Link Search Menu Expand Document

Get Word Coordinates in JSON - VB.NET

PDF Extractor SDK sample in VB.NET demonstrating ‘Get Word Coordinates in JSON’

Module1.vb
Imports System
Imports System.Collections.Generic
Imports System.Text
Imports Bytescout.PDFExtractor
Imports System.Diagnostics

Namespace ConsoleApplication1

    Class Program

        Shared Sub Main(ByVal args As String())

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

            ' Load sample PDF document
            extractor.LoadDocumentFromFile("sample3.pdf")

            ' Add the following params to get clean data with word nodes only
            extractor.DetectNewColumnBySpacesRatio = 0.1 ' This splits all text into words
            extractor.PreserveFormattingOnTextExtraction = False ' Get rid Of empty nodes

            extractor.SaveJSONToFile("output.json")

            ' Cleanup
            extractor.Dispose()

            Console.WriteLine()
            Console.WriteLine("Data has been extracted to 'output.json' file.")
            Console.WriteLine()
            Console.WriteLine("Press any key to continue and open JSON file in default viewer...")
            Console.ReadKey()

            ' Open result file in default associated application (for demo purposes)
            Process.Start("output.json")

        End Sub

    End Class
    
End Namespace


Resources.Designer.vb
��'------------------------------------------------------------------------------

' <auto-generated>

'     This code was generated by a tool.

'     Runtime Version:2.0.50727.1433

'

'     Changes to this file may cause incorrect behavior and will be lost if

'     the code is regenerated.

' </auto-generated>

'------------------------------------------------------------------------------



Option Strict On

Option Explicit On





Namespace My.Resources

    

    'This class was auto-generated by the StronglyTypedResourceBuilder

    'class via a tool like ResGen or Visual Studio.

    'To add or remove a member, edit your .ResX file then rerun ResGen

    'with the /str option, or rebuild your VS project.

    '<summary>

    '  A strongly-typed resource class, for looking up localized strings, etc.

    '</summary>

    <Global.System.CodeDom.Compiler.GeneratedCodeAttribute("System.Resources.Tools.StronglyTypedResourceBuilder", "2.0.0.0"),  _

     Global.System.Diagnostics.DebuggerNonUserCodeAttribute(),  _

     Global.System.Runtime.CompilerServices.CompilerGeneratedAttribute(),  _

     Global.Microsoft.VisualBasic.HideModuleNameAttribute()>  _

    Friend Module Resources

        

        Private resourceMan As Global.System.Resources.ResourceManager

        

        Private resourceCulture As Global.System.Globalization.CultureInfo

        

        '<summary>

        '  Returns the cached ResourceManager instance used by this class.

        '</summary>

        <Global.System.ComponentModel.EditorBrowsableAttribute(Global.System.ComponentModel.EditorBrowsableState.Advanced)>  _

        Friend ReadOnly Property ResourceManager() As Global.System.Resources.ResourceManager

            Get

                If Object.ReferenceEquals(resourceMan, Nothing) Then

                    Dim temp As Global.System.Resources.ResourceManager = New Global.System.Resources.ResourceManager("ConsoleApplication1.Resources", GetType(Resources).Assembly)

                    resourceMan = temp

                End If

                Return resourceMan

            End Get

        End Property

        

        '<summary>

        '  Overrides the current thread's CurrentUICulture property for all

        '  resource lookups using this strongly typed resource class.

        '</summary>

        <Global.System.ComponentModel.EditorBrowsableAttribute(Global.System.ComponentModel.EditorBrowsableState.Advanced)>  _

        Friend Property Culture() As Global.System.Globalization.CultureInfo

            Get

                Return resourceCulture

            End Get

            Set(ByVal value As Global.System.Globalization.CultureInfo)

                resourceCulture = value

            End Set

        End Property

    End Module

End Namespace


Settings.Designer.vb
��'------------------------------------------------------------------------------

' <auto-generated>

'     This code was generated by a tool.

'     Runtime Version:2.0.50727.1433

'

'     Changes to this file may cause incorrect behavior and will be lost if

'     the code is regenerated.

' </auto-generated>

'------------------------------------------------------------------------------



Option Strict On

Option Explicit On





Namespace My



    <Global.System.Runtime.CompilerServices.CompilerGeneratedAttribute(),  _

     Global.System.CodeDom.Compiler.GeneratedCodeAttribute("Microsoft.VisualStudio.Editors.SettingsDesigner.SettingsSingleFileGenerator", "8.0.0.0"),  _

     Global.System.ComponentModel.EditorBrowsableAttribute(Global.System.ComponentModel.EditorBrowsableState.Advanced)>  _

    Partial Friend NotInheritable Class MySettings

        Inherits Global.System.Configuration.ApplicationSettingsBase

        

        Private Shared defaultInstance As MySettings = CType(Global.System.Configuration.ApplicationSettingsBase.Synchronized(New MySettings), MySettings)

        

#Region "My.Settings Auto-Save Functionality"

#If _MyType = "WindowsForms" Then

        Private Shared addedHandler As Boolean



        Private Shared addedHandlerLockObject As New Object



        <Global.System.Diagnostics.DebuggerNonUserCodeAttribute(), Global.System.ComponentModel.EditorBrowsableAttribute(Global.System.ComponentModel.EditorBrowsableState.Advanced)> _

        Private Shared Sub AutoSaveSettings(ByVal sender As Global.System.Object, ByVal e As Global.System.EventArgs)

            If My.Application.SaveMySettingsOnExit Then

                My.Settings.Save()

            End If

        End Sub

#End If

#End Region

        

        Public Shared ReadOnly Property [Default]() As MySettings

            Get

                

#If _MyType = "WindowsForms" Then

                   If Not addedHandler Then

                        SyncLock addedHandlerLockObject

                            If Not addedHandler Then

                                AddHandler My.Application.Shutdown, AddressOf AutoSaveSettings

                                addedHandler = True

                            End If

                        End SyncLock

                    End If

#End If

                Return defaultInstance

            End Get

        End Property

    End Class

End Namespace



Namespace My

    

    <Global.Microsoft.VisualBasic.HideModuleNameAttribute(),  _

     Global.System.Diagnostics.DebuggerNonUserCodeAttribute(),  _

     Global.System.Runtime.CompilerServices.CompilerGeneratedAttribute()>  _

    Friend Module MySettingsProperty

        

        <Global.System.ComponentModel.Design.HelpKeywordAttribute("My.Settings")>  _

        Friend ReadOnly Property Settings() As Global.ConsoleApplication1.My.MySettings

            Get

                Return Global.ConsoleApplication1.My.MySettings.Default

            End Get

        End Property

    End Module

End Namespace


Download Source Code (.zip)

Return to the previous page Explore PDF Extractor SDK