From 6a1ecbe21c7914e091ec778182578001c229f341 Mon Sep 17 00:00:00 2001
From: j <j@0xdb.org>
Date: Sun, 11 May 2008 17:07:09 +0200
Subject: [PATCH] imdb needs some decodeHtml and credits are all optional

---
 ox/imdb.py | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/ox/imdb.py b/ox/imdb.py
index 8bc5b6f..a603acb 100644
--- a/ox/imdb.py
+++ b/ox/imdb.py
@@ -150,7 +150,7 @@ def creditList(data, section=None):
     credits_ = re.compile('''<tr>.*?<td valign="top">(.*?)</td><td.*?</td><td valign="top">(.*?)</td></tr>''').findall(data)
   credits = []
   for c_ in credits_:
-    c = [c_[0].strip(), c_[1].strip()]
+    c = [decodeHtml(c_[0]).strip(), decodeHtml(c_[1]).strip()]
     if section=='writers':
       c[1] = c[1].replace('<br>', '').strip().replace(')', '').replace('(','')
       if c[1].endswith(' and'): c[1] = c[1][:-4]
@@ -256,6 +256,7 @@ def getMovieTrivia(imdbId):
       t = str(t).replace('<br />', '').strip()
       if t.startswith('<li>') and t.endswith('</li>'):
         t = t[4:-5].strip()
+      t=decodeHtml(t)
       trivia.append(t)
   return trivia
 
@@ -339,9 +340,13 @@ class IMDb:
         parsed_value = int(parsed_value) * 60
     elif key in ('country', 'language'):
       parsed_value = value.split(' / ')
+      if len(parsed_value) == 1:
+        parsed_value = parsed_value[0].split(' | ')
       parsed_value = [v.strip() for v in parsed_value]
     elif key == 'genre':
       parsed_value = value.replace('more', '').strip().split(' / ')
+      if len(parsed_value) == 1:
+        parsed_value = parsed_value[0].split(' | ')
       parsed_value = [v.strip() for v in parsed_value]
     elif key == 'tagline':
       parsed_value = value.replace('more', '').strip()
@@ -484,10 +489,10 @@ class IMDb:
     def getNames(creditList):
       return [stripTags(c[0]) for c in creditList]
 
-    credits['director'] = getNames(raw_credits['directors'])
-    credits['writer'] = getNames(raw_credits['writers'])
-    credits['producer'] = getNames(raw_credits['producers'])
-    credits['cast'] = [(stripTags(c[0]),stripTags(c[1])) for c in raw_credits['cast']]
+    credits['director'] = getNames(raw_credits.get('directors', ''))
+    credits['writer'] = getNames(raw_credits.get('writers', ''))
+    credits['producer'] = getNames(raw_credits.get('producers', ''))
+    credits['cast'] = [(stripTags(c[0]),stripTags(c[1])) for c in raw_credits.get('cast', [])]
 
     self.credits = credits
     return self.credits