0x2620/scrapeit
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

stills

Browse source
This commit is contained in:
j^ 2008-04-07 11:53:17 +02:00
parent 2663c29e6b
commit fd24107260
1 changed files with 16 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
scrapeit/imdb.py
View file

@ -249,6 +249,7 @@ class IMDb:
IMDbDict['release_date'] = self.parseReleaseinfo()
IMDbDict['business'] = self.parseBusiness()
IMDbDict['reviews'] = self.parseExternalreviews()
IMDbDict['stills'] = getMovieStills(self.imdb)
#IMDbDict['trailer'] = self.parseTrailer()
self.IMDbDict = IMDbDict
@ -559,6 +560,20 @@ def getEpisodeData(title, episode, show_url = None):
episodeData['imdb'] = i['episodes'][episode]['imdb']
return episodeData
def getMovieStills(id):
data = read_url("http://imdb.com/gallery/ss/%s" % id)
s_ = re.compile('''<img width="(\d*?)" height="(\d*?)" src="http://i.imdb.com/Photos/Ss/%s/th-(.*?).jpg"''' % id).findall(data)
stills = []
for s in s_:
if int(s[0]) > int(s[1]):
stills.append("http://i.imdb.com/Photos/Ss/%s/%s.jpg" % (id, s[2]))
if not stills:
s_ = re.compile('''<img width="(\d*?)" height="(\d*?)" src="http://(.*?)p.jpg"''').findall(data)
stills = []
for s in s_:
if int(s[0]) > int(s[1]):
stills.append("http://%sf.jpg" % s[2])
return stills
if __name__ == '__main__':
import sys