summaryrefslogtreecommitdiff
path: root/data/rbot/plugins/imdb.rb
blob: a70b2b3b626d3bf798edcd761ca55d538eb311ac (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
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
#-- vim:sw=2:et
#++
#
# :title: IMDB plugin for rbot
#
# Author:: Arnaud Cornet <arnaud.cornet@gmail.com>
# Author:: Giuseppe "Oblomov" Bilotta <giuseppe.bilotta@gmail.com>
#
# Copyright:: (C) 2005 Arnaud Cornet
# Copyright:: (C) 2007 Giuseppe Bilotta
#
# License:: MIT license

class Imdb
  IMDB = "http://us.imdb.com"
  TITLE_OR_NAME_MATCH = /<a href="(\/(?:title|name)\/(?:tt|nm)[0-9]+\/?)[^"]*"(?:[^>]*)>([^<]*)<\/a>/
  TITLE_MATCH = /<a href="(\/title\/tt[0-9]+\/?)[^"]*"(?:[^>]*)>([^<]*)<\/a>/
  NAME_MATCH = /<a href="(\/name\/nm[0-9]+\/?)[^"]*"(?:[^>]*)>([^<]*)<\/a>/
  CREDIT_NAME_MATCH = /#{NAME_MATCH}<\/td><td[^>]+> \.\.\. <\/td><td[^>]+>(.+?)<\/td>/
  FINAL_ARTICLE_MATCH = /, ([A-Z]\S{0,2})$/

  MATCHER = {
    :title => TITLE_MATCH,
    :name => NAME_MATCH,
    :both => TITLE_OR_NAME_MATCH
  }

  def initialize(bot)
    @bot = bot
  end

  def search(rawstr, rawopts={})
    str = CGI.escape(rawstr)
    str << ";site=aka" if @bot.config['imdb.aka']
    opts = rawopts.dup
    opts[:type] = :both unless opts[:type]
    return do_search(str, opts)
  end

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


    matcher = MATCHER[opts[:type]]

    if resp.code == "200"
      m = []
      m << matcher.match(resp.body) if @bot.config['imdb.popular']
      if resp.body.match(/\(Exact Matches\)<\/b>/) and @bot.config['imdb.exact']
        m << matcher.match($')
      end
      m.compact!
      unless m.empty?
        return m.map { |mm|
          mm[1]
        }.uniq
      end
    elsif resp.code == "302"
      debug "automatic redirection"
      new_loc = resp['location'].gsub(IMDB, "")
      if new_loc.match(/\/find\?q=(.*)/)
        return do_search($1, opts)
      else
        return [new_loc.gsub(/\?.*/, "")]
      end
    end
    return nil
  end

  def info(rawstr, opts={})
    debug opts.inspect
    urls = search(rawstr, opts)
    debug urls
    if urls.nil_or_empty?
      debug "IMDB: search returned NIL"
      return nil
    end
    results = []
    urls.each { |sr|
      type = sr.match(/^\/([^\/]+)\//)[1].downcase.intern rescue nil
      case type
      when :title
        results << info_title(sr, opts)
      when :name
        results << info_name(sr, opts)
      else
        results << "#{sr}"
      end
    }
    return results
  end

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

  def fix_article(org_tit)
    title = org_tit.dup
    debug title.inspect
    if title.match(/^"(.*)"$/)
      return "\"#{fix_article($1)}\""
    end
    if @bot.config['imdb.fix_article'] and title.gsub!(FINAL_ARTICLE_MATCH, '')
      art = $1.dup
      debug art.inspect
      if art[-1,1].match(/[A-Za-z]/)
        art << " "
      end
      return art + title
    end
    return title
  end

  def info_title(sr, opts={})
    resp = nil
    begin
      resp = @bot.httputil.get_response(IMDB + sr, :max_redir => -1)
    rescue Exception => e
      error e.message
      warning e.backtrace.join("\n")
      return nil
    end

    info = []

    if resp.code == "200"
      m = /<title>([^<]*)<\/title>/.match(resp.body)
      return nil if !m
      title_date = m[1]
      pre_title, date, extra = title_date.scan(/^(.*)\((\d\d\d\d(?:\/[IV]+)?)\)\s*(.+)?$/).first
      pre_title.strip!
      title = fix_article(pre_title.ircify_html)

      dir = nil
      data = grab_info(/Directors?/, resp.body)
      if data
        dir = data.scan(NAME_MATCH).map { |url, name|
          name.ircify_html
        }.join(', ')
      end

      country = nil
      data = grab_info(/Country/, resp.body)
      if data
        country = data.ircify_html.gsub(' / ','/')
      end

      info << [title, "(#{country}, #{date})", extra, dir ? "[#{dir}]" : nil, ": http://us.imdb.com#{sr}"].compact.join(" ")

      return info if opts[:title_only]

      if opts[:characters]
        info << resp.body.scan(CREDIT_NAME_MATCH).map { |url, name, role|
          "%s: %s" % [name, role]
        }.join('; ')
        return info
      end

      ratings = "no votes"
      m = /<b>([0-9.]+)\/10<\/b>\n?\r?\s+<small>\(<a href="ratings">([0-9,]+) votes?<\/a>\)<\/small>/.match(resp.body)
      if m
        ratings = "#{m[1]}/10 (#{m[2]} voters)"
      end

      genre = Array.new
      resp.body.scan(/<a href="\/Sections\/Genres\/[^\/]+\/">([^<]+)<\/a>/) do |gnr|
        genre << gnr
      end

