Link Search Menu Expand Document

Parsing and reading data from Airline Tickets - VB.NET

Document Parser sample in VB.NET demonstrating ‘Parsing and reading data from Airline Tickets’

Module1.vb
Imports System.Collections.Specialized
Imports System.IO
Imports System.Net
Imports System.Text
Imports System.Threading
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 = ".\SampleTicket.pdf"

    ' PDF document password. Leave empty for unprotected documents.
    Const Password As String = ""

    ' Destination TXT file name
    Const DestinationFile As String = ".\result.json"

    ' (!) Make asynchronous job
    Const Async As Boolean = True

    Sub Main()

        ' Template text. Use Document Parser (https://pdf.co/document-parser, https://app.pdf.co/document-parser)
        ' to create templates.
        ' Read template from file
        Dim templateText As String = File.ReadAllText("SampleTicket.yml")


        ' 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

                ' 3. PARSE UPLOADED PDF DOCUMENT

                ' URL for `Document Parser` API call
                query = Uri.EscapeUriString(
                    String.Format("https://api.pdf.co/v1/pdf/documentparser?url={0}&async={1}", uploadedFileUrl, Async)
                    )

                Dim requestBody As New NameValueCollection()
                requestBody.Add("template", templateText)

                ' Execute request
                Dim responseBytes As Byte() = webClient.UploadValues(query, "POST", requestBody)
                response = Encoding.UTF8.GetString(responseBytes)

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

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

                    ' Asynchronous job ID
                    Dim jobId As String = json("jobId").ToString()
                    ' URL of generated PDF file that will available after the job completion
                    Dim resultFileUrl As String = json("url").ToString()

                    ' Check the job status in a loop. 
                    ' If you don't want to pause the main thread you can rework the code 
                    ' to use a separate thread for the status checking and completion.
                    Do
                        Dim status As String = CheckJobStatus(jobId) ' Possible statuses: "working", "failed", "aborted", "success".

                        ' Display timestamp and status (for demo purposes)
                        Console.WriteLine(DateTime.Now.ToLongTimeString() + ": " + status)

                        If status = "success" Then

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

                            Console.WriteLine("Generated JSON file saved as ""{0}"" file.", DestinationFile)
                            Exit Do

                        ElseIf status = "working" Then

                            ' Pause for a few seconds
                            Thread.Sleep(3000)

                        Else

                            Console.WriteLine(status)
                            Exit Do

                        End If

                    Loop

                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


    Function CheckJobStatus(jobId As String) As String

        Using webClient As WebClient = New WebClient()

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

            Dim url As String = "https://api.pdf.co/v1/job/check?jobid=" + jobId

            Dim response As String = webClient.DownloadString(url)
            Dim json As JObject = JObject.Parse(response)

            Return Convert.ToString(json("status"))

        End Using

    End Function

End Module
SampleTicket.yml
templateName: MakeMyTrip Booking
templateVersion: 4
templatePriority: 0
detectionRules:
  keywords:
  - MakeMyTrip
  - Eticket-Dom-Flight
objects:
- name: BookingNo
  objectType: field
  fieldProperties:
    fieldType: rectangle
    regex: true
    rectangle:
    - 198.75
    - 85.625
    - 96.875
    - 12.500001
    pageIndex: 0
- name: BookingDate
  objectType: field
  fieldProperties:
    fieldType: rectangle
    regex: true
    dataType: date
    rectangle:
    - 133.125
    - 97.5000076
    - 78.75
    - 12.500001
    pageIndex: 0
- name: DepartureFrom
  objectType: field
  fieldProperties:
    fieldType: rectangle
    regex: true
    rectangle:
    - 153
    - 176
    - 77
    - 8.5
    pageIndex: 0
- name: ArrivalTo
  objectType: field
  fieldProperties:
    fieldType: rectangle
    regex: true
    rectangle:
    - 285
    - 176
    - 84
    - 8.5
    pageIndex: 0
- name: DepartureAt
  objectType: field
  fieldProperties:
    fieldType: rectangle
    regex: true
    dataType: date
    rectangle:
    - 153.75
    - 187.5
    - 123.75
    - 10.625
    pageIndex: 0
- name: ArrivalAt
  objectType: field
  fieldProperties:
    fieldType: rectangle
    regex: true
    dataType: date
    rectangle:
    - 288.125
    - 186.875
    - 125.625008
    - 11.25
    pageIndex: 0
- name: FlightType
  objectType: field
  fieldProperties:
    fieldType: rectangle
    regex: true
    rectangle:
    - 433.5
    - 159.5
    - 68
    - 10.5
    pageIndex: 0
- name: FlightDuration
  objectType: field
  fieldProperties:
    fieldType: rectangle
    regex: true
    rectangle:
    - 474.375031
    - 170.625
    - 30.0000019
    - 10
    pageIndex: 0
- name: CabinType
  objectType: field
  fieldProperties:
    fieldType: rectangle
    regex: true
    rectangle:
    - 463.125031
    - 194.375015
    - 51.25
    - 10
    pageIndex: 0
- name: PassengerName
  objectType: field
  fieldProperties:
    fieldType: rectangle
    regex: true
    rectangle:
    - 85
    - 238.125
    - 93.125
    - 14.375
    pageIndex: 0
- name: PassengerType
  objectType: field
  fieldProperties:
    fieldType: rectangle
    regex: true
    rectangle:
    - 229.375015
    - 238.125
    - 31.25
    - 13.75
    pageIndex: 0
- name: AirlinePNR
  objectType: field
  fieldProperties:
    fieldType: rectangle
    regex: true
    rectangle:
    - 375
    - 240.000015
    - 46.25
    - 13.75
    pageIndex: 0


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 Document Parser endpoint