RPA Robotic Process Automation - PDF Invoices to Spreadsheet - VB.NET - ByteScout
Announcement
Our ByteScout SDK products are sunsetting as we focus on expanding new solutions.
Learn More Open modal
Close modal
Announcement Important Update
ByteScout SDK Sunsetting Notice
Our ByteScout SDK products are sunsetting as we focus on our new & improved solutions. Thank you for being part of our journey, and we look forward to supporting you in this next chapter!
PDF.co
Introducing PDF.co
Try PDF.co for document processing & automation via Web APIs
Learn More Service link
MuPDF
Introducing MuPDF
Try MuPDF.NET for advanced document processing solutions in your .NET environment
Learn More Service link
Contact Sales Contact Support    
×

RPA Robotic Process Automation – PDF Invoices to Spreadsheet – VB.NET

  • Home
  • /
  • Articles
  • /
  • RPA Robotic Process Automation – PDF Invoices to Spreadsheet – VB.NET

PDF invoices to spreadsheet in VB.NET and ByteScout Robotic Process Automation

ByteScout Robotic Process Automation is components and tools for quick RPA (Robotic Process Automation) implementation.

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

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

InvoicesToSpreadsheet.VS2005.vbproj

      
<?xml version="1.0" encoding="utf-8"?>
<Project 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>{3035D0B9-6453-4C07-9D4E-638B1052E70C}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <StartupObject>InvoicesToSpreadsheet.Module1</StartupObject>
    <RootNamespace>InvoicesToSpreadsheet</RootNamespace>
    <AssemblyName>InvoicesToSpreadsheet</AssemblyName>
    <FileAlignment>512</FileAlignment>
    <MyType>Console</MyType>
    <ProductVersion>8.0.50727</ProductVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <DefineDebug>true</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <OutputPath>bin\Debug\</OutputPath>
    <DocumentationFile>InvoicesToSpreadsheet.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugType>pdbonly</DebugType>
    <DefineDebug>false</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DocumentationFile>InvoicesToSpreadsheet.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup>
    <OptionExplicit>On</OptionExplicit>
  </PropertyGroup>
  <PropertyGroup>
    <OptionCompare>Binary</OptionCompare>
  </PropertyGroup>
  <PropertyGroup>
    <OptionStrict>Off</OptionStrict>
  </PropertyGroup>
  <PropertyGroup>
    <OptionInfer>On</OptionInfer>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=6.30.0.2431, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout PDF Extractor SDK\net2.00\Bytescout.PDFExtractor.dll</HintPath>
    </Reference>
    <Reference Include="Bytescout.Spreadsheet, Version=0.0.0.0, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout Spreadsheet SDK\Bytescout.Spreadsheet.dll</HintPath>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Deployment" />
    <Reference Include="System.Drawing" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
    <Import Include="Microsoft.VisualBasic" />
    <Import Include="System" />
    <Import Include="System.Collections" />
    <Import Include="System.Collections.Generic" />
    <Import Include="System.Data" />
    <Import Include="System.Diagnostics" />
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Module1.vb" />
  </ItemGroup>
  <ItemGroup>
    <None Include="Sample_Files\InvoiceApr.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
    <None Include="Sample_Files\InvoiceMar.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </ItemGroup>
  <Import Project="$(MSBuildBinPath)\Microsoft.VisualBasic.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>

InvoicesToSpreadsheet.VS2008.vbproj

      
<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="3.5" 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>{3035D0B9-6453-4C07-9D4E-638B1052E70C}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <StartupObject>InvoicesToSpreadsheet.Module1</StartupObject>
    <RootNamespace>InvoicesToSpreadsheet</RootNamespace>
    <AssemblyName>InvoicesToSpreadsheet</AssemblyName>
    <FileAlignment>512</FileAlignment>
    <MyType>Console</MyType>
    <TargetFrameworkVersion>v2.0</TargetFrameworkVersion>
    <ProductVersion>9.0.30729</ProductVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <DefineDebug>true</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <OutputPath>bin\Debug\</OutputPath>
    <DocumentationFile>InvoicesToSpreadsheet.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugType>pdbonly</DebugType>
    <DefineDebug>false</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DocumentationFile>InvoicesToSpreadsheet.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup>
    <OptionExplicit>On</OptionExplicit>
  </PropertyGroup>
  <PropertyGroup>
    <OptionCompare>Binary</OptionCompare>
  </PropertyGroup>
  <PropertyGroup>
    <OptionStrict>Off</OptionStrict>
  </PropertyGroup>
  <PropertyGroup>
    <OptionInfer>On</OptionInfer>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=6.30.0.2431, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout PDF Extractor SDK\net2.00\Bytescout.PDFExtractor.dll</HintPath>
    </Reference>
    <Reference Include="Bytescout.Spreadsheet, Version=0.0.0.0, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout Spreadsheet SDK\Bytescout.Spreadsheet.dll</HintPath>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Deployment" />
    <Reference Include="System.Drawing" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
    <Import Include="Microsoft.VisualBasic" />
    <Import Include="System" />
    <Import Include="System.Collections" />
    <Import Include="System.Collections.Generic" />
    <Import Include="System.Data" />
    <Import Include="System.Diagnostics" />
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Module1.vb" />
  </ItemGroup>
  <ItemGroup>
    <None Include="Sample_Files\InvoiceApr.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
    <None Include="Sample_Files\InvoiceMar.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.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>

