import os,sys,re,urllib

titleReg       = re.compile(r'<title>(.*)<.*?')
directorsReg   = re.compile(r'.*?Directed by.*')
writersReg     = re.compile(r'.*?Writing credits.*')
genresReg      = re.compile(r'.*?Genre:.*')
yearReg        = re.compile(r'<a href="/Sections/Years/.*">(.*?)</a>')
taglineReg     = re.compile(r'.*?Tagline:</b>(.*?)<a href.*')
plotReg        = re.compile(r'.*?Plot Outline:</b>(.*?)<a href.*')
ratingReg      = re.compile(r'.*?User Rating.*')
#ratingReg      = re.compile(r'<b>(.*?/.*?)</b>(.*)')
runtimeReg     = re.compile(r'.*?Runtime.*')
#runtimeReg     = re.compile(r'(.*? min).*')
castReg        = re.compile(r'.*?Cast overview.*')
countryReg     = re.compile(r'.*?Country:.*')
languageReg    = re.compile(r'.*?Language:.*')
details        = re.compile(r'<p class="plotpar">(.*?)</p>')

class IMDb:
   def __init__(self,url):
      self.title     = None
      self.directors = None
      self.writers   = None
      self.genres    = None
      self.details   = None
      self.year      = None
      self.tagline   = None
      self.plot      = None
      self.rating    = None
      self.runtime   = None
      self.cast      = None
      self.country   = None
      self.language  = None

      #sock = open(url,'rb')
      sock = urllib.urlopen(url)
      page = sock.readlines()
      sock.close()

      i = 0
      while i < len(page):
         if titleReg.match(page[i]):
            self.title = titleReg.search(page[i]).group(1).strip()
         if directorsReg.match(page[i]):
            in_directors = re.compile(r'.*?">(.*?)</.*?')
            i += 1
            self.directors = in_directors.findall(page[i])
         if writersReg.match(page[i]):
            in_writers = re.compile(r'<a href="/name/.*?>(.*?)<')
            i += 3
            if in_writers.search(page[i]) != None:
               self.writers = in_writers.findall(page[i])
         if genresReg.match(page[i]):
            in_genres = re.compile(r'<a href="/Sections/Genres/.*?>(.*?)<')
            i += 1
            self.genres = in_genres.findall(page[i])
         if yearReg.match(page[i]):
            self.year = yearReg.search(page[i]).group(1).strip()
         if taglineReg.match(page[i]):
            self.tagline = taglineReg.search(page[i]).group(1).strip()
         if plotReg.match(page[i]):
            self.plot = plotReg.search(page[i]).group(1).strip()
         if ratingReg.match(page[i]):
            in_rating = re.compile(r'<b>(.*?)</b> (.*)')
            i += 4
            rating_all = in_rating.findall(page[i])
            for rate in rating_all:
                rated = '%s %s' % (rate[0],rate[1])
                self.rating = rated
            # self.rating = ratingReg.search(page[i]).group(1).strip()
         if runtimeReg.match(page[i]):
            in_runtime = re.compile(r'(.*)\n')
            i += 1
            self.runtime = in_runtime.findall(page[i])
            # self.runtime = runtimeReg.search(page[i]).group(1).strip()
         if castReg.match(page[i]):
            in_actor = re.compile(r'.*?<a href="/name.*?>(.*?)<.*?top">.*?</td>')
            in_char = re.compile(r'.*?<a href="/name.*?>.*?<.*?top">(.*?)</td>')
            actor = in_actor.findall(page[i])
            char = in_char.findall(page[i])
            self.Cast = dict(zip(('actor','character'),(actor,char)))
            for i in range(len(self.Cast['actor'])):
                self.cast = '%s as %s' % (self.Cast['actor'][i],self.Cast['character'][i])

         if countryReg.match(page[i]):
            in_country = re.compile(r'<a href=.*?>(.*?)</a>')
            i += 1
            self.country = in_country.findall(page[i])
         if languageReg.match(page[i]):
            in_language = re.compile(r'<a href=.*?>(.*?)</a>')
            i += 1
            self.language = in_language.findall(page[i])
         i+=1

      try:
          sock = urllib.urlopen(url+'plotsummary')
          #sock = open('C:\\Documents and Settings\\No1\\Desktop\\plotsummary1.htm','rb')
          page = sock.readlines()
          sock.close()
      except:
          pass

      for i in page:
         match = details.search(i)
         if match != None:
            self.details = match.group(1).strip()
            break


#flick = IMDb("C:\\Documents and Settings\\No1\\Desktop\\Rt.htm")
flick = IMDb("http://www.imdb.com/title/tt0265666/")
Title = flick.title
Directors = flick.directors
Writers = flick.writers
Genres = flick.genres
Details = flick.details
Year = flick.year
Tagline = flick.tagline
Plot = flick.plot
Rating = flick.rating
Runtime = flick.runtime
Cast = flick.cast
Country = flick.country
Language = flick.language

print "Title:\n" + str(Title)
print "Director:\n" + str(Directors)
print "Writers:\n" + str(Writers)
print "Genres:\n" + str(Genres)
print "Details:\n" + str(Details)
print "Year:\n" + str(Year)
print "Tagline:\n" + str(Tagline)
print "Plot:\n" + str(Plot)
print "Rating:\n" + str(Rating)
print "Runtime:\n" + str(Runtime)
print "Cast:\n" + str(Cast)
print "Country:\n" + str(Country)
print "Language:\n" + str(Language)