ByteScout PDF Extractor SDK – C# – Find PDF Table And Extract As Text

Home
/
Articles
/
ByteScout PDF Extractor SDK – C# – Find PDF Table And Extract As Text

printable version:
ByteScout-PDF-Extractor-SDK-C-sharp-Find-PDF-Table-And-Extract-As-Text.pdf

How to find PDF table and extract as text in C# using 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.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="sample3.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>

FindTableAndExtractAsText.VS2005.csproj

      <?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>{25E68A98-BA0D-428D-99F4-0ED8C42DD41C}</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>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=2.10.0.362, 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="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Drawing" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup></ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
    <Compile Include="Properties\AssemblyInfo.cs" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="sample3.pdf">
      <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>

FindTableAndExtractAsText.VS2008.csproj

      <?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>{25E68A98-BA0D-428D-99F4-0ED8C42DD41C}</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>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=2.10.0.362, 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="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Drawing" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup></ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
    <Compile Include="Properties\AssemblyInfo.cs" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="sample3.pdf">
      <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>

FindTableAndExtractAsText.VS2010.csproj

      <?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>{25E68A98-BA0D-428D-99F4-0ED8C42DD41C}</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>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=2.10.0.362, 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="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Drawing" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup></ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
    <Compile Include="Properties\AssemblyInfo.cs" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="sample3.pdf">
      <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>

Program.cs

      using System.Diagnostics;
using Bytescout.PDFExtractor;

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

            // Create Bytescout.PDFExtractor.TableDetector instance
            TableDetector tableDetector = new TableDetector();
            tableDetector.RegistrationKey = "demo";
            tableDetector.RegistrationName = "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 3 ...
            tableDetector.DetectionMinNumberOfColumns = 3;
            // ... and we set min required number of rows to 3
            tableDetector.DetectionMinNumberOfRows = 3;

            // Load sample PDF document
            textExtractor.LoadDocumentFromFile(@".\sample3.pdf");
            tableDetector.LoadDocumentFromFile(@".\sample3.pdf");

            // Get page count
            int pageCount = tableDetector.GetPageCount();

            for (int i = 0; i < pageCount; i++)
            {
                int t = 1;
                // Find first table and continue if found
                if (tableDetector.FindTable(i))
                {
                    do
                    {
                        // Set extraction area for CSV extractor to rectangle received from the table detector
                        textExtractor.SetExtractionArea(tableDetector.FoundTableLocation);
                        // Export the table to TEXT file
                        textExtractor.SavePageTextToFile(i, "page-" + i + "-table-" + t + ".txt");
                        t++;
                    } 
                    while (tableDetector.FindNextTable()); // search next table
                }
            }

            // Cleanup
            textExtractor.Dispose();
            tableDetector.Dispose();

            // Open first output file in default associated application (for demo purposes)
            ProcessStartInfo processStartInfo = new ProcessStartInfo("page-0-table-1.txt");
            processStartInfo.UseShellExecute = true;
            Process.Start(processStartInfo);
        }
    }
}