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

ox.web.imdb.get_episodes: get all episodes of a series

Browse source
This commit is contained in:
j 2012-08-26 15:27:16 +02:00
parent ec04c29bcd
commit 2d04e03d3d
1 changed files with 16 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
ox/web/imdb.py
View file

@ -575,6 +575,22 @@ def get_movie_poster(imdbId):
return get_movie_poster(info['series']) return get_movie_poster(info['series'])
return '' return ''
def get_episodes(imdbId, season=None):
episodes = {}
url = 'http://www.imdb.com/title/tt%s/episodes' % imdbId
if season:
url += '?season=%d' % season
data = ox.cache.read_url(url)
for e in re.compile('<div data-const="tt(\d{7})".*?>.*?<div>S(\d+), Ep(\d+)<\/div>\n<\/div>', re.DOTALL).findall(data):
episodes['S%02dE%02d' %(int(e[1]), int(e[2]))] = e[0]
else:
data = ox.cache.read_url(url)
match = re.compile('<strong>Season (\d+)</strong>').findall(data)
if match:
for season in range(1, int(match[0]) + 1):
episodes.update(get_episodes(imdbId, season))
return episodes
def max_votes(): def max_votes():
url = 'http://www.imdb.com/search/title?num_votes=500000,&sort=num_votes,desc' url = 'http://www.imdb.com/search/title?num_votes=500000,&sort=num_votes,desc'
data = ox.cache.read_url(url) data = ox.cache.read_url(url)