Convert each PDF page to separate DOCX documents in C# and .NET


This simple Console App shows how to convert each page of PDF document into a separate DOCX file with the name "{filename} - page {number}.docx".

Complete code

using System;
using System.IO;

namespace Sample
{
    class Sample
    {
        static void Main(string[] args)
        {
            // Convert whole PDF document to separate Word documents.
            // Each PDF page will be converted to a single Word document.

            // Path to a PDF file.
            string pdfPath = Path.GetFullPath(@"..\..\..\simple text.pdf");

            // Directory to store Word documents.
            string docxDir = Directory.GetCurrentDirectory();
                                             // Get your free 30-day key here:   
            // https://sautinsoft.com/start-for-free/
			
            SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();

            f.OpenPdf(pdfPath);

            // Convert each PDF page to separate Word document.
            // simple text - page 1.docx, simple text- page 2.docx ... simple text - page N.doc.
            for (int page = 1; page <= f.PageCount; page++)
            {
                // You may select between Docx and Rtf formats.
                f.WordOptions.Format = SautinSoft.PdfFocus.CWordOptions.eWordDocument.Docx;

                byte [] docxBytes = f.ToWord(page, page);

                string tempName = Path.GetFileNameWithoutExtension(pdfPath) + String.Format(" - page {0}.docx", page);
                string docxPath = Path.Combine(docxDir, tempName);
                File.WriteAllBytes(docxPath, docxBytes);

                // Let's show first and last Word pages.
                if (page == 1 || page==f.PageCount)
                    System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(docxPath) { UseShellExecute = true });
            }
        }
    }
}

Download

Imports System.IO
Imports System.Drawing.Imaging
Imports System.Collections.Generic
Imports SautinSoft

Module Sample

    Sub Main()
        ' Convert whole PDF document to separate Word documents.
        ' Each PDF page will be converted to a single Word document.

        ' Path to a PDF file.
        Dim pdfPath As String = Path.GetFullPath("..\..\..\simple text.pdf")

        ' Directory to store Word documents.
        Dim docxDir As String = Directory.GetCurrentDirectory()
                                ' Get your free 30-day key here: 
                                ' https://sautinsoft.com/start-for-free/
		
        Dim f As New SautinSoft.PdfFocus()

        f.OpenPdf(pdfPath)

        ' Convert each PDF page to separate Word document.
        ' simple text - page 1.docx, simple text- page 2.docx ... simple text - page N.doc.
        For page As Integer = 1 To f.PageCount

            ' You may select between Docx and Rtf formats.
            f.WordOptions.Format = SautinSoft.PdfFocus.CWordOptions.eWordDocument.Docx

            Dim docxBytes() As Byte = f.ToWord(page, page)

            Dim tempName As String = Path.GetFileNameWithoutExtension(pdfPath) & String.Format(" - page {0}.docx", page)
            Dim docxPath As String = Path.Combine(docxDir, tempName)
            File.WriteAllBytes(docxPath, docxBytes)

            ' Let's show first and last Word pages.
            If page = 1 OrElse page = f.PageCount Then
                System.Diagnostics.Process.Start(New System.Diagnostics.ProcessStartInfo(docxPath) With {.UseShellExecute = True})
            End If
        Next page
    End Sub
End Module

Download

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:


Questions and suggestions from you are always welcome!

We are developing .Net components since 2002. We know PDF, DOCX, RTF, HTML, XLSX and Images formats. If you need any assistance with creating, modifying or converting documents in various formats, we can help you. We will write any code example for you absolutely free.