ByteScout Document Parser SDK – C# – Extract Text from Foldable Brochure Booklet

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

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

ExtractTextFromFoldableBrochure.csproj

      
<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="15.0" 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>{A73776C6-D2B2-4E37-B852-06C6454D1B5B}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <RootNamespace>ExtractTextFromFoldableBrochure</RootNamespace>
    <AssemblyName>ExtractTextFromFoldableBrochure</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="ByteScout.DocumentParser, Version=1.0.0.100, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>c:\Program Files\ByteScout Document Parser SDK\net40\ByteScout.DocumentParser.dll</HintPath>
    </Reference>
    <Reference Include="Newtonsoft.Json, Version=12.0.0.0, Culture=neutral, PublicKeyToken=30ad4fe6b2a6aeed, processorArchitecture=MSIL">
      <HintPath>packages\Newtonsoft.Json.12.0.3\lib\net40\Newtonsoft.Json.dll</HintPath>
    </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="..\..\SampleFoldable.pdf">
      <Link>SampleFoldable.pdf</Link>
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
    <None Include="SampleFoldable.yml">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
    <None Include="packages.config" />
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.CSharp.targets" />
</Project>
    

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Document Parser SDK Home Page

Explore ByteScout Document Parser SDK Documentation

Explore Samples

Sign Up for ByteScout Document Parser SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

ExtractTextFromFoldableBrochure.sln

      

Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 15
VisualStudioVersion = 15.0.27703.2018
MinimumVisualStudioVersion = 10.0.40219.1
Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "ExtractTextFromFoldableBrochure", "ExtractTextFromFoldableBrochure.csproj", "{A73776C6-D2B2-4E37-B852-06C6454D1B5B}"
EndProject
Global
	GlobalSection(SolutionConfigurationPlatforms) = preSolution
		Debug|Any CPU = Debug|Any CPU
		Release|Any CPU = Release|Any CPU
	EndGlobalSection
	GlobalSection(ProjectConfigurationPlatforms) = postSolution
		{A73776C6-D2B2-4E37-B852-06C6454D1B5B}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
		{A73776C6-D2B2-4E37-B852-06C6454D1B5B}.Debug|Any CPU.Build.0 = Debug|Any CPU
		{A73776C6-D2B2-4E37-B852-06C6454D1B5B}.Release|Any CPU.ActiveCfg = Release|Any CPU
		{A73776C6-D2B2-4E37-B852-06C6454D1B5B}.Release|Any CPU.Build.0 = Release|Any CPU
	EndGlobalSection
	GlobalSection(SolutionProperties) = preSolution
		HideSolutionNode = FALSE
	EndGlobalSection
	GlobalSection(ExtensibilityGlobals) = postSolution
		SolutionGuid = {7E6DAA79-020B-421A-844A-5FE05EFC9B15}
	EndGlobalSection
EndGlobal

    

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Document Parser SDK Home Page

Explore ByteScout Document Parser SDK Documentation

Explore Samples

Sign Up for ByteScout Document Parser SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

Program.cs

      
using ByteScout.DocumentParser;
using Newtonsoft.Json.Linq;
using System;
using System.Diagnostics;
using System.IO;
using System.Text;

namespace ExtractTextFromFoldableBrochure
{
    class Program
    {
        static void Main(string[] args)
        {
            // Sample document containing foldable PDF
            string sampleDocument = @".\SampleFoldable.pdf";

            // Sample template
            string sampleTemplate = @".\SampleFoldable.yml";

            // Output 
            var resFile = "result.txt";
            var sOutput = new StringBuilder(string.Empty);

            // Create DocumentParser instance
            using (DocumentParser documentParser = new DocumentParser("demo", "demo"))
            {
                // Add sample template
                documentParser.AddTemplate(sampleTemplate);

                // Parse document data in JSON format
                string jsonString = documentParser.ParseDocument(sampleDocument, OutputFormat.JSON);

                // Parse json to foldable structure
                var parsedRes = ParseJsonToFoldableStructure(jsonString);

                // Append all parts to return output
                sOutput.AppendLine(parsedRes.Part1);
                sOutput.AppendLine(parsedRes.Part2);
                sOutput.AppendLine(parsedRes.Part3);

                // Write output file
                File.WriteAllText(resFile, sOutput.ToString());

                Console.WriteLine({code}quot;Extracted text saved to {resFile}");

                // Open result file with default application
                Process.Start(resFile);
            }

            Console.WriteLine();
            Console.WriteLine("Press any key to continue...");
            Console.ReadLine();
        }

        /// <summary>
        /// Parse Json to Foldable Structure
        /// </summary>
        static FoldableStructure ParseJsonToFoldableStructure(string jsonData)
        {
            // Get Object data from input file
            JObject jsonObj = JObject.Parse(jsonData);

            var oRet = new FoldableStructure();
            oRet.Part1 = Convert.ToString(jsonObj["fields"]["part1"]["value"]);
            oRet.Part2 = Convert.ToString(jsonObj["fields"]["part2"]["value"]);
            oRet.Part3 = Convert.ToString(jsonObj["fields"]["part3"]["value"]);

            return oRet;
        }
    }

    class FoldableStructure
    {
        public string Part1 { get; set; }
        public string Part2 { get; set; }
        public string Part3 { get; set; }
    }
}

    

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Document Parser SDK Home Page

Explore ByteScout Document Parser SDK Documentation

Explore Samples

Sign Up for ByteScout Document Parser SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

SampleFoldable.yml

      
templateVersion: 3
templatePriority: 0
sourceId: Untitled document kind
detectionRules:
  keywords: []
fields:
  Part1:
    type: rectangle
    rectangle:
    - 7.5
    - 33.75
    - 244.5
    - 353.25
    pageIndex: 0
  Part2:
    type: rectangle
    rectangle:
    - 273.75
    - 201.75
    - 247.5
    - 198
    pageIndex: 0
  Part3:
    type: rectangle
    rectangle:
    - 537.75
    - 27
    - 246
    - 268.5
    pageIndex: 0


    

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Document Parser SDK Home Page

Explore ByteScout Document Parser SDK Documentation

Explore Samples

Sign Up for ByteScout Document Parser SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

packages.config

      
<?xml version="1.0" encoding="utf-8"?>
<packages>
  <package id="Newtonsoft.Json" version="12.0.3" targetFramework="net40" />
</packages>
    

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Document Parser SDK Home Page

Explore ByteScout Document Parser SDK Documentation

Explore Samples

Sign Up for ByteScout Document Parser SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Document Parser SDK Home Page

Explore ByteScout Document Parser SDK Documentation

Explore Samples

Sign Up for ByteScout Document Parser SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples