Codecs: How to convert PDF to DOCX?

In This Topic

VintaSoft Imaging .NET SDK allows to convert PDF document to a DOCX document using class DocumentConverter, ImageCollection or PdfToDocxConverter. Usage of DocumentConverter class provides the best performance because DocumentConverter class uses multi-threading.

Here is C#/VB.NET code that shows how to convert PDF document to a DOCX document using DocumentConverter class:

/// <summary>
/// Converts PDF file to a DOCX file using Vintasoft.Imaging.DocumentConverter class.
/// </summary>
public static void ConvertPdfToDocx_DocumentConverter(string pdfFileName, string docxFileName)
{
    Vintasoft.Imaging.DocumentConverter.Convert(pdfFileName, docxFileName);
}

VB.NET

''' <summary>
''' Converts PDF file to a DOCX file using Vintasoft.Imaging.DocumentConverter class.
''' </summary>
Public Shared Sub ConvertPdfToDocx_DocumentConverter(pdfFileName As String, docxFileName As String)
    Vintasoft.Imaging.DocumentConverter.Convert(pdfFileName, docxFileName)
End Sub

Here is C#/VB.NET code that shows how to convert PDF document to a DOCX document using ImageCollection class:

/// <summary>
/// Converts PDF file to a DOCX file using Vintasoft.Imaging.ImageCollection class.
/// </summary>
public static void ConvertPdfToDocx_ImageCollection(string pdfFileName, string docxFileName)
{
    // create image collection
    using (Vintasoft.Imaging.ImageCollection imageCollection = new Vintasoft.Imaging.ImageCollection())
    {
        // add PDF document to collection
        imageCollection.Add(pdfFileName);

        // save images of image collection to a DOCX file
        imageCollection.SaveSync(docxFileName);

        // dispose images
        imageCollection.ClearAndDisposeItems();
    }
}

VB.NET

''' <summary>
''' Converts PDF file to a DOCX file using Vintasoft.Imaging.ImageCollection class.
''' </summary>
Public Shared Sub ConvertPdfToDocx_ImageCollection(pdfFileName As String, docxFileName As String)
    ' create image collection
    Using imageCollection As New Vintasoft.Imaging.ImageCollection()
        ' add PDF document to collection
        imageCollection.Add(pdfFileName)

        ' save images of image collection to a DOCX file
        imageCollection.SaveSync(docxFileName)

        ' dispose images
        imageCollection.ClearAndDisposeItems()
    End Using
End Sub

Here is C#/VB.NET code that shows how to convert PDF document to a DOCX document using PdfToDocxConverter class:

/// <summary>
/// Converts the PDF document to a DOCX document.
/// </summary>
/// <param name="inputPdfFilename">The name of input PDF file.</param>
/// <param name="outputDocxFilename">The name of output DOCX file.</param>
public static void ConvertPdfToDocx(string inputPdfFilename, string outputDocxFilename)
{
    // create converter that allows to convert PDF to DOCX
    using (Vintasoft.Imaging.Pdf.Office.PdfToDocxConverter converter = new Vintasoft.Imaging.Pdf.Office.PdfToDocxConverter())
    {
        // set output DOCX filename
        converter.OutputFilename = outputDocxFilename;

        // enable table detection
        converter.DetectTables = true;
        converter.TableDetectionCommand = new Vintasoft.Imaging.ImageProcessing.Info.TableDetection.TableWithBordersDetectionCommand();

        // set rendering settings, which should be used for rendering graphics content on PDF page
        converter.RenderingSettings = new Vintasoft.Imaging.Codecs.Decoders.RenderingSettings(new Vintasoft.Imaging.Resolution(96));

        using (Vintasoft.Imaging.Processing.ProcessingState processingState = new Vintasoft.Imaging.Processing.ProcessingState(ProgressHandler))
        {
            // execute conversion from PDF to DOCX
            converter.Execute(inputPdfFilename, processingState);
        }
    }
}

/// <summary>
/// Called when conversion progress is changing.
/// </summary>
/// <param name="sender">The sender.</param>
/// <param name="e">The <see cref="Vintasoft.Imaging.ProgressEventArgs"/> instance containing the event data.</param>
private static void ProgressHandler(object sender, Vintasoft.Imaging.ProgressEventArgs e)
{
    System.Console.WriteLine(string.Format("Conversion {0}%...", e.Progress));
}

VB.NET

''' <summary>
''' Converts the PDF document to a DOCX document.
''' </summary>
''' <param name="inputPdfFilename">The name of input PDF file.</param>
''' <param name="outputDocxFilename">The name of output DOCX file.</param>
Public Shared Sub ConvertPdfToDocx(inputPdfFilename As String, outputDocxFilename As String)
    ' create converter that allows to convert PDF to DOCX
    Using converter As New Vintasoft.Imaging.Pdf.Office.PdfToDocxConverter()
        ' set output DOCX filename
        converter.OutputFilename = outputDocxFilename

        ' enable table detection
        converter.DetectTables = True
        converter.TableDetectionCommand = New Vintasoft.Imaging.ImageProcessing.Info.TableDetection.TableWithBordersDetectionCommand()

        ' set rendering settings, which should be used for rendering graphics content on PDF page
        converter.RenderingSettings = New Vintasoft.Imaging.Codecs.Decoders.RenderingSettings(New Vintasoft.Imaging.Resolution(96))

        Using processingState As New Vintasoft.Imaging.Processing.ProcessingState(AddressOf ProgressHandler)
            ' execute conversion from PDF to DOCX
            converter.Execute(inputPdfFilename, processingState)
        End Using
    End Using
End Sub

''' <summary>
''' Called when conversion progress is changing.
''' </summary>
''' <param name="sender">The sender.</param>
''' <param name="e">The <see cref="Vintasoft.Imaging.ProgressEventArgs"/> instance containing the event data.</param>
Private Shared Sub ProgressHandler(sender As Object, e As Vintasoft.Imaging.ProgressEventArgs)
    System.Console.WriteLine(String.Format("Conversion {0}%...", e.Progress))
End Sub

Send Feedback