ByteScout PDF Extractor SDK – VB.NET – Load Unicode CSV to DataTable using OLEDB

Home
/
Articles
/
ByteScout PDF Extractor SDK – VB.NET – Load Unicode CSV to DataTable using OLEDB

printable version:
ByteScout-PDF-Extractor-SDK-VB-NET-Load-Unicode-CSV-to-DataTable-using-OLEDB.pdf

How to load unicode CSV to datatable using OLEDB in VB.NET with ByteScout PDF Extractor SDK

ByteScout PDF Extractor SDK: the SDK is designed to help developers with pdf tables and pdf data extraction from unstructured documents like pdf, tiff, scans, images, scanned and electronic forms. The library is powered by OCR, computer vision and AI to provide unique functionality like table detection, automatic table structure extraction, data restoration, data restructuring and reconstruction. Supports PDF, TIFF, PNG, JPG images as input and can output CSV, XML, JSON formatted data. Includes full set of utilities like pdf splitter, pdf merger, searchable pdf maker and other utilities.

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

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

ConsoleApplication1.VS2005.vbproj

      <?xml version="1.0" encoding="utf-8"?>
<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>{ECE4C758-259D-4A66-BBE5-C8922179A44C}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <StartupObject>ConsoleApplication1.ConsoleApplication1.Program</StartupObject>
    <RootNamespace>ConsoleApplication1</RootNamespace>
    <AssemblyName>ConsoleApplication1</AssemblyName>
    <MyType>Console</MyType>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <DefineDebug>true</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <OutputPath>bin\Debug\</OutputPath>
    <DocumentationFile>ConsoleApplication1.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <DebugType>pdbonly</DebugType>
    <DefineDebug>false</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DocumentationFile>ConsoleApplication1.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=1.0.0.12, Culture=neutral, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Deployment" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
  </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" />
    <Compile Include="My Project\AssemblyInfo.vb" />
    <Compile Include="My Project\Application.Designer.vb">
      <AutoGen>True</AutoGen>
      <DependentUpon>Application.myapp</DependentUpon>
    </Compile>
    <Compile Include="My Project\Resources.Designer.vb">
      <AutoGen>True</AutoGen>
      <DesignTime>True</DesignTime>
      <DependentUpon>Resources.resx</DependentUpon>
    </Compile>
    <Compile Include="My Project\Settings.Designer.vb">
      <AutoGen>True</AutoGen>
      <DependentUpon>Settings.settings</DependentUpon>
      <DesignTimeSharedInput>True</DesignTimeSharedInput>
    </Compile>
  </ItemGroup>
  <ItemGroup>
    <EmbeddedResource Include="My Project\Resources.resx">
      <Generator>VbMyResourcesResXFileCodeGenerator</Generator>
      <LastGenOutput>Resources.Designer.vb</LastGenOutput>
      <CustomToolNamespace>My.Resources</CustomToolNamespace>
      <SubType>Designer</SubType>
    </EmbeddedResource>
  </ItemGroup>
  <ItemGroup>
    <None Include="My Project\Application.myapp">
      <Generator>MyApplicationCodeGenerator</Generator>
      <LastGenOutput>Application.Designer.vb</LastGenOutput>
    </None>
    <None Include="My Project\Settings.settings">
      <Generator>SettingsSingleFileGenerator</Generator>
      <CustomToolNamespace>My</CustomToolNamespace>
      <LastGenOutput>Settings.Designer.vb</LastGenOutput>
    </None>
  </ItemGroup>
  <ItemGroup>
    <Content Include="..\..\UnicodeSample.pdf">
      <Link>UnicodeSample.pdf</Link>
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </Content>
  </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>

