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'<b>(.*?/.*?)</b>(.*)')
runtimeReg     = re.compile(r'(.*? min).*')
castReg        = re.compile(r'.*?Cast overview.*?(<tr>.*)')
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)
      #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]):
            self.rating = ratingReg.search(page[i]).group(1).strip()
         if runtimeReg.match(page[i]):
            self.runtime = runtimeReg.search(page[i]).group(1).strip()
         if castReg.match(page[i]):
            in_cast = re.compile(r'.*?<a href="/name.*?>(.*?)<.*?top">(.*?)</td>')
            self.cast = {}
            l = castReg.search(page[i]).group(1).split('</tr><tr>')
            for j in l:
               r = in_cast.search(j)
               if r != None:
                  self.cast[r.group(1).strip()] = r.group(2).strip()
         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

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

      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\\TheRoyalTenenbaums.htm")
#flick = IMDb("http://www.imdb.com/title/tt0265666/")
print flick.title
print flick.directors
print flick.writers
print flick.genres
print flick.details
print flick.year
print flick.tagline
print flick.plot
print flick.rating
print flick.runtime
print flick.cast
print flick.country
print flick.language