Imports System.Collections.Specialized
Imports System.IO
Imports System.Net
Imports System.Text
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 = ".\MultiPageTable.pdf"

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

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

    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("MultiPageTable-template1.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 = "https://api.pdf.co/v1/pdf/documentparser"

                Dim requestBody As New NameValueCollection()
                requestBody.Add("url", uploadedFileUrl)
                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

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

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

                    Console.WriteLine("Generated JSON 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

templateName: Multipage Table Test
templateVersion: 4
templatePriority: 0
detectionRules:
  keywords:
  - Sample document with multi-page table
objects:
- name: total
  objectType: field
  fieldProperties:
    fieldType: macros
    expression: TOTAL{{Spaces}}({{Number}})
    regex: true
    dataType: decimal
- name: table1
  objectType: table
  tableProperties:
    start:
      expression: Item{{Spaces}}Description{{Spaces}}Price
      regex: true
    end:
      expression: TOTAL{{Spaces}}{{Number}}
      regex: true
    row:
      expression: '{{LineStart}}{{Spaces}}(?<itemNo>{{Digits}}){{Spaces}}(?<description>{{SentenceWithSingleSpaces}}){{Spaces}}(?<price>{{Number}}){{Spaces}}(?<qty>{{Digits}}){{Spaces}}(?<extPrice>{{Number}})'
      regex: true
    columns:
    - name: itemNo
      dataType: integer
    - name: description
      dataType: string
    - name: price
      dataType: decimal
    - name: qty
      dataType: integer
    - name: extPrice
      dataType: decimal
    multipage: true