ByteScout PDF Suite – VB.NET – Convert Scanned PDF to Excel

Home
/
Articles
/
ByteScout PDF Suite – VB.NET – Convert Scanned PDF to Excel

printable version:
ByteScout-PDF-Suite-VB-NET-Convert-Scanned-PDF-to-Excel.pdf

How to convert scanned PDF to excel in VB.NET with ByteScout PDF Suite

This code in VB.NET shows how to convert scanned PDF to excel with this how to tutorial

Convert scanned PDF to excel is simple to apply in VB.NET if you use these source codes below. ByteScout PDF Suite is the bundle that provides six different SDK libraries to work with PDF from generating rich PDF reports to extracting data from PDF documents and converting them to HTML. This bundle includes PDF (Generator) SDK, PDF Renderer SDK, PDF Extractor SDK, PDF to HTML SDK, PDF Viewer SDK and PDF Generator SDK for Javascript. It can be applied to convert scanned PDF to excel using VB.NET.

Want to save time? You will save a lot of time on writing and testing code as you may just take the VB.NET code from ByteScout PDF Suite for convert scanned PDF to excel below and use it in your application. Just copy and paste the code into your VB.NET application’s code and follow the instructions. Want to see how it works with your data then code testing will allow the function to be tested and work properly.

You can download free trial version of ByteScout PDF Suite from our website to see and try many others source code samples for VB.NET.

On-demand (REST Web API) version:
Web API (on-demand version)

On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)

Form1.Designer.vb

      Partial Class Form1
	''' <summary>
	''' Required designer variable.
	''' </summary>
	Private components As System.ComponentModel.IContainer = Nothing

	''' <summary>
	''' Clean up any resources being used.
	''' </summary>
	''' <param name="disposing">true if managed resources should be disposed; otherwise, false.</param>
	Protected Overrides Sub Dispose(disposing As Boolean)
		If disposing AndAlso (components IsNot Nothing) Then
			components.Dispose()
		End If
		MyBase.Dispose(disposing)
	End Sub

	#Region "Windows Form Designer generated code"

	''' <summary>
	''' Required method for Designer support - do not modify
	''' the contents of this method with the code editor.
	''' </summary>
	Private Sub InitializeComponent()
        Dim resources As System.ComponentModel.ComponentResourceManager = New System.ComponentModel.ComponentResourceManager(GetType(Form1))
        Me.pdfViewerControl1 = New Bytescout.PDFViewer.PDFViewerControl()
        Me.toolStrip1 = New System.Windows.Forms.ToolStrip()
        Me.tsbOpen = New System.Windows.Forms.ToolStripButton()
        Me.ToolStripSeparator1 = New System.Windows.Forms.ToolStripSeparator()
        Me.tsbExportToCSV = New System.Windows.Forms.ToolStripButton()
        Me.tsbExportToXLSX = New System.Windows.Forms.ToolStripButton()
        Me.toolStrip1.SuspendLayout
        Me.SuspendLayout
        '
        'pdfViewerControl1
        '
        Me.pdfViewerControl1.BackColor = System.Drawing.SystemColors.ButtonShadow
        Me.pdfViewerControl1.Dock = System.Windows.Forms.DockStyle.Fill
        Me.pdfViewerControl1.Location = New System.Drawing.Point(0, 25)
        Me.pdfViewerControl1.MouseMode = Bytescout.PDFViewer.MouseMode.Selection
        Me.pdfViewerControl1.Name = "pdfViewerControl1"
        Me.pdfViewerControl1.RegistrationKey = Nothing
        Me.pdfViewerControl1.RegistrationName = Nothing
        Me.pdfViewerControl1.ResetRotationOnPageChange = false
        Me.pdfViewerControl1.Scale = 100
        Me.pdfViewerControl1.SelectionColor = System.Drawing.Color.Red
        Me.pdfViewerControl1.ShowImageObjects = true
        Me.pdfViewerControl1.ShowTextObjects = true
        Me.pdfViewerControl1.ShowVectorObjects = true
        Me.pdfViewerControl1.Size = New System.Drawing.Size(842, 514)
        Me.pdfViewerControl1.TabIndex = 0
        '
        'toolStrip1
        '
        Me.toolStrip1.Items.AddRange(New System.Windows.Forms.ToolStripItem() {Me.tsbOpen, Me.ToolStripSeparator1, Me.tsbExportToCSV, Me.tsbExportToXLSX})
        Me.toolStrip1.Location = New System.Drawing.Point(0, 0)
        Me.toolStrip1.Name = "toolStrip1"
        Me.toolStrip1.Size = New System.Drawing.Size(842, 25)
        Me.toolStrip1.TabIndex = 1
        Me.toolStrip1.Text = "toolStrip1"
        '
        'tsbOpen
        '
        Me.tsbOpen.Image = Global.Sample_UI_Application.My.Resources.Resources.folder_page
        Me.tsbOpen.ImageTransparentColor = System.Drawing.Color.Magenta
        Me.tsbOpen.Name = "tsbOpen"
        Me.tsbOpen.Size = New System.Drawing.Size(80, 22)
        Me.tsbOpen.Text = "&Open PDF"
        '
        'ToolStripSeparator1
        '
        Me.ToolStripSeparator1.Name = "ToolStripSeparator1"
        Me.ToolStripSeparator1.Size = New System.Drawing.Size(6, 25)
        '
        'tsbExportToCSV
        '
        Me.tsbExportToCSV.Image = CType(resources.GetObject("tsbExportToCSV.Image"),System.Drawing.Image)
        Me.tsbExportToCSV.ImageTransparentColor = System.Drawing.Color.Magenta
        Me.tsbExportToCSV.Name = "tsbExportToCSV"
        Me.tsbExportToCSV.Size = New System.Drawing.Size(100, 22)
        Me.tsbExportToCSV.Text = "Export To CSV"
        '
        'tsbExportToXLSX
        '
        Me.tsbExportToXLSX.Image = CType(resources.GetObject("tsbExportToXLSX.Image"),System.Drawing.Image)
        Me.tsbExportToXLSX.ImageTransparentColor = System.Drawing.Color.Magenta
        Me.tsbExportToXLSX.Name = "tsbExportToXLSX"
        Me.tsbExportToXLSX.Size = New System.Drawing.Size(105, 22)
        Me.tsbExportToXLSX.Text = "Export To XLSX"
        '
        'Form1
        '
        Me.AutoScaleDimensions = New System.Drawing.SizeF(6!, 13!)
        Me.AutoScaleMode = System.Windows.Forms.AutoScaleMode.Font
        Me.ClientSize = New System.Drawing.Size(842, 539)
        Me.Controls.Add(Me.pdfViewerControl1)
        Me.Controls.Add(Me.toolStrip1)
        Me.Name = "Form1"
        Me.StartPosition = System.Windows.Forms.FormStartPosition.CenterScreen
        Me.Text = "Form1"
        Me.toolStrip1.ResumeLayout(false)
        Me.toolStrip1.PerformLayout
        Me.ResumeLayout(false)
        Me.PerformLayout