InvoicesToSpreadsheet.VS2010.vbproj

      
<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="4.0" 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>{3035D0B9-6453-4C07-9D4E-638B1052E70C}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <StartupObject>InvoicesToSpreadsheet.Module1</StartupObject>
    <RootNamespace>InvoicesToSpreadsheet</RootNamespace>
    <AssemblyName>InvoicesToSpreadsheet</AssemblyName>
    <FileAlignment>512</FileAlignment>
    <MyType>Console</MyType>
    <TargetFrameworkVersion>v4.0</TargetFrameworkVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <DefineDebug>true</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <OutputPath>bin\Debug\</OutputPath>
    <DocumentationFile>InvoicesToSpreadsheet.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugType>pdbonly</DebugType>
    <DefineDebug>false</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DocumentationFile>InvoicesToSpreadsheet.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup>
    <OptionExplicit>On</OptionExplicit>
  </PropertyGroup>
  <PropertyGroup>
    <OptionCompare>Binary</OptionCompare>
  </PropertyGroup>
  <PropertyGroup>
    <OptionStrict>Off</OptionStrict>
  </PropertyGroup>
  <PropertyGroup>
    <OptionInfer>On</OptionInfer>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=6.30.0.2431, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout PDF Extractor SDK\net2.00\Bytescout.PDFExtractor.dll</HintPath>
    </Reference>
    <Reference Include="Bytescout.Spreadsheet, Version=0.0.0.0, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout Spreadsheet SDK\Bytescout.Spreadsheet.dll</HintPath>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Deployment" />
    <Reference Include="System.Drawing" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
    <Import Include="Microsoft.VisualBasic" />
    <Import Include="System" />
    <Import Include="System.Collections" />
    <Import Include="System.Collections.Generic" />
    <Import Include="System.Data" />
    <Import Include="System.Diagnostics" />
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Module1.vb" />
  </ItemGroup>
  <ItemGroup>
    <None Include="Sample_Files\InvoiceApr.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
    <None Include="Sample_Files\InvoiceMar.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.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>

InvoicesToSpreadsheet.VS2012.vbproj

      
<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="4.0" 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>{3035D0B9-6453-4C07-9D4E-638B1052E70C}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <StartupObject>InvoicesToSpreadsheet.Module1</StartupObject>
    <RootNamespace>InvoicesToSpreadsheet</RootNamespace>
    <AssemblyName>InvoicesToSpreadsheet</AssemblyName>
    <FileAlignment>512</FileAlignment>
    <MyType>Console</MyType>
    <TargetFrameworkVersion>v4.0</TargetFrameworkVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <DefineDebug>true</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <OutputPath>bin\Debug\</OutputPath>
    <DocumentationFile>InvoicesToSpreadsheet.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugType>pdbonly</DebugType>
    <DefineDebug>false</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DocumentationFile>InvoicesToSpreadsheet.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup>
    <OptionExplicit>On</OptionExplicit>
  </PropertyGroup>
  <PropertyGroup>
    <OptionCompare>Binary</OptionCompare>
  </PropertyGroup>
  <PropertyGroup>
    <OptionStrict>Off</OptionStrict>
  </PropertyGroup>
  <PropertyGroup>
    <OptionInfer>On</OptionInfer>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=6.30.0.2431, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout PDF Extractor SDK\net2.00\Bytescout.PDFExtractor.dll</HintPath>
    </Reference>
    <Reference Include="Bytescout.Spreadsheet, Version=0.0.0.0, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout Spreadsheet SDK\Bytescout.Spreadsheet.dll</HintPath>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Deployment" />
    <Reference Include="System.Drawing" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
    <Import Include="Microsoft.VisualBasic" />
    <Import Include="System" />
    <Import Include="System.Collections" />
    <Import Include="System.Collections.Generic" />
    <Import Include="System.Data" />
    <Import Include="System.Diagnostics" />
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Module1.vb" />
  </ItemGroup>
  <ItemGroup>
    <None Include="Sample_Files\InvoiceApr.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
    <None Include="Sample_Files\InvoiceMar.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.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>

