Method: SelectPdf::PdfToTextClient#text_from_url_async

Defined in:

lib/selectpdf.rb

#text_from_url_async(url) ⇒ Object

Get the text from the specified pdf with an asynchronous call.

Parameters:

• Address of the PDF file.

Returns:

• Extracted text.

Raises:

# File 'lib/selectpdf.rb', line 2323

def text_from_url_async(url)
  if !url.downcase.start_with?('http://') && !url.downcase.start_with?('https://')
    raise ApiException.new('The supported protocols for the PDFs available online are http:// and https://.'),
          'The supported protocols for the PDFs available online are http:// and https://.'
  end

  if url.downcase.start_with?('http://localhost')
    raise ApiException.new('Cannot convert local urls via this method. Use getTextFromFile instead.'),
          'Cannot convert local urls via this method. Use text_from_file_async instead.'
  end

  @parameters['action'] = 'Convert'

  @files = {}
  @parameters['url'] = url

  job_id = start_async_job_multipart_form_data

  if job_id.nil? || job_id.empty?
    raise ApiException.new('An error occurred launching the asynchronous call.'), 'An error occurred launching the asynchronous call.'
  end

  no_pings = 0

  while no_pings < @async_calls_max_pings
    no_pings += 1

    # sleep for a few seconds before next ping
    sleep(@async_calls_ping_interval)

    async_job_client = AsyncJobClient.new(@parameters['key'], @job_id)
    async_job_client.api_endpoint = @api_async_endpoint

    result = async_job_client.result

    next if result.nil?

    @number_of_pages = async_job_client.number_of_pages

    return result
  end

  raise ApiException.new('Asynchronous call did not finish in expected timeframe.'),
        'Asynchronous call did not finish in expected timeframe.'
end