How to batch process PDF files in ASP.NET, C#, Delphi, VB.NET, and VBScript (VB6) using PDF Extractor SDK

This example demonstrates how to batch process PDF files using Bytescout PDF Extractor SDK and lists 5 code snippets below (ASP.net, C#, Delphi, VB.net, and VBScript).

You may also find helpful this article that shows how to reduce memory usage (when processing huge PDF files) by disabling page data caching in C#, VB.NET, and VBScript

Select your programming language:

• ASP.NET
• C#
• Delphi
• Visual Basic .NET
• VBScript (Visual Basic 6)

How to batch process PDF files in ASP.NET

using System;
using System.IO;
using Bytescout.PDFExtractor;

namespace BatchProcessing
{
    public partial class _Default : System.Web.UI.Page
    {
        protected void Page_Load(object sender, EventArgs e)
        {
            // Directory containing test files
            String inputFolder = Server.MapPath(@".\bin");

            // Create Bytescout.PDFExtractor.TextExtractor instance
            TextExtractor extractor = new TextExtractor();
            extractor.RegistrationName = "demo";
            extractor.RegistrationKey = "demo";

            Response.Clear();
            Response.ContentType = "text/html";

            // Get PDF files 
            string[] pdfFiles = Directory.GetFiles(inputFolder, "*.pdf");

            foreach (string file in pdfFiles)
            {
                // Load document
                extractor.LoadDocumentFromFile(file);

                // Save extracted text to output stream
                extractor.SaveTextToStream(Response.OutputStream);

                // Reset the extractor before load another file
                extractor.Reset();
            }

            Response.End();
        }
    }
}

How to batch process PDF files in C#

using System.IO;
using Bytescout.PDFExtractor;

namespace BatchProcessing
{
    class Program
    {
        static void Main()
        {
            // Create Bytescout.PDFExtractor.TextExtractor instance
            TextExtractor extractor = new TextExtractor();
            extractor.RegistrationName = "demo";
            extractor.RegistrationKey = "demo";

            // Get PDF files 
            string[] pdfFiles = Directory.GetFiles(".", "*.pdf");

            foreach (string file in pdfFiles)
            {
                // Load document
                extractor.LoadDocumentFromFile(file);

                // Save extracted text to .txt file
                extractor.SaveTextToFile(Path.ChangeExtension(file, ".txt"));

                // Reset the extractor before load another file
                extractor.Reset();
            }
        }
    }
}

How to batch process PDF files in Delphi

program Project1;

{$APPTYPE CONSOLE}

{
 IMPORTANT:
  To work with Bytescout PDF Extractor SDK you need to import this as a component into Delphi
 To import Bytescout PDF Extractor SDK into Delphi 2006 or higher do the following:
 1) Click Component | Import Component..
 2) Select Type Library and click Next
 3) Find and select Bytescout PDF Extractor SDK in the list of available type libraries and
 4) Click Next
 5) Click Next on next screen
 6) Select "Add Bytescout_PDFExtractor_TLB.pas" into Project" and click Finish
 This will add Bytescout_PDFExtractor_TLB.pas into your project and now you can use TextExtractor, InfoExtractor, CSVExtractor, XMLExtractor, ImageExtractor object interfaces (_TextExtractor, _InfoExtractor, _CSVExtractor, _XMLExtractor, _ImageExtractor classes)
 For Delphi 5,6,7,8 / C++ Builder 5,6,7,8 (for 2006 or higher versions please see above)
1) Start Delphi (or C++ Builder)
2) Select Component menu and "Import ActiveX control.."
3) Find the library in the list of available ActiveX/COM objects
4) Select this library and click "Install" 
5) Create a new package for this library imported (for example, TPDFExtractorSDKActiveX)
6) Click OK
7) Answer "Yes" when Delphi (or C++ Builder) asks to rebuild the package
8) The IDE will rebuild the package and will inform that the control has been installed. Close the package and answer "Yes" to save changes
9) The library object is now available on "ActiveX" tab on Tools Pallete. You can simply drag and drop it into the form in your application and use it
}

uses
  SysUtils,
  ActiveX,
  Bytescout_PDFExtractor_TLB in 'c:\program files\borland\bds\4.0\Imports\Bytescout_PDFExtractor_TLB.pas';

var
 extractor: _CSVExtractor;
begin
 CoInitialize(nil);

// Create Bytescout.PDFExtractor.CSVExtractor object using CoCSVExtractor class
 extractor := CoCSVExtractor.Create();


 extractor.RegistrationName := 'demo';
 extractor.RegistrationKey := 'demo';

 // Load sample PDF document
 extractor.LoadDocumentFromFile ('../../sample3.pdf');

// extractor.CSVSeparatorSymbol = ','; // you can change CSV separator symbol (if needed) from "," symbol to another if needed for non-US locales

 extractor.SaveCSVToFile ('output.csv');

 // reset the extractor so could load another file
 extractor.Reset();

 // now load another file
 // Load sample PDF document
 extractor.LoadDocumentFromFile ('../../sample2.pdf');

 extractor.SaveCSVToFile ('output2.csv');


 // destroy the extractor object
 extractor := nil;

end.

How to batch process PDF files in Visual Basic .NET

Imports Bytescout.PDFExtractor
Imports System.IO

Module Module1

    Sub Main()

        ' Create Bytescout.PDFExtractor.TextExtractor instance
        Dim extractor = New TextExtractor()
        extractor.RegistrationName = "demo"
        extractor.RegistrationKey = "demo"

        ' Get PDF files 
        Dim pdfFiles() = Directory.GetFiles(".", "*.pdf")

        For Each file As String In pdfFiles

            ' Load document
            extractor.LoadDocumentFromFile(file)

            ' Save extracted text to .txt file
            extractor.SaveTextToFile(Path.ChangeExtension(file, ".txt"))

            ' Reset the extractor before load another file
            extractor.Reset()

        Next

    End Sub

End Module

How to batch process PDF files in VBScript (Visual Basic 6)

' Create Bytescout.PDFExtractor.TextExtractor object
Set extractor = CreateObject("Bytescout.PDFExtractor.TextExtractor")
extractor.RegistrationName = "demo"
extractor.RegistrationKey = "demo"

' Get all files in folder
Set objFSO = CreateObject("Scripting.FileSystemObject")
Set objFolder = objFSO.GetFolder("..\..")
Set colFiles = objFolder.Files

' Convert every PDF file to text 
For Each objFile In colFiles
	if objFSO.GetExtensionName(objFile) = "pdf" Then
		' Load PDF file
    	extractor.LoadDocumentFromFile objFile.Path
    	' Save extracted text to .txt file
    	extractor.SaveTextToFile Replace(objFile.Name, "." & objFSO.GetExtensionName(objFile),".txt")
    	' Reset the extractor before load another file
    	extractor.Reset
    End If
Next