictToSupportedNumberingFormats = False
        .ImageHandler = Function(imageinfo)

                            localDirInfo = New DirectoryInfo(strImageDirectoryName)
                            If Not localDirInfo.Exists Then localDirInfo.Create()
                            iImageCounter += 1

                            strExtension = imageinfo.ContentType.Split("/"c)(1).ToLower()

                            If strExtension = "png" Then
                                imageFormat = ImageFormat.Png
                            ElseIf strExtension = "gif" Then
                                imageFormat = ImageFormat.Gif
                            ElseIf strExtension = "bmp" Then
                                imageFormat = ImageFormat.Bmp
                            ElseIf strExtension = "jpeg" Then
                                imageFormat = ImageFormat.Jpeg
                            ElseIf strExtension = "tiff" Then
                                strExtension = "gif"
                                imageFormat = ImageFormat.Gif
                            ElseIf strExtension = "x-wmf" Then
                                strExtension = "wmf"
                                imageFormat = ImageFormat.Wmf
                            ElseIf strExtension = "x-emf" Then
                                strExtension = "emf"
                                imageFormat = ImageFormat.Emf
                            End If

                            If imageFormat Is Nothing Then Return Nothing

                            Using ms As MemoryStream = New MemoryStream()
                                imageinfo.Bitmap.Save(ms, imageFormat)
                                arrByte = ms.ToArray()
                                strBase64 = Convert.ToBase64String(arrByte)
                            End Using

                            format = imageinfo.Bitmap.RawFormat
                            codec = ImageCodecInfo.GetImageDecoders().First(Function(c) c.FormatID = format.Guid)
                            strMimeType = codec.MimeType
                            strImageSource = String.Format("data:{0};base64,{1}", strMimeType, strBase64)
                            img = New XElement(Xhtml.img,
                                               New XAttribute(NoNamespace.src, strImageSource), imageinfo.ImgStyleAttribute,
                                               If(imageinfo.AltText IsNot Nothing, New XAttribute(NoNamespace.alt, imageinfo.AltText), Nothing))

                            Return img

                        End Function

    End With

    htmlElement = WmlToHtmlConverter.ConvertToHtml(wdDoc, HtmlSettings)
    html = New XDocument(New XDocumentType("html", Nothing, Nothing, Nothing), htmlElement)
    strHtml = html.ToString(SaveOptions.DisableFormatting)
    File.WriteAllText(destFileName.FullName, strHtml, Encoding.UTF8)

End Sub

Answer 1

现在我已经成功地将 docx 转换为带有 emf 图像的 html