Convert PDF to HTML format in 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("....");

Document .Net supports these formats:

PDF DOCX RTF HTML Text Image
Create/Read/Write Create/Read/Write Create/Read/Write Create/Read/Write Create/Read/Write Create/Read(OCR)/Write

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/

            ConvertFromFile();
            ConvertFromStream();
        }

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

            // Specifying PdfLoadOptions we explicitly set that a loadable document is PDF.
            PdfLoadOptions pdfLO = new PdfLoadOptions()
            {
                // 'false' - means to load vector graphics as is. Don't transform it to raster images.
                RasterizeVectorGraphics = false,

                // The PDF format doesn't have real tables, in fact it's a set of orthogonal graphic lines.
                // In case of 'true' the component will detect and recreate tables from graphic lines.
                DetectTables = false,                
                // 'Disabled' - Never load embedded fonts in PDF. Use the fonts with the same name installed at the system or similar by font metrics.
				// 'Enabled' - Always load embedded fonts in PDF.
				// 'Auto' - Load only embedded fonts missing in the system. In other case, use the system fonts.				
                PreserveEmbeddedFonts = PropertyState.Auto
            };

            DocumentCore dc = DocumentCore.Load(inpFile, pdfLO);
            dc.Save(outFile, new HtmlFixedSaveOptions());
			
			// 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 PDF to HTML (using Stream).
        /// </summary>
		/// <remarks>
        /// Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-pdf-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.pdf";
            string outFile = @"ResultStream.html";
            byte[] inpData = File.ReadAllBytes(inpFile);
            byte[] outData = null;

            using (MemoryStream msInp = new MemoryStream(inpData))
            {
                // Specifying PdfLoadOptions we explicitly set that a loadable document is PDF.
                PdfLoadOptions pdfLO = new PdfLoadOptions()
                {
                    // 'false' - means to load vector graphics as is. Don't transform it to raster images.
                    RasterizeVectorGraphics = false,

                    // The PDF format doesn't have real tables, in fact it's a set of orthogonal graphic lines.
                    // In case of 'true' the component will detect and recreate tables from graphic lines.
                    DetectTables = false,
                    // 'Disabled' - Never load embedded fonts in PDF. Use the fonts with the same name installed at the system or similar by font metrics.
					// 'Enabled' - Always load embedded fonts in PDF.
					// 'Auto' - Load only embedded fonts missing in the system. In other case, use the system fonts.					
                    PreserveEmbeddedFonts = PropertyState.Auto
                };

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

                // Save the document to HTML format.
                using (MemoryStream outMs = new MemoryStream())
                {
                    dc.Save(outMs, new HtmlFixedSaveOptions() );
                    outData = outMs.ToArray(); 

			// Important for Linux: Install MS Fonts
			// sudo apt install ttf-mscorefonts-installer -y					
                }
                // 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.IO
Imports SautinSoft.Document

Namespace Example
    Friend Class Program
        Shared Sub Main(ByVal args() As String)
            ConvertFromFile()
            ConvertFromStream()
        End Sub
        ''' Get your free 100-day key here:   
        ''' https://sautinsoft.com/start-for-free/
        ''' <summary>
        ''' Convert PDF to HTML (file to file).
        ''' </summary>
        ''' <remarks>
        ''' Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-pdf-to-html-in-csharp-vb.php
        ''' </remarks>
        Private Shared Sub ConvertFromFile()
            Dim inpFile As String = "..\..\..\example.pdf"
            Dim outFile As String = "Result.html"

            ' Specifying PdfLoadOptions we explicitly set that a loadable document is PDF.
            Dim pdfLO As New PdfLoadOptions()
            With pdfLO
                .RasterizeVectorGraphics = False
                .DetectTables = False
                ' 'Disabled' - Never load embedded fonts in PDF. Use the fonts with the same name installed at the system or similar by font metrics.
                ' 'Enabled' - Always load embedded fonts in PDF.
                ' 'Auto' - Load only embedded fonts missing in the system. In other case, use the system fonts.
                .PreserveEmbeddedFonts = PropertyState.Auto
            End With

            ' RasterizeVectorGraphics = False
            ' This means to load vector graphics as is. Don't transform it to raster images.

            ' DetectTables = False
            ' This means don't detect tables.
            ' The PDF format doesn't have real tables, in fact it's a set of orthogonal graphic lines.
            ' Set it to 'True' and the component will detect and recreate tables from graphic lines.

            Dim dc As DocumentCore = DocumentCore.Load(inpFile, pdfLO)
            dc.Save(outFile, New HtmlFixedSaveOptions())
			
			' 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 PDF to HTML (using Stream).
        ''' </summary>
        ''' <remarks>
        ''' Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-pdf-to-html-in-csharp-vb.php
        ''' </remarks>
        Private Shared Sub ConvertFromStream()

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

            Using msInp As New MemoryStream(inpData)

                ' Specifying PdfLoadOptions we explicitly set that a loadable document is PDF.
                Dim pdfLO As New PdfLoadOptions()
                With pdfLO
                    .RasterizeVectorGraphics = False
                    .DetectTables = False
                    ' 'Disabled' - Never load embedded fonts in PDF. Use the fonts with the same name installed at the system or similar by font metrics.
                    ' 'Enabled' - Always load embedded fonts in PDF.
                    ' 'Auto' - Load only embedded fonts missing in the system. In other case, use the system fonts.
                    .PreserveEmbeddedFonts = PropertyState.Auto
                End With


                ' RasterizeVectorGraphics = False
                ' This means to load vector graphics as is. Don't transform it to raster images.

                ' DetectTables = False
                ' This means don't detect tables.
                ' The PDF format doesn't have real tables, in fact it's a set of orthogonal graphic lines.
                ' Set it to 'True' and the component will detect and recreate tables from graphic lines.

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

                ' 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 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.