stills

scrapeit/imdb.py

@@ -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
     
@@ -558,7 +559,21 @@ def getEpisodeData(title, episode, show_url = None):
     episodeData['description'] = i['episodes'][episode]['description']
     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