Generated on Sat Jul 07 22:37:29 -0400 2007 with rcov 0.8.0
Code reported as executed by Ruby looks like this... and this: this line is also marked as covered. Lines considered as run by rcov, but not reported by Ruby, look like this, and this: these lines were inferred by rcov (using simple heuristics). Finally, here's a line marked as not executed.
| Name | Total lines | Lines of code | Total coverage | Code coverage | ||||||||
| IMDB.rb | 505 | 306 |
|
|
1 #This class takes a name of a movie and gets data from imdb 2 # Author:: Stephen Becker IV (mailto:sbecker@x.y@gmail ) 3 # Copyright:: Copyright 4 # License:: Distributes under the same terms as Ruby 5 # version:: High Plains Drifter (0.5) 6 ### IMDB class 7 ##thank you why for hpricot! 8 ## thank you for the text()! 9 require 'rubygems' 10 #needs version >= 0.5.00 of hpricot 11 #works with version 6.0 ruby 12 require 'hpricot' 13 require 'open-uri' 14 require 'uri' 15 require 'pp' 16 require "rexml/document" 17 18 #read about my suggestion @ http://code.whytheluckystiff.net/hpricot/ticket/37 19 #this will just run next node X times 20 #node_at just did not float my boat. 21 module Hpricot 22 module Traverse 23 # Returns the node neighboring this node to the south: just below it. 24 # This method includes text nodes and comments and such. 25 def next_node(loop=1) 26 sib = parent.children 27 sib[sib.index(self) + loop] if parent 28 end 29 end 30 end 31 32 class IMDB 33 class << self 34 #returns a hash of the differnt titles and what they are 35 # {"Titles (Exact Matches)"=>["Office Space"], 36 #"Titles (Partial Matches)"=>["'Office Space': Out of the Office"], 37 #"Popular Titles"=>["Office Space"], 38 #"Titles (Approx Matches)"=>["Spice Girls: One Hour of Girl Power"]} 39 def title_search(title) 40 movie_name = title 41 movie_name.downcase! 42 #_ is used in the folder names 43 movie_name.gsub!("_","+") 44 movie_name.gsub!(" ","+") 45 #first search 46 #create a hpricot object 47 doc = Hpricot(open(URI.encode("http://www.imdb.com/find?s=all&q=#{movie_name}"))) 48 z = [] 49 doc.search("p").each{|x| z.push(x) if !x.search("table").nil? && !x.search("b").first.nil? && x.search("b").first.inner_html.to_s.downcase.include?("title") } 50 p = {} 51 z.each{|x| p.merge!({x.search("b").first.inner_html => x.search("a").collect{|z| z.inner_html}.delete_if{|u| u.include?("<img")}.uniq})} 52 return p 53 end 54 55 end 56 57 #We save some things for a single load of the page 58 #other things do not need to be saved and i will try 59 #benchmarking the diffrence one day 60 def initialize(movie="",interactive_load=false) 61 @imdb_link = nil 62 #max guessing links 63 @MAXCOUNT = 15 64 @html_info_tags = nil 65 #does command line menu if true 66 @interactive_load = interactive_load 67 #not title 68 @movie_name = movie 69 #html section of imdb that includes the poster year title director 70 @short_details = nil 71 #html of the whole page. only get this once 72 @page_html = nil 73 #viewing time 74 @movie_length = nil 75 #plot 76 @movie_plot = nil 77 #cast_html that will be replaced with a better representation 78 @cast_html = nil 79 @movie_title = nil 80 @movie_year = nil 81 end 82 83 ##Complete html of page 84 def page_html 85 load_page.to_html 86 end 87 alias_method :to_html,:page_html 88 alias_method :html,:page_html 89 90 # the link to the poster 91 def poster_link 92 doc=load_page 93 #just following the xpath 94 return (doc/"//a[@name='poster']/img").first["src"] 95 end 96 97 #the link 98 def imdb_link 99 @imdb_link 100 end 101 102 103 def to_xml 104 data = REXML::Document.new("<?xml version='1.0' encoding='ISO-8859-1'?>") 105 base = data.add_element("movie") 106 base.attributes["name"]=self.title 107 base.attributes["api_version"]="0.2" 108 a=base.add_element("cast") 109 actors.each{|key,value| 110 b=a.add_element("actor") 111 b.add_element("name").text=key 112 b.add_element("role").text=value 113 } 114 base.add_element("run_time").text=runtime 115 base.add_element("plot").text=plot 116 base.add_element("director").text=directors.join(",") 117 base.add_element("writer").text=writers.join(",") 118 #dont think the link plays nice with xml, need to use 119 #base.add_element("poster link").text=poster 120 #CGI::escapeHTML(string) or ERB::Util.html_escape 121 base.add_element("link").text=imdb_link 122 base.add_element("title").text=title 123 base.add_element("date").text=date.to_s 124 base.add_element("rating").text=mpaa 125 base.add_element("user_comments").text=user_comments 126 base.add_element("tag_line").text=tagline 127 base.add_element("plot").text=plot 128 #base.add_element("keywords").text=unescapeHTML(keywords.join(",")) 129 g=base.add_element("genres") 130 genres.each{|value| 131 g.add_element("type").text=value 132 } 133 result = "" 134 data.write(result) 135 return result 136 end 137 138 #returns an array of the possable titles for a search. 139 #if its not in the list try a differnt name 140 def title_search 141 return IMDB.title_search(@movie_name) 142 end 143 ###############olds 144 145 146 def tagline 147 #"Work Sucks." 148 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="tagline"} 149 return z.first.search("h5").first.next_node.to_s.strip unless z.first.nil? 150 "" 151 end 152 153 #returns an array of genres 154 def genre 155 #["Comedy", "Crime"] 156 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="genre"} 157 return z.first.search("a").select{|z| !z.classes.include?("inline")}.collect{|b| b.inner_html} unless z.first.nil? 158 [] 159 end 160 alias_method :genres,:genre 161 162 #returns a date object with the release date 163 def release_date 164 #19 February 1999 (USA) 165 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="release_date"} 166 return Date.new if z.first.nil? 167 date2 = z.first.search("h5").first.next_node.to_s.strip.split 168 day = date2[0] 169 month = Date::MONTHNAMES.index(date2[2]) 170 year = date2[3] 171 x=Date.parse(date2[0...3].join(" "),"%d %B %Y") 172 x 173 end 174 alias_method :date,:release_date 175 176 #returns an array of writers 177 def writer 178 #["Mike Judge"] 179 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="writers"} 180 return z.first.search("a").select{|z| !z.inner_html.include?('(WGA)') && !z.classes.include?("tn15more")}.collect{|b| b.inner_html.to_s.strip}.uniq unless z.first.nil? 181 [] 182 end 183 alias_method :writers,:writer 184 185 #returns an array of directors 186 def director 187 #["Mike Judge"] 188 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="director"} 189 return z.first.search("a").select{|z| !z.classes.include?("tn15more")}.collect{|b| b.inner_html.to_s.strip}.uniq unless z.first.nil? 190 [] 191 end 192 alias_method :directors,:director 193 194 #a string with what hollywood calls plot these days 195 def plot 196 #Comedic tale of company workers who hate their jobs and decide to rebel against their greedy boss. 197 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="plot_outline"} 198 return z.first.search("h5").first.next_node.to_s.strip unless z.first.nil? 199 "" 200 end 201 alias_method :plot_outline,:plot 202 203 #not sure about supporting this yet 204 #["This plot synopsis is empty. Add a synopsis"] 205 #@html_info_tags.select{|x| text_clean(x.search("h5").text())=="plot_synopsis"}.first.search("a").select{|z| !z.classes.include?("inline")}.collect{|b| b.inner_html} 206 207 #an array of key words? 208 #["Hypnosis", "Cult Comedy", "Kung Fu", "Post It", "Arson"] 209 def plot_keywords 210 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="plot_keywords"} 211 return z.first.search("a").select{|z| !z.classes.include?("inline")}.collect{|b| unescapeHTML(b.inner_html)} unless z.first.nil? 212 [] 213 end 214 alias_method :keywords,:plot_keywords 215 216 #string i hope. 217 #2 nominations 218 def awards 219 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="awards"} 220 return z.first.search("h5").first.next_node.to_s.strip unless z.first.nil? 221 "" 222 end 223 224 #some say its cheating... @html_info_tags.select{|x| text_clean(x.search("h5").text())=="[[%s]]"}.first.search("h5").first.next_node.to_s.strip# 225 #string of some user comments 226 def user_comments 227 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="user_comments"} 228 return z.first.search("h5").first.next_node.to_s.strip unless z.first.nil? 229 "" 230 end 231 232 #title else where in the world 