以编程方式计算保存在不同位置的多个pdf文件中的总页数

Question

我目前在vb.net工作。我的公司正在走向无纸化，我想做一个关于节省纸张的成本节约分析。目前，我们将所有的PDF文件保存到服务器上。文件路径类似于"Server>Folder1>Folder2>Folder3>Folder4>PDF文件“。文件夹1和2始终用于导航。文件夹3是部门列表，文件夹4是每个作业。每个文件夹4具有多个pdf文件。简单地说，文件夹1和文件夹2的名称是静态的，而文件夹3和4是动态的。让事情变得更难的是，位于文件夹4之后的所有PDF文件都有不同的名称。我有下面的一小段代码来检测一个pdf有多少页，而不需要打开它，但它需要文件路径。考虑到有成百上千个pdf文件，我想以编程方式遍历所有这些文件，检测文件是否为pdf文件，然后对找到的所有页面求和。然后，我可以使用这个数字来计算无纸化的成本节约。

 PdfReader pr = new PdfReader("/path/to/yourFile.pdf");
 return pr.getNumberOfPages();

另一个想法是以某种方式将所有文件合并成一个单独的PDF文件，这将使它像打开文件一样简单，看看有多少页。

Answer 1

这是一个VBA解决方案。在Excel中运行代码。

Sub PDFandNumPages()

   Dim Folder As Object
   Dim file As Object
   Dim fso As Object
   Dim iExtLen As Integer, iRow As Integer
   Dim sFolder As String, sExt As String
   Dim sPDFName As String

   sExt = "pdf"
   iExtLen = Len(sExt)
   iRow = 1
   ' Must have a '\' at the end of path
   sFolder = "C:\your_path_here\"

   Set fso = CreateObject("Scripting.FileSystemObject")

   If sFolder <> "" Then
      Set Folder = fso.GetFolder(sFolder)
      For Each file In Folder.Files
         If Right(file, iExtLen) = sExt Then
            Cells(iRow, 1).Value = file.Name
            Cells(iRow, 2).Value = pageCount(sFolder & file.Name)
            iRow = iRow + 1
         End If
      Next file
   End If

End Sub

Function pageCount(sFilePathName As String) As Integer

Dim nFileNum As Integer
Dim sInput As String
Dim sNumPages As String
Dim iPosN1 As Integer, iPosN2 As Integer
Dim iPosCount1 As Integer, iPosCount2 As Integer
Dim iEndsearch As Integer

' Get an available file number from the system
nFileNum = FreeFile

'OPEN the PDF file in Binary mode
Open sFilePathName For Binary Lock Read Write As #nFileNum

  ' Get the data from the file
  Do Until EOF(nFileNum)
      Input #1, sInput
      sInput = UCase(sInput)
      iPosN1 = InStr(1, sInput, "/N ") + 3
      iPosN2 = InStr(iPosN1, sInput, "/")
      iPosCount1 = InStr(1, sInput, "/COUNT ") + 7
      iPosCount2 = InStr(iPosCount1, sInput, "/")

   If iPosN1 > 3 Then
      sNumPages = Mid(sInput, iPosN1, iPosN2 - iPosN1)
      Exit Do
   ElseIf iPosCount1 > 7 Then
      sNumPages = Mid(sInput, iPosCount1, iPosCount2 - iPosCount1)
      Exit Do
   ' Prevent overflow and assigns 0 to number of pages if strings are not in binary
   ElseIf iEndsearch > 1001 Then
      sNumPages = "0"
      Exit Do
   End If
      iEndsearch = iEndsearch + 1
   Loop

  ' Close pdf file
  Close #nFileNum
  pageCount = CInt(sNumPages)

End Function

这里有另一种方法来做本质上相同的事情。

Sub Test()
    Dim MyPath As String, MyFile As String
    Dim i As Long
    MyPath = "C:\your_path_here\"
    MyFile = Dir(MyPath & Application.PathSeparator & "*.pdf", vbDirectory)
    Range("A:B").ClearContents
    Range("A1") = "File Name": Range("B1") = "Pages"
    Range("A1:B1").Font.Bold = True
    i = 1
    Do While MyFile <> ""
        i = i + 1
        Cells(i, 1) = MyFile
        Cells(i, 2) = GetPageNum(MyPath & Application.PathSeparator & MyFile)
        MyFile = Dir
    Loop
    Columns("A:B").AutoFit
    MsgBox "Total of " & i - 1 & " PDF files have been found" & vbCrLf _
           & " File names and corresponding count of pages have been written on " _
           & ActiveSheet.Name, vbInformation, "Report..."
End Sub
'
Function GetPageNum(PDF_File As String)
    'Haluk 19/10/2008
    Dim FileNum As Long
    Dim strRetVal As String
    Dim RegExp
    Set RegExp = CreateObject("VBscript.RegExp")
    RegExp.Global = True
    RegExp.Pattern = "/Type\s*/Page[^s]"
    FileNum = FreeFile
    Open PDF_File For Binary As #FileNum
        strRetVal = Space(LOF(FileNum))
        Get #FileNum, , strRetVal
    Close #FileNum
    GetPageNum = RegExp.Execute(strRetVal).Count
End Function