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('<em>','').replace('</em>','').replace('<br>','')
    return(s)


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.*')
runtimeReg     = re.compile(r'.*?Runtime.*')
castReg        = re.compile(r'.*?(?:Cast overview, first billed only|Complete credited cast).*?(<tr>.*)')
countriesReg   = re.compile(r'.*?Country:.*')
languagesReg   = re.compile(r'.*?Language:.*')
mpaaReg        = re.compile(r'.*?/mpaa">MPAA</a>:</b>(.*?)<br>')
details        = re.compile(r'<p class="plotpar">(.*?)</p>')
cover          = re.compile(r'.*?src="(http://.*?m.jpg)" height="(.*?)" width="(.*?)"></a>.*')

class IMDb:
   def __init__(self,url):
      self.Title           = 'N/A'
      self.Directors       = 'N/A'
      self.Writers         = 'N/A'
      self.Genres          = 'N/A'
      self.Details         = 'N/A'
      self.Year            = 'N/A'
      self.Tagline         = 'N/A'
      self.Plot            = 'N/A'
      self.Rating          = 'N/A'
      self.MPAA            = 'N/A'
      self.Runtime         = 'N/A'
      self.Cast            = 'N/A'
      self.Countries       = 'N/A'
      self.Languages       = 'N/A'
      self.Searchresults   = 'N/A'
      self.CoverURL        = 'N/A'
      self.CoverSize       = 'N/A'

      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
              ratings_all = in_rating.findall(page[i])
              for rate in ratings_all:
                  self.Rating = '%s %s' % (rate[0],rate[1])
          if mpaaReg.match(page[i]):
              self.MPAA = mpaaReg.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])
          if castReg.match(page[i]):
              in_cast = re.compile(r'.*?<a href="/name.*?>(.*?)<.*?(?:top|middle)">(.*?)</td>')
              self.Cast = {}
              l = page[i].replace('</tr> <tr','</tr><tr').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 cover.match(page[i]):
              self.CoverSize = {}
              Cover = cover.findall(page[i])
              for a in Cover:
                  self.CoverURL = a[0]
                  self.CoverSize[a[1]] = a[2]
          if countriesReg.match(page[i]):
              in_countries = re.compile(r'<a href=.*?>(.*?)</a>')
              i += 1
              self.Countries = in_countries.findall(page[i])
          if languagesReg.match(page[i]):
              in_languages = re.compile(r'<a href=.*?>(.*?)</a>')
              i += 1
              self.Languages = in_languages.findall(page[i])
          i+=1

      try:
          sock = urllib.urlopen(url+'plotsummary')
          page = sock.readlines()
          sock.close()
      except:
          pass

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

class IMDbSearch:
    def __init__(self, find):
        find = find.strip().translate(string.maketrans('',''),'~!@#$%^&*()_+`-={}|[]\:";\'<>?,./').replace(' ','+')
        self.SearchResults = {}
        sock = urllib.urlopen('http://www.imdb.com/find?s=tt&q=' + find)
        page = sock.read()
        sock.close()
        search = re.compile('<a href="/title/(.*?)/.*?">(.*?)</a>((.*?))</li>')
        title = search.findall(page)
        if title != None:
            for a in title:
                b = "%s%s" % (a[1],a[2])
                url = "http://www.imdb.com/title/%s/" % (a[0])
                Title = fix(str(b))
                self.SearchResults[Title] = url