ByteScout PDF Extractor SDK – VB.NET – Find Table in PDF And Extract As Text

Home
/
Articles
/
ByteScout PDF Extractor SDK – VB.NET – Find Table in PDF And Extract As Text

printable version:
ByteScout-PDF-Extractor-SDK-VB-NET-Find-Table-in-PDF-And-Extract-As-Text.pdf

How to find table in PDF and extract as text in VB.NET with ByteScout PDF Extractor SDK

ByteScout PDF Extractor SDK is 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)

FindTableAndExtractAsText.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>{34509168-5D95-4323-8808-2A10FDE4E9A9}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <AppDesignerFolder>Properties</AppDesignerFolder>
    <RootNamespace>FindTableAndExtractAsText</RootNamespace>
    <AssemblyName>FindTableAndExtractAsText</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>
  <Import Project="$(MSBuildBinPath)\Microsoft.VisualBasic.Targets" />
  <ItemGroup>
    <Import Include="Microsoft.VisualBasic" />
    <Import Include="System" />
    <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.Drawing" />
    <Reference Include="System.Xml" />
    <Compile Include="Program.vb" />
    <Compile Include="Properties\AssemblyInfo.vb" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="sample3.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </Content>
  </ItemGroup>
</Project>

FindTableAndExtractAsText.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>{34509168-5D95-4323-8808-2A10FDE4E9A9}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <AppDesignerFolder>Properties</AppDesignerFolder>
    <RootNamespace>FindTableAndExtractAsText</RootNamespace>
    <AssemblyName>FindTableAndExtractAsText</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>
  <Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.Targets" />
  <ItemGroup>
    <Import Include="Microsoft.VisualBasic" />
    <Import Include="System" />
    <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.Drawing" />
    <Reference Include="System.Xml" />
    <Compile Include="Program.vb" />
    <Compile Include="Properties\AssemblyInfo.vb" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="sample3.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </Content>
  </ItemGroup>
</Project>

FindTableAndExtractAsText.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>
    <SchemaVersion>2.0</SchemaVersion>
    <ProjectGuid>{34509168-5D95-4323-8808-2A10FDE4E9A9}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <AppDesignerFolder>Properties</AppDesignerFolder>
    <RootNamespace>FindTableAndExtractAsText</RootNamespace>
    <AssemblyName>FindTableAndExtractAsText</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>
  <PropertyGroup>
    <StartupObject>Sub Main</StartupObject>
  </PropertyGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.Targets" />
  <ItemGroup>
    <Import Include="Microsoft.VisualBasic" />
    <Import Include="System" />
    <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.Drawing" />
    <Reference Include="System.Xml" />
    <Compile Include="Program.vb" />
    <Compile Include="Properties\AssemblyInfo.vb" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="sample3.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </Content>
  </ItemGroup>
</Project>

Program.vb

      Imports Bytescout.PDFExtractor

Class Program
	Friend Shared Sub Main(args As String())

        ' Create Bytescout.PDFExtractor.TextExtractor instance
        Dim textExtractor As New TextExtractor()
        textExtractor.RegistrationName = "demo"
        textExtractor.RegistrationKey = "demo"

        ' Create Bytescout.PDFExtractor.TableDetector instance
        Dim tableDetector As New TableDetector()
        tableDetector.RegistrationName = "demo"
        tableDetector.RegistrationKey = "demo"

        ' We should define what kind of tables we should detect.
        ' So we set min required number of columns to 3 ...
        tableDetector.DetectionMinNumberOfColumns = 3
        ' ... and we set min required number of rows to 3
        tableDetector.DetectionMinNumberOfRows = 3

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

        ' Load sample PDF document
        textExtractor.LoadDocumentFromFile(".\sample3.pdf")
        tableDetector.LoadDocumentFromFile(".\sample3.pdf")

		' Get page count
        Dim pageCount As Integer = tableDetector.GetPageCount()

        ' Iterate through pages
		For i As Integer = 0 To pageCount - 1
            Dim t As Integer = 1
            ' Find first table and continue if found
            If (tableDetector.FindTable(i)) Then
                Do
                    ' Set extraction area for JSON extractor to rectangle received from the table detector
                    textExtractor.SetExtractionArea(tableDetector.FoundTableLocation)
                    ' Export the table to JSON file
                    textExtractor.SavePageTextToFile(i, "page-" + i.ToString() + "-table-" + t.ToString() + ".txt")
                    t = t + 1
                Loop While tableDetector.FindNextTable()
            End If
        Next

        ' Cleanup
        textExtractor.Dispose()
        tableDetector.Dispose()

        ' Open first output file in default associated application (for demo purposes)
        System.Diagnostics.Process.Start("page-0-table-1.txt")

    End Sub
End Class