Convert PDF To HTML From URL Asynchronously | C#ByteScout PDF To HTML SDK

Convert PDF To HTML From URL Asynchronously | C#

Program.cs:

C#
using System;
using System.IO;
using System.Net;
using Newtonsoft.Json.Linq;
using System.Threading;
using System.Collections.Generic;
using Newtonsoft.Json;


// Cloud API asynchronous "PDF To HTML" job example.
// Allows to avoid timeout errors when processing huge or scanned PDF documents.

namespace ByteScoutWebApiExample
{
    class Program
    {
        // The authentication key (API Key).
        // Get your own by registering at https://app.pdf.co
        const String API_KEY = "***********************************";

        // Direct URL of source PDF file.
        // You can also upload your own file into PDF.co and use it as url. Check "Upload File" samples for code snippets: https://github.com/bytescout/pdf-co-api-samples/tree/master/File%20Upload/
        const string SourceFileUrl = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-html/sample.pdf";
        // Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
        const string Pages = "";
        // PDF document password. Leave empty for unprotected documents.
        const string Password = "";
        // Destination HTML file name
        const string DestinationFile = @".\result.html";
        // Set to `true` to get simplified HTML without CSS. Default is the rich HTML keeping the document design.
        const bool PlainHtml = false;
        // Set to `true` if your document has the column layout like a newspaper.
        const bool ColumnLayout = false;
        // (!) Make asynchronous job
        const bool Async = true;


        static void Main(string[] args)
        {
            // Create standard .NET web client instance
            WebClient webClient = new WebClient();

            // Set API Key
            webClient.Headers.Add("x-api-key", API_KEY);

            try
            {
                // URL for `PDF To HTML` API call
                String url = "https://api.pdf.co/v1/pdf/convert/to/html";

                // Prepare requests params as JSON
                Dictionary<string, object> parameters = new Dictionary<string, object>();
                parameters.Add("name", Path.GetFileName(DestinationFile));
                parameters.Add("password", Password);
                parameters.Add("pages", Pages);
                parameters.Add("simple", PlainHtml);
                parameters.Add("columns", ColumnLayout);
                parameters.Add("url", SourceFileUrl);
                parameters.Add("async", Async);

                // Convert dictionary of params to JSON
                string jsonPayload = JsonConvert.SerializeObject(parameters);

                // Execute POST request with JSON payload
                string response = webClient.UploadString(url, jsonPayload);

                // Parse JSON response
                JObject json = JObject.Parse(response);

                if (json["error"].ToObject<bool>() == false)
                {
                    // Asynchronous job ID
                    string jobId = json["jobId"].ToString();
                    // URL of generated HTML file that will available after the job completion
                    string resultFileUrl = json["url"].ToString();

                    // Check the job status in a loop. 
                    // If you don't want to pause the main thread you can rework the code 
                    // to use a separate thread for the status checking and completion.
                    do
                    {
                        string status = CheckJobStatus(jobId); // Possible statuses: "working", "failed", "aborted", "success".

                        // Display timestamp and status (for demo purposes)
                        Console.WriteLine(DateTime.Now.ToLongTimeString() + ": " + status);

                        if (status == "success")
                        {
                            // Download HTML file
                            webClient.DownloadFile(resultFileUrl, DestinationFile);

                            Console.WriteLine("Generated HTML file saved as \"{0}\" file.", DestinationFile);
                            break;
                        }
                        else if (status == "working")
                        {
                            // Pause for a few seconds
                            Thread.Sleep(3000);
                        }
                        else
                        {
                            Console.WriteLine(status);
                            break;
                        }
                    }
                    while (true);
                }
                else
                {
                    Console.WriteLine(json["message"].ToString());
                }
            }
            catch (WebException e)
            {
                Console.WriteLine(e.ToString());
            }

            webClient.Dispose();

            Console.WriteLine();
            Console.WriteLine("Press any key...");
            Console.ReadKey();
        }

        static string CheckJobStatus(string jobId)
        {
            using (WebClient webClient = new WebClient())
            {
                // Set API Key
                webClient.Headers.Add("x-api-key", API_KEY);

                string url = "https://api.pdf.co/v1/job/check?jobid=" + jobId;

                string response = webClient.DownloadString(url);
                JObject json = JObject.Parse(response);

                return Convert.ToString(json["status"]);
            }
        }
    }
}