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.vbproj

      <?xml version="1.0" encoding="utf-8"?>
<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>{ECE4C758-259D-4A66-BBE5-C8922179A44C}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <StartupObject>ConsoleApplication1.ConsoleApplication1.Program</StartupObject>
    <RootNamespace>ConsoleApplication1</RootNamespace>
    <AssemblyName>ConsoleApplication1</AssemblyName>
    <MyType>Console</MyType>
    <OldToolsVersion>2.0</OldToolsVersion>
    <TargetFrameworkVersion>v3.5</TargetFrameworkVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <DefineDebug>true</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <OutputPath>bin\Debug\</OutputPath>
    <DocumentationFile>ConsoleApplication1.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <DebugType>pdbonly</DebugType>
    <DefineDebug>false</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DocumentationFile>ConsoleApplication1.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=1.0.0.12, Culture=neutral, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Deployment" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
  </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" />
    <Compile Include="My Project\AssemblyInfo.vb" />
    <Compile Include="My Project\Application.Designer.vb">
      <AutoGen>True</AutoGen>
      <DependentUpon>Application.myapp</DependentUpon>
    </Compile>
    <Compile Include="My Project\Resources.Designer.vb">
      <AutoGen>True</AutoGen>
      <DesignTime>True</DesignTime>
      <DependentUpon>Resources.resx</DependentUpon>
    </Compile>
    <Compile Include="My Project\Settings.Designer.vb">
      <AutoGen>True</AutoGen>
      <DependentUpon>Settings.settings</DependentUpon>
      <DesignTimeSharedInput>True</DesignTimeSharedInput>
    </Compile>
  </ItemGroup>
  <ItemGroup>
    <EmbeddedResource Include="My Project\Resources.resx">
      <Generator>VbMyResourcesResXFileCodeGenerator</Generator>
      <LastGenOutput>Resources.Designer.vb</LastGenOutput>
      <CustomToolNamespace>My.Resources</CustomToolNamespace>
      <SubType>Designer</SubType>
    </EmbeddedResource>
  </ItemGroup>
  <ItemGroup>
    <None Include="My Project\Application.myapp">
      <Generator>MyApplicationCodeGenerator</Generator>
      <LastGenOutput>Application.Designer.vb</LastGenOutput>
    </None>
    <None Include="My Project\Settings.settings">
      <Generator>SettingsSingleFileGenerator</Generator>
      <CustomToolNamespace>My</CustomToolNamespace>
      <LastGenOutput>Settings.Designer.vb</LastGenOutput>
    </None>
  </ItemGroup>
  <ItemGroup>
    <Content Include="..\..\UnicodeSample.pdf">
      <Link>UnicodeSample.pdf</Link>
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </Content>
  </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>

