RPA Robotic Process Automation – Regular Expression Search and Highlight in PDF – VB.NET

Home
/
Articles
/
RPA Robotic Process Automation – Regular Expression Search and Highlight in PDF – VB.NET

printable version:
ByteScout-Robotic-Process-Automation-VB-NET-VB-NET.pdf

How to regular expression search and highlight in PDF in VB.NET using ByteScout Robotic Process Automation

ByteScout Robotic Process Automation is set of tools for rapid implementation of robotic process automation applications.

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

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

Module1.vb

      Imports System.Drawing
Imports Bytescout.PDF
Imports Bytescout.PDFExtractor

Module Module1

    Sub Main()

        Dim inputFile As String = ".\sample.pdf"
        Dim pageIndex As Integer = 0
        Dim searchPattern As String = "\d+\.\d+"

        ' Prepare TextExtractor
        Using textExtractor As TextExtractor = New TextExtractor("demo", "demo")

            textExtractor.RegexSearch = true
            textExtractor.LoadDocumentFromFile(inputFile)

            ' Load document with PDF SDK
            Using pdfDocument As Document = New Document(inputFile)

                pdfDocument.RegistrationName = "demo"
                pdfDocument.RegistrationKey = "demo"

                Dim pdfDocumentPage As Page = pdfDocument.Pages(pageIndex)
                Dim canvas As Canvas = pdfDocumentPage.Canvas

                Dim fillBrush As Bytescout.PDF.SolidBrush = new Bytescout.PDF.SolidBrush(new ColorRGB(255, 0, 0))
                fillBrush.Opacity = 50 ' make the brush transparent

                ' Search for pattern and highlight found pieces
                If textExtractor.Find(pageIndex, searchPattern, caseSensitive := False)

                    Do
                        For Each foundPiece In textExtractor.FoundText.Elements
                            
                            ' Inflate the rectangle a bit
                            Dim rect As RectangleF = RectangleF.Inflate(foundPiece.Bounds, 1, 2)
                            ' Draw rectangle over the PDF page
                            canvas.DrawRectangle(fillBrush, rect)

                        Next

                    Loop While textExtractor.FindNext()

                End If

                ' Save as new PDF document
                pdfDocument.Save("result.pdf")

                ' Open result document in default associated application (for demo purposes)
                Process.Start("result.pdf")
                
            End Using

        End Using

    End Sub

End Module

SearchAndHighlightExample.sln

      
Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 15
VisualStudioVersion = 15.0.27703.2018
MinimumVisualStudioVersion = 10.0.40219.1
Project("{F184B08F-C81C-45F6-A57F-5ABD9991F28F}") = "SearchAndHighlightExample", "SearchAndHighlightExample.vbproj", "{23DFDE65-1DB4-4348-84C2-0E5BFD4473C1}"
EndProject
Global
	GlobalSection(SolutionConfigurationPlatforms) = preSolution
		Debug|Any CPU = Debug|Any CPU
		Release|Any CPU = Release|Any CPU
	EndGlobalSection
	GlobalSection(ProjectConfigurationPlatforms) = postSolution
		{23DFDE65-1DB4-4348-84C2-0E5BFD4473C1}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
		{23DFDE65-1DB4-4348-84C2-0E5BFD4473C1}.Debug|Any CPU.Build.0 = Debug|Any CPU
		{23DFDE65-1DB4-4348-84C2-0E5BFD4473C1}.Release|Any CPU.ActiveCfg = Release|Any CPU
		{23DFDE65-1DB4-4348-84C2-0E5BFD4473C1}.Release|Any CPU.Build.0 = Release|Any CPU
	EndGlobalSection
	GlobalSection(SolutionProperties) = preSolution
		HideSolutionNode = FALSE
	EndGlobalSection
	GlobalSection(ExtensibilityGlobals) = postSolution
		SolutionGuid = {D7B1CFBF-B914-4A51-9EC0-B8C10A2BEAB0}
	EndGlobalSection
EndGlobal

SearchAndHighlightExample.vbproj

      <?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>{23DFDE65-1DB4-4348-84C2-0E5BFD4473C1}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <StartupObject>SearchAndHighlightExample.Module1</StartupObject>
    <RootNamespace>SearchAndHighlightExample</RootNamespace>
    <AssemblyName>SearchAndHighlightExample</AssemblyName>
    <FileAlignment>512</FileAlignment>
    <MyType>Console</MyType>
    <TargetFrameworkVersion>v4.0</TargetFrameworkVersion>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <DefineDebug>true</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <OutputPath>bin\Debug\</OutputPath>
    <DocumentationFile>SearchAndHighlightExample.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugType>pdbonly</DebugType>
    <DefineDebug>false</DefineDebug>
    <DefineTrace>true</DefineTrace>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DocumentationFile>SearchAndHighlightExample.xml</DocumentationFile>
    <NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
  </PropertyGroup>
  <PropertyGroup>
    <OptionExplicit>On</OptionExplicit>
  </PropertyGroup>
  <PropertyGroup>
    <OptionCompare>Binary</OptionCompare>
  </PropertyGroup>
  <PropertyGroup>
    <OptionStrict>Off</OptionStrict>
  </PropertyGroup>
  <PropertyGroup>
    <OptionInfer>On</OptionInfer>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDF, Version=1.8.1.246, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout PDF SDK\net4.0\Bytescout.PDF.dll</HintPath>
    </Reference>
    <Reference Include="Bytescout.PDFExtractor, Version=9.0.0.3087, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>C:\Program Files\Bytescout PDF Extractor SDK\net4.00\Bytescout.PDFExtractor.dll</HintPath>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Drawing" />
    <Reference Include="System.Xml" />
    <Reference Include="System.Core" />
    <Reference Include="System.Xml.Linq" />
  </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" />
    <Import Include="System.Linq" />
    <Import Include="System.Xml.Linq" />
  </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>
    <Content Include="sample.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </Content>
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.targets" />
</Project>