scraper.rb

require 'nokogiri'
require 'open-uri'
require 'pry' # gem install pry (for debugging)
# gem 'httplog'

# - cast:
#     - "Tim Robbins"
#     - "Morgan Freeman"
#     - "Bob Gunton"
#     # Only the first 3 first actress/actors
#   director: "Frank Darabont"
#   storyline: |
#     Chronicles the experiences of a formerly successful banker as a prisoner in the gloomy jailhouse of Shawshank after being found guilty of a crime he did not commit. The film portrays the man's unique way of dealing with his new, torturous life; along the way he befriends a number of fellow prisoners, most notably a wise long-term inmate named Red.
#   title: "The Shawshank Redemption"
#   year: 1994

TOP_IMDB_URL = "https://www.imdb.com/chart/top"

# => Array of Hashes
def top_n_imdb(n)
  return {} if n.zero?

  # Trick
  title = link = year = director = storyline = actors = nil
  results = []

  top_imdb_source = URI.open(
    TOP_IMDB_URL,
    "Accept-Language" => "en",
    "User-Agent" => "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.16; rv:84.0) Gecko/20100101 Firefox/84.0"
  ).read

  parsed = Nokogiri::HTML(top_imdb_source)
  parsed.search(".titleColumn").first(n).each do |node|
    title = node.css("a").text
    link = node.css("a").first["href"]
    year = node.css("span.secondaryInfo").text.delete(")").delete("(").to_i

    movie_page = URI.open(
      "https://www.imdb.com/" + link,
      "Accept-Language" => "en",
      "User-Agent" => "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.16; rv:84.0) Gecko/20100101 Firefox/84.0"
    ).read
    parsed_movie = Nokogiri::HTML(movie_page)

    director = parsed_movie.search(".credit_summary_item").css("a").first.text
    storyline = parsed_movie.search(".summary_text").text.strip
    actors = [
      parsed_movie.search(".cast_list .odd").first.text.strip.split("\n").first,
      parsed_movie.search(".cast_list .even").first.text.strip.split("\n").first,
      parsed_movie.search(".cast_list .odd")[1].text.strip.split("\n").first
    ]

    results << {
      director: director,
      storyline: storyline,
      title: title,
      year: year,
      actors: actors
    }
  end

  return results
end

results = top_n_imdb(20)
File.write("storage.yml", YAML.dump(results))

scraper_spec.rb

require "rspec"
require_relative "../scraper.rb"

describe "#top_n_imdb" do
  it "should empty hash if called with 0" do
    actual = top_n_imdb(0)
    expected = {}
    expect(actual).to eq(expected)
  end

  xit "should process saved HTML" do
    # TODO: Implement with mock API request if you want to have
    # LOTS OF FUN
  end
end