(.*)<.*?') return in_title.findall(fromInfo) def Year(fromInfo): # Movie's Year fromInfo saved into a list in_year = re.compile('/Sections/Years/([0-9]*)') return in_year.findall(fromInfo) def Directors(fromInfo): # Movie's Directors fromInfo saved into a list in_directors = re.compile('.*?Directed by.*\n(.*)') get_directors = str(in_directors.findall(fromInfo)) from_directors = re.compile('<a [^>]*>([^<]*)</a>') return from_directors.findall(get_directors) def MPAA(fromInfo): #Movie's MPAA Rating fromInfo saved into a list in_mpaa = re.compile('MPAA</a>:([^<]*)<') return in_mpaa.findall(fromInfo) def Tagline(fromInfo): # Movie's Tagline fromInfo saved into a list in_tagline = re.compile('Tagline:([^<]*)<') Tagline = [] for a in in_tagline.findall(fromInfo): Tagline.append(a.strip()) return Tagline def Runtime(fromInfo): # Movie's Runtime fromInfo saved into a list in_runtime = re.compile('me:\n(.*)') Runtime = [] for a in in_runtime.findall(fromInfo): Runtime.append(a.strip()) return Runtime def CoverURL(fromInfo): # Movie's Cover Image URL fromInfo saved into a list in_cover = re.compile('(http://.*?m.jpg)') return in_cover.findall(fromInfo) def Writers(fromInfo): # Movie's Writers saved into a list in_writers = re.compile('ts\n.*\n.*\n(.*)') #\n') get_writers = str(in_writers.findall(fromInfo)) from_writers = re.compile('/">(.*?)<') return from_writers.findall(get_writers) def Rating(fromInfo): # Movie's IMDb Rating fromInfo saved into a list in_rating = re.compile('(.*?) (.*)') Rating = [] for a in in_rating.findall(fromInfo): Rating.append('%s %s' % (a[0],a[1])) return Rating def Genres(fromInfo): in_genres = re.compile('res/(.*?)/') return in_genres.findall(fromInfo) def Details(fromDetails): in_details = re.compile('ar">(.*?)<') return in_details.findall(fromDetails) def Plot(fromInfo): in_plot = re.compile('tline:([^<]*)<') return in_plot.findall(fromInfo) def Cast(fromInfo): # Movie's Actor & Alias names saved in separate lists in_cast = re.compile('d valign=.*?/">(.*?)<.*?e">(.*?)<') Cast = in_cast.findall(fromInfo) CastActor = [] CastAlias = [] for a in Cast: CastActor.append(a[0]) CastAlias.append(a[1]) return CastActor, CastAlias def Countries(fromInfo): in_countries = re.compile('ries/(.*?)/') return in_countries.findall(fromInfo) def Languages(fromInfo): in_languages = re.compile('uages/(.*?)/') return in_languages.findall(fromInfo) def Color(fromInfo): in_color = re.compile('o=.*?">(.*?)<') return in_color.findall(fromInfo) def SoundMix(fromInfo): in_sound = re.compile('x=.*?">(.*?)</a>') return in_sound.findall(fromInfo) def Certificates(fromInfo): in_cert = re.compile('tes=.*?">(.*?)<') return in_cert.findall(fromInfo) def Trivia(fromInfo): in_trivia = re.compile('ia:\n(.*)') return in_trivia.findall(fromInfo) def Goofs(fromInfo): in_goofs = re.compile('fs:\n(.*)') return in_goofs.findall(fromInfo) def Quotes(fromInfo): in_qoutes = re.compile('">(.*?)</a>:\n(.*?)<') Quotes = [] for a in in_qoutes.findall(fromInfo): Quotes.append('%s: %s' % (a[0], a[1])) return Quotes def Galleries(fromGallery, page='0'): in_gallery = re.compile('"(photogallery.*?|/gallery/.*?)"><img src="(.*?jpg)"') Gallery = [] Thumbs = [] for a in in_gallery.findall(fromGallery): Gallery.append(a[0]) thumbs = urllib.urlopen(url + a[0][:-1] + page).read() test = in_gallery.findall(thumbs) for a in test: Thumbs.append(a[1].replace('th-','')) return Gallery, Thumbs num = '0' Next = int(num) + 12 url = 'http://www.imdb.com/title/tt0315824/' Gallery = IMDb(url).fromGallery gal, thumb = Galleries(Gallery, page=num) print gal print thumb #print Title(fromInfo) #print Year(fromInfo) #print Directors(fromInfo) #print MPAA(fromInfo) #print Tagline(fromInfo) #print Runtime(fromInfo) #print CoverURL(fromInfo) #print Writers(fromInfo) #print Rating(fromInfo) #print Genres(fromInfo) #print Details(fromDetails) #print Plot(fromInfo) #print Cast(fromInfo) #print Countries(fromInfo) #print Languages(fromInfo) #print Color(fromInfo) #print SoundMix(fromInfo) #print Certificates(fromInfo) #print Trivia(fromInfo) #print Goofs(fromInfo) #print Quotes(fromInfo)

import os, sys, re, urllib, string reg = re.compile(r"&#[0-9]{1,3};") def fix(s): codes = reg.findall(s) for i in codes: s = s.replace(i,'%c'%(int(i.replace('&#','').replace(';','')))).replace('','').replace('','') #.replace('
