Click here to Skip to main content
14,602,858 members

PDF First Page

Rate this:
4.20 (2 votes)
Please Sign up or sign in to vote.
4.20 (2 votes)
4 Aug 2011CPOL
This Windows application lets you delete all of your pages from your PDF files except for the first one.

PDF_First_Page/FirstPage.gif

Introduction

This complete Windows application lets you delete all of your pages from your PDF files except for the first one. This is useful for file indexing when the information you want to index is located on the first page. It uses free iTextSharp library.

Using the Code

To use this program, simply select a folder and click Process. The program will delete old PDF files and create a new file in its place with just the first page. It will do the same with each subfolder. Please make sure to BACKUP the old folder!!!

Here is the code:

    Private Sub btnFrom_Click(ByVal sender As System.Object, _
             ByVal e As System.EventArgs) Handles btnFrom.Click
        fldFrom.ShowDialog()
        txtFrom.Text = fldFrom.SelectedPath
    End Sub

    Private Sub btnProcess_Click(ByVal sender As System.Object, _
                   ByVal e As System.EventArgs) Handles btnProcess.Click

        Dim sFromPath As String = txtFrom.Text
        If Not Directory.Exists(sFromPath) Then
            MsgBox("Folder does not exist")
            Exit Sub
        End If

        txtOutput.Text = ""
        txtOutput.Text += "Starting..." & vbCrLf
        ProccessFolder(sFromPath)
        txtOutput.Text += "Done!"
    End Sub

    Sub ProccessFolder(ByVal sFolderPath As String)

        btnProcess.Enabled = False

        Dim bOutputfileAlreadyExists As Boolean = False
        Dim oFolderInfo As New System.IO.DirectoryInfo(sFolderPath)

		txtOutput.Text += "Processing folder: " & sFolderPath & vbCrLf

		Dim oFiles As String() = Directory.GetFiles(sFolderPath)
		ProgressBar1.Maximum = oFiles.Length

		For i As Integer = 0 To oFiles.Length - 1
			Dim sInFilePath As String = oFiles(i)
			Dim oFileInfo As New FileInfo(sInFilePath)
			Dim sOutFilePath As String = sFolderPath & _
			"\" & oFileInfo.Name & "_processed.pdf"
			Dim sExt As String = UCase(oFileInfo.Extension).Substring(1, 3)
			Dim bError As Boolean = False

			If sExt = "PDF" Then
				txtOutput.Text += "Processing file: " & sInFilePath & vbCrLf

				'Deleting previous temp file
				If IO.File.Exists(sOutFilePath) Then
					Try
						IO.File.Delete(sOutFilePath)
					Catch ex As Exception
						txtOutput.Text += "Error deleting previous temp file: _
						" & sOutFilePath & vbTab & ex.Message & vbCrLf
						bError = True
					End Try
				End If

				'Processing File
				If bError = False Then
					Try
                        'ProcessPdf(sInFilePath, sOutFilePath)
                        AddPdf(sInFilePath, sOutFilePath, selPages.Text)
					Catch ex As Exception
						txtOutput.Text += "Error processing: " _
						& sInFilePath & vbTab & ex.Message & vbCrLf
						bError = True
					End Try
				End If

				'Deleting current PDF file
				If bError = False And IO.File.Exists(sInFilePath) Then
					Try
						IO.File.Delete(sInFilePath)
					Catch ex As Exception
						txtOutput.Text += "Error deleting current file: _
						" & sInFilePath & vbTab & ex.Message & vbCrLf
						bError = True
					End Try
				End If

				'renaming temp file
				If bError = False And IO.File.Exists(sOutFilePath) Then
					Try
						IO.File.Move(sOutFilePath, sInFilePath)
					Catch ex As Exception
						txtOutput.Text += "Error renaming temp file from: " & _
						sOutFilePath & " to " & sInFilePath & vbTab & ex.Message & vbCrLf
					End Try
				End If

				'Cleanup after error: deleting temp file
				If bError And IO.File.Exists(sOutFilePath) Then
					Try
						IO.File.Delete(sOutFilePath)
					Catch ex As Exception
						txtOutput.Text += "Error deleting temp file: " & _
						        sOutFilePath & vbTab & ex.Message & vbCrLf
						bError = True
					End Try
				End If

