Link Search Menu Expand Document

Advanced Conversion Options - C#

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

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
        const String API_KEY = "***********************************";

        // Direct URL of source PDF file.
        // You can also upload your own file into and use it as url. Check "Upload File" samples for code snippets:
        const string SourceFileUrl = "";
		// 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 XLS file name
		const string DestinationFile = @".\result.xls";

		Some of advanced options available through profiles:
		(JSON can be single/double-quoted and contain comments.)
		    "profiles": [
		            "profile1": {
		                "NumberDecimalSeparator": "", // Allows to customize decimal separator in numbers.
		                "NumberGroupSeparator": "", // Allows to customize thousands separator.
		                "AutoDetectNumbers": true, // Whether to detect numbers. Values: true / false
		                "RichTextFormatting": true, // Whether to keep text style and fonts. Values: true / false
		                "PageToWorksheet": true, // Whether to create separate worksheet for each page of PDF document. Values: true / false
		                "ExtractInvisibleText": true, // Invisible text extraction. Values: true / false
		                "ExtractShadowLikeText": true, // Shadow-like text extraction. Values: true / false
		                "LineGroupingMode": "None", // Values: "None", "GroupByRows", "GroupByColumns", "JoinOrphanedRows"
		                "ColumnDetectionMode": "ContentGroupsAndBorders", // Values: "ContentGroupsAndBorders", "ContentGroups", "Borders", "BorderedTables"
		                "Unwrap": false, // Unwrap grouped text in table cells. Values: true / false
		                "ShrinkMultipleSpaces": false, // Shrink multiple spaces in table cells that affect column detection. Values: true / false
		                "DetectNewColumnBySpacesRatio": 1, // Spacing ratio that affects column detection.
		                "CustomExtractionColumns": [ 0, 50, 150, 200, 250, 300 ], // Explicitly specify columns coordinates for table extraction.
		                "CheckPermissions": true, // Ignore document permissions. Values: true / false
        // Sample profile that sets advanced conversion options.
        // Advanced options are properties of XLSExtractor class from ByteScout PDF Extractor SDK used in the back-end:
        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 XLS` API call
			string url = "";

			// 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);

				// 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 XLS file
					string resultFileUrl = json["url"].ToString();

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

					Console.WriteLine("Generated XLS file saved as \"{0}\" file.", DestinationFile);
			catch (WebException e)


			Console.WriteLine("Press any key...");
  "profiles": [
      "profile1": {
        "RichTextFormatting": false,
        "PageToWorksheet": false
} 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 API key here!

Download Source Code (.zip)

return to the previous page explore PDF To XLS endpoint