ByteScout Premium Suite - C# - Convert Scanned PDF to Excel - ByteScout

ByteScout Premium Suite – C# – Convert Scanned PDF to Excel

  • Home
  • /
  • Articles
  • /
  • ByteScout Premium Suite – C# – Convert Scanned PDF to Excel

How to convert scanned PDF to excel in C# using ByteScout Premium Suite

If you want to learn more then this tutorial will show how to convert scanned PDF to excel in C#

These source code samples are assembled by their programming language and functions they apply. What is ByteScout Premium Suite? It is the set that includes 12 SDK products from ByteScout including tools and components for PDF, barcodes, spreadsheets, screen video recording. It can help you to convert scanned PDF to excel in your C# application.

Want to save time? You will save a lot of time on writing and testing code as you may just take the C# code from ByteScout Premium Suite for convert scanned PDF to excel below and use it in your application. This C# sample code is all you need for your app. Just copy and paste the code, add references (if needs to) and you are all set! If you want to use these C# sample examples in one or many applications then they can be used easily.

You can download free trial version of ByteScout Premium Suite from our website to see and try many others source code samples for C#.

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.cs
      
namespace Sample_UI_Application { partial class Form1 { /// <summary> /// Required designer variable. /// </summary> private System.ComponentModel.IContainer components = null; /// <summary> /// Clean up any resources being used. /// </summary> /// <param name="disposing">true if managed resources should be disposed; otherwise, false.</param> protected override void Dispose(bool disposing) { if (disposing && (components != null)) { components.Dispose(); } base.Dispose(disposing); } #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 void InitializeComponent() { System.ComponentModel.ComponentResourceManager resources = new System.ComponentModel.ComponentResourceManager(typeof(Form1)); this.pdfViewerControl1 = new Bytescout.PDFViewer.PDFViewerControl(); this.toolStrip1 = new System.Windows.Forms.ToolStrip(); this.tsbOpen = new System.Windows.Forms.ToolStripButton(); this.toolStripSeparator1 = new System.Windows.Forms.ToolStripSeparator(); this.tsbExportToCSV = new System.Windows.Forms.ToolStripButton(); this.tsbExportToXLSX = new System.Windows.Forms.ToolStripButton(); this.toolStrip1.SuspendLayout(); this.SuspendLayout(); // // pdfViewerControl1 // this.pdfViewerControl1.BackColor = System.Drawing.SystemColors.ButtonShadow; this.pdfViewerControl1.Dock = System.Windows.Forms.DockStyle.Fill; this.pdfViewerControl1.Location = new System.Drawing.Point(0, 25); this.pdfViewerControl1.MouseMode = Bytescout.PDFViewer.MouseMode.Selection; this.pdfViewerControl1.Name = "pdfViewerControl1"; this.pdfViewerControl1.RegistrationKey = null; this.pdfViewerControl1.RegistrationName = null; this.pdfViewerControl1.ResetRotationOnPageChange = false; this.pdfViewerControl1.Scale = 100; this.pdfViewerControl1.SelectionColor = System.Drawing.Color.Red; this.pdfViewerControl1.ShowImageObjects = true; this.pdfViewerControl1.ShowTextObjects = true; this.pdfViewerControl1.ShowVectorObjects = true; this.pdfViewerControl1.Size = new System.Drawing.Size(842, 514); this.pdfViewerControl1.TabIndex = 0; // // toolStrip1 // this.toolStrip1.Items.AddRange(new System.Windows.Forms.ToolStripItem[] { this.tsbOpen, this.toolStripSeparator1, this.tsbExportToCSV, this.tsbExportToXLSX}); this.toolStrip1.Location = new System.Drawing.Point(0, 0); this.toolStrip1.Name = "toolStrip1"; this.toolStrip1.Size = new System.Drawing.Size(842, 25); this.toolStrip1.TabIndex = 1; this.toolStrip1.Text = "toolStrip1"; // // tsbOpen // this.tsbOpen.Image = global::Sample_UI_Application.Properties.Resources.folder_page; this.tsbOpen.ImageTransparentColor = System.Drawing.Color.Magenta; this.tsbOpen.Name = "tsbOpen"; this.tsbOpen.Size = new System.Drawing.Size(80, 22); this.tsbOpen.Text = "&Open PDF"; this.tsbOpen.Click += new System.EventHandler(this.tsbOpen_Click); // // toolStripSeparator1 // this.toolStripSeparator1.Name = "toolStripSeparator1"; this.toolStripSeparator1.Size = new System.Drawing.Size(6, 25); // // tsbExportToCSV // this.tsbExportToCSV.Image = ((System.Drawing.Image)(resources.GetObject("tsbExportToCSV.Image"))); this.tsbExportToCSV.ImageTransparentColor = System.Drawing.Color.Magenta; this.tsbExportToCSV.Name = "tsbExportToCSV"; this.tsbExportToCSV.Size = new System.Drawing.Size(100, 22); this.tsbExportToCSV.Text = "Export To CSV"; this.tsbExportToCSV.Click += new System.EventHandler(this.tsbExportToCSV_Click); // // tsbExportToXLSX // this.tsbExportToXLSX.Image = ((System.Drawing.Image)(resources.GetObject("tsbExportToXLSX.Image"))); this.tsbExportToXLSX.ImageTransparentColor = System.Drawing.Color.Magenta; this.tsbExportToXLSX.Name = "tsbExportToXLSX"; this.tsbExportToXLSX.Size = new System.Drawing.Size(105, 22); this.tsbExportToXLSX.Text = "Export To XLSX"; this.tsbExportToXLSX.Click += new System.EventHandler(this.tsbExportToXLSX_Click); // // Form1 // this.AutoScaleDimensions = new System.Drawing.SizeF(6F, 13F); this.AutoScaleMode = System.Windows.Forms.AutoScaleMode.Font; this.ClientSize = new System.Drawing.Size(842, 539); this.Controls.Add(this.pdfViewerControl1); this.Controls.Add(this.toolStrip1); this.Name = "Form1"; this.StartPosition = System.Windows.Forms.FormStartPosition.CenterScreen; this.Text = "Form1"; this.toolStrip1.ResumeLayout(false); this.toolStrip1.PerformLayout(); this.ResumeLayout(false); this.PerformLayout(); } #endregion private Bytescout.PDFViewer.PDFViewerControl pdfViewerControl1; private System.Windows.Forms.ToolStrip toolStrip1; private System.Windows.Forms.ToolStripButton tsbOpen; private System.Windows.Forms.ToolStripSeparator toolStripSeparator1; private System.Windows.Forms.ToolStripButton tsbExportToCSV; private System.Windows.Forms.ToolStripButton tsbExportToXLSX; } }

