Convert DOCX to HTML format within C# and .NET

  1. Add SautinSoft.Document from Nuget.
  2. Load an input document.
  3. Save to a HTML format.

Document .Net can help your application to convert a document from a one format to another.
You'll need only to Load() a document and Save() to a desired format:


            DocumentCore dc = DocumentCore.Load("...");
            dc.Save("....");

Complete code

using System.IO;
using SautinSoft.Document;

namespace Example
{
    class Program
    {
        static void Main(string[] args)
        {
            // Get your free trial key here:   
            // https://sautinsoft.com/start-for-free/

            ConvertFromFile();
            ConvertFromStream();
        }

        /// <summary>
        /// Convert DOCX to HTML (file to file).
        /// </summary>
		/// <remarks>
        /// Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-docx-to-html-in-csharp-vb.php
        /// </remarks>
        static void ConvertFromFile()
        {
            string inpFile = @"..\..\..\example.docx";
            string outFile = @"Result.html";

            DocumentCore dc = DocumentCore.Load(inpFile);
            dc.Save(outFile);
			
			// Important for Linux: Install MS Fonts
			// sudo apt install ttf-mscorefonts-installer -y

            // Open the result for demonstration purposes.
            System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile) { UseShellExecute = true });
        }

        /// <summary>
        /// Convert DOCX to HTML (using Stream).
        /// </summary>
		/// <remarks>
        /// Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-docx-to-html-in-csharp-vb.php
        /// </remarks>
        static void ConvertFromStream()
        {

            // We need files only for demonstration purposes.
            // The conversion process will be done completely in memory.
            string inpFile = @"..\..\..\example.docx";
            string outFile = @"ResultStream.html";
            byte[] inpData = File.ReadAllBytes(inpFile);
            byte[] outData = null;

            using (MemoryStream msInp = new MemoryStream(inpData))
            {

                // Load a document.
                DocumentCore dc = DocumentCore.Load(msInp, new DocxLoadOptions());

                // Save the document to HTML format.
                using (MemoryStream outMs = new MemoryStream())
                {
                    dc.Save(outMs, new HtmlFixedSaveOptions());
					
					// Important for Linux: Install MS Fonts
					// sudo apt install ttf-mscorefonts-installer -y
			
                    outData = outMs.ToArray();
                }
                // Show the result for demonstration purposes.
                if (outData != null)
                {
                    File.WriteAllBytes(outFile, outData);
                    System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile) { UseShellExecute = true });
                }
            }
        }
    }
}

Download

Imports System
Imports System.IO
Imports SautinSoft.Document

Module Sample
    Sub Main()
        ConvertFromFile()
        ConvertFromStream()
    End Sub
    ''' Get your free trial key here:   
    ''' https://sautinsoft.com/start-for-free/
    ''' <summary>
    ''' Convert DOCX to HTML (file to file).
    ''' </summary>
    ''' <remarks>
    ''' Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-docx-to-html-in-csharp-vb.php
    ''' </remarks>
    Sub ConvertFromFile()
        Dim inpFile As String = "..\..\..\example.docx"
        Dim outFile As String = "Result.html"

        Dim dc As DocumentCore = DocumentCore.Load(inpFile)
        dc.Save(outFile)
		
		' Important for Linux: Install MS Fonts
		' sudo apt install ttf-mscorefonts-installer -y

        ' Open the result for demonstration purposes.
        System.Diagnostics.Process.Start(New System.Diagnostics.ProcessStartInfo(outFile) With {.UseShellExecute = True})
    End Sub

    ''' <summary>
    ''' Convert DOCX to HTML (using Stream).
    ''' </summary>
    ''' <remarks>
    ''' Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-docx-to-html-in-csharp-vb.php
    ''' </remarks>
    Sub ConvertFromStream()

        ' We need files only for demonstration purposes.
        ' The conversion process will be done completely in memory.
        Dim inpFile As String = "..\..\..\example.docx"
        Dim outFile As String = "ResultStream.html"
        Dim inpData() As Byte = File.ReadAllBytes(inpFile)
        Dim outData() As Byte = Nothing

        Using msInp As New MemoryStream(inpData)

            ' Load a document.
            Dim dc As DocumentCore = DocumentCore.Load(msInp, New DocxLoadOptions())

            ' Save the document to HTML format.
            Using outMs As New MemoryStream()
                dc.Save(outMs, New HtmlFixedSaveOptions())
                outData = outMs.ToArray()
            End Using
            ' Show the result for demonstration purposes.
            If outData IsNot Nothing Then
                File.WriteAllBytes(outFile, outData)
                System.Diagnostics.Process.Start(New System.Diagnostics.ProcessStartInfo(outFile) With {.UseShellExecute = True})
            End If
        End Using
    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:

Captcha

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.