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

      info << ["Ratings: " << ratings, "Genre: " << genre.join('/') , plot].compact.join(". ")

      return info
    end
    return nil
  end

  def info_name(sr, opts={})
    resp = nil
    begin
      resp = @bot.httputil.get_response(IMDB + sr, :max_redir => -1)
    rescue Exception => e
      error e.message
      warning e.backtrace.join("\n")
      return nil
    end

    info = []

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

      info << "#{name} : http://us.imdb.com#{sr}"

      return info if opts[:name_only]

      if opts[:movies_by_year]
        filmoyear = @bot.httputil.get(IMDB + sr + "filmoyear")
        if filmoyear
          info << filmoyear.scan(/#{TITLE_MATCH} \((\d\d\d\d)\)[^\[\n]*((?:\s+\[[^\]]+\](?:\s+\([^\[<]+\))*)+)\s+</)
        end
        return info
      end

      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

      info << [birth, death].compact.join('. ') if birth or death

      movies = {}

      filmorate = nil
      begin
        filmorate = @bot.httputil.get(IMDB + 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
          movies[what] = str.scan(TITLE_MATCH)[0..2].map { |url, tit|
            fix_article(tit.ircify_html)
          }
        }
      end

      preferred = ['Actor', 'Director']
      if resp.body.match(/Jump to filmography as:&nbsp;(.*?)<\/div>/)
        txt = $1
        preferred = txt.scan(/<a[^>]+>([^<]+)<\/a>/)[0..2].map { |pref|
          pref.first
        }
      end

      unless movies.empty?
        all_keys = movies.keys.sort
        debug all_keys.inspect
        keys = []
        preferred.each { |key|
          keys << key if all_keys.include? key
        }
        keys = all_keys if keys.empty?
        ar = []
        keys.each { |key|
          ar << key.dup
          ar.last << ": " + movies[key].join('; ')
        }
        info << ar.join('. ')
      end
      return info

    end
    return nil
  end

  def year_movies(urls, years_txt_org, role_req)
    years_txt = years_txt_org.dup
    years_txt.sub!(/^'/,'')
    years_txt = "9#{years_txt}" if years_txt.match(/^\d\ds?$/)
    years_txt = "1#{years_txt}" if years_txt.match(/^\d\d\ds?$/)

    years = []
    case years_txt
    when /^\d\d\d\d$/
      years << years_txt
    when /^(\d\d\d\d)s$/
      base = $1.to_i
      base.upto(base+9) { |year|
        years << year.to_s
      }
    end

    urls.map { |url|
      info = info_name(url, :movies_by_year => true)

      debug info.inspect

      name_url = info.first
      data = info[1]

      movies = []
      # Sort by pre-title putting movies before TV series
      data.sort { |a, b|
        aclip = a[1][0,5]
        bclip = b[1][0,5]
        quot = '&#34;'
        (aclip == quot ? 1 : -1) <=> (bclip == quot ? 1 : -1)
      }.each { |url, pre_title, year, pre_roles|
        next unless years.include?(year)
        title = fix_article(pre_title.ircify_html)
        if title[0] == ?" and not @bot.config['imdb.tv_series_in_movies']
          next
        end
        title << " (#{year})" unless years.length == 1
        role_array = []
        pre_roles.strip.scan(/\[([^\]]+)\]((?:\s+\([^\[]+\))+)?/) { |txt, comm|
          role = nil
          extra = nil
          if txt.match(/^(.*)\s+\.\.\.\.\s+(.*)$/)
            role = $1
            extra = "(#{$2.ircify_html})"
          else
            role = txt
          end
          next if role_req and not role.match(/^#{role_req}/i)
          if comm
            extra ||= ""
            extra += comm.ircify_html if comm
          end
          role_array << [role, extra]
        }
        next if role_req and role_array.empty?

        roles = role_array.map { |ar|
          if role_req
            ar[1] # works for us both if it's nil and if it's something
          else
            ar.compact.join(" ")
          end
        }.compact.join(', ')
        roles = nil if roles.empty?
        movies << [roles, title].compact.join(": ")
      }

      if movies.empty?
        [name_url, nil]
      else
        [name_url, movies.join(" | ")]
      end
    }
  end

  def name_in_movie(name_urls, movie_urls)
    info = []
    movie_urls.each { |movie|
      title_info = info_title(movie, :title_only => true)
      valid = []

      data = @bot.httputil.get(IMDB + movie + "fullcredits")
      data.scan(CREDIT_NAME_MATCH).each { |url, name, role|
        valid << [url, name.ircify_html, role.ircify_html] if name_urls.include?(url)
      }
      valid.each { |url, name, role|
        info << "%s : %s was %s in %s" % [name, IMDB + url, role, title_info]
      }
    }
    return info
  end


end

class ImdbPlugin < Plugin
  BotConfig.register BotConfigBooleanValue.new('imdb.aka',
    :default => true,
    :desc => "Look for IMDB matches also in translated titles and other 'also known as' information")
  BotConfig.register BotConfigBooleanValue.new('imdb.popular',
    :default => true,
    :desc => "Display info on popular IMDB entries matching the request closely")
  BotConfig.register BotConfigBooleanValue.new('imdb.exact',
    :default => true,
    :desc => "Display info on IMDB entries matching the request exactly")
  BotConfig.register BotConfigBooleanValue.new('imdb.fix_article',
    :default => false,
    :desc => "Try to detect an article placed at the end and move it in front of the title")
  BotConfig.register BotConfigBooleanValue.new('imdb.tv_series_in_movies',
    :default => false,
    :desc => "Whether searching movies by person/year should also return TV series")

  def help(plugin, topic="")
    "imdb <string> => search http://www.imdb.org for <string>: prefix <string> with 'name' or 'title' if you only want to search for people or films respectively, e.g.: imdb name ed wood"
  end

  attr_reader :i

  def initialize
    super
    @i = Imdb.new(@bot)
  end

  # Find a person or movie on IMDB. A :type (name/title, default both) can be
  # specified to limit the search to either.
  #
  def imdb(m, params)
    if params[:movie]
      movie = params[:movie].to_s
      info = i.info(movie, :type => :title, :characters => true)
    else
      what = params[:what].to_s
      type = params[:type].intern
      info = i.info(what, :type => type)
      if !info
        m.reply "nothing found for #{what}"
        return nil
      end
    end
    if info.length == 1
      m.reply Utils.decode_html_entities info.first.join("\n")
    else
      m.reply info.map { |si|
        Utils.decode_html_entities si.join(" | ")
      }.join("\n")
    end
  end

  # Find the movies with a participation of :who in the year :year
  # TODO: allow year to be either a year or a decade ('[in the] 1960s') 
  #
  def movies(m, params)
    who = params[:who].to_s
    years = params[:years]
    role = params[:role]
    if role and role.downcase == 'anything'
      role = nil
    elsif not role
      case params[:prefix].intern
      when :with
        role = /actor|actress/i
      when :by
        role = 'director'
      end
    end

    name_urls = i.search(who, :type => :name)
    unless name_urls
      m.reply "nothing found about #{who}, sorry"
      return
    end

    movie_urls = i.year_movies(name_urls, years, role)
    debug movie_urls.inspect
    debug movie_urls[0][1]

    if movie_urls.length == 1 and movie_urls[0][1]
      m.reply movie_urls.join("\n")
    else
      m.reply movie_urls.map { |si|
        si[1] = "no movies in #{years}" unless si[1]
        Utils.decode_html_entities si.join(" | ")
      }.join("\n")
    end
  end

  # Find the character played by :who in :movie
  #
  def character(m, params)
    who = params[:who].to_s
    movie = params[:movie].to_s

    name_urls = i.search(who, :type => :name)
    unless name_urls
      m.reply "nothing found about #{who}, sorry"
      return
    end

    movie_urls = i.search(movie, :type => :title)
    unless movie_urls
      m.reply "nothing found about #{who}, sorry"
      return
    end

    info = i.name_in_movie(name_urls, movie_urls)
    if info.empty?
      m.reply "nothing found about #{who} in #{movie}, sorry"
    else
      m.reply info.join("\n")
    end
  end

  # Report the characters in movie :movie
  #
  def characters(m, params)
    movie = params[:movie].to_s

    urls = i.search(movie, :type => :title)
    unless urls
      m.reply "nothing found about #{movie}"
    end

  end

end

plugin = ImdbPlugin.new

plugin.map "imdb [:type] *what", :requirements => { :type => /name|title/ }, :defaults => { :type => 'both' }
plugin.map "movies :prefix *who in [the] :years [as :role]", :requirements => { :prefix => /with|by|from/, :years => /'?\d+s?/ }
plugin.map "character [played] by *who in *movie"
plugin.map "character of *who in *movie"
plugin.map "characters in *movie", :action => :imdb