Cloud API - PDF To Text - C# - Convert PDF To Text From URL Asynchronously - ByteScout

Cloud API – PDF To Text – C# – Convert PDF To Text From URL Asynchronously

  • Home
  • /
  • Articles
  • /
  • Cloud API – PDF To Text – C# – Convert PDF To Text From URL Asynchronously

Cloud API – PDF To Text – C# – Convert PDF To Text From URL Asynchronously

Program.cs

using System;
using System.IO;
using System.Net;
using System.Threading;
using Newtonsoft.Json.Linq;

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

namespace ByteScoutWebApiExample
{
	class Program
	{
		// (!) If you are getting '(403) Forbidden' error please ensure you have set the correct API_KEY
		
		// The authentication key (API Key).
		// Get your own by registering at https://secure.bytescout.com/users/sign_up
		const String API_KEY = "***********************************";
		
		// Direct URL of source PDF file.
		const string SourceFileUrl = "https://s3-us-west-2.amazonaws.com/bytescout-com/files/demo-files/cloud-api/pdf-to-text/long-processed-document.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 TXT file name
		const string DestinationFile = @".\result.txt";
		// (!) 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);

			// Prepare URL for `PDF To Text` API call
			string query = Uri.EscapeUriString(string.Format(
				"https://api.pdf.co/v1/pdf/convert/to/text?name={0}&password={1}&pages={2}&url={3}&async={4}",
				Path.GetFileName(DestinationFile),
				Password,
				Pages,
				SourceFileUrl,
				Async));

			try
			{
				// Execute request
				string response = webClient.DownloadString(query);

				// 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 TXT file that will be 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: "InProgress", "Failed", "Aborted", "Finished".

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

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

							Console.WriteLine("Generated TXT file saved as \"{0}\" file.", DestinationFile);
							break;
						}
						else if (status == "InProgress")
						{
							// 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())
			{
				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"]);
			}
		}
	}
}


  Click here to get your Free Trial version of the SDK

Tutorials:

prev
next