我正在尝试将许多旧的 .DOC 文件转换为 PDF 格式或 RTF 格式。到目前为止，我已经找到了完成后者（转换为 RTF）的方法，但是旧 Word 应用程序的格式仍然存在于文档中。如果您打开 Microsoft Word（我使用的是 2010）并单击“文件”>“打开”，则会出现一个下拉菜单，可让您选择“从任何文件（.）中恢复文本”。是否可以在转换过程中使用它来过滤掉 .DOC 文档中的格式数据？以下是我目前尝试修改的几个脚本示例：
尽管它似乎只是将 .rtf 附加到文件的末尾而不是更改格式，但它已经奏效了：
Sub SaveAllAsDOCX()
Dim strFilename As String
Dim strDocName As String
Dim strPath As String
Dim oDoc As Document
Dim fDialog As FileDialog
Dim intPos As Integer
Set fDialog = Application.FileDialog(msoFileDialogFolderPicker)
With fDialog
.Title = "Select folder and click OK"
.AllowMultiSelect = False
..InitialView = msoFileDialogViewList
If .Show <> -1 Then
MsgBox "Cancelled By User", , "List Folder Contents"
Exit Sub
End If
strPath = fDialog.SelectedItems.Item(1)
If Right(strPath, 1) <> "\" Then strPath = strPath + "\"
End With
If Documents.Count > 0 Then
Documents.Close SaveChanges:=wdPromptToSaveChanges
End If
If Left(strPath, 1) = Chr(34) Then
strPath = Mid(strPath, 2, Len(strPath) - 2)
End If
strFilename = Dir$(strPath & "*.doc")
While Len(strFilename) <> 0
Set oDoc = Documents.Open(strPath & strFilename)
strDocName = ActiveDocument.FullName
intPos = InStrRev(strDocName, ".")
strDocName = Left(strDocName, intPos - 1)
strDocName = strDocName & ".docx"
oDoc.SaveAs FileName:=strDocName, _
FileFormat:=wdFormatDocumentDefault
oDoc.Close SaveChanges:=wdDoNotSaveChanges
strFilename = Dir$()
Wend
End Sub
到目前为止，这个在任何转换中都没有成功：
Option Explicit
Sub ChangeDocsToTxtOrRTFOrHTML()
'with export to PDF in Word 2007
Dim fs As Object
Dim oFolder As Object
Dim tFolder As Object
Dim oFile As Object
Dim strDocName As String
Dim intPos As Integer
Dim locFolder As String
Dim fileType As String
On Error Resume Next
locFolder = InputBox("Enter the folder path to DOCs", "File Conversion", "C:\myDocs")
Select Case Application.Version
Case Is < 12
Do
fileType = UCase(InputBox("Change DOC to TXT, RTF, HTML", "File Conversion", "TXT"))
Loop Until (fileType = "TXT" Or fileType = "RTF" Or fileType = "HTML")
Case Is >= 12
Do
fileType = UCase(InputBox("Change DOC to TXT, RTF, HTML or PDF(2007+ only)", "File Conversion", "TXT"))
Loop Until (fileType = "TXT" Or fileType = "RTF" Or fileType = "HTML" Or fileType = "PDF")
End Select
Application.ScreenUpdating = False
Set fs = CreateObject("Scripting.FileSystemObject")
Set oFolder = fs.GetFolder(locFolder)
Set tFolder = fs.CreateFolder(locFolder & "Converted")
Set tFolder = fs.GetFolder(locFolder & "Converted")
For Each oFile In oFolder.Files
Dim d As Document
Set d = Application.Documents.Open(oFile.Path)
strDocName = ActiveDocument.Name
intPos = InStrRev(strDocName, ".")
strDocName = Left(strDocName, intPos - 1)
ChangeFileOpenDirectory tFolder
Select Case fileType
Case Is = "TXT"
strDocName = strDocName & ".txt"
ActiveDocument.SaveAs FileName:=strDocName, FileFormat:=wdFormatText
Case Is = "RTF"
strDocName = strDocName & ".rtf"
ActiveDocument.SaveAs FileName:=strDocName, FileFormat:=wdFormatRTF
Case Is = "HTML"
strDocName = strDocName & ".html"
ActiveDocument.SaveAs FileName:=strDocName, FileFormat:=wdFormatFilteredHTML
Case Is = "PDF"
strDocName = strDocName & ".pdf"
' *** Word 2007 users - remove the apostrophe at the start of the next line ***
'ActiveDocument.ExportAsFixedFormat OutputFileName:=strDocName, ExportFormat:=wdExportFormatPDF
End Select
d.Close
ChangeFileOpenDirectory oFolder
Next oFile
Application.ScreenUpdating = True
End Sub