Ruby: Retrieving and processing files via Selenium and JavaScript

Copyrequire "selenium-webdriver"

selenium_driver = Selenium::WebDriver.for :chrome
selenium_driver.navigate.to('https://example.com')
link_to_pdf = 'https://blobs.example.com/random-pdf'

binary_data_array = selenium_driver.execute_script(<<-JS, link_to_pdf)
  const response = await fetch(arguments[0])

  if (!response.ok) {
    # throwing an error from JS within execute_script raises Selenium::WebDriver::Error::JavascriptError 
    # which you could handle in ruby
    throw new Error(`Unsuccessful request: ${response.status}`) 
  }

  const contentType = response.headers.get('content-type')
  if (!contentType || !contentType.includes('application/pdf')) {
    throw new Error(`Invalid MIME type: ${contentType}`)
  }

  # turn response into binary data 
  const arrayBuffer = await response.arrayBuffer() 
  # convert array buffer to typed array in order to interact with the data
  # now we have the binary data represented as a typed array of 8-bit unsigned integers 
  # => [37, 208, 212, ...]
  const unsingedInt8Array = new Uint8Array(arrayBuffer)
  return unsingedInt8Array 
JS

# convert the array we got from JS into a binary string which we can use to create a file
binary_string = binary_data_array.pack('C*')