How to convert PDF to HTML programmatically in C#

If you are looking for a good solution for converting PDF files to a HTML programmatically, try our PDF Focus .Net.

1. Convert PDF file to HTML in C# and .Net:

					        public static void PdfToHtmlAsFiles()
        {
            string pdfFile = @"..\..\..\..\..\simple text.pdf";
            string htmlFile = Path.ChangeExtension(pdfFile, ".htm");

            PdfFocus f = new PdfFocus();

            // The same path where the final HTML document. This folder must already exist.
            f.HtmlOptions.ImageFolder = Path.GetDirectoryName(pdfFile);
            // This folder will be created by the component to store images.
            // Like a "zoo_images".
            f.HtmlOptions.ImageSubFolder = String.Format("{0}_images",
             Path.GetFileNameWithoutExtension(pdfFile));            
            f.HtmlOptions.ImageType = PdfFocus.CHtmlOptions.eHtmlImageType.Png;
            f.HtmlOptions.Title = "Zoo page";

            f.OpenPdf(pdfFile);

            if (f.PageCount > 0)
            {
                int result = f.ToHtml(htmlFile);
            }
        }

				

2. Convert PDF to HTML in memory using MemoryStream in C#:

					        public static void PdfToHtmlAsMemoryStream()
        {
            // We are using files only for demonstration.
            // The whole conversion process will be done in memory.
            string pdfFile = @"d:\Zoo.pdf";

            PdfFocus f = new PdfFocus();

            using (FileStream pdfStream = new FileStream(pdfFile, FileMode.Open))
            {
                f.OpenPdf(pdfStream);
                if (f.PageCount > 0)
                {
                    // Let's force the component to store images inside HTML document
                    // using base-64 encoding.
                    // Thus the component will not use HDD.
                    f.HtmlOptions.IncludeImageInHtml = true;
                    f.HtmlOptions.InlineCSS = true;

                    string html = f.ToHtml();
                // Here we have the HTML result as string object.
                }
            }              
        }
				

3. Convert PDF to HTML in memory as byte[] using C#:

					        public static void PdfToHtmlAsByteArray()
        {
            // We are using files only for demonstration.
            // The whole conversion process will be done in memory.
            string pdfFile = @"d:\Zoo.pdf";
            byte[] pdfBytes = File.ReadAllBytes(pdfFile);

            PdfFocus f = new PdfFocus();

            f.OpenPdf(pdfBytes);
            if (f.PageCount > 0)
            {
                // Let's force the component to store images inside HTML document
                // using base-64 encoding.
                // Thus the component will not use HDD.
                f.HtmlOptions.IncludeImageInHtml = true;
                f.HtmlOptions.InlineCSS = true;

                string html = f.ToHtml();
                // Here we have the HTML result as string object.
            }
        }