PDF.co Web API - PDF To CSV API - C# - Advanced Conversion Options

printable version:
PDF-co-Web-API-C-sharp-Advanced-Conversion-Options.pdf

PDF to CSV API in C# with PDF.co Web API

Tutorial: how to do PDF to CSV API in C#

The sample source codes on this page will demonstrate you how to make PDF to CSV API in C#. PDF.co Web API was made to help with PDF to CSV API in C#. PDF.co Web API is 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.

C#, code samples for C#, developers help to speed up the application development and writing a code when using PDF.co Web API. In order to implement this functionality, you should copy and paste code below into your app using code editor. Then compile and run your application. Further enhancement of the code will make it more vigorous.

Trial version can be obtained from our website for free. It includes this and other source code samples for C#.

On-demand (REST Web API) version:
Web API (on-demand version)

On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)

ByteScoutWebApiExample.csproj

      <?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="12.0" DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <Import Project="$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props" Condition="Exists('$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props')" />
  <PropertyGroup>
    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
    <ProjectGuid>{1E1C2C34-017E-4605-AE2B-55EA3313BE51}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <RootNamespace>ByteScoutWebApiExample</RootNamespace>
    <AssemblyName>ByteScoutWebApiExample</AssemblyName>
    <TargetFrameworkVersion>v4.0</TargetFrameworkVersion>
    <FileAlignment>512</FileAlignment>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <Optimize>false</Optimize>
    <OutputPath>bin\Debug\</OutputPath>
    <DefineConstants>DEBUG;TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugType>pdbonly</DebugType>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DefineConstants>TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Newtonsoft.Json, Version=10.0.0.0, Culture=neutral, PublicKeyToken=30ad4fe6b2a6aeed, processorArchitecture=MSIL">
      <HintPath>packages\Newtonsoft.Json.10.0.3\lib\net40\Newtonsoft.Json.dll</HintPath>
      <Private>True</Private>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Core" />
    <Reference Include="System.Xml.Linq" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
  </ItemGroup>
  <ItemGroup>
    <None Include="packages.config" />
    <None Include="profile.json">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.CSharp.targets" />
  <!-- To modify your build process, add your task inside one of the targets below and uncomment it. 
       Other similar extension points exist, see Microsoft.Common.targets.
  <Target Name="BeforeBuild">
  </Target>
  <Target Name="AfterBuild">
  </Target>
  -->
</Project>

ByteScoutWebApiExample.sln

      
Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 2013
VisualStudioVersion = 12.0.40629.0
MinimumVisualStudioVersion = 10.0.40219.1
Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "ByteScoutWebApiExample", "ByteScoutWebApiExample.csproj", "{1E1C2C34-017E-4605-AE2B-55EA3313BE51}"
EndProject
Global
	GlobalSection(SolutionConfigurationPlatforms) = preSolution
		Debug|Any CPU = Debug|Any CPU
		Release|Any CPU = Release|Any CPU
	EndGlobalSection
	GlobalSection(ProjectConfigurationPlatforms) = postSolution
		{1E1C2C34-017E-4605-AE2B-55EA3313BE51}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
		{1E1C2C34-017E-4605-AE2B-55EA3313BE51}.Debug|Any CPU.Build.0 = Debug|Any CPU
		{1E1C2C34-017E-4605-AE2B-55EA3313BE51}.Release|Any CPU.ActiveCfg = Release|Any CPU
		{1E1C2C34-017E-4605-AE2B-55EA3313BE51}.Release|Any CPU.Build.0 = Release|Any CPU
	EndGlobalSection
	GlobalSection(SolutionProperties) = preSolution
		HideSolutionNode = FALSE
	EndGlobalSection
EndGlobal

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/documentation/api
		const String API_KEY = "**************************************";

        // Direct URL of source PDF file.
        const string SourceFileUrl = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-csv/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 CSV file name
		const string DestinationFile = @".\result.csv";

		/*
		Some of advanced options available through profiles:
		(JSON can be single/double-quoted and contain comments.)
		{
			"profiles": [
				{
					"profile1": {
						"CSVSeparatorSymbol": ",", // Separator symbol.
						"CSVQuotaionSymbol": "\"", // Quotation symbol.
						"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 CSVExtractor class from ByteScout PDF Extractor SDK used in the back-end:
        // https://cdn.bytescout.com/help/BytescoutPDFExtractorSDK/html/87ce5fa6-3143-167d-abbd-bc7b5e160fe5.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);

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

			// 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["status"].ToString() != "error")
                {
					// Get URL of generated CSV file
					string resultFileUrl = json["url"].ToString();

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

					Console.WriteLine("Generated CSV 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();
		}
	}
}

packages.config

      <?xml version="1.0" encoding="utf-8"?>
<packages>
  <package id="Newtonsoft.Json" version="10.0.3" targetFramework="net40" />
</packages>

profile.json

      {
  "profiles": [
    {
      "profile1": {
        "OCRMode": "TextFromImagesAndVectorsAndFonts",
        "CSVSeparatorSymbol": "|"
      }
    }
  ]
}

VIDEO

ON-PREMISE OFFLINE SDK

Get 60 Day Free Trial

ON-DEMAND REST WEB API

Get Your API Key

See also:

printable version:
PDF-co-Web-API-C-sharp-Advanced-Conversion-Options.pdf