ByteScout Document Parser SDK – VB.NET – Extract line items from tables on multiple pages

Home
/
Articles
/
ByteScout Document Parser SDK – VB.NET – Extract line items from tables on multiple pages

printable version:
ByteScout-Document-Parser-SDK-VB-NET-Extract-line-items-from-tables-on-multiple-pages.pdf

How to extract line items from tables on multiple pages in VB.NET and ByteScout Document Parser SDK

What is ByteScout Document Parser SDK? It is the robost offline data extraction platform for template based data extraction and processing. Supports high load with millions of documents as input. Templates can be quickly created and updated with no special technical knowledge required.

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

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

ExtractLineItemFromTableOnMultiplePages.sln

      
Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 15
VisualStudioVersion = 15.0.27703.2026
MinimumVisualStudioVersion = 10.0.40219.1
Project("{F184B08F-C81C-45F6-A57F-5ABD9991F28F}") = "ExtractLineItemFromTableOnMultiplePages", "ExtractLineItemFromTableOnMultiplePages.vbproj", "{A5FA1293-C15B-4249-A771-ED4301658454}"
EndProject
Global
	GlobalSection(SolutionConfigurationPlatforms) = preSolution
		Debug|Any CPU = Debug|Any CPU
		Release|Any CPU = Release|Any CPU
	EndGlobalSection
	GlobalSection(ProjectConfigurationPlatforms) = postSolution
		{A5FA1293-C15B-4249-A771-ED4301658454}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
		{A5FA1293-C15B-4249-A771-ED4301658454}.Debug|Any CPU.Build.0 = Debug|Any CPU
		{A5FA1293-C15B-4249-A771-ED4301658454}.Release|Any CPU.ActiveCfg = Release|Any CPU
		{A5FA1293-C15B-4249-A771-ED4301658454}.Release|Any CPU.Build.0 = Release|Any CPU
	EndGlobalSection
	GlobalSection(SolutionProperties) = preSolution
		HideSolutionNode = FALSE
	EndGlobalSection
	GlobalSection(ExtensibilityGlobals) = postSolution
		SolutionGuid = {DCA85560-1523-40E0-917A-5BB3AA7E031F}
	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

ExtractLineItemFromTableOnMultiplePages.vbproj

      <?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>{A5FA1293-C15B-4249-A771-ED4301658454}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <StartupObject>ExtractLineItemFromTableOnMultiplePages.Module1</StartupObject>
    <RootNamespace>ExtractLineItemFromTableOnMultiplePages</RootNamespace>
    <AssemblyName>ExtractLineItemFromTableOnMultiplePages</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>
    <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>
    <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.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="System" />
    <Reference Include="System.Core" />
  </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" />
    <Import Include="System.Linq" />
    <Import Include="System.Xml.Linq" />
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Module1.vb" />
  </ItemGroup>
  <ItemGroup>
    <None Include="..\..\MultiPageTable.pdf">
      <Link>MultiPageTable.pdf</Link>
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
    <None Include="..\..\_Sample Templates\MultiPageTable-template1.yml">
      <Link>MultiPageTable-template1.yml</Link>
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
    <None Include="..\..\_Sample Templates\MultiPageTable-template2.yml">
      <Link>MultiPageTable-template2.yml</Link>
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.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

Module1.vb

      Imports ByteScout.DocumentParser

' This example demonstrates extracting line items from tables on multiple pages with two different approaches.
' See comments in the code of templates.

Module Module1

    Sub Main()

        Dim inputDocument As String = ".\MultiPageTable.pdf"
        Dim template1 As String = ".\MultiPageTable-template1.yml"
        Dim template2 As String = ".\MultiPageTable-template2.yml"

        ' Process using template-1
        Using documentParser As New DocumentParser("demo", "demo")

            Console.WriteLine("Loading template 1...")
            documentParser.AddTemplate(template1)

            Console.WriteLine("Template 1 loaded.")
            Console.WriteLine()

            Console.WriteLine({code}quot;Parsing ""{inputDocument}""...")
            Console.WriteLine()

            ' Parse document data in JSON format
            documentParser.ParseDocument(inputDocument, "result1.json", OutputFormat.JSON)
            
            Console.WriteLine("Parsing results saved to `result1.json`.")
            Console.WriteLine()

        End Using

        ' Process using template-2
        Using documentParser As New DocumentParser("demo", "demo")

            Console.WriteLine("Loading template 2...")
            documentParser.AddTemplate(template2)

            Console.WriteLine("Template 2 loaded.")
            Console.WriteLine()

            Console.WriteLine({code}quot;Parsing ""{inputDocument}""...")
            Console.WriteLine()

            ' Parse document data in JSON format
            documentParser.ParseDocument(inputDocument, "result2.json", OutputFormat.JSON)
            
            Console.WriteLine("Parsing results saved to `result2.json`.")
            Console.WriteLine()

        End Using

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

    End Sub

End Module