ByteScout PDF Extractor SDK – C# – PDF To XLSX by pages

Home
/
Articles
/
ByteScout PDF Extractor SDK – C# – PDF To XLSX by pages

printable version:
ByteScout-PDF-Extractor-SDK-C-sharp-PDF-To-XLSX-by-pages.pdf

PDF to XLSX by pages in C# and 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)

PDF2XLSX.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" />
    <None Include="..\..\ProductsMonthWise.pdf" Link="ProductsMonthWise.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>

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

PDF2XLSX.VS2005.csproj

      <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>{5FD39006-92D8-4ACC-B2EB-A43ECBC67F99}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <RootNamespace>PDF2XLSX</RootNamespace>
    <AssemblyName>PDF2XLSX</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=2.0.0.186, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="..\..\ProductsMonthWise.pdf">
      <Link>ProductsMonthWise.pdf</Link>
      <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>

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

PDF2XLSX.VS2008.csproj

      <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>{5FD39006-92D8-4ACC-B2EB-A43ECBC67F99}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <RootNamespace>PDF2XLSX</RootNamespace>
    <AssemblyName>PDF2XLSX</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=2.0.0.186, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="..\..\ProductsMonthWise.pdf">
      <Link>ProductsMonthWise.pdf</Link>
      <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>

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

PDF2XLSX.VS2010.csproj

      <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>{5FD39006-92D8-4ACC-B2EB-A43ECBC67F99}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <RootNamespace>PDF2XLSX</RootNamespace>
    <AssemblyName>PDF2XLSX</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=2.0.0.186, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
  </ItemGroup>
  <ItemGroup>
    <Content Include="..\..\ProductsMonthWise.pdf">
      <Link>ProductsMonthWise.pdf</Link>
      <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>

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

Program.cs

      using Bytescout.PDFExtractor;
using System;

namespace PDF2XLS
{

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

            // Load sample PDF document
            extractor.LoadDocumentFromFile("ProductsMonthWise.pdf");

            // Uncomment this line if you need all pages converted into a single worksheet:
            //extractor.PageToWorksheet = false;

            // Set the output format to XLSX
            extractor.OutputFormat = SpreadseetOutputFormat.XLSX;

            // No of Pages
            var pageCount = extractor.GetPageCount();

            for (int i = 0; i < pageCount; i++)
            {
                string outputName = {code}quot;page_{i + 1}.xlsx";

                // Save page to spreadsheet file
                extractor.SavePageToXLSFile(i, outputName);

                Console.WriteLine("'{0}' Created", outputName);
            }

            // Cleanup
            extractor.Dispose();

            Console.ReadLine();
        }
    }
}