Module: Crawler::Movie::Providers::Imdb

Defined in:
lib/crawler/movie/providers/imdb.rb,
lib/crawler/movie/providers/imdb/version.rb

Constant Summary collapse

VERSION = 
'1.0.0'

Class Method Summary collapse

Class Method Details

.find(id) ⇒ Object 



13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
 
# File 'lib/crawler/movie/providers/imdb.rb', line 13

def self.find(id)
  response = Faraday.get("https://www.imdb.com/title/#{id}/")

  return if !response.success? || response.body.blank?

  html = Nokogiri::HTML(response.body)
  widget = html.css('#title-overview-widget')
  title = widget.css('.title_wrapper h1 > text()').text.tr("\u00A0", '').strip
  original_title = widget.css('.title_wrapper .originalTitle > text()').text.presence
  genres = (html.css('#titleStoryLine .see-more:contains("Genres:") a') || []).map { |genre| genre.text.strip }
  poster = widget.css('.poster img')
  poster_url = poster.presence && "#{poster.attr('src').value.split('@').first}@._V1_.jpg"
  overview = widget.css('.summary_text').text.sub(/See full (synopsis|summary) »/, '').strip
  overview = nil if overview == 'Add a Plot »'
  release_date_matches = html.css('#titleDetails .txt-block:contains("Release Date:") > text()').text.match(/(?<release_date>\d{1,2} \w+ \d{4})/)
  release_date = release_date_matches && Date.parse(release_date_matches[:release_date])
  original_languages = (html.css('#titleDetails .txt-block:contains("Language:") a') || []).each_with_object([]) do |lang, acc|
    begin
      uri = URI(lang.attr('href'))
      params = URI.decode_www_form(uri.query).to_h
      accc << params['primary_language']
    rescue StandardError
      # Ignored
    end
  end

  {
    id: id,
    source: 'internet-movie-database',
    title: title,
    poster_url: poster_url,
    backdrop_url: nil,
    original_languages: original_languages,
    original_titles: original_title,
    genres: genres,
    overview: overview,
    release_date: release_date
  }
end

.search(query) ⇒ Object 



53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
 
# File 'lib/crawler/movie/providers/imdb.rb', line 53

def self.search(query)
  movies = []
  current_start = 1

  loop do
    response = Faraday.get('https://www.imdb.com/search/title/',
      title: query,
      title_type: 'feature,short',
      count: 50,
      start: current_start
    )

    break if !response.success? || !response.body

    html = Nokogiri::HTML(response.body)
    results = html.css('.lister .lister-item').map do |movie|
      item_content = movie.css('.lister-item-content')
      title = item_content.css('.lister-item-header a').text
      genres = item_content.css('.genre').text.strip.split(', ')
      overview = item_content.css('.text-muted')[2].text.sub(/See full (synopsis|summary) »/, '').strip
      overview = nil if overview == 'Add a Plot'
      year_matches = item_content.css('.lister-item-year').text.match(/\((?<year>\d+)\)/)
      release_date = year_matches && Date.parse("#{year_matches[:year]}-1-1")
      item_image = movie.css('.lister-item-image img')
      id = item_image.attr('data-tconst').value
      poster_url = item_image.attr('loadlate').value.split('@').first
      poster_url = nil if poster_url.match?(%r{/nopicture/})
      poster_url += '@._V1_.jpg' if poster_url
      details = find(id)

      next details if details

      {
        id: id,
        source: 'internet-movie-database',
        title: title,
        poster_url: poster_url,
        backdrop_url: nil,
        original_language: nil,
        original_title: nil,
        genres: genres,
        overview: overview,
        release_date: release_date
      }
    end

    movies.concat(results)
    next_page = html.css('.lister-page-next').first

    break unless next_page

    current_start += results.length
  end

  movies
end