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.vbproj

      <?xml version="1.0" encoding="utf-8"?>
<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>{ECE4C758-259D-4A66-BBE5-C8922179A44C}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <StartupObject>ConsoleApplication1.ConsoleApplication1.Program</StartupObject>
    <RootNamespace>ConsoleApplication1</RootNamespace>
    <AssemblyName>ConsoleApplication1</AssemblyName>
    <MyType>Console</MyType>
    <OldToolsVersion>3.5</OldToolsVersion>
    <TargetFrameworkVersion>v4.0</TargetFrameworkVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <DefineDebug>true</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <OutputPath>bin\Debug\</OutputPath>
    <DocumentationFile>ConsoleApplication1.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <DebugType>pdbonly</DebugType>
    <DefineDebug>false</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DocumentationFile>ConsoleApplication1.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup Condition="'$(Configuration)|$(Platform)' == 'Debug|x86'">
    <DebugSymbols>true</DebugSymbols>
    <DefineDebug>true</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <OutputPath>bin\x86\Debug\</OutputPath>
    <DocumentationFile>ConsoleApplication1.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
    <DebugType>full</DebugType>
    <PlatformTarget>x86</PlatformTarget>
    <CodeAnalysisRuleSet>MinimumRecommendedRules.ruleset</CodeAnalysisRuleSet>
  </PropertyGroup>
  <PropertyGroup Condition="'$(Configuration)|$(Platform)' == 'Release|x86'">
    <DefineTrace>true</DefineTrace>
    <OutputPath>bin\x86\Release\</OutputPath>
    <DocumentationFile>ConsoleApplication1.xml</DocumentationFile>
    <Optimize>true</Optimize>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
    <DebugType>pdbonly</DebugType>
    <PlatformTarget>x86</PlatformTarget>
    <CodeAnalysisRuleSet>MinimumRecommendedRules.ruleset</CodeAnalysisRuleSet>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=1.0.0.12, Culture=neutral, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Deployment" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
  </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" />
    <Compile Include="My Project\AssemblyInfo.vb" />
    <Compile Include="My Project\Application.Designer.vb">
      <AutoGen>True</AutoGen>
      <DependentUpon>Application.myapp</DependentUpon>
    </Compile>
    <Compile Include="My Project\Resources.Designer.vb">
      <AutoGen>True</AutoGen>
      <DesignTime>True</DesignTime>
      <DependentUpon>Resources.resx</DependentUpon>
    </Compile>
    <Compile Include="My Project\Settings.Designer.vb">
      <AutoGen>True</AutoGen>
      <DependentUpon>Settings.settings</DependentUpon>
      <DesignTimeSharedInput>True</DesignTimeSharedInput>
    </Compile>
  </ItemGroup>
  <ItemGroup>
    <EmbeddedResource Include="My Project\Resources.resx">
      <Generator>VbMyResourcesResXFileCodeGenerator</Generator>
      <LastGenOutput>Resources.Designer.vb</LastGenOutput>
      <CustomToolNamespace>My.Resources</CustomToolNamespace>
      <SubType>Designer</SubType>
    </EmbeddedResource>
  </ItemGroup>
  <ItemGroup>
    <None Include="My Project\Application.myapp">
      <Generator>MyApplicationCodeGenerator</Generator>
      <LastGenOutput>Application.Designer.vb</LastGenOutput>
    </None>
    <None Include="My Project\Settings.settings">
      <Generator>SettingsSingleFileGenerator</Generator>
      <CustomToolNamespace>My</CustomToolNamespace>
      <LastGenOutput>Settings.Designer.vb</LastGenOutput>
    </None>
  </ItemGroup>
  <ItemGroup>
    <Content Include="..\..\UnicodeSample.pdf">
      <Link>UnicodeSample.pdf</Link>
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </Content>
  </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>

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

Module1.vb

      Imports System.Data.OleDb
Imports System.Globalization
Imports System.IO
Imports Bytescout.PDFExtractor

Namespace ConsoleApplication1

    Class Program

        Shared Sub Main(ByVal args As String())

            Dim inputDocument As String = Path.GetFullPath(".\UnicodeSample.pdf")
            Dim csvFilePath As String = Path.ChangeExtension(inputDocument, ".csv")
            Dim csvFileName As String = Path.GetFileName(csvFilePath)
            Dim csvDirectory As String = Path.GetDirectoryName(Path.GetFullPath(csvFilePath))

            ' Create Bytescout.PDFExtractor.CSVExtractor instance
            Using extractor As CSVExtractor = New CSVExtractor("demo", "demo")

                extractor.LoadDocumentFromFile(inputDocument)

                extractor.CSVSeparatorSymbol = ","

                Dim csvText As String = extractor.GetCSV()

                ' Save csv text in UTF-8 encoding without BOM (byte order mark):
                File.WriteAllText(csvFilePath, csvText)

            End Using

            ' Please Note: Target the project to x86 because Microsoft.Jet.OLEDB.4.0 driver is 32-bit only.
            Using connection As OleDbConnection = New OleDbConnection({code}quot;Provider=Microsoft.Jet.OLEDB.4.0;Data Source=""{csvDirectory}"";Extended Properties=""Text;FMT=$;HDR=No;CharacterSet=65001""")

                Using command As OleDbCommand = New OleDbCommand({code}quot;select * from [{csvFileName}]", connection)

                    Using adapter As OleDbDataAdapter = New OleDbDataAdapter(command)
                        Dim table As DataTable = New DataTable()
                        table.Locale = CultureInfo.CurrentCulture
                        adapter.Fill(table)
                        Console.WriteLine({code}quot;Loaded {table.Rows.Count} lines.")
                    End Using

                End Using

            End Using

            Console.ReadKey()

        End Sub

    End Class
End Namespace