Link Search Menu Expand Document

Convert PDF To HTML From Uploaded File - C#

PDF to HTML sample in C# demonstrating ‘Convert PDF To HTML From Uploaded File’

Program.cs
using System;
using System.Collections.Generic;
using System.IO;
using System.Net;
using Newtonsoft.Json;
using Newtonsoft.Json.Linq;

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

		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);

			// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
			// * If you already have the direct file URL, skip to the step 3.
			
			// Prepare URL for `Get Presigned URL` API call
			string query = Uri.EscapeUriString(string.Format(
				"https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name={0}", 
				Path.GetFileName(SourceFile)));

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

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

				if (json["error"].ToObject<bool>() == false)
				{
					// Get URL to use for the file upload
					string uploadUrl = json["presignedUrl"].ToString();
					string uploadedFileUrl = json["url"].ToString();

					// 2. UPLOAD THE FILE TO CLOUD.

					webClient.Headers.Add("content-type", "application/octet-stream");
					webClient.UploadFile(uploadUrl, "PUT", SourceFile); // You can use UploadData() instead if your file is byte[] or Stream
					webClient.Headers.Remove("content-type");

					// 3. CONVERT UPLOADED PDF FILE TO HTML

					// URL for `PDF To HTML` API call
					var 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", uploadedFileUrl);

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

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

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

					if (json["error"].ToObject<bool>() == false)
					{
						// Get URL of generated HTML file
						string resultFileUrl = json["url"].ToString();

						// Download HTML file
						webClient.DownloadFile(resultFileUrl, DestinationFile);

						Console.WriteLine("Generated HTML file saved as \"{0}\" file.", DestinationFile);
					}
					else
					{
						Console.WriteLine(json["message"].ToString());
					}
				}
				else
				{
					Console.WriteLine(json["message"].ToString());
				}
			}
			catch (WebException e)
			{
				Console.WriteLine(e.ToString());
			}

			webClient.Dispose();

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

PDF.co Web API: the Web API with a set of tools for documents manipulation, data conversion, data extraction, splitting and merging of documents. Includes image recognition, built-in OCR, barcode generation and barcode decoders to decode bar codes from scans, pictures and pdf.

Get your PDF.co API key here!

Download Source Code (.zip)

return to the previous page explore PDF to HTML endpoint