download_the_image_files.rb

download_images.rb

#!/usr/bin/env ruby

require 'rubygems'
require 'httparty'
require 'nokogiri'

# Set the URL of the page we want to scrape
url = "https://www.kitronik.co.uk/5632-klip-halo-for-the-bbc-microbit.html"

# Download the webpage
response = HTTParty.get url

# Make the raw HTML response a Nokogiri Document
doc = Nokogiri::HTML response.body

# Get the title 
title = doc.search('title').inner_text

# print out the title
puts title
puts

# Get the description 
description_html = doc.search('#product_tabs_description_tabbed_contents').first.inner_html.strip

# print out the description HTML
# puts description_html


# Get the links
link_nodes =  doc.search('.ig_lightbox2')

# This returns an array of link nodes
# puts link_nodes

# Extract the href elements from the link_nodes...
link_nodes.each do |node|
  puts node.attr('href') # Print out the URL

  # Download the image content and put it into a variable
  image_content = HTTParty.get node.attr('href') 

  # Get the filename
  file_name = node.attr('href').split('/').last
  
  # print the file name
  puts file_name
  
  # Save the file to disk
  File.open("./#{file_name}", 'wb') { |file| file.write(image_content) }
end