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Premium Suite Home Page

Explore ByteScout Premium Suite Documentation

Explore Samples

Sign Up for ByteScout Premium Suite Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

Form1.cs
      
using System; using System.Diagnostics; using System.Drawing; using System.Windows.Forms; using Bytescout.PDFExtractor; namespace Sample_UI_Application { // This example requires 'PDF Viewer SDK' and 'PDF Extractor SDK' installed. // Download link: http://cdn.bytescout.com/ByteScoutInstaller.exe public partial class Form1 : Form { public Form1() { InitializeComponent(); } protected override void OnLoad(EventArgs e) { // Preload document into viewer pdfViewerControl1.InputFile = @".\sample_ocr.pdf"; base.OnLoad(e); } private void tsbOpen_Click(object sender, EventArgs e) { using (OpenFileDialog openFileDialog = new OpenFileDialog()) { openFileDialog.Title = @"Open PDF Document"; openFileDialog.Filter = @"PDF Files (*.pdf)|*.pdf|All Files|*.*"; if (openFileDialog.ShowDialog() == DialogResult.OK) { this.Text = openFileDialog.FileName; Cursor = Cursors.WaitCursor; try { pdfViewerControl1.InputFile = openFileDialog.FileName; } catch (Exception exception) { MessageBox.Show(exception.Message); } finally { Cursor = Cursors.Default; } } } } private void tsbExportToCSV_Click(object sender, EventArgs e) { // Get selections from viewer RectangleF[] selections = pdfViewerControl1.SelectionInPoints; string outputFile = @".\result.csv"; using (CSVExtractor csvExtractor = new CSVExtractor("demo", "demo")) { // 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\"; // There are double spaces between some words in your document. // To avoid such words break column structure increase the space ratio to 2. csvExtractor.DetectNewColumnBySpacesRatio = 2; // 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) csvExtractor.SetExtractionArea(selections[0]); // Save extraction results to CSV files csvExtractor.SavePageCSVToFile(pdfViewerControl1.CurrentPageIndex, outputFile); } Process.Start(outputFile); } private void tsbExportToXLSX_Click(object sender, EventArgs e) { // Get selections from viewer RectangleF[] selections = pdfViewerControl1.SelectionInPoints; string outputFile = @".\result.xlsx"; using (XLSExtractor xlsExtractor = new XLSExtractor("demo", "demo")) { // Load document into extractor xlsExtractor.LoadDocumentFromFile(pdfViewerControl1.InputFile); 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; // There are double spaces between some words in your document. // To avoid such words break column structure increase the space ratio to 2. xlsExtractor.DetectNewColumnBySpacesRatio = 2; // 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) xlsExtractor.SetExtractionArea(selections[0]); // Save extraction results to XLSX files xlsExtractor.SavePageToXLSFile(pdfViewerControl1.CurrentPageIndex, outputFile); } Process.Start(outputFile); } } }

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Premium Suite Home Page

Explore ByteScout Premium Suite Documentation

Explore Samples

Sign Up for ByteScout Premium Suite Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

Program.cs
      
using System; using System.Collections.Generic; using System.Windows.Forms; namespace Sample_UI_Application { static class Program { /// <summary> /// The main entry point for the application. /// </summary> [STAThread] static void Main() { Application.EnableVisualStyles(); Application.SetCompatibleTextRenderingDefault(false); Application.Run(new Form1()); } } }

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Premium Suite Home Page

Explore ByteScout Premium Suite Documentation

Explore Samples

Sign Up for ByteScout Premium 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> <startup><supportedRuntime version="v4.0" sku=".NETFramework,Version=v4.0"/></startup></configuration>

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Premium Suite Home Page

Explore ByteScout Premium Suite Documentation

Explore Samples

Sign Up for ByteScout Premium Suite Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

VIDEO

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Premium Suite Home Page

Explore ByteScout Premium Suite Documentation

Explore Samples

Sign Up for ByteScout Premium Suite Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

Tutorials:

prev
next