233 def also_known_as 234 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="also_known_as"} 235 return z.first.search("h5").first.next_node.to_s.strip unless z.first.nil? 236 "" 237 end 238 239 alias_method :aka,:also_known_as 240 241 #string of the rating and why 242 def mpaa 243 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="mpaa"} 244 return z.first.search("h5").first.next_node.to_s.strip unless z.first.nil? 245 "" 246 end 247 alias_method :ratings,:mpaa 248 alias_method :rating,:mpaa 249 250 #string # min (hopefully is the format) 251 def runtime 252 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="runtime"} 253 return z.first.search("h5").first.next_node.to_s.strip unless z.first.nil? 254 "" 255 end 256 257 #country as a string. most likely abbrv 258 def country 259 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="country"} 260 return z.first.search("h5").first.next_node(2).inner_html unless z.first.nil? 261 "" 262 end 263 264 #orgrinal lang 265 def language 266 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="language"} 267 return z.first.search("h5").first.next_node(2).inner_html unless z.first.nil? 268 "" 269 end 270 #was it shot in color? 271 def color 272 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="color"} 273 return z.first.search("h5").first.next_node(2).inner_html unless z.first.nil? 274 "" 275 end 276 277 #string 278 def aspect_ratio 279 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="aspect_ratio"} 280 return z.first.search("h5").first.next_node.to_s.strip unless z.first.nil? 281 "" 282 end 283 alias_method :aspect,:aspect_ratio 284 285 #string 286 def company 287 z = page_info_tags.select{|x| text_clean(x.search("h5").text())=="company"} 288 return z.first.search("h5").first.next_node(2).inner_html unless z.first.nil? 289 "" 290 end 291 292 #ratings around the world. its a hash! 293 def certification 294 cert_hash = {} 295 begin 296 #{"UK"=>"15", "Ireland"=>"15", "Chile"=>"TE", "Australia"=>"M", "Argentina"=>"Atp", "Iceland"=>"L", "Sweden"=>"Btl", "Portugal"=>"M/12", "Spain"=>"T", "USA"=>"R", "Finland"=>"S", "France"=>"U", "Peru"=>"PT", "Canada"=>"AA", "Norway"=>"7", "Germany"=>"12", "Netherlands"=>"AL"} 297 page_info_tags.select{|x| text_clean(x.search("h5").text())=="certification"}.first.search("a").select{|z| !z.classes.include?("inline")}.each{|b| xx = b.inner_html.split(':') 298 cert_hash.merge!({xx[0]=>xx[1]}) 299 } 300 rescue Exception => e 301 end 302 cert_hash 303 end 304 alias_method :certs,:certification 305 alias_method :certifications,:certification 306 307 #just the title incase it is differnt then the one you had used 308 def title 309 doc = load_page 310 title = doc.search("h1").first.inner_html 311 clean_html_tags(title) 312 clean_9_0(title) 313 title 314 end 315 316 def actors 317 doc = load_page 318 p = {} 319 begin 320 doc.search("table[@class='cast']").first.search("tr").each{|x| p.merge!({x.search("td[@class='nm']/a").inner_html => x.search("td[@class='char']").inner_html})} 321 rescue Exception =>e 322 end 323 p 324 end 325 alias_method :cast,:actors 326 327 private 328 329 330 #needs better xpath 331 #gets the upper level to find the poster html. should be broken out in xpaths 332 def details_based_on_poster_attribute 333 doc = load_page 334 data = [] 335 doc.search("table").each{|rate| (rate/"a").each{|link| data.push(rate) if link.attributes['name']=="poster" }} 336 return data 337 end 338 #so i dont have to run the info tag search alot 339 def page_info_tags 340 return @html_info_tags if @html_info_tags 341 doc = load_page 342 @html_info_tags = doc.search("div[@class='info']") 343 end 344 345 #loads the page data once and stores it in @page_html 346 def load_page 347 #check if we have page html if so return 348 if @page_html 349 350 doc = Hpricot(@page_html) 351 352 else 353 #alter the passed in name to fit the imdb search 354 movie_name = @movie_name 355 movie_name.downcase! 356 #_ is used in the folder names 357 movie_name.gsub!("_","+") 358 movie_name.gsub!(" ","+") 359 #first search 360 #create a hpricot object 361 #for testing... 