Saves a specific PDF page or range of pages in Text document and returns it as string

Namespace:  SautinSoft
Assembly:  SautinSoft.PdfFocus (in SautinSoft.PdfFocus.dll) Version: 6.6.9.7 (6.6.9.7)

Syntax

      
 C#  Visual Basic 
public string ToText(
	int fromPage,
	int toPage
)
Public Function ToText ( _
	fromPage As Integer, _
	toPage As Integer _
) As String

Parameters

fromPage
Int32
The starting page for export in Text document
toPage
Int32
The ending page for export in Text document

Return Value

String with Unicode Text - in case of converting successful
null - in case of converting failed

Remarks

To start the process, please download the most fresh version of PDF Focus .Net.



Examples

CopyHow to extract Text from 1nd page of PDF in C#
using System;
using System.IO;

namespace Sample
{
    class Sample
    {
        static void Main(string[] args)
        {
            string pdfFile = @"..\..\..\..\..\simple text.pdf";

            // Assume that we already have PDF as byte array
            byte[] pdfBytes = File.ReadAllBytes(pdfFile);            

            // Extract Text from PDF only from 1st page
            SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();
            //this property is necessary only for registered version
            //f.Serial = "XXXXXXXXXXX";

            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 = Path.ChangeExtension(pdfFile, ".txt");
                File.WriteAllText(textFile, textString);
                System.Diagnostics.Process.Start(textFile);
            }
        }
    }
}
CopyHow to Text from 1nd page of PDF in VB.Net
Imports System.IO
Imports System.Drawing.Imaging
Imports System.Collections.Generic
Imports SautinSoft

Module Sample

    Sub Main()
        Dim pdfFile As String = "..\..\..\..\simple text.pdf"

        ' Assume that we already have PDF as byte array
        Dim pdfBytes() As Byte = File.ReadAllBytes(pdfFile)

        ' Extract Text from PDF only from 1st page
        Dim f As New SautinSoft.PdfFocus()
        'this property is necessary only for registered version
        'f.Serial = "XXXXXXXXXXX";


        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 = Path.ChangeExtension(pdfFile, ".txt")
            File.WriteAllText(textFile, textString)
            System.Diagnostics.Process.Start(textFile)
        End If
    End Sub
End Module

See Also