PDF.co Web API - PDF To XML API - C# - Convert PDF To XML From URL Asynchronously

printable version:
PDF-co-Web-API-C-sharp-Convert-PDF-To-XML-From-URL-Asynchronously.pdf

How to convert PDF to XML from URL asynchronously for PDF to XML API in C# and PDF.co Web API

See how to convert PDF to XML from URL asynchronously to have PDF to XML API in C#

Today we will explain the steps and algorithm of how to convert PDF to XML from URL asynchronously and how to make it work in your application. PDF.co Web API was made to help with PDF to XML 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.

You will save a lot of time on writing and testing code as you may just take the code below and use it in your application. For implimentation of this functionality, please copy and paste code below into your app using code editor. Then compile and run your app. This basic programming language sample code for C# will do the whole work for you in implementing PDF to XML API in your app.

Trial version of ByteScout is available for free download from our website. This and other source code samples for C# and other programming languages are available.

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>
    <AppDesignerFolder>Properties</AppDesignerFolder>
    <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" />
    <Compile Include="Properties\AssemblyInfo.cs" />
  </ItemGroup>
  <ItemGroup>
    <None Include="packages.config" />
  </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 System.Threading;
using Newtonsoft.Json;
using Newtonsoft.Json.Linq;

// Cloud API asynchronous "PDF To XML" job example.
// Allows to avoid timeout errors when processing huge or scanned PDF documents.

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-text/long-processed-document.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 XML file name
		const string DestinationFile = @".\result.xml";
		// (!) Make asynchronous job
		const bool Async = true;


		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 XML` API call
			string url = "https://api.pdf.co/v1/pdf/convert/to/xml";

			// 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("async", Async);

			// 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)
				{
					// Asynchronous job ID
					string jobId = json["jobId"].ToString();
					// URL of generated XML file that will be available after the job completion
					string resultFileUrl = json["url"].ToString();

					// Check the job status in a loop. 
					// If you don't want to pause the main thread you can rework the code 
					// to use a separate thread for the status checking and completion.
					do
					{
						string status = CheckJobStatus(jobId); // Possible statuses: "working", "failed", "aborted", "success".

						// Display timestamp and status (for demo purposes)
						Console.WriteLine(DateTime.Now.ToLongTimeString() + ": " + status);

						if (status == "success")
						{
							// Download XML file
							webClient.DownloadFile(resultFileUrl, DestinationFile);

							Console.WriteLine("Generated XML file saved as \"{0}\" file.", DestinationFile);
							break;
						}
						else if (status == "working")
						{
							// Pause for a few seconds
							Thread.Sleep(3000);
						}
						else 
						{
							Console.WriteLine(status);
							break;
						}
					}
					while (true);
				}
				else
				{
					Console.WriteLine(json["message"].ToString());
				}
			}
			catch (WebException e)
			{
				Console.WriteLine(e.ToString());
			}

			webClient.Dispose();

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

		static string CheckJobStatus(string jobId)
		{
			using (WebClient webClient = new WebClient())
			{
				// Set API Key
                webClient.Headers.Add("x-api-key", API_KEY);
				
				string url = "https://api.pdf.co/v1/job/check?jobid=" + jobId;

				string response = webClient.DownloadString(url);
				JObject json = JObject.Parse(response);

				return Convert.ToString(json["status"]);
			}
		}
	}
}

packages.config

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

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-Convert-PDF-To-XML-From-URL-Asynchronously.pdf