','') return(s) class IMDb: def __init__(self, url): fromInfo = urllib.urlopen(url).read() self.fromInfo = fix(fromInfo).replace(' / ','').replace(' ',' ').replace('','') self.fromDetails = urllib.urlopen(url + 'plotsummary').read() self.fromGallery = urllib.urlopen(url + 'photogallery').read() def Title(fromInfo): # Movie's Title fromInfo saved into a list in_title = re.compile('(.*)<.*?') return in_title.findall(fromInfo) def Year(fromInfo): # Movie's Year fromInfo saved into a list in_year = re.compile('/Sections/Years/([0-9]*)') return in_year.findall(fromInfo) def Directors(fromInfo): # Movie's Directors fromInfo saved into a list in_directors = re.compile('.*?Directed by.*\n(.*)') get_directors = str(in_directors.findall(fromInfo)) from_directors = re.compile('<a [^>]*>([^<]*)</a>') return from_directors.findall(get_directors) def MPAA(fromInfo): #Movie's MPAA Rating fromInfo saved into a list in_mpaa = re.compile('MPAA</a>:([^<]*)<') return in_mpaa.findall(fromInfo) def Tagline(fromInfo): # Movie's Tagline fromInfo saved into a list in_tagline = re.compile('Tagline:([^<]*)<') Tagline = [] for a in in_tagline.findall(fromInfo): Tagline.append(a.strip()) return Tagline def Runtime(fromInfo): # Movie's Runtime fromInfo saved into a list in_runtime = re.compile('me:\n(.*)') Runtime = [] for a in in_runtime.findall(fromInfo): Runtime.append(a.strip()) return Runtime def CoverURL(fromInfo): # Movie's Cover Image URL fromInfo saved into a list in_cover = re.compile('(http://.*?m.jpg)') return in_cover.findall(fromInfo) def Writers(fromInfo): # Movie's Writers saved into a list in_writers = re.compile('ts\n.*\n.*\n(.*)') #\n') get_writers = str(in_writers.findall(fromInfo)) from_writers = re.compile('/">(.*?)<') return from_writers.findall(get_writers) def Rating(fromInfo): # Movie's IMDb Rating fromInfo saved into a list in_rating = re.compile('(.*?) (.*)') Rating = [] for a in in_rating.findall(fromInfo): Rating.append('%s %s' % (a[0],a[1])) return Rating def Genres(fromInfo): in_genres = re.compile('res/(.*?)/') return in_genres.findall(fromInfo) def Details(fromDetails): in_details = re.compile('ar">(.*?)<') return in_details.findall(fromDetails) def Plot(fromInfo): in_plot = re.compile('tline:([^<]*)<') return in_plot.findall(fromInfo) def Cast(fromInfo): # Movie's Actor & Alias names saved in separate lists in_cast = re.compile('d valign=.*?/">(.*?)<.*?e">(.*?)<') Cast = in_cast.findall(fromInfo) CastActor = [] CastAlias = [] for a in Cast: CastActor.append(a[0]) CastAlias.append(a[1]) return CastActor, CastAlias def Countries(fromInfo): in_countries = re.compile('ries/(.*?)/') return in_countries.findall(fromInfo) def Languages(fromInfo): in_languages = re.compile('uages/(.*?)/') return in_languages.findall(fromInfo) def Color(fromInfo): in_color = re.compile('o=.*?">(.*?)<') return in_color.findall(fromInfo) def SoundMix(fromInfo): in_sound = re.compile('x=.*?">(.*?)</a>') return in_sound.findall(fromInfo) def Certificates(fromInfo): in_cert = re.compile('tes=.*?">(.*?)<') return in_cert.findall(fromInfo) def Trivia(fromInfo): in_trivia = re.compile('ia:\n(.*)') return in_trivia.findall(fromInfo) def Goofs(fromInfo): in_goofs = re.compile('fs:\n(.*)') return in_goofs.findall(fromInfo) def Quotes(fromInfo): in_qoutes = re.compile('">(.*?)</a>:\n(.*?)<') Quotes = [] for a in in_qoutes.findall(fromInfo): Quotes.append('%s: %s' % (a[0], a[1])) return Quotes def Galleries(fromGallery, page='0'): in_gallery = re.compile('"(photogallery.*?|/gallery/.*?)"><img src="(.*?jpg)"') Gallery = [] Thumbs = [] for a in in_gallery.findall(fromGallery): Gallery.append(a[0]) thumbs = urllib.urlopen(url + a[0][:-1] + page).read() test = in_gallery.findall(thumbs) for a in test: Thumbs.append(a[1].replace('th-','')) return Gallery, Thumbs num = '0' Next = int(num) + 12 url = 'http://www.imdb.com/title/tt0315824/' Gallery = IMDb(url).fromGallery gal, thumb = Galleries(Gallery, page=num) print gal print thumb #print Title(fromInfo) #print Year(fromInfo) #print Directors(fromInfo) #print MPAA(fromInfo) #print Tagline(fromInfo) #print Runtime(fromInfo) #print CoverURL(fromInfo) #print Writers(fromInfo) #print Rating(fromInfo) #print Genres(fromInfo) #print Details(fromDetails) #print Plot(fromInfo) #print Cast(fromInfo) #print Countries(fromInfo) #print Languages(fromInfo) #print Color(fromInfo) #print SoundMix(fromInfo) #print Certificates(fromInfo) #print Trivia(fromInfo) #print Goofs(fromInfo) #print Quotes(fromInfo)