ByteScout PDF Extractor SDK – C# – Remove SSN Number from PDF Document

Home
/
Articles
/
ByteScout PDF Extractor SDK – C# – Remove SSN Number from PDF Document

printable version:
ByteScout-PDF-Extractor-SDK-C-sharp-Remove-SSN-Number-from-PDF-Document.pdf

How to remove SSN number from PDF document in C# with ByteScout PDF Extractor SDK

ByteScout PDF Extractor SDK is the Software Development Kit (SDK) that is designed to help developers with 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.

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

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

Program.cs

      using Bytescout.PDFExtractor;
using System;
using System.Diagnostics;

namespace RemoveSNNumber
{
    class Program
    {
        static void Main(string[] args)
        {
            string inputDocument = @".\samplePDF_SSNNo.pdf";
            string outputDocument = @".\samplePDF_SSNNo_edited.pdf";

            try
            {
                // Create Bytescout.PDFExtractor.TextExtractor instance
                using (TextExtractor extractor = new TextExtractor("demo", "demo"))
                {
                    // Create Bytescout.PDFExtractor.Remover2 instance
                    using (Remover2 remover = new Remover2("demo", "demo"))
                    {
                        // Load sample PDF document
                        extractor.LoadDocumentFromFile("samplePDF_SSNNo.pdf");
                        remover.LoadDocumentFromFile(inputDocument);

                        extractor.RegexSearch = true; // Enable the regular expressions

                        int pageCount = extractor.GetPageCount();

                        // Search through pages
                        for (int pageIndex = 0; pageIndex < pageCount; pageIndex++)
                        {
                            // Search SSN in format 202-55-0130 using regular expression.
                            // See the complete regular expressions reference at https://msdn.microsoft.com/en-us/library/az24scfc(v=vs.110).aspx
                            string regexPattern = "[0-9]{3}-[0-9]{2}-[0-9]{4}";

                            // Search each page for the pattern
                            ISearchResult[] searchResults = extractor.FindAll(pageIndex, regexPattern, caseSensitive: false);
                            
                            foreach (var element in searchResults)
                            {
                                Console.WriteLine("Found SSN No: " + element.Text);
                                // Add rectangle of the found SSN to Remover
                                remover.AddTextToRemove(pageIndex, element.Bounds);
                            }
                        }

                        // Mask replaced text with black rectangle
                        remover.MaskRemovedText = true;
                        // Change the color of the mask rectangle, if necessary
                        //remover.MaskColor = Color.Red;

                        remover.PerformRemoval(outputDocument);

                        Console.WriteLine("Found SSNs removed, result saved to file \"" + outputDocument + "\"");
                    }
                }

                // Open result file in default associated application (for the demonstration purpose)
                var processStartInfo = new ProcessStartInfo(outputDocument) { UseShellExecute = true };
                Process.Start(processStartInfo);
            }
            catch (Exception ex)
            {
                Console.WriteLine("Error: " + ex.Message);
            }

            Console.WriteLine();
            Console.WriteLine("Press enter key to continue...");
            Console.ReadLine();
        }
    }
}

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

RemoveSNNumber.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="samplePDF_SSNNo.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

RemoveSNNumber.csproj

      <?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>{99735776-2956-463D-9795-EBCE16928C30}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <RootNamespace>RemoveSNNumber</RootNamespace>
    <AssemblyName>RemoveSNNumber</AssemblyName>
    <TargetFrameworkVersion>v2.0</TargetFrameworkVersion>
    <FileAlignment>512</FileAlignment>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <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' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <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=9.1.0.3170, 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.Xml" />
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
  </ItemGroup>
  <ItemGroup>
    <None Include="samplePDF_SSNNo.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.CSharp.targets" />
</Project>