# -*- coding: UTF-8 -*- # vi:si:et:sw=4:sts=4:ts=4 import re from oxlib.cache import getHeaders, readUrl, readUrlUnicode from oxlib import findRe, stripTags def readUrlByImdb(imdb): #this would also wor but does not cache: ''' from urllib2 import urlopen u = urlopen(url) return u.url ''' url = "http://www.rottentomatoes.com/alias?type=imdbid&s=%s" % imdb data = readUrl(url) if "movie_title" in data: movies = re.compile('(/m/.*?/)').findall(data) if movies: return "http://www.rottentomatoes.com" + movies[0] return None def getData(url): data = readUrlUnicode(url) r = {} r['title'] = findRe(data, '

(.*?)

') if '(' in r['title']: r['year'] = findRe(r['title'], '\((\d*?)\)') r['title'] = re.sub('\((\d*?)\)', '', r['title']).strip() r['synopsis'] = findRe(data, '(.*?)') r['average rating'] = findRe(data, '
(.*?)
').strip() return r