4 # :title: IMDB plugin for rbot
6 # Author:: Arnaud Cornet <arnaud.cornet@gmail.com>
7 # Author:: Giuseppe "Oblomov" Bilotta <giuseppe.bilotta@gmail.com>
9 # Copyright:: (C) 2005 Arnaud Cornet
10 # Copyright:: (C) 2007 Giuseppe Bilotta
12 # License:: MIT license
17 IMDB = "http://us.imdb.com"
18 TITLE_OR_NAME_MATCH = /<a href="(\/(?:title|name)\/(?:tt|nm)[0-9]+\/?)[^"]*"(?:[^>]*)>([^<]*)<\/a>/
19 TITLE_MATCH = /<a href="(\/title\/tt[0-9]+\/?)[^"]*"(?:[^>]*)>([^<]*)<\/a>/
20 NAME_MATCH = /<a href="(\/name\/nm[0-9]+\/?)[^"]*"(?:[^>]*)>([^<]*)<\/a>/
21 FINAL_ARTICLE_MATCH = /, ([A-Z]\S{0,2})$/
24 :title => TITLE_MATCH,
26 :both => TITLE_OR_NAME_MATCH
33 def search(rawstr, rawopts={})
34 str = URI.escape(rawstr)
35 str << ";site=aka" if @bot.config['imdb.aka']
37 opts[:type] = :both unless opts[:type]
38 return do_search(str, opts)
41 def do_search(str, opts={})
44 resp = @bot.httputil.get_response(IMDB + "/find?q=#{str}",
48 warning e.backtrace.join("\n")
53 matcher = MATCHER[opts[:type]]
57 m << matcher.match(resp.body) if @bot.config['imdb.popular']
58 if resp.body.match(/\(Exact Matches\)<\/b>/) and @bot.config['imdb.exact']
59 m << matcher.match($')
67 elsif resp.code == "302"
68 debug "automatic redirection"
69 new_loc = resp['location'].gsub(IMDB, "")
70 if new_loc.match(/\/find\?q=(.*)/)
71 return do_search($1, opts)
73 return [new_loc.gsub(/\?.*/, "")]
79 def info(rawstr, opts={})
81 urls = search(rawstr, opts)
84 debug "IMDB: search returned NIL"
89 type = sr.match(/^\/([^\/]+)\//)[1].downcase.intern rescue nil
92 results << info_title(sr)
94 results << info_name(sr)
102 def grab_info(info, body)
103 /<div class="info">\s+<h5>#{info}:<\/h5>\s+(.*?)<\/div>/mi.match(body)[1] rescue nil
106 def fix_article(org_tit)
109 if title.match(/^"(.*)"$/)
110 return "\"#{fix_article($1)}\""
112 if @bot.config['imdb.fix_article'] and title.gsub!(FINAL_ARTICLE_MATCH, '')
115 if art[-1,1].match(/[A-Za-z]/)
126 resp = @bot.httputil.get_response(IMDB + sr, :max_redir => -1)
127 rescue Exception => e
129 warning e.backtrace.join("\n")
135 if resp.code == "200"
136 m = /<title>([^<]*)<\/title>/.match(resp.body)
139 pre_title, date, extra = title_date.scan(/^(.*)\((\d\d\d\d(?:\/[IV]+)?)\)\s*(.+)?$/).first
141 title = fix_article(pre_title.ircify_html)
144 data = grab_info(/Directors?/, resp.body)
146 dir = data.scan(NAME_MATCH).map { |url, name|
152 data = grab_info(/Country/, resp.body)
154 country = data.ircify_html.gsub(' / ','/')
157 info << [title, "(#{country}, #{date})", extra, dir ? "[#{dir}]" : nil, ": http://us.imdb.com#{sr}"].compact.join(" ")
160 m = /<b>([0-9.]+)\/10<\/b>\n?\r?\s+<small>\(<a href="ratings">([0-9,]+) votes?<\/a>\)<\/small>/.match(resp.body)
162 ratings = "#{m[1]}/10 (#{m[2]} voters)"
166 resp.body.scan(/<a href="\/Sections\/Genres\/[^\/]+\/">([^<]+)<\/a>/) do |gnr|
171 data = grab_info(/Plot (?:Outline|Summary)/, resp.body)
173 plot = "Plot: " + data.ircify_html.gsub(/\s+more$/,'')
176 info << ["Ratings: " << ratings, "Genre: " << genre.join('/') , plot].compact.join(". ")
183 def info_name(sr, opts={})
186 resp = @bot.httputil.get_response(IMDB + sr, :max_redir => -1)
187 rescue Exception => e
189 warning e.backtrace.join("\n")
195 if resp.code == "200"
196 m = /<title>([^<]*)<\/title>/.match(resp.body)
200 info << "#{name} : http://us.imdb.com#{sr}"
202 if year = opts[:movies_in_year]
203 filmoyear = @bot.httputil.get(IMDB + sr + "filmoyear")
