问PDF到纯文本，遇到了Acrobat中的一些困难页面

EN

Sub LoopThroughFiles()
    
    Dim StrFile As String
    Dim pdfPath As String
    
    StrFile = Dir("C:\temp\PDFs\")
    fileRoot = "C:\temp\PDFs\"
    If Right(fileRoot, 1) <> "\" Then fileRoot = fileRoot & "\" 'ensure terminating \
    
    Do While Len(StrFile) > 0
        
        Debug.Print StrFile
        n = StrFile
        pdfPath = fileRoot & StrFile
        
        Debug.Print pdfPath
        
    'Convert to WordDoc
    success = ConvertPdf2(pdfPath, fileRoot & StrFile & ".doc")
    StrFile = Dir
    On Error Resume Next
        
    oWd.Quit
        
    'Convert to PlainText
    Debug.Print pdfPath & ".doc"

    success2 = GetTextFromWord(pdfPath & ".doc", n)
    
Loop
End Sub

'returns true if conversion was successful (based on whether `Open` succeeded or not)
Function ConvertPdf2(pdfPath As String, textPath As String) As Boolean
    Dim AcroXApp As Acrobat.AcroApp
    Dim AcroXAVDoc As Acrobat.AcroAVDoc
    Dim AcroXPDDoc As Acrobat.AcroPDDoc
    Dim jsObj As Object, success As Boolean

    Set AcroXApp = CreateObject("AcroExch.App")
    Set AcroXAVDoc = CreateObject("AcroExch.AVDoc")
    success = AcroXAVDoc.Open(pdfPath, "Acrobat") '<<< returns false if fails
    If success Then
    
Application.Wait (Now + TimeValue("0:00:2")) 'Helps PC have some time to go through data, can cause PC to freeze without

        Set AcroXPDDoc = AcroXAVDoc.GetPDDoc
        Set jsObj = AcroXPDDoc.GetJSObject
        jsObj.SaveAs textPath, "com.adobe.acrobat.doc"
        AcroXAVDoc.Close False
    End If
    AcroXApp.Hide
    AcroXApp.Exit
    ConvertPdf2 = success 'report success/failure
End Function

Function GetTextFromWord(DocStr As String, n)

    Dim filePath As String
    Dim fso As FileSystemObject
    Dim fileStream As TextStream
    Dim oWd As Object, oDoc As Object, fileRoot As String
    Const wdFormatText As Long = 2, wdCRLF As Long = 0
    
    Set fso = New FileSystemObject
    Set oWd = CreateObject("word.application")
    
    fileRoot = "C:\temp\PDFs" 'read this once
    If Right(fileRoot, 1) <> "\" Then fileRoot = fileRoot & "\" 'ensure terminating \
    
            Set oDoc = Nothing
            On Error Resume Next 'ignore error if no document...
            Set oDoc = oWd.Documents.Open(DocStr)
            On Error GoTo 0      'stop ignoring errors
            
            Debug.Print n
            If Not oDoc Is Nothing Then
                filePath = fileRoot & n & ".txt"  'filename
                Debug.Print filePath
                
                
        oDoc.SaveAs2 Filename:=filePath, _
        FileFormat:=wdFormatText, LockComments:=False, Password:="", _
        AddToRecentFiles:=True, WritePassword:="", ReadOnlyRecommended:=False, _
        EmbedTrueTypeFonts:=False, SaveNativePictureFormat:=False, SaveFormsData _
        :=False, SaveAsAOCELetter:=False, Encoding:=1252, InsertLineBreaks:=False _
        , AllowSubstitutions:=True, LineEnding:=wdCRLF, CompatibilityMode:=0
        
    oDoc.Close False
    
    End If
    oWd.Quit
                
   
    GetTextFromWord = success2
    
End Function

@echo off
if not exist "%~dpn1.txt" goto help

REM because of method we need to append an extra new line to input (some cases may need two?)
echo/&echo Preparing files
echo/>temp_nl.txt&copy /b "%~dpn1.txt"+temp_nl.txt temp_out.txt >nul:

REM tool will not replace files in binary mode unless it sees there is a dummy backup to use !
echo temp_nl.txt >temp_out.txt.bak

echo/&echo Processing ...&echo/
REM 1st pass ensure binary line feeds are converted to some plain text
fart.exe  -q -b --binary --c-style  temp_out.txt "\x0D\x0A" "<NL>" >nul: 2>&1

REM 2nd pass ensure double "<NL><NL>" are converted back to single new line
fart.exe  --c-style  temp_out.txt "<NL><NL>" "\x0D\x0A\x0D\x0A"

echo/&echo de-hypenating line ends&echo/
REM 3rd pass remove hyphenation (Caution that may not always be desirable
fart.exe  --c-style  temp_out.txt "\x2D<NL>" "\x20"

REM 4th pass ensure remaining line markers are converted to single with little leading space
fart.exe  --c-style  temp_out.txt "\x20\x20\x20\x20\x20\x20\x20\x20" "\x20\x20\x20\x20"
REM 4th pass ensure remaining line markers are converted to single with little leading space
fart.exe  --c-style  temp_out.txt "\x20\x20\x20\x20" "\x20\x20"
REM 4th pass ensure remaining line markers are converted to single with little leading space
fart.exe  --c-style  temp_out.txt "\x20\x20\x20\x20" "\x20\x20"
REM 4th pass ensure remaining line markers are converted to single with little leading space
fart.exe  --c-style  temp_out.txt "\x20\x20\x20\x20" "\x20\x20"
REM 4th pass ensure remaining line markers are converted to single with little leading space
fart.exe  --c-style  temp_out.txt "\x20\x20\x20\x20" "\x20\x20"
REM 4th pass ensure remaining line markers are converted to single with little leading space
fart.exe  --c-style  temp_out.txt "\x20\x20\x20\x20" "\x20\x20"
REM 4th pass ensure remaining line markers are converted to single with little leading space
fart.exe  --c-style  temp_out.txt "\x20\x20\x20" "\x20\x20"
REM 4th pass ensure remaining line markers are converted to single with little leading space
fart.exe  --c-style  temp_out.txt "<NL>\x20\x20" "<NL>\x20"



REM 5th pass ensure remaining line markers are converted to single space
fart.exe  --c-style  temp_out.txt "<NL>" "\x20"

echo/
echo Done
pause
goto eof
:help
echo/
echo Input must be a filename.txt accepts drag and drop
echo/
echo Usage txt2par filename.txt
echo/
echo Will convert single line feeds to space and
echo convert double line feeds to single line gap
echo/
pause