37 lines
1,004 B
Python
37 lines
1,004 B
Python
# -*- Mode: Python; -*-
|
|
# -*- coding: utf-8 -*-
|
|
# vi:si:et:sw=2:sts=2:ts=2
|
|
|
|
from urllib import quote
|
|
import re
|
|
|
|
from BeautifulSoup import BeautifulSoup
|
|
|
|
from utils import read_url
|
|
|
|
|
|
def getRottenTomatoes(rating = 70):
|
|
'''
|
|
Get movie TITLES
|
|
rated ABOVE 70 or value passed as first argument
|
|
from RottenTomatoes
|
|
'''
|
|
movies = []
|
|
offset = 0
|
|
titles = ['1']
|
|
while titles:
|
|
url = "http://www.rottentomatoes.com/browser.php?movietype=1&genre=&tomatometer=&avgrating=%s&numreviews=10&mpaa=&x=56&y=10&start_index=%d" % (rating, offset)
|
|
page = read_url(url)
|
|
soup = BeautifulSoup(page)
|
|
titles = [link.contents[0] for link in soup.findAll('a', {'class': 'movie-link'})]
|
|
data = str(soup)
|
|
ratings = re.compile('<span class="bold">(.*?) %</span>').findall(data)
|
|
|
|
ratings = ratings[len(ratings)- len(titles):]
|
|
|
|
for title in titles:
|
|
movies.append({'title': title, 'rating': ratings[titles.index(title)], 'torrent': ''})
|
|
|
|
offset += 10
|
|
return movies
|
|
|