summaryrefslogtreecommitdiff
path: root/data/rbot/plugins/imdb.rb
blob: 5615ac00c4dd7e4cb07fc1a8b807738a8501d77d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
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
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
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
#-- vim:sw=2:et
#++
#
# :title: IMDB plugin for rbot
#
# Author:: Arnaud Cornet <arnaud.cornet@gmail.com>
# Copyright:: (C) 2005 Arnaud Cornet
# License:: MIT license
#
# Notes by Giuseppe Bilotta:
# TODO return more than one match (configurable)

require 'uri/common'

class Imdb
  def initialize(bot)
    @bot = bot
  end

  def search(rawstr)
    str = URI.escape(rawstr) << ";site=aka"
    return do_search(str)
  end

  def do_search(str)
    resp = nil
    begin
      resp = @bot.httputil.get_response("http://us.imdb.com/find?q=#{str}",
                                        :max_redir => -1)
    rescue Exception => e
      error e.message
      warning e.backtrace.join("\n")
      return nil
    end

    if resp.code == "200"
      m = /<a href="(\/(?:title|name)\/(?:tt|nm)[0-9]+\/?)[^"]*"(?:[^>]*)>(?:[^<]*)<\/a>/.match(resp.body)
      if m
        url = m[1]
        return url
      end
    elsif resp.code == "302"
      new_loc = resp['location'].gsub(/http:\/\/us.imdb.com/, "")
      if new_loc.match(/\/find\?q=(.*)/)
        return do_search($1)
      else
        return new_loc.gsub(/\?.*/, "")
      end
    end
    return nil
  end

  def info(rawstr)
    sr = search(rawstr)
    if !sr
      debug "IMDB: search returned NIL"
      return nil
    end
    type = sr.match(/^\/([^\/]+)\//)[1].downcase.intern rescue nil
    case type
    when :title
      return info_title(sr)
    when :name
      return info_name(sr)
    else
      return "#{sr}"
    end
  end

  def grab_info(info, body)
    /<div class="info">\s+<h5>#{info}:<\/h5>\s+(.*?)<\/div>/mi.match(body)[1] rescue nil
  end

  def info_title(sr)
    resp = nil
    begin
      resp = @bot.httputil.get_response('http://us.imdb.com' + sr,
                                        :max_redir => -1)
    rescue Exception => e
      error e.message
      warning e.backtrace.join("\n")
      return nil
    end

    if resp.code == "200"
      m = /<title>([^<]*)<\/title>/.match(resp.body)
      return nil if !m
      title = Utils.decode_html_entities(m[1])

      m = /<b>([0-9.]+)\/10<\/b>\n?\r?\s+<small>\(<a href="ratings">([0-9,]+) votes?<\/a>\)<\/small>/.match(resp.body)
      return nil if !m
      score = m[1]
      votes = m[2]

      plot = nil
      data = grab_info(/Plot (?:Outline|Summary)/, resp.body)
      if data
        plot = "Plot: #{data.ircify_html.gsub(/\s+more$/,'')}"
      end

      genre = Array.new
      resp.body.scan(/<a href="\/Sections\/Genres\/[^\/]+\/">([^<]+)<\/a>/) do |gnr|
        genre << gnr
      end
      info = "#{title} : http://us.imdb.com#{sr}\n"
      info << "Ratings: #{score}/10 (#{votes} voters). Genre: #{genre.join('/')}\n"
      info << plot if plot
      return info
    end
    return nil
  end

  def info_name(sr)
    resp = nil
    begin
      resp = @bot.httputil.get_response('http://us.imdb.com' + sr,
                                        :max_redir => -1)
    rescue Exception => e
      error e.message
      warning e.backtrace.join("\n")
      return nil
    end

    if resp.code == "200"
      m = /<title>([^<]*)<\/title>/.match(resp.body)
      return nil if !m
      name = Utils.decode_html_entities(m[1])

      birth = nil
      data = grab_info("Date of Birth", resp.body)
      if data
        birth = "Birth: #{data.ircify_html.gsub(/\s+more$/,'')}"
      end

      death = nil
      data = grab_info("Date of Death", resp.body)
      if data
        death = "Death: #{data.ircify_html.gsub(/\s+more$/,'')}"
      end

      movies = {}

      filmorate = nil
      begin
        filmorate = @bot.httputil.get("http://us.imdb.com" + sr + "filmorate")
      rescue Exception
      end

      if filmorate
        filmorate.scan(/<div class="filmo">.*?<a href="\/title.*?<\/div>/m) { |str|
          what = str.match(/<a name="[^"]+">([^<]+)<\/a>/)[1] rescue nil
          # next unless what
          next unless ['Actor', 'Director'].include?(what)
          movies[what] = str.scan(/<a href="\/title\/[^"]+">([^<]+)<\/a>/)[0..2].map { |tit|
            Utils.decode_html_entities(tit)
          }
        }
      end
      debug movies.inspect

      info = "#{name} : http://us.imdb.com#{sr}\n"
      info << [birth, death].compact.join('. ') << "\n"
      unless movies.empty?
        info << "Top Movies:: "
        ar = []
        movies.keys.sort.each { |key|
          ar << key.dup
          ar.last << ": " + movies[key].join(', ')
        }
        info << ar.join('. ')
      end
      return info

    end
    return nil
  end
end

class ImdbPlugin < Plugin
  def help(plugin, topic="")
    "imdb <string> => search http://www.imdb.org for <string>"
  end

  def imdb(m, params)
    what = params[:what].to_s
    i = Imdb.new(@bot)
    info = i.info(what)
    if !info
      m.reply "Nothing found for #{what}"
      return nil
    end
    m.reply info
  end
end

plugin = ImdbPlugin.new
plugin.map "imdb *what"