InvoicesToSpreadsheet.VS2013.vbproj

      
<?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>{3035D0B9-6453-4C07-9D4E-638B1052E70C}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <StartupObject>InvoicesToSpreadsheet.Module1</StartupObject>
    <RootNamespace>InvoicesToSpreadsheet</RootNamespace>
    <AssemblyName>InvoicesToSpreadsheet</AssemblyName>
    <FileAlignment>512</FileAlignment>
    <MyType>Console</MyType>
    <TargetFrameworkVersion>v4.0</TargetFrameworkVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <DefineDebug>true</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <OutputPath>bin\Debug\</OutputPath>
    <DocumentationFile>InvoicesToSpreadsheet.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugType>pdbonly</DebugType>
    <DefineDebug>false</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DocumentationFile>InvoicesToSpreadsheet.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup>
    <OptionExplicit>On</OptionExplicit>
  </PropertyGroup>
  <PropertyGroup>
    <OptionCompare>Binary</OptionCompare>
  </PropertyGroup>
  <PropertyGroup>
    <OptionStrict>Off</OptionStrict>
  </PropertyGroup>
  <PropertyGroup>
    <OptionInfer>On</OptionInfer>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=6.30.0.2431, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout PDF Extractor SDK\net2.00\Bytescout.PDFExtractor.dll</HintPath>
    </Reference>
    <Reference Include="Bytescout.Spreadsheet, Version=0.0.0.0, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout Spreadsheet SDK\Bytescout.Spreadsheet.dll</HintPath>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Deployment" />
    <Reference Include="System.Drawing" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
    <Import Include="Microsoft.VisualBasic" />
    <Import Include="System" />
    <Import Include="System.Collections" />
    <Import Include="System.Collections.Generic" />
    <Import Include="System.Data" />
    <Import Include="System.Diagnostics" />
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Module1.vb" />
  </ItemGroup>
  <ItemGroup>
    <None Include="Sample_Files\InvoiceApr.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
    <None Include="Sample_Files\InvoiceMar.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.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>

InvoicesToSpreadsheet.VS2015.vbproj

      
<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="14.0" 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>{3035D0B9-6453-4C07-9D4E-638B1052E70C}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <StartupObject>InvoicesToSpreadsheet.Module1</StartupObject>
    <RootNamespace>InvoicesToSpreadsheet</RootNamespace>
    <AssemblyName>InvoicesToSpreadsheet</AssemblyName>
    <FileAlignment>512</FileAlignment>
    <MyType>Console</MyType>
    <TargetFrameworkVersion>v4.0</TargetFrameworkVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <DefineDebug>true</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <OutputPath>bin\Debug\</OutputPath>
    <DocumentationFile>InvoicesToSpreadsheet.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugType>pdbonly</DebugType>
    <DefineDebug>false</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DocumentationFile>InvoicesToSpreadsheet.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup>
    <OptionExplicit>On</OptionExplicit>
  </PropertyGroup>
  <PropertyGroup>
    <OptionCompare>Binary</OptionCompare>
  </PropertyGroup>
  <PropertyGroup>
    <OptionStrict>Off</OptionStrict>
  </PropertyGroup>
  <PropertyGroup>
    <OptionInfer>On</OptionInfer>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=6.30.0.2431, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout PDF Extractor SDK\net2.00\Bytescout.PDFExtractor.dll</HintPath>
    </Reference>
    <Reference Include="Bytescout.Spreadsheet, Version=0.0.0.0, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout Spreadsheet SDK\Bytescout.Spreadsheet.dll</HintPath>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Deployment" />
    <Reference Include="System.Drawing" />
    <Reference Include="System.Web.Extensions" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
    <Import Include="Microsoft.VisualBasic" />
    <Import Include="System" />
    <Import Include="System.Collections" />
    <Import Include="System.Collections.Generic" />
    <Import Include="System.Data" />
    <Import Include="System.Diagnostics" />
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Module1.vb" />
  </ItemGroup>
  <ItemGroup>
    <None Include="Sample_Files\InvoiceApr.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
    <None Include="Sample_Files\InvoiceMar.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.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>

