Save document pages as HTML using C# and .NET


Load a document and save all pages as separate HTML documents.

Complete code

using System.IO;
using SautinSoft.Document;

namespace Example
{
    class Program
    {
        static void Main(string[] args)
        {
            // Get your free 100-day key here:   
            // https://sautinsoft.com/start-for-free/

            SeparateDocumentToHtmlPages();
        }
        /// <summary>
        /// Load a document and save all pages as separate HTML documents.
        /// </summary>
        /// <remarks>
        /// Details: https://sautinsoft.com/products/document/help/net/developer-guide/pagination-save-document-pages-as-html-net-csharp-vb.php
        /// </remarks>
        static void SeparateDocumentToHtmlPages()
        {
            string filePath = @"..\..\..\example.docx";
            DocumentCore dc = DocumentCore.Load(filePath);
            string folderPath = Path.GetFullPath(@"Result-files");
            DocumentPaginator dp = dc.GetPaginator();
            for (int i = 0; i < dp.Pages.Count; i++)
            {
                DocumentPage page = dp.Pages[i];
                Directory.CreateDirectory(folderPath);

                // Save the each page into HTML format.
                page.Save(folderPath + @"\Page - " + (i + 1).ToString() + ".html", SaveOptions.HtmlFixedDefault);
            }
            System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(folderPath) { UseShellExecute = true });
        }
    }
}

Download

Imports System.IO
Imports SautinSoft.Document

Namespace Example
	Friend Class Program
		Shared Sub Main(ByVal args() As String)
			SeparateDocumentToHtmlPages()
		End Sub
                ''' Get your free 100-day key here:   
                ''' https://sautinsoft.com/start-for-free/
		''' <summary>
		''' Load a document and save all pages as separate HTML documents.
		''' </summary>
		''' <remarks>
		''' Details: https://sautinsoft.com/products/document/help/net/developer-guide/pagination-save-document-pages-as-html-net-csharp-vb.php
		''' </remarks>
		Private Shared Sub SeparateDocumentToHtmlPages()
			Dim filePath As String = "..\..\..\example.docx"
			Dim dc As DocumentCore = DocumentCore.Load(filePath)
			Dim folderPath As String = Path.GetFullPath("Result-files")
			Dim dp As DocumentPaginator = dc.GetPaginator()
			For i As Integer = 0 To dp.Pages.Count - 1
				Dim page As DocumentPage = dp.Pages(i)
				Directory.CreateDirectory(folderPath)

				' Save the each page into HTML format.
				page.Save(folderPath & "\Page - " & (i + 1).ToString() & ".html", SaveOptions.HtmlFixedDefault)
			Next i
			System.Diagnostics.Process.Start(New System.Diagnostics.ProcessStartInfo(folderPath) With {.UseShellExecute = True})
		End Sub
	End Class
End Namespace

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.