python-oxweb/oxweb/rottentomatoes.py

35 lines
1 KiB
Python
Raw Normal View History

2008-07-03 20:22:32 +00:00
# -*- 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
2008-07-03 20:22:32 +00:00
def readUrlByImdb(imdb):
2008-07-03 20:22:32 +00:00
#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)
2008-07-03 20:22:32 +00:00
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)
2008-07-03 20:22:32 +00:00
r = {}
r['title'] = findRe(data, '<h1 class="movie_title">(.*?)</h1>')
if '(' in r['title']:
r['year'] = findRe(r['title'], '\((\d*?)\)')
r['title'] = re.sub('\((\d*?)\)', '', r['title']).strip()
r['synopsis'] = findRe(data, '<span id="movie_synopsis_all".*?>(.*?)</span>')
r['average rating'] = findRe(data, '<div id="bubble_allCritics".*?>(.*?)</div>').strip()
return r