[Get web page source] Get the contents of a web page using Ruby's built-in open-uri library

get_web_page.rb

require 'open-uri'

url = 'https://www.google.com/'
file = URI.open(url)
contents = file.read
puts contents

get_web_page.strip_html.rb

require 'open-uri'
require 'htmlentities'

# get page source
url = 'https://www.google.com/'
source = open(url) { |f| f.read }.encode!('UTF-8', 'UTF-8', invalid: :replace)

# replace HTML entities
coder = HTMLEntities.new
source = coder.decode(source)

# split into array
source = source.split("\n").collect{ |line| line.strip.chomp }