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

Learn to code in C# to make PDF to XML API with this simple How-To tutorial

ByteScout tutorials describe the stuff for programmers who use C#. PDF to XML API in C# can be applied with PDF.co Web API. 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.

Save time on writing and testing code by using the code below and use it in your application. If you want to know how it works, then this C# sample code should be copied and pasted into your application’s code editor. Then just compile and run it. Check these C# sample code examples to see if they acknowledge to your needs and requirements for the project.

Trial version can be downloaded from our website for free. It contains 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)


<?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=, 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" /> <Content Include="sample-rotated.pdf"> <CopyToOutputDirectory>Always</CopyToOutputDirectory> </Content> <Content Include="profile.json"> <CopyToOutputDirectory>Always</CopyToOutputDirectory> </Content> </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>


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


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 = "*************************************"; // Source PDF file const string SourceFile = @".\sample-rotated.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"; /* Some of advanced options available through profiles: (it can be single/double-quoted and contain comments.) { "profiles": [ { "profile1": { "SaveImages": "None", // Whether to extract images. Values: "None", "Embed". "ImageFormat": "PNG", // Image format for extracted images. Values: "PNG", "JPEG", "GIF", "BMP". "SaveVectors": false, // Whether to extract vector objects (vertical and horizontal lines). 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 XMLExtractor class from ByteScout PDF Extractor SDK used in the back-end: // https://cdn.bytescout.com/help/BytescoutPDFExtractorSDK/html/87ce5fa6-3143-167d-abbd-bc7b5e160fe5.htm /* Valid RotationAngle values: 0 - no rotation 1 - 90 degrees 2 - 180 degrees 3 - 270 degrees */ 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); // 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["status"].ToString() != "error") { // 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. CONVERT UPLOADED PDF FILE TO XML // URL for `PDF To XML` API call var 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", uploadedFileUrl); parameters.Add("profiles", Profiles); // Convert dictionary of params to JSON string jsonPayload = JsonConvert.SerializeObject(parameters); // Execute POST request with JSON payload response = webClient.UploadString(url, jsonPayload); // Parse JSON response json = JObject.Parse(response); if (json["status"].ToString() != "error") { // Get URL of generated XML file string resultFileUrl = json["url"].ToString(); // Download XML file webClient.DownloadFile(resultFileUrl, DestinationFile); Console.WriteLine("Generated XML 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(); } } }


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


{ "profiles": [ { "profile1": { "RotationAngle": 1 } } ] }



Get 60 Day Free Trial

See also:


Get Your API Key

See also:

Related Samples: