Link Search Menu Expand Document

Advanced Conversion Options - C#

PDF To TEXT sample in C# demonstrating ‘Advanced Conversion Options’

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 = "***********************************";

        // 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-text/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 TXT file name
		const string DestinationFile = @".\result.txt";

		/*
		Some of advanced options available through profiles:
		(JSON can be single/double-quoted and contain comments.)
		{
		    "profiles": [
		        {
		            "profile1": {                
		                "ExtractInvisibleText": true, // Invisible text extraction. Values: true / false
		                "ExtractShadowLikeText": true, // Shadow-like text extraction. Values: true / false
		                "ExtractAnnotations": true, // Whether to extract PDF annotations.
		                "CheckPermissions": true, // Ignore document permissions. Values: true / false
		                "DetectNewColumnBySpacesRatio": 1.2, // A ratio affecting number of spaces between words. 
		            }
		        }
		    ]
		}
		*/
		
        // Sample profile that sets advanced conversion options
        // Advanced options are properties of TextExtractor class from ByteScout Text Extractor SDK used in the back-end:
        // https://cdn.bytescout.com/help/BytescoutPDFExtractorSDK/html/8a2bae5a-346f-8338-b5aa-6f3522dca0d4.htm
        static string Profiles = File.ReadAllText("profile.json");


        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);

			// URL for `PDF To TXT` API call
			string url = "https://api.pdf.co/v1/pdf/convert/to/text";

			// 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("url", SourceFileUrl);
			parameters.Add("profiles", Profiles);

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

			try
			{
				// 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)
				{
					// Get URL of generated TXT file
					string resultFileUrl = json["url"].ToString();

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

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

			webClient.Dispose();

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

profile.json
{
  "profiles": [
    {
      "profile1": {
        "TrimSpaces": "False",
        "PreserveFormattingOnTextExtraction": "True",
        "Unwrap": "True"
      }
    }
  ]
}

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 TEXT endpoint