ByteScout PDF Extractor SDK – C# – Extraction From Complex Borderless Tables

Home
/
Articles
/
ByteScout PDF Extractor SDK – C# – Extraction From Complex Borderless Tables

printable version:
ByteScout-PDF-Extractor-SDK-C-sharp-Extraction-From-Complex-Borderless-Tables.pdf

extraction from complex borderless tables in C# with ByteScout PDF Extractor SDK

What is ByteScout PDF Extractor SDK? It is the SDK that helps developers to extract data from unstructured documents, pdf, images, scanned and electronic forms. Includes AI functions like automatic table detection, automatic table extraction and restructuring, text recognition and text restoration from pdf and scanned documents. Includes PDF to CSV, PDF to XML, PDF to JSON, PDF to searchable PDF functions as well as methods for low level data extraction.

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

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

ConsoleApplication1.NETCore.csproj

      <?xml version="1.0" encoding="utf-8"?>
<Project Sdk="Microsoft.NET.Sdk">
  <PropertyGroup>
    <OutputType>Exe</OutputType>
    <TargetFramework>netcoreapp2.0</TargetFramework>
    <EnableDefaultCompileItems>false</EnableDefaultCompileItems>
    <GenerateAssemblyCompanyAttribute>false</GenerateAssemblyCompanyAttribute>
    <GenerateAssemblyConfigurationAttribute>false</GenerateAssemblyConfigurationAttribute>
    <GenerateAssemblyFileVersionAttribute>false</GenerateAssemblyFileVersionAttribute>
    <GenerateAssemblyInformationalVersionAttribute>false</GenerateAssemblyInformationalVersionAttribute>
    <GenerateAssemblyProductAttribute>false</GenerateAssemblyProductAttribute>
    <GenerateAssemblyTitleAttribute>false</GenerateAssemblyTitleAttribute>
    <GenerateAssemblyVersionAttribute>false</GenerateAssemblyVersionAttribute>
    <GenerateAssemblyCopyrightAttribute>false</GenerateAssemblyCopyrightAttribute>
    <GenerateAssemblyTrademarkAttribute>false</GenerateAssemblyTrademarkAttribute>
    <GenerateAssemblyCultureAttribute>false</GenerateAssemblyCultureAttribute>
    <GenerateAssemblyDescriptionAttribute>false</GenerateAssemblyDescriptionAttribute>
  </PropertyGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
    <Compile Include="Properties\AssemblyInfo.cs" />
    <None Include="..\..\borderless_table.pdf" Link="borderless_table.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </ItemGroup>
  <ItemGroup>
    <PackageReference Include="Microsoft.Windows.Compatibility" Version="2.0.0" />
  </ItemGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>c:\Program Files\Bytescout PDF Extractor SDK\netcoreapp2.0\Bytescout.PDFExtractor.dll</HintPath>
    </Reference>
    <Reference Include="Bytescout.PDFExtractor.OCRExtension">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>c:\Program Files\Bytescout PDF Extractor SDK\netcoreapp2.0\Bytescout.PDFExtractor.OCRExtension.dll</HintPath>
    </Reference>
  </ItemGroup>
</Project>

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page

Explore ByteScout PDF Extractor SDK Documentation

Explore Samples

Sign Up for ByteScout PDF Extractor SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

ConsoleApplication1.VS2005.csproj

      <Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <PropertyGroup>
    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
    <ProductVersion>8.0.50727</ProductVersion>
    <SchemaVersion>2.0</SchemaVersion>
    <ProjectGuid>{5FD39006-92D8-4ACC-B2EB-A43ECBC67F99}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <AppDesignerFolder>Properties</AppDesignerFolder>
    <RootNamespace>ConsoleApplication1</RootNamespace>
    <AssemblyName>ConsoleApplication1</AssemblyName>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <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' ">
    <DebugType>pdbonly</DebugType>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DefineConstants>TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=1.10.0.73, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
    <Compile Include="Properties\AssemblyInfo.cs" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="..\..\borderless_table.pdf">
      <Link>borderless_table.pdf</Link>
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </Content>
  </ItemGroup>
  <Import Project="$(MSBuildBinPath)\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>

