Cloud API – PDF To HTML – VB.NET – Convert PDF To HTML From URL Asynchronously

Home
/
Articles
/
Cloud API – PDF To HTML – VB.NET – Convert PDF To HTML From URL Asynchronously
Cloud API – PDF To HTML – VB.NET – Convert PDF To HTML From URL Asynchronously

Module1.vb
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
Imports System.IO
Imports System.Net
Imports System.Threading
Imports Newtonsoft.Json.Linq
 
 
' Cloud API asynchronous "PDF To HTML" job example.
' Allows to avoid timeout errors when processing huge or scanned PDF documents.
 
Module Module1
 
    ' (!) If you are getting '(403) Forbidden' error please ensure you have set the correct API_KEY
 
    ' The authentication key (API Key).
    ' Get your own by registering at https://secure.bytescout.com/users/sign_up
    Const API_KEY As String = "***********************************"
 
    ' Direct URL of source PDF file.
    Const SourceFileUrl As String = "https://s3-us-west-2.amazonaws.com/bytescout-com/files/demo-files/cloud-api/pdf-to-html/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 HTML file name
    Const DestinationFile As String = ".\result.html"
    ' Set to `true` to get simplified HTML without CSS. Default is the rich HTML keeping the document design.
    Const PlainHtml As Boolean = False
    ' Set to `true` if your document has the column layout like a newspaper.
    Const ColumnLayout As Boolean = False
    ' (!) Make asynchronous job
    Const Async As Boolean = True
 
 
    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)
 
        ' Prepare URL for `PDF To HTML` API call
        Dim query As String = Uri.EscapeUriString(String.Format(
            "https://api.pdf.co/v1/pdf/convert/to/html?name={0}&password={1}&pages={2}&simple={3}&columns={4}&url={5}&async={6}",
            Path.GetFileName(DestinationFile),
            Password,
            Pages,
            PlainHtml,
            ColumnLayout,
            SourceFileUrl,
            Async))
 
        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
 
                ' Asynchronous job ID
                Dim jobId As String = json("jobId").ToString()
                ' URL of generated HTML 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: "InProgress", "Failed", "Aborted", "Finished".
 
                    ' Display timestamp and status (for demo purposes)
                    Console.WriteLine(DateTime.Now.ToLongTimeString() + ": " + status)
 
                    If status = "Finished" Then
 
                        ' Download HTML file
                        webClient.DownloadFile(resultFileUrl, DestinationFile)
 
                        Console.WriteLine("Generated HTML file saved as ""{0}"" file.", DestinationFile)
                        Exit Do
 
                    ElseIf status = "InProgress" 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
 
        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()
 
            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
Click here to get your Free Trial version of the SDK
Cloud API – PDF To HTML – VB.NET – Convert PDF To HTML From URL Asynchronously

Cloud API – PDF To HTML – VB.NET – Convert PDF To HTML From URL Asynchronously

Tutorials:
