Imports Bytescout.PDFExtractor

' This example demonstrates the use of Optical Character Recognition (OCR) with "OCRMaximizeCPUUtilization" property to extract text
' from scanned PDF documents and raster images.

' To make OCR work you should add the following references to your project:
' "Bytescout.PDFExtractor.dll", "Bytescout.PDFExtractor.OCRExtension.dll".

Class Program

    Friend Shared Sub Main(args As String())

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

        ' Load sample PDF document
        extractor.LoadDocumentFromFile("sample_ocr.pdf")

        ' Enable Optical Character Recognition (OCR)
        ' in .Auto mode (SDK automatically checks if needs to use OCR or not)
        extractor.OCRMode = OCRMode.Auto

        ' Set the location of OCR language data files
        extractor.OCRLanguageDataFolder = "c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\"

        ' Set OCR language
        extractor.OCRLanguage = "eng"  ' "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in "ocrdata" folder
        ' Find more language files at https://github.com/bytescout/ocrdata

        ' Set PDF document rendering resolution
        extractor.OCRResolution = 300

        ' Enables max use of CPU And max use of multiple threads during OCR
        extractor.OCRMaximizeCPUUtilization = True

        ' Save extracted text to file
        extractor.SaveTextToFile("output.txt")

        ' Cleanup
        extractor.Dispose()

        ' Open output file in default associated application
        System.Diagnostics.Process.Start("output.txt")

    End Sub

End Class