Extract Text By Pages from PDF | VB.NETByteScout PDF Extractor SDK

Extract Text By Pages from PDF | VB.NET

Program.vb:

VB
Imports Bytescout.PDFExtractor

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(".\sample2.pdf")

        ' Get page count
        Dim pageCount As Integer = extractor.GetPageCount()

        For i As Integer = 0 To pageCount - 1
            Dim fileName As String = "page" & i & ".txt"

            ' Save extracted page text to file
            extractor.SavePageTextToFile(i, fileName)
        Next

        ' Cleanup
        extractor.Dispose()

        ' Open result file in default associated application (for demo purposes)
        System.Diagnostics.Process.Start(".\page1.txt")

    End Sub
End Class