import os,sys,re,urllib

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(';',''))))
   return(s)

## TitleReg = re.compile(r'<li>  <a href="/title/.*')

class IMDbSearch:
    def __init__(self, find):
        self.SearchResults = [] #'N/A'
        sock = urllib.urlopen('http://www.imdb.com/find?s=tt&q=' + find)
        print find
        page = sock.read()
        sock.close()
        search = re.compile('<a href="/title/(.*?)/.*?">(.*?)</a>(.*?)</li>')
        self.SearchResults = search.findall(page)

##        i = 0
##        while i < len(page):
##            if TitleReg.match(page[i]) != None:
##                search = re.compile(r'<a href="/title/(.*?)/.*?">(.*?)</a>(.*?)</li>')
##                self.SearchResults = search.findall(page[i])
##                #print self.SearchResults
##            i+=1

Movie = IMDbSearch('space')
print Movie.SearchResults