| Author: J Johnny 16 Oct 2009 | Member Level: Bronze Points : 2 |
Dharmaraj's code logic was what I needed for my program. I'm using VB .Net instead C#. Below is the function I created in VB based on the above code.
Imports System.IO
Imports System.Text.RegularExpressions
Private Function pageCountPDF(ByRef pdfFile As FileInfo) As Integer
' Function for finding the number of pages in a given PDF file
' based on code found at http://www.dotnetspider.com/resources/21866-Count-pages-PDF-file.aspx
pageCountPDF = 0
If pdfFile.Exists Then
Dim fs As FileStream = New FileStream(pdfFile.FullName, FileMode.Open, FileAccess.Read)
Dim sr As StreamReader = New StreamReader(fs)
Dim pdfMagicNumber() As Char = "0000".ToArray
sr.Read(pdfMagicNumber, 0, 4) ' put the first for characters of
' the file into the pdfMagicNumber array
If pdfMagicNumber = "%PDF".ToArray Then 'The first four characters
' of a PDF file should start with %PDF
Dim pdfContents As String = sr.ReadToEnd()
Dim rx As Regex = New Regex("/Type\s/Page[^s]")
Dim match As MatchCollection = rx.Matches(pdfContents)
pageCountPDF = match.Count
Else
Throw New Exception("File does not appear to be a PDF file (magic number not found).")
End If
Else
Throw New Exception("File does not exist.")
End If
End Function
|