Link Search Menu Expand Document

Parse Uploaded File - C#

Document Parser sample in C# demonstrating ‘Parse Uploaded File’

MultiPageTable-template1.yml
templateName: Multipage Table Test
templateVersion: 4
templatePriority: 0
detectionRules:
  keywords:
  - Sample document with multi-page table
objects:
- name: total
  objectType: field
  fieldProperties:
    fieldType: macros
    expression: TOTAL{{Spaces}}({{Number}})
    regex: true
    dataType: decimal
- name: table1
  objectType: table
  tableProperties:
    start:
      expression: Item{{Spaces}}Description{{Spaces}}Price
      regex: true
    end:
      expression: TOTAL{{Spaces}}{{Number}}
      regex: true
    row:
      expression: '{{LineStart}}{{Spaces}}(?<itemNo>{{Digits}}){{Spaces}}(?<description>{{SentenceWithSingleSpaces}}){{Spaces}}(?<price>{{Number}}){{Spaces}}(?<qty>{{Digits}}){{Spaces}}(?<extPrice>{{Number}})'
      regex: true
    columns:
    - name: itemNo
      dataType: integer
    - name: description
      dataType: string
    - name: price
      dataType: decimal
    - name: qty
      dataType: integer
    - name: extPrice
      dataType: decimal
    multipage: true


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

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 = @".\MultiPageTable.pdf";
		// PDF document password. Leave empty for unprotected documents.
		const string Password = "";
		// Destination TXT file name
		const string DestinationFile = @".\result.json";

		static void Main(string[] args)
		{
			// Template text. Use Document Parser (https://pdf.co/document-parser, https://app.pdf.co/document-parser)
			// to create templates.
			// Read template from file:
			String templateText = File.ReadAllText(@".\MultiPageTable-template1.yml");

			// 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 a 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. PARSE UPLOADED PDF DOCUMENT

					// URL of `Document Parser` API call
					string url = "https://api.pdf.co/v1/pdf/documentparser";

                    Dictionary<string, string> requestBody = new Dictionary<string, string>();
                    requestBody.Add("template", templateText);
					requestBody.Add("name", Path.GetFileName(DestinationFile));
					requestBody.Add("url", uploadedFileUrl);

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

					// Execute request
					response = webClient.UploadString(url, "POST", jsonPayload);

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

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

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

						Console.WriteLine("Generated JSON 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 Document Parser endpoint