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page

Explore ByteScout PDF Extractor SDK Documentation

Explore Samples

Sign Up for ByteScout PDF Extractor SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

ConsoleApplication1.VS2008.csproj

      <Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003" ToolsVersion="3.5">
  <PropertyGroup>
    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
    <ProductVersion>9.0.21022</ProductVersion>
    <SchemaVersion>2.0</SchemaVersion>
    <ProjectGuid>{5FD39006-92D8-4ACC-B2EB-A43ECBC67F99}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <AppDesignerFolder>Properties</AppDesignerFolder>
    <RootNamespace>ConsoleApplication1</RootNamespace>
    <AssemblyName>ConsoleApplication1</AssemblyName>
    <OldToolsVersion>2.0</OldToolsVersion>
    <TargetFrameworkVersion>v3.5</TargetFrameworkVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <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' ">
    <DebugType>pdbonly</DebugType>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DefineConstants>TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=1.10.0.73, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
    <Compile Include="Properties\AssemblyInfo.cs" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="..\..\borderless_table.pdf">
      <Link>borderless_table.pdf</Link>
      <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>

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page

Explore ByteScout PDF Extractor SDK Documentation

Explore Samples

Sign Up for ByteScout PDF Extractor SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

ConsoleApplication1.VS2010.csproj

      <Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003" ToolsVersion="4.0">
  <PropertyGroup>
    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
    <ProductVersion>
    </ProductVersion>
    <SchemaVersion>2.0</SchemaVersion>
    <ProjectGuid>{5FD39006-92D8-4ACC-B2EB-A43ECBC67F99}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <AppDesignerFolder>Properties</AppDesignerFolder>
    <RootNamespace>ConsoleApplication1</RootNamespace>
    <AssemblyName>ConsoleApplication1</AssemblyName>
    <OldToolsVersion>3.5</OldToolsVersion>
    <TargetFrameworkVersion>v4.0</TargetFrameworkVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <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' ">
    <DebugType>pdbonly</DebugType>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DefineConstants>TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=1.10.0.73, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
    <Compile Include="Properties\AssemblyInfo.cs" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="..\..\borderless_table.pdf">
      <Link>borderless_table.pdf</Link>
      <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>

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page

Explore ByteScout PDF Extractor SDK Documentation

Explore Samples

Sign Up for ByteScout PDF Extractor SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

Program.cs

      using Bytescout.PDFExtractor;
using System;
using System.Diagnostics;

namespace ConsoleApplication1
{
    class Program
    {
        static void Main(string[] args)
        {
            // Create Bytescout.PDFExtractor.CSVExtractor instance
            CSVExtractor extractor = new CSVExtractor();
            extractor.RegistrationName = "demo";
            extractor.RegistrationKey = "demo";

            // Load sample PDF document
            extractor.LoadDocumentFromFile("borderless_table.pdf");

            // Set extraction columns explicitly.
            // Coordinates in CustomExtractionColumns must match the left edges of the columns.
            // To get coordinates in PDF points you can use PDF Multitool application 
            // installed with the SDK. It shows mouse cursor coodinates in PDF points in the toolbar.
            extractor.CustomExtractionColumns = new double[] { 0, 124.5, 185, 241 };

            // Save extracted CSV data
            extractor.SaveCSVToFile("output.csv");

            // Cleanup
            extractor.Dispose();

            Console.WriteLine();
            Console.WriteLine("Data has been extracted to 'output.csv' file.");
            Console.WriteLine();
            Console.WriteLine("Press any key to continue and open CSV in default CSV viewer (or Excel)...");
            Console.ReadKey();

            // Open result document in default associated application (for demo purpose)
            ProcessStartInfo processStartInfo = new ProcessStartInfo("output.csv");
            processStartInfo.UseShellExecute = true;
            Process.Start(processStartInfo);
        }
    }
}