Link Search Menu Expand Document

Advanced Conversion Options With Rotated Input - VB.NET

PDF To XML sample in VB.NET demonstrating ‘Advanced Conversion Options With Rotated Input’

Module1.vb
Imports System.IO
Imports System.Net
Imports Newtonsoft.Json
Imports Newtonsoft.Json.Linq

Module Module1

    ' The authentication key (API Key).
    ' Get your own by registering at https://app.pdf.co
    Const API_KEY As String = "******************************"

    ' Source PDF file
    Const SourceFile As String = ".\sample-rotated.pdf"
    ' Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
    Const Pages As String = ""
    ' PDF document password. Leave empty for unprotected documents.
    Const Password As String = ""
    ' Destination XML file name
    Const DestinationFile As String = ".\result.xml"

    ' Some of advanced options available through profiles:
    ' (it can be single/double-quoted and contain comments.)
    ' {
    ' 	"profiles": [
    ' 		{
    ' 			"profile1": {
    ' 				"SaveImages": "None", // Whether to extract images. Values: "None", "Embed".
    ' 				"ImageFormat": "PNG", // Image format for extracted images. Values: "PNG", "JPEG", "GIF", "BMP".
    ' 				"SaveVectors": false, // Whether to extract vector objects (vertical and horizontal lines). Values: true / false
    ' 				"ExtractInvisibleText": true, // Invisible text extraction. Values: true / false
    ' 				"ExtractShadowLikeText": true, // Shadow-like text extraction. Values: true / false
    ' 				"LineGroupingMode": "None", // Values: "None", "GroupByRows", "GroupByColumns", "JoinOrphanedRows"
    ' 				"ColumnDetectionMode": "ContentGroupsAndBorders", // Values: "ContentGroupsAndBorders", "ContentGroups", "Borders", "BorderedTables"
    ' 				"Unwrap": false, // Unwrap grouped text in table cells. Values: true / false
    ' 				"ShrinkMultipleSpaces": false, // Shrink multiple spaces in table cells that affect column detection. Values: true / false
    ' 				"DetectNewColumnBySpacesRatio": 1, // Spacing ratio that affects column detection.
    ' 				"CustomExtractionColumns": [ 0, 50, 150, 200, 250, 300 ], // Explicitly specify columns coordinates for table extraction.
    ' 				"CheckPermissions": true, // Ignore document permissions. Values: true / false
    ' 			}
    ' 		}
    ' 	]
    ' }

    ' Sample profile that sets advanced conversion options.
    ' Advanced options are properties of XMLExtractor class from ByteScout PDF Extractor SDK used in the back-end:
    ' https://cdn.bytescout.com/help/BytescoutPDFExtractorSDK/html/87ce5fa6-3143-167d-abbd-bc7b5e160fe5.htm

    'Valid RotationAngle values
    '0 - no rotation
    '1 - 90 degrees
    '2 - 180 degrees
    '3 - 270 degrees
    ReadOnly Profiles As String = File.ReadAllText("profile.json")

    Sub Main()

        ' Create standard .NET web client instance
        Dim webClient As WebClient = New WebClient()

        ' Set API Key
        webClient.Headers.Add("x-api-key", API_KEY)

        ' 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
        ' * If you already have a direct file URL, skip to the step 3.

        ' Prepare URL for `Get Presigned URL` API call
        Dim query As String = Uri.EscapeUriString(String.Format(
            "https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name={0}",
            Path.GetFileName(SourceFile)))

        Try
            ' Execute request
            Dim response As String = webClient.DownloadString(query)

            ' Parse JSON response
            Dim json As JObject = JObject.Parse(response)

            If json("error").ToObject(Of Boolean) = False Then
                ' Get URL to use for the file upload
                Dim uploadUrl As String = json("presignedUrl").ToString()
                ' Get URL of uploaded file to use with later API calls
                Dim uploadedFileUrl As String = json("url").ToString()

                ' 2. UPLOAD THE FILE TO CLOUD.

                webClient.Headers.Add("content-type", "application/octet-stream")
                webClient.UploadFile(uploadUrl, "PUT", SourceFile) ' You can use UploadData() instead if your file is byte array or Stream

                ' Set JSON content type
                webClient.Headers.Add("Content-Type", "application/json")

                ' 3. CONVERT UPLOADED PDF FILE TO XML

                ' Prepare URL for `PDF To XML` API call
                Dim url As String = "https://api.pdf.co/v1/pdf/convert/to/xml"

                ' Prepare requests params as JSON
                ' See documentation: https : //apidocs.pdf.co
                Dim parameters As New Dictionary(Of String, Object)
                parameters.Add("name", Path.GetFileName(DestinationFile))
                parameters.Add("password", Password)
                parameters.Add("pages", Pages)
                parameters.Add("url", uploadedFileUrl)
                parameters.Add("profiles", Profiles)

                ' Convert dictionary of params to JSON
                Dim jsonPayload As String = JsonConvert.SerializeObject(parameters)

                ' Execute POST request with JSON payload
                response = webClient.UploadString(url, jsonPayload)

                ' Parse JSON response
                json = JObject.Parse(response)

                If json("error").ToObject(Of Boolean) = False Then

                    ' Get URL of generated XML file
                    Dim resultFileUrl As String = json("url").ToString()

                    ' Download XML file
                    webClient.DownloadFile(resultFileUrl, DestinationFile)

                    Console.WriteLine("Generated XML file saved as ""{0}"" file.", DestinationFile)

                Else
                    Console.WriteLine(json("message").ToString())
                End If

            End If

        Catch ex As WebException
            Console.WriteLine(ex.ToString())
        End Try

        webClient.Dispose()


        Console.WriteLine()
        Console.WriteLine("Press any key...")
        Console.ReadKey()

    End Sub

End Module

profile.json
{
  "profiles": [
    {
      "profile1": {
        "RotationAngle": 1
      }
    }
  ]
}
Resources.Designer.vb
'------------------------------------------------------------------------------
' <auto-generated>
'     This code was generated by a tool.
'     Runtime Version:4.0.30319.42000
'
'     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", "4.0.0.0"), _
	 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("ByteScoutWebApiExample.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:4.0.30319.42000
'
'     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", "11.0.0.0"), _
	 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.ByteScoutWebApiExample.My.MySettings
			Get
				Return Global.ByteScoutWebApiExample.My.MySettings.Default
			End Get
		End Property
	End Module
End Namespace

PDF.co Web API: the Web API with a set of tools for documents manipulation, data conversion, data extraction, splitting and merging of documents. Includes image recognition, built-in OCR, barcode generation and barcode decoders to decode bar codes from scans, pictures and pdf.

Get your PDF.co API key here!

Download Source Code (.zip)

return to the previous page explore PDF To XML endpoint