Convert only tables from PDF to Excel in C# and .NET


Complete code

using System;
using System.IO;

namespace Sample
{
    class Sample
    {
        static void Main(string[] args)
        {
            string pathToPdf = Path.GetFullPath(@"..\..\..\Table.pdf");
            string pathToExcel = "Result.xlsx";
                                  // Get your free 30-day key here:   
			 // https://sautinsoft.com/start-for-free/
			
            // Convert only tables from PDF to XLS spreadsheet and skip all textual data.
            SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();

            // The output result will be in XLSX (Excel modern format) or in XLS (Excel 97-2003 Workbook)
            f.ExcelOptions.Format = SautinSoft.PdfFocus.Format.Xlsx;
            // f.ExcelOptions.Format = SautinSoft.PdfFocus.Format.Xls;
            
            // 'true' = Convert all data to spreadsheet (tabular and even textual).
            // 'false' = Skip textual data and convert only tabular (tables) data.
            f.ExcelOptions.ConvertNonTabularDataToSpreadsheet = false;

            // 'true'  = Preserve original page layout.
            // 'false' = Place tables before text.
            f.ExcelOptions.PreservePageLayout = true;

            // The information includes the names for the culture, the writing system, 
            // the calendar used, the sort order of strings, and formatting for dates and numbers.
            System.Globalization.CultureInfo ci = new System.Globalization.CultureInfo("en-US");
            ci.NumberFormat.NumberDecimalSeparator = ",";
            ci.NumberFormat.NumberGroupSeparator = ".";
            f.ExcelOptions.CultureInfo = ci;

            f.OpenPdf(pathToPdf);

            if (f.PageCount > 0)
            {
                int result = f.ToExcel(pathToExcel);
                
                // Open the resulted Excel workbook.
                if (result==0)
                {
					System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(pathToExcel) { UseShellExecute = true });                    
                }
            }
        }
    }
}

Download

Imports System.IO
Imports System.Drawing.Imaging
Imports System.Collections.Generic
Imports SautinSoft

Module Sample

    Sub Main()
        Dim pathToPdf As String = Path.GetFullPath("..\..\..\Table.pdf")
        Dim pathToExcel As String = "Result.xlsx"
                                ' Get your free 30-day key here: 
                                ' https://sautinsoft.com/start-for-free/
		
        ' Convert only tables from PDF to XLS spreadsheet and skip all textual data.
        Dim f As New SautinSoft.PdfFocus()
		
		' The output result will be in XLSX (Excel modern format) or in XLS (Excel 97-2003 Workbook)
        f.ExcelOptions.Format = SautinSoft.PdfFocus.Format.Xlsx
        ' f.ExcelOptions.Format = SautinSoft.PdfFocus.Format.Xls

		
        ' 'true' = Convert all data to spreadsheet (tabular and even textual).
        ' 'false' = Skip textual data and convert only tabular (tables) data.
        f.ExcelOptions.ConvertNonTabularDataToSpreadsheet = False

        ' 'true'  = Preserve original page layout.
        ' 'false' = Place tables before text.
        f.ExcelOptions.PreservePageLayout = True

        ' The information includes the names for the culture, the writing system, 
        ' the calendar used, the sort order of strings, and formatting for dates and numbers.
        Dim ci As New System.Globalization.CultureInfo("en-US")
        ci.NumberFormat.NumberDecimalSeparator = ","
        ci.NumberFormat.NumberGroupSeparator = "."
        f.ExcelOptions.CultureInfo = ci

        f.OpenPdf(pathToPdf)

        If f.PageCount > 0 Then
            Dim result As Integer = f.ToExcel(pathToExcel)

            ' Open the resulted Excel workbook.
            If result = 0 Then
                System.Diagnostics.Process.Start(New System.Diagnostics.ProcessStartInfo(pathToExcel) With {.UseShellExecute = True})
            End If
        End If
    End Sub
End Module

Download


If you need a new code example or have a question: email us at support@sautinsoft.com or ask at Online Chat (right-bottom corner of this page) or use the Form below:



Questions and suggestions from you are always welcome!

We are developing .Net components since 2002. We know PDF, DOCX, RTF, HTML, XLSX and Images formats. If you need any assistance with creating, modifying or converting documents in various formats, we can help you. We will write any code example for you absolutely free.