From 1b9c4d288c8894f22958b5ade8cd9723cf0dab31 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Sat, 15 Oct 2011 19:03:32 +0200
Subject: [PATCH 01/14] check before use

---
 ox/web/imdb.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index a9d3d88..5771b5b 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -330,7 +330,8 @@ class Imdb(SiteParser):
                 self[key] = filter(lambda x: x.lower() != 'home', self[key])
 
         if 'creator' in self:
-            self['episodeDirector'] = self['director']
+            if 'director' in self:
+                self['episodeDirector'] = self['director']
             self['director'] = self['creator']
         if 'series' in self:
             if 'episodeTitle' in self:

From 0b380abaebf8cca2911f379c3ba06e709b4d52f6 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Sat, 15 Oct 2011 21:32:32 +0200
Subject: [PATCH 02/14] series creator(s) fixed #25

---
 ox/web/imdb.py | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index 5771b5b..417d15b 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -88,7 +88,7 @@ class Imdb(SiteParser):
         'creator': {
             'page': 'combined',
             're': [
-                '<h5>Creators:</h5>.*?<div class="info-content">(.*?)</div>',
+                '<h5>Creator.?:</h5>.*?<div class="info-content">(.*?)</div>',
                 '<a href="/name/.*?>(.*?)</a>'
             ],
             'type': 'list'
@@ -329,10 +329,6 @@ class Imdb(SiteParser):
             if key in self:
                 self[key] = filter(lambda x: x.lower() != 'home', self[key])
 
-        if 'creator' in self:
-            if 'director' in self:
-                self['episodeDirector'] = self['director']
-            self['director'] = self['creator']
         if 'series' in self:
             if 'episodeTitle' in self:
                 self['seriesTitle'] = self['title']
@@ -344,7 +340,8 @@ class Imdb(SiteParser):
                 if key in self:
                     self['episode%s'%key] = self[key.lowe()]
             series = Imdb(self['series'])
-            for key in ['director', 'year']:
+
+            for key in ['creator', 'year']:
                 if key in series:
                     self[key] = series[key]
             if 'originalTitle' in self:
@@ -353,6 +350,10 @@ class Imdb(SiteParser):
             for key in ('seriesTitle', 'episodeTitle', 'season', 'episode'):
                 if key in self:
                     del self[key]
+        if 'creator' in self:
+            if 'director' in self:
+                self['episodeDirector'] = self['director']
+            self['director'] = self['creator']
 
         if 'budget' in self and 'gross' in self:
             self['profit'] = self['gross'] - self['budget']

From ae6b2abaafc4fd8cdb16879ce61f3da96de57c4d Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Mon, 17 Oct 2011 12:00:39 +0200
Subject: [PATCH 03/14] series country

---
 ox/web/imdb.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index 417d15b..c555ab3 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -337,11 +337,11 @@ class Imdb(SiteParser):
                 self['title'] = "%s (S%02dE%02d) %s" % (
                         self['seriesTitle'], self['season'], self['episode'], self['episodeTitle'])
             for key in ('Director', 'Year'):
-                if key in self:
-                    self['episode%s'%key] = self[key.lowe()]
+                if key.lower() in self:
+                    self['episode%s'%key] = self[key.lower()]
             series = Imdb(self['series'])
 
-            for key in ['creator', 'year']:
+            for key in ['creator', 'year', 'country']:
                 if key in series:
                     self[key] = series[key]
             if 'originalTitle' in self:

From d76b60736378aaf7f129c7e29a457f4ca4a95c58 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Mon, 17 Oct 2011 13:56:49 +0200
Subject: [PATCH 04/14] .

---
 ox/movie.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ox/movie.py b/ox/movie.py
index 75c5dab..c13d108 100644
--- a/ox/movie.py
+++ b/ox/movie.py
@@ -61,7 +61,7 @@ def parse_movie_path(path):
         director = []
 
     #extension/language
-    fileparts = parts[-1].split('.')
+    fileparts = [x.replace('||', '. ') for x in parts[-1].replace('. ', '||').split('.')]
     extension = fileparts[-1]
 
     if len(fileparts[-2]) == 2:

From 7a0fad1e03c16ad3022e9ed541ce6a8318714060 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Mon, 17 Oct 2011 22:53:02 +0200
Subject: [PATCH 05/14] series without episodes

---
 ox/movie.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ox/movie.py b/ox/movie.py
index c13d108..6b6eae0 100644
--- a/ox/movie.py
+++ b/ox/movie.py
@@ -152,7 +152,7 @@ def get_oxid(title, director=[], year='',
         return hashlib.sha1(string.encode('utf-8')).hexdigest().upper()
     director = ', '.join(director)
     episode_director = ', '.join(episode_director)
-    if not episode:
+    if not episode and not episode_title:
         oxid = get_hash(director)[:8] + get_hash('\n'.join([title, str(year)]))[:8]
     else:
         oxid = get_hash('\n'.join([director, title, str(year), str(season)]))[:8] + \

From fc95c4797b24a6ec6da0265bc60df12c13e26f77 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Tue, 18 Oct 2011 10:19:02 +0200
Subject: [PATCH 06/14] script titles

---
 ox/web/imdb.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index c555ab3..ba2154e 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -266,6 +266,7 @@ class Imdb(SiteParser):
         #only list one country per alternative title
 
         def is_international_title(t):
+            if 'script title' in t[1].lower(): return False
             if 'recut version' in t[1].lower(): return False
             if 'working title' in t[1].lower(): return False
             if 'complete title' in t[1].lower(): return False

From 2057e699bde0de7fcba10943728f778aec80d743 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Tue, 18 Oct 2011 12:58:03 +0200
Subject: [PATCH 07/14] special case series without creator but a director

---
 ox/web/imdb.py | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index ba2154e..3696b8a 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -102,6 +102,14 @@ class Imdb(SiteParser):
             ],
             'type': 'list'
         },
+        '_director': {
+            'page': 'combined',
+            're': [
+                '<h5>Director:</h5>.*?<div class="info-content">(.*?)</div>',
+                '<a href="/name/.*?>(.*?)</a>'
+            ],
+            'type': 'list'
+        },
         'editor': {
             'page': 'combined',
             're': [
@@ -329,6 +337,9 @@ class Imdb(SiteParser):
         for key in ('country', 'genre'