			End If

			ProgressBar1.Value = i
		Next

		ProgressBar1.Value = 0
		btnProcess.Enabled = True

		Dim oFolders As String() = Directory.GetDirectories(sFolderPath)
		For i As Integer = 0 To oFolders.Length - 1
			Dim sChildFolder As String = oFolders(i)
			Dim iPos As Integer = sChildFolder.LastIndexOf("\")
			Dim sFolderName As String = sChildFolder.Substring(iPos + 1)
			ProccessFolder(sChildFolder)
		Next

    End Sub

    Sub AddPdf(ByVal sInFilePath As String, _
           ByVal sOutFilePath As String, ByVal iIncludePages As Integer)

        Dim oPdfDoc As New iTextSharp.text.Document()
        Dim oPdfWriter As PdfWriter = PdfWriter.GetInstance_
                   (oPdfDoc, New FileStream(sOutFilePath, FileMode.Create))
        oPdfDoc.Open()

        Dim oDirectContent As iTextSharp.text.pdf.PdfContentByte = oPdfWriter.DirectContent
        Dim oPdfReader As iTextSharp.text.pdf.PdfReader = _
                           New iTextSharp.text.pdf.PdfReader(sInFilePath)
        Dim iNumberOfPages As Integer = oPdfReader.NumberOfPages
        Dim iPage As Integer = 0

        Do While (iPage < iNumberOfPages)
            iPage += 1

            If iPage <= iIncludePages Then
                oPdfDoc.SetPageSize(oPdfReader.GetPageSizeWithRotation(iPage))
                oPdfDoc.NewPage()

                Dim oPdfImportedPage As iTextSharp.text.pdf.PdfImportedPage = _
                                   oPdfWriter.GetImportedPage(oPdfReader, iPage)
                Dim iRotation As Integer = oPdfReader.GetPageRotation(iPage)
                If (iRotation = 90) Or (iRotation = 270) Then
                    oDirectContent.AddTemplate(oPdfImportedPage, 0, -1.0F, 1.0F, 0, 0, _
                    oPdfReader.GetPageSizeWithRotation(iPage).Height)
                Else
                    oDirectContent.AddTemplate(oPdfImportedPage, 1.0F, 0, 0, 1.0F, 0, 0)
                End If
            End If

        Loop

        oPdfDoc.Close()
        oPdfWriter.Close()

    End Sub

    Private Sub Form1_Load(ByVal sender As System.Object, ByVal e As System.EventArgs) _
            Handles MyBase.Load
        selPages.SelectedIndex = 0

    End Sub

History

  • 5th August, 2011: Initial version

License

This article, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

Share

About the Author

Igor Krupitsky
Web Developer
United States United States
Igor is a business intelligence consultant working in Tampa, Florida. He has a BS in Finance from University of South Carolina and Masters in Information Management System from University of South Florida. He also has following professional certifications: MCSD, MCDBA, MCAD.

Comments and Discussions

 
GeneralI want to vote a 1 on this... [modified] Pin
Slacker0074-Aug-11 23:31
professionalSlacker0074-Aug-11 23:31 
GeneralRe: I want to vote a 1 on this... Pin
Igor Krupitsky14-Aug-11 19:26
mvaIgor Krupitsky14-Aug-11 19:26 
Dear Slacker007,

I appreciate your supportive (but not too patronizing) tone. However, I am not writing my articles for the general public but for people that have real life problems (the PDF indexing in this case).

I understand that you stumbled upon this article just because it was recently published. I generally ignore these first time comments because users that later discover my articles via Google generally appreciate them because they resolve their problems and don’t mind that they are glib.

Regards,
Igor
GeneralMy vote of 1 Pin
Skif4-Aug-11 6:23
MemberSkif4-Aug-11 6:23 

General General    News News    Suggestion Suggestion    Question Question    Bug Bug    Answer Answer    Joke Joke    Praise Praise    Rant Rant    Admin Admin   

Use Ctrl+Left/Right to switch messages, Ctrl+Up/Down to switch threads, Ctrl+Shift+Left/Right to switch pages.

Article
Posted 3 Aug 2011

Tagged as

Stats

17.5K views
9 bookmarked