Module1.vb

      
Imports System.Drawing
Imports System.IO
Imports Bytescout.PDFExtractor
Imports Bytescout.Spreadsheet

Module Module1

    Sub Main()

        Dim allInputFiles As String() = {"Sample_Files\InvoiceMar.pdf", "Sample_Files\InvoiceApr.pdf"}
        Dim resultFileName = "output.xlsx"

        ' Set page index
        Dim pageIndex = 0

        ' Create output Spreadsheet
        Using document As New Spreadsheet()

            ' Add new worksheet
            Dim worksheet As Worksheet = document.Worksheets.Add("Invoices")

            Dim ws_row As Int32 = 0
            Dim ws_column As Int32 = 0

            ' Set Header value
            worksheet.Cell(ws_row, ws_column).Font = New Font("Arial", 11, FontStyle.Bold)
            worksheet.Cell(ws_row, ws_column).Value = "Invoice"
            ws_column += 1

            worksheet.Cell(ws_row, ws_column).Font = New Font("Arial", 11, FontStyle.Bold)
            worksheet.Cell(ws_row, ws_column).Value = "Product Name"
            ws_column += 1

            worksheet.Cell(ws_row, ws_column).Font = New Font("Arial", 11, FontStyle.Bold)
            worksheet.Cell(ws_row, ws_column).Value = "Price"
            ws_row += 1
            ws_column += 1

            ' Loop through all input files
            For Each itmFile In allInputFiles

                Dim invName = Path.GetFileNameWithoutExtension(itmFile)

                ' Create TextExtractor instance
                Using tableExtractor As New StructuredExtractor("demo", "demo")

                    Dim tableExtractionArea = GetTableExtractionArea(itmFile, pageIndex)
                    If tableExtractionArea.HasValue Then

                        ' Load document from file
                        tableExtractor.LoadDocumentFromFile(itmFile)

                        ' Set extraction area
                        tableExtractor.SetExtractionArea(tableExtractionArea)

                        ' Prepare table structure
                        tableExtractor.PrepareStructure(pageIndex)

                        Dim rowCount As Int32 = tableExtractor.GetRowCount(pageIndex)

                        ' Ignoring first title row
                        For row As Int32 = 1 To rowCount - 1

                            Dim columnCount As Int32 = tableExtractor.GetColumnCount(pageIndex, row)

                            ' Write Invoice Data
                            ws_column = 0
                            worksheet.Cell(ws_row, ws_column).Value = invName
                            ws_column += 1

                            For column As Int32 = 0 To columnCount - 1

                                ' Get table cell value
                                Dim tableCellValue = tableExtractor.GetCellValue(pageIndex, row, column)

                                ' Write to spreadsheet
                                worksheet.Cell(ws_row, ws_column).Value = tableCellValue
                                ws_column += 1
                            Next

                            ' Set row pointer to next row
                            ws_row += 1
                        Next

                    End If

                End Using

            Next

            ' Save document
            document.SaveAs(resultFileName, Constants.SpreadsheetFormatType.XLSX)

        End Using

        ' Open generated XLSX file in default program
        Process.Start(resultFileName)

    End Sub

    ''' <summary>
    ''' Gets table extraction area
    ''' </summary>
    Private Function GetTableExtractionArea(ByVal inputFile As String, ByVal Optional pageIndex As Int32 = 0) As Nullable(Of RectangleF)

        ' Create Bytescout.PDFExtractor.TableDetector instance
        Using tableDetector As New TableDetector("demo", "demo")

            ' Set table detection mode to "bordered tables" - best for tables with closed solid borders.
            tableDetector.ColumnDetectionMode = ColumnDetectionMode.BorderedTables

            ' We should define what kind of tables we should detect.
            ' So we set min required number of columns to 2 ...
            tableDetector.DetectionMinNumberOfColumns = 2
            ' ... And we set min required number of rows to 2
            tableDetector.DetectionMinNumberOfRows = 2

            tableDetector.LoadDocumentFromFile(inputFile)

            If Not tableDetector.FindTable(pageIndex) Then
                Return Nothing
            End If

            ' Getting first found table location
            Return tableDetector.FoundTableLocation

        End Using

    End Function

End Module

VIDEO

ON-PREMISE OFFLINE SDK

Get 60 Day Free Trial

See also:

ON-DEMAND REST WEB API

Get Your API Key

See also:

Tutorials:

prev
next


  REQUEST MORE INFORMATION