convert a pdf into html in csharp

main.cs
using System.IO;
using iTextSharp.text;
using iTextSharp.text.pdf;
using iTextSharp.tool.xml;

class Program
{
    static void Main(string[] args)
    {
        // Load the PDF file
        var pdfReader = new PdfReader("example.pdf");

        // Create a string writer to hold the HTML output
        var stringWriter = new StringWriter();

        // Set up the HTML conversion options
        var htmlContext = new HtmlPipelineContext(null);
        htmlContext.SetTagFactory(Tags.GetHtmlTagProcessorFactory());

        // Create a PDF-to-HTML converter
        var pdfToHtml = new PdfToHtmlConverter();

        // Set the output writer and conversion options
        pdfToHtml.SetOpenFile(false);
        pdfToHtml.SetHtmlStyleClass("pdf2html");
        pdfToHtml.SetDestinationEncoding("UTF-8");
        pdfToHtml.SetContext(htmlContext);
        pdfToHtml.SetHtmlWriter(new XMLWorkerHelper().GetDefaultCssResolver(true), stringWriter);

        // Convert the PDF to HTML
        pdfToHtml.ConvertPdf(pdfReader);

        // Display the HTML output
        Console.WriteLine(stringWriter.ToString());
    }
}
1118 chars
37 lines