205 info << filmoyear.scan(/#{TITLE_MATCH} \(#{year}\)[^\[\n]*\[(.*)\]([^<]+)?(?:$|\s*<)/)
211 data = grab_info("Date of Birth", resp.body)
213 birth = "Birth: #{data.ircify_html.gsub(/\s+more$/,'')}"
217 data = grab_info("Date of Death", resp.body)
219 death = "Death: #{data.ircify_html.gsub(/\s+more$/,'')}"
222 info << [birth, death].compact.join('. ') if birth or death
228 filmorate = @bot.httputil.get(IMDB + sr + "filmorate")
233 filmorate.scan(/<div class="filmo">.*?<a href="\/title.*?<\/div>/m) { |str|
234 what = str.match(/<a name="[^"]+">([^<]+)<\/a>/)[1] rescue nil
236 movies[what] = str.scan(TITLE_MATCH)[0..2].map { |url, tit|
237 fix_article(tit.ircify_html)
242 preferred = ['Actor', 'Director']
243 if resp.body.match(/Jump to filmography as: (.*?)<\/div>/)
245 preferred = txt.scan(/<a[^>]+>([^<]+)<\/a>/)[0..2].map { |pref|
251 all_keys = movies.keys.sort
252 debug all_keys.inspect
254 preferred.each { |key|
255 keys << key if all_keys.include? key
257 keys = all_keys if keys.empty?
261 ar.last << ": " + movies[key].join('; ')
263 info << ar.join('. ')
271 def year_movies(urls, year)
273 info = info_name(url, :movies_in_year => year)
277 name_url = info.first
281 # Sort by pre-title putting movies before TV series
282 debug data.map { |a| a[1] }.join("\n")
287 (aclip == quot ? 1 : -1) <=> (bclip == quot ? 1 : -1)
289 debug data.map { |a| a[1] }.join("\n")
290 data.each { |url, pre_title, pre_roles, extra|
291 title = fix_article(pre_title.ircify_html)
292 role_array = pre_roles.split(/\]\s+\[/).map { |txt|
293 if txt.match(/^(.*)\s+\.\.\.\.\s+(.*)$/)
299 role_array.last << " " + extra.ircify_html if extra
301 roles = role_array.join(', ')
302 movies << [roles, title].join(": ")
308 [name_url, movies.join(" | ")]
315 class ImdbPlugin < Plugin
316 BotConfig.register BotConfigBooleanValue.new('imdb.aka',
318 :desc => "Look for IMDB matches also in translated titles and other 'also known as' information")
319 BotConfig.register BotConfigBooleanValue.new('imdb.popular',
321 :desc => "Display info on popular IMDB entries matching the request closely")
322 BotConfig.register BotConfigBooleanValue.new('imdb.exact',
324 :desc => "Display info on IMDB entries matching the request exactly")
325 BotConfig.register BotConfigBooleanValue.new('imdb.fix_article',
327 :desc => "Try to detect an article placed at the end and move it in front of the title")
329 def help(plugin, topic="")
330 "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"
341 what = params[:what].to_s
342 type = params[:type].intern
343 info = i.info(what, :type => type)
345 m.reply "Nothing found for #{what}"
349 m.reply Utils.decode_html_entities info.first.join("\n")
351 m.reply info.map { |si|
352 Utils.decode_html_entities si.join(" | ")
357 def movies(m, params)
358 who = params[:who].to_s
361 name_urls = i.search(who, :type => :name)
363 m.reply "nothing found about #{who}, sorry"
367 movie_urls = i.year_movies(name_urls, year)
368 debug movie_urls.inspect
369 debug movie_urls[0][1]
371 if movie_urls.length == 1 and movie_urls[0][1]
372 m.reply movie_urls.join("\n")
374 m.reply movie_urls.map { |si|
375 si[1] = "no movies in #{year}" unless si[1]
376 Utils.decode_html_entities si.join(" | ")
383 plugin = ImdbPlugin.new
384 plugin.map "movies :prefix *who in :year", :requirements => { :prefix => /with|by|from/, :year => /\d+/ }
385 plugin.map "imdb [:type] *what", :requirements => { :type => /name|title/ }, :defaults => { :type => 'both' }