Extract Text from PDF only from 1st page in memory
using C# and VB.NET
Complete code.
using System;
using System.IO;
namespace Sample
{
class Sample
{
static void Main(string[] args)
{
string pdfFile = @"..\..\Potato Beetle.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);
}
}
}
}
Imports System.IO
Imports System.Drawing.Imaging
Imports System.Collections.Generic
Imports SautinSoft
Module Sample
Sub Main()
Dim pdfFile As String = "..\Potato Beetle.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
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: