Extract Text from PDF only from 1st page in memory using C# and .NET


Complete code

using System;
using System.IO;

namespace Sample
{
    class Sample
    {
        static void Main(string[] args)
        {
            string pdfFile = Path.GetFullPath(@"..\..\..\Potato Beetle.pdf");

            // Assume that we already have PDF as byte array
            byte[] pdfBytes = File.ReadAllBytes(pdfFile);            
                                  // Get your free 30-day key here:   
			 // https://sautinsoft.com/start-for-free/
			
            // Extract Text from PDF only from 1st page
            SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();
	    	
            f.OpenPdf(pdfFile);

            if (f.PageCount > 0)
            {
                // Convert only 1st page
                string textString = f.ToText(1,1);

                // Save 'textString' to a file only for demonstration purposes.                
                string textFile = "Result.txt";
                File.WriteAllText(textFile, textString);
                System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(textFile) { UseShellExecute = true });
            }
        }
    }
}

Download

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

Module Sample

    Sub Main()
        Dim pdfFile As String = Path.GetFullPath("..\..\..\Potato Beetle.pdf")

        ' Assume that we already have PDF as byte array
        Dim pdfBytes() As Byte = File.ReadAllBytes(pdfFile)
                                ' Get your free 30-day key here: 
                                ' https://sautinsoft.com/start-for-free/
		
        ' Extract Text from PDF only from 1st page
        Dim f As New SautinSoft.PdfFocus()

        f.OpenPdf(pdfFile)

        If f.PageCount > 0 Then
            ' Convert only 1st page
            Dim textString As String = f.ToText(1, 1)

            ' Save 'textString' to a file only for demonstration purposes.                
            Dim textFile As String = "Result.txt"
            File.WriteAllText(textFile, textString)
            System.Diagnostics.Process.Start(New System.Diagnostics.ProcessStartInfo(textFile) With {.UseShellExecute = True})
        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.