livecode scraping

scraper.rb

require 'open-uri'
require 'nokogiri'
require 'pry-byebug'
BASE_URL = "https://www.imdb.com"

def fetch_urls
  url = "https://www.imdb.com/chart/top"

  html_file = open(url).read # string
  html_doc = Nokogiri::HTML(html_file) #Nokogiri::HTML::Document

  urls = []
  movie_list = html_doc.search('.titleColumn a').each do |element|
    suburl_with_query = element['href'] # this is a string
    match_data = suburl_with_query.match(/(.+)(\?.+)/) # matchdata object
    suburl = match_data[1] # this is a string
    urls << BASE_URL + suburl # string contatenation
  end

  urls.take(5)
end

def get_movie_info(url)
  return {} if url.empty?
  html_file = open(url, "Accept-Language" => "en").read
  html_doc = Nokogiri::HTML(html_file)

url
  title_string = html_doc.search('h1').text
  match_data = title_string.match(/(?<title>.+)\((?<year>\d{4}).+[[:space:]]/)
  title = match_data[:title][0..-2]
  year = match_data[:year].to_i

  storyline = html_doc.search('.summary_text').text.strip
  director = html_doc.search('span[itemprop="director"]').text.strip
  actors = html_doc.search('span[itemprop="actors"]') # array like object
  cast = []
  actors.each do |actor|
    cast << actor.text.strip.split(',').first # string
  end

  hash = {
    title: title,
    year: year,
    storyline: storyline,
    director: director,
    cast: cast

  }
  hash
end

# get_movie_info('https://www.imdb.com/title/tt0111161/')

scraper_spec.rb

require_relative '../scraper.rb'

describe '#fetch_urls' do
  it "should return an array of the top 5 urls" do
    actual = fetch_urls
    expected = [
      "https://www.imdb.com/title/tt0111161/",
      "https://www.imdb.com/title/tt0068646/",
      "https://www.imdb.com/title/tt0071562/",
      "https://www.imdb.com/title/tt0468569/",
      "https://www.imdb.com/title/tt0050083/"
    ]
    expect(actual).to eq(expected)
  end
end

describe '#get_movie_info' do
  it "should return and empty hash if passed invalid url" do
    url = ""
    actual = get_movie_info(url)
    expected = {}
    expect(actual).to eq(expected)
  end

  it "should return a hash with the correct movie info" do
    url = 'https://www.imdb.com/title/tt0111161/'
    actual = get_movie_info(url)
    expected = {
      title: "The Shawshank Redemption",
      year: 1994,
      cast: ['Tim Robbins', 'Morgan Freeman', 'Bob Gunton'],
      storyline: 'Two imprisoned men bond over a number of years, finding solace and eventual redemption through acts of common decency.',
      director: 'Frank Darabont'
    }
    expect(actual).to eq(expected)
  end
 end