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 = "***********************************"

    ' Direct URL of source PDF file.
    ' You can also upload your own file into PDF.co and use it as url. Check "Upload File" samples for code snippets: https://github.com/bytescout/pdf-co-api-samples/tree/master/File%20Upload/   
    Const SourceFileUrl As String = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-text/sample.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 TXT file name
	const DestinationFile as string = ".\result.txt"

	' Some of advanced options available through profiles:
	' (JSON can be single/double-quoted and contain comments.)
	' {
	'     "profiles": [
	'         {
	'             "profile1": {                
	'                 "ExtractInvisibleText": true, // Invisible text extraction. Values: true / false
	'                 "ExtractShadowLikeText": true, // Shadow-like text extraction. Values: true / false
	'                 "ExtractAnnotations": true, // Whether to extract PDF annotations.
	'                 "CheckPermissions": true, // Ignore document permissions. Values: true / false
	'                 "DetectNewColumnBySpacesRatio": 1.2, // A ratio affecting number of spaces between words. 
	'             }
	'         }
	'     ]
	' }

    ' Sample profile that sets advanced conversion options
    ' Advanced options are properties of TextExtractor class from ByteScout Text Extractor SDK used in the back-end:
    ' https://cdn.bytescout.com/help/BytescoutPDFExtractorSDK/html/8a2bae5a-346f-8338-b5aa-6f3522dca0d4.htm
    ReadOnly Profiles = 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)

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

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

        ' 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", SourceFileUrl)
		parameters.Add("profiles", Profiles)

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

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

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

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

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

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

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

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

{
  "profiles": [
    {
      "profile1": {
        "TrimSpaces": "False",
        "PreserveFormattingOnTextExtraction": "True",
        "Unwrap": "True"
      }
    }
  ]
}