362 #File.open("/home/sbecker/moo.html","r") { |f| @page_html=f.read } 363 #@imdb_link="adff" 364 #doc=Hpricot(@page_html) 365 366 doc = Hpricot(open(URI.encode("http://www.imdb.com/find?s=all&q=#{movie_name}"))) 367 #find all links 368 elements = doc.search("a") 369 arr = [] 370 #if the inner html of the link is the same as the movie name add it to the 371 #list. 372 elements.each{|link| arr.push(link.attributes['href']) if link.attributes['href'] && link.attributes['href'].include?("title")} 373 if doc.search("h1").first.nil? 374 #use the first link with the same name as what we search for create a 375 #menu system if more or create more then one entry? 376 if !@interactive_load 377 @imdb_link = "http://www.imdb.com#{arr.first}" 378 else 379 @imdb_link = "http://www.imdb.com"+movie_menu(elements) 380 end 381 doc=Hpricot(open(@imdb_link)) 382 @page_html = doc.to_html 383 @html_info_tags = doc.search("div[@class='info']") 384 #some movies do not take you to a search page example is robin hood men 385 #in tights i guess sometimes there is no need for a search page 386 elsif (doc/"/html/head/title").inner_html!="IMDb Search" 387 @imdb_link = "http://www.imdb.com/find?s=all&q=#{movie_name}" 388 @page_html = doc.to_html 389 @html_info_tags = doc.search("div[@class='info']") 390 else 391 #all searches have failed 392 raise "Error: No Inner HTML links found!" 393 end 394 end 395 return doc 396 end 397 398 399 #@html_info_tags = doc.search("div[@class='info']") 400 def movie_menu(elements) 401 count = 0 402 array = [] 403 puts "Pick a number to load" 404 elements.each{|link| 405 if link.attributes['href'] && link.attributes['href'].include?('/title/') && count<@MAXCOUNT 406 puts count.to_s+")"+unescapeHTML(link.inner_html)+" "+link.next_node.to_s 407 array.push(link.attributes['href']) 408 count = count+1 409 end 410 } 411 number = gets 412 return array[number.to_i%array.size] 413 end 414 415 #needed to clean a few things 416 def text_clean(text) 417 cleaned = text 418 cleaned.downcase! 419 clean_html_tags(cleaned) 420 clean_9_0(cleaned) 421 cleaned.gsub!(/[^a-z\s]*/,'') 422 cleaned.strip! 423 cleaned.gsub!(/ /,'_') 424 cleaned 425 end 426 def clean_html_tags(cleaned) 427 cleaned.gsub!(/<[^<]*>/,'') 428 end 429 def clean_9_0(cleaned) 430 cleaned.gsub!(/\([^\(]*\)/,'') 431 end 432 #Jacked from http://www.rubycentral.com/book/tut_stdtypes.html 433 def unescapeHTML(string) 434 str = string.dup 435 str.gsub!(/&(.*?);/n) { 436 match = $1.dup 437 case match 438 when /\Aamp\z/ni then '&' 439 when /\Aquot\z/ni then '"' 440 when /\Agt\z/ni then '>' 441 when /\Alt\z/ni then '<' 442 when /\A#(\d+)\z/n then Integer($1).chr 443 when /\A#x([0-9a-f]+)\z/ni then $1.hex.chr 444 end 445 } 446 str 447 end 448 449 end 450 #begin 451 # ["scotland pa","MaLlRaTs","Doctor+Zhivago","blue_velvet","die hard","die hard 2","ghost in the shell","pi","office_space","11:14","high plains drifter"].each{|movie| 452 # puts movie 453 # movie=IMDB.new(movie)# or office_space or OFFICE_SPACE 454 # #pp movie.get_links 455 # pp movie.actors 456 # pp movie.title 457 # pp movie.poster_link 458 # pp movie.rating 459 # pp movie.aka 460 # pp movie.also_known_as 461 # pp movie.aspect 462 # pp movie.aspect_ratio 463 # pp movie.awards 464 # pp movie.certification 465 # pp movie.certifications 466 # pp movie.certs 467 # pp movie.color 468 # pp movie.company 469 # pp movie.country 470 # pp movie.date 471 # pp movie.director 472 # pp movie.directors 473 # pp movie.genre 474 # pp movie.genres 475 # pp movie.imdb_link 476 # pp movie.keywords 477 # pp movie.language 478 # pp movie.mpaa 479 # pp movie.page_html 480 # pp movie.plot 481 # pp movie.plot_keywords 482 # pp movie.plot_outline 483 # pp movie.poster_link 484 # pp movie.rating 485 # pp movie.ratings 486 # pp movie.release_date 487 # pp movie.runtime 488 # pp movie.tagline 489 # pp movie.user_comments 490 # pp movie.writer 491 # pp movie.writers 492 # pp movie.title_search 493 # pp movie.to_xml 494 # sleep 30 495 # } 496 #rescue Exception=>e 497 # puts "------------"+e 498 # puts e.backtrace*"\n" 499 #end 500 # 501 #begin 502 # pp IMDB.title_search("white strips") 503 #rescue Exception => e 504 # pp e 505 #end
Generated using the rcov code coverage analysis tool for Ruby version 0.8.0.