Class: Imdb

Inherits:
Object
  • Object
show all
Defined in:
lib/imdb/imdb.rb

Constant Summary collapse

IMDB_MOVIE_BASE_URL = 
"http://www.imdb.com/title/"
IMDB_NAME_BASE_URL = 
"http://www.imdb.com/name/"
IMDB_COMPANY_BASE_URL = 
"http://www.imdb.com/company/"
IMDB_GENRE_BASE_URL = 
"http://www.imdb.com/Sections/Genres/"
IMDB_SEARCH_BASE_URL = 
"http://imdb.com/find?s=all&q="

Class Method Summary collapse

Class Method Details

.find_movie_by_id(id, fetch_releaseinfos = false) ⇒ Object

Returns an ImdbMovie.

If fetch_releasesinfos is set alternative titles and the full releases dates will be fetched.



30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
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
 
# File 'lib/imdb/imdb.rb', line 30

def self.find_movie_by_id(id, fetch_releaseinfos = false)
  coder = HTMLEntities.new

  data = Hpricot(open(IMDB_MOVIE_BASE_URL + id))
  
  movie = ImdbMovie.new
  
  movie.imdb_id = id
  movie.title = coder.decode(data.at("meta[@name='title']")['content'].gsub(/\((\d{4}(\/[^)]*)?|[A-Z]+)\)/,'').strip)

  rating_text = (data/"div.rating/div.meta/b").inner_text
  if rating_text =~ /([\d\.]+)\/10/
    movie.rating = $1
  end

  begin
    movie.poster_url = data.at("div.photo/a[@name='poster']/img")['src']
  rescue
    movie.poster_url = nil
  end

  infos = (data/"div.info")
  infos.each do |info|
    info_title = (info/"h5").inner_text
    case info_title
    when /Directors?:/
      movie.directors = parse_names(info)
    when /Writers?[^:]+:/
      movie.writers = parse_names(info)
    when /Company:/
      movie.company = parse_company(info)
    when "Tagline:"
      movie.tagline = coder.decode(parse_info(info).strip)
    when "Runtime:"
      movie.runtime = parse_info(info).strip
      if (movie.runtime)
        movie.runtime.gsub!(/^[^:]+:\s*/, '')
        movie.runtime.gsub!(/min .*/, 'min')
      end
    when "Plot:"
      movie.plot = parse_info(info).strip
      movie.plot = movie.plot.gsub(/\s*\|\s*add synopsis$/, '')
      movie.plot = movie.plot.gsub(/\s*\|\s*full synopsis$/, '')
      movie.plot = movie.plot.gsub(/\s*\|\s*add summary$/, '')
      movie.plot = movie.plot.gsub(/full summary$/, '')
      movie.plot = movie.plot.gsub(/more$/, '')
      movie.plot = coder.decode(movie.plot.strip)
    when "Genre:"
      movie.genres = parse_genres(info)
    when "Release Date:"
      begin
        if (parse_info(info).strip =~ /(\d{1,2}) ([a-zA-Z]+) (\d{4})/)
          movie.release_date = Date.parse("#{$2} #{$1}, #{$3}")
        end
      rescue
        movie.release_date = nil
      end
    when "Certification:"
      begin
        movie.certification = (info/"a").map { |v| v.inner_html }.select { |v| v =~ /^USA:/ && v !~ /Unrated/ }.map { |v| v[/^USA:/]=''; v.strip }.first
      end
    end
  end 

  cast = (data/"table.cast"/"tr")
  cast.each do |cast_member|
      actor_a = (cast_member/"td.nm").inner_html
      actor_a =~ /name\/([^"]+)\//
      actor_id = $1
      actor_name = coder.decode((cast_member/"td.nm"/"a").inner_text)
      actor_role = coder.decode((cast_member/"td.char").inner_text)
      movie.actors = movie.actors << ImdbName.new(actor_id, actor_name, actor_role)
  end    
  self.parse_releaseinfo(id, movie) if fetch_releaseinfos
  movie # return movie

end

.search_movies_by_title(title, use_akas = nil) ⇒ Object

Returns an Array of Hashes of => String of imdb-id, :title => String of the title.

If use_akas is set alternative titles will be included in the search.



12
13
14
15
16
17
18
19
20
21
22
23
24
25
 
# File 'lib/imdb/imdb.rb', line 12

def self.search_movies_by_title(title, use_akas = nil)
  document = Hpricot(open("#{IMDB_SEARCH_BASE_URL}#{CGI::escape(title)};s=tt#{";site=aka" if use_akas}").read)
  # we got search results
  if document.search('title').inner_text == "IMDb Title Search"
    results = document.search('a[@href^="/title/tt"]').reject do |element|
      element.innerHTML.strip_tags.empty?
    end.map do |element|
      {:imdb_id => element['href'][/tt\d+/], :title => element.innerHTML.strip_tags.unescape_html}
    end
    results.uniq
  else
    [{:imdb_id => document.search('link[@href^="http://www.imdb.com/title/tt"]').first['href'].match(/tt\d+/).to_s, :title => document.search('meta[@name="title"]').first["content"].gsub(/\(\d\d\d\d\)$/, '').strip}]
  end
end