0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

update rottentomatoes and metacritic

Browse source
This commit is contained in:
j 2012-07-08 13:09:58 +02:00
commit e74dc77ab1
2 changed files with 65 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

29
ox/web/rottentomatoes.py
View file

@ -6,7 +6,7 @@ from ox.cache import getHeaders, readUrl, readUrlUnicode
from ox import findRe, stripTags
def readUrlByImdb(imdb):
def getUrlByImdb(imdb):
#this would also wor but does not cache:
'''
from urllib2 import urlopen
@ -21,14 +21,33 @@ def readUrlByImdb(imdb):
return "http://www.rottentomatoes.com" + movies[0]
return None
def get_og(data, key):
return findRe(data, '<meta property="og:%s".*?content="(.*?)"' % key)
def getData(url):
data = readUrlUnicode(url)
data = readUrl(url)
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()
r['title'] = stripTags(re.sub('\((\d*?)\)', '', r['title'])).strip()
r['summary'] = stripTags(findRe(data, '<p id="movieSynopsis" class="movie_synopsis" itemprop="description">(.*?)</p>')).strip()
r['summary'] = r['summary'].replace('\t', ' ').replace('\n', ' ').replace(' ', ' ').replace(' ', ' ')
if not r['summary']:
r['summary'] = get_og(data, 'description')
meter = re.compile('<span id="all-critics-meter" class="meter(.*?)">(.*?)</span>').findall(data)
meter = filter(lambda m: m[1].isdigit(), meter)
if meter:
r['tomatometer'] = meter[0][1]
r['rating'] = findRe(data, 'Average Rating: <span>([\d.]+)/10</span>')
r['user_score'] = findRe(data, '<span class="meter popcorn numeric ">(\d+)</span>')
r['user_rating'] = findRe(data, 'Average Rating: ([\d.]+)/5')
poster = get_og(data, 'image')
if poster and not 'poster_default.gif' in poster:
r['posters'] = [poster]
for key in r.keys():
if not r[key]:
del r[key]
return r