using System;
using System.Diagnostics;
using System.IO;
using Bytescout.PDF2HTML;

namespace ExtractHTMLFromPage
{
    class Program
    {
        static void Main(string[] args)
        {
            // Create Bytescout.PDF2HTML.HTMLExtractor instance
            HTMLExtractor extractor = new HTMLExtractor();
            extractor.RegistrationName = "demo";
            extractor.RegistrationKey = "demo";

            // Set HTML with CSS extraction mode
            extractor.ExtractionMode = HTMLExtractionMode.HTMLWithCSS;

            // Input file Url
            var inputUrl = @"https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-text/sample.pdf";

            // Get Input Stream
            var inpStream = GetStreamFromUrl(inputUrl);

            // Load sample PDF document
            extractor.LoadDocumentFromStream(inpStream);

            // Convert 1-st page to HTML and save it to file
            extractor.SaveHtmlPageToFile(0, "output.html");

            // Cleanup
            extractor.Dispose();

            // Open result document in default associated application (for demo purpose)
            ProcessStartInfo processStartInfo = new ProcessStartInfo("output.html");
            processStartInfo.UseShellExecute = true;
            Process.Start(processStartInfo);
        }

        /// <summary>
        /// Get stream from Url
        /// </summary>
        private static Stream GetStreamFromUrl(string url)
        {
            byte[] oData = null;

            using (var wc = new System.Net.WebClient())
                oData = wc.DownloadData(url);

            return new MemoryStream(oData);
        }

    }
}