End Sub

	#End Region

	Private pdfViewerControl1 As Bytescout.PDFViewer.PDFViewerControl
	Private toolStrip1 As System.Windows.Forms.ToolStrip
    Private WithEvents tsbOpen As System.Windows.Forms.ToolStripButton
    Friend WithEvents ToolStripSeparator1 As Windows.Forms.ToolStripSeparator
    Friend WithEvents tsbExportToCSV As Windows.Forms.ToolStripButton
    Friend WithEvents tsbExportToXLSX As Windows.Forms.ToolStripButton
End Class

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF Suite Home Page

Explore ByteScout PDF Suite Documentation

Explore Samples

Sign Up for ByteScout PDF Suite Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

Form1.vb

      Imports System.Diagnostics
Imports System.Drawing
Imports System.Windows.Forms
Imports Bytescout.PDFExtractor

' This example requires 'PDF Viewer SDK' and 'PDF Extractor SDK' installed.
' Download link: http://cdn.bytescout.com/ByteScoutInstaller.exe

Public Partial Class Form1
    Inherits Form

	Public Sub New()
		InitializeComponent()
	End Sub

	Protected Overrides Sub OnLoad(e As EventArgs)

	    ' Preload document into viewer
	    pdfViewerControl1.InputFile = ".\sample_ocr.pdf"

	    MyBase.OnLoad(e)
	End Sub

	Private Sub tsbOpen_Click(ByVal sender As Object, ByVal e As EventArgs) Handles tsbOpen.Click

        Using openFileDialog As New OpenFileDialog()

            openFileDialog.Title = "Open PDF Document"
            openFileDialog.Filter = "PDF Files (*.pdf)|*.pdf|All Files|*.*"

            If openFileDialog.ShowDialog() = DialogResult.OK Then

                Me.Text = openFileDialog.FileName

                Cursor = Cursors.WaitCursor

                Try
                    pdfViewerControl1.InputFile = openFileDialog.FileName
                Catch exception As Exception
                    MessageBox.Show(exception.Message)
                Finally
                    Cursor = Cursors.[Default]
                End Try

            End If

        End Using

    End Sub

    Private Sub tsbExportToCSV_Click(sender As Object, e As EventArgs) Handles tsbExportToCSV.Click

        ' Get selections from viewer
        Dim selections As RectangleF() = pdfViewerControl1.SelectionInPoints

        Dim outputFile As String = ".\result.csv"

        Using csvExtractor As CSVExtractor = New CSVExtractor()

            ' Load document into extractor
            csvExtractor.LoadDocumentFromFile(pdfViewerControl1.InputFile)

            ' Enable OCR to recongize text from images
            csvExtractor.OCRMode = OCRMode.Auto
            csvExtractor.OCRResolution = 300
            csvExtractor.OCRLanguage = "eng"
            csvExtractor.OCRLanguageDataFolder = "c:\Program Files\Bytescout PDF Extractor SDK\net4.00\tessdata\"

            
            ' FYI, removing horizontal lines may increase the text recognition quality in some cases
            'csvExtractor.OCRImagePreprocessingFilters.AddHorizontalLinesRemover()
            ' Another filter able to improve the recognition 
            'csvExtractor.OCRImagePreprocessingFilters.AddGammaCorrection()

            ' If selection exists set the extraction area.
            ' Overwise it will extract the whole page.
            If selections.Length > 0 Then
                csvExtractor.SetExtractionArea(selections(0))
            End If

            ' Save extraction results to CSV files
            csvExtractor.SavePageCSVToFile(pdfViewerControl1.CurrentPageIndex, outputFile)

        End Using

        Process.Start(outputFile)

    End Sub

    Private Sub tsbExportToXLSX_Click(sender As Object, e As EventArgs) Handles tsbExportToXLSX.Click

        ' Get selections from viewer
        Dim selections As RectangleF() = pdfViewerControl1.SelectionInPoints

        Dim outputFile As String = ".\result.xlsx"

        Using xlsExtractor As XLSExtractor = New XLSExtractor()

            ' Load document into extractor
            xlsExtractor.LoadDocumentFromFile(pdfViewerControl1.InputFile)

            ' Enable OCR to recongize text from images
            xlsExtractor.OCRMode = OCRMode.Auto
            xlsExtractor.OCRResolution = 300
            xlsExtractor.OCRLanguage = "eng"
            xlsExtractor.OCRLanguageDataFolder = "c:\Program Files\Bytescout PDF Extractor SDK\net4.00\tessdata\"

            xlsExtractor.OutputFormat = SpreadseetOutputFormat.XLSX
            xlsExtractor.RichTextFormatting = false

            ' FYI, removing horizontal lines may increase the text recognition quality in some cases
            'xlsExtractor.OCRImagePreprocessingFilters.AddHorizontalLinesRemover()
            ' Another filter able to improve the recognition 
            'xlsExtractor.OCRImagePreprocessingFilters.AddGammaCorrection()

            ' If selection exists set the extraction area.
            ' Overwise it will extract the whole page.
            If selections.Length > 0 Then
                xlsExtractor.SetExtractionArea(selections(0))
            End If

            ' Save extraction results to CSV files
            xlsExtractor.SavePageToXLSFile(pdfViewerControl1.CurrentPageIndex, outputFile)

        End Using

        Process.Start(outputFile)

    End Sub
End Class

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF Suite Home Page

Explore ByteScout PDF Suite Documentation

Explore Samples

Sign Up for ByteScout PDF Suite Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

Program.vb

      Imports System.Collections.Generic
Imports System.Windows.Forms

NotInheritable Class Program
	Private Sub New()
	End Sub
	''' <summary>
	''' The main entry point for the application.
	''' </summary>
	<STAThread> _
	Friend Shared Sub Main()
		Application.EnableVisualStyles()
		Application.SetCompatibleTextRenderingDefault(False)
		Application.Run(New Form1())
	End Sub
End Class

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF Suite Home Page

Explore ByteScout PDF Suite Documentation

Explore Samples

Sign Up for ByteScout PDF Suite Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

app.config

      <?xml version="1.0" encoding="utf-8"?>
<configuration>
    <system.diagnostics>
        <sources>
            <!-- This section defines the logging configuration for My.Application.Log -->
            <source name="DefaultSource" switchName="DefaultSwitch">
                <listeners>
                    <add name="FileLog"/>
                    <!-- Uncomment the below section to write to the Application Event Log -->
                    <!--<add name="EventLog"/>-->
                </listeners>
            </source>
        </sources>
        <switches>
            <add name="DefaultSwitch" value="Information"/>
        </switches>
        <sharedListeners>
            <add name="FileLog" type="Microsoft.VisualBasic.Logging.FileLogTraceListener, Microsoft.VisualBasic, Version=8.0.0.0, Culture=neutral, PublicKeyToken=b03f5f7f11d50a3a, processorArchitecture=MSIL" initializeData="FileLogWriter"/>
            <!-- Uncomment the below section and replace APPLICATION_NAME with the name of your application to write to the Application Event Log -->
            <!--<add name="EventLog" type="System.Diagnostics.EventLogTraceListener" initializeData="APPLICATION_NAME"/> -->
        </sharedListeners>
    </system.diagnostics>
<startup><supportedRuntime version="v4.0" sku=".NETFramework,Version=v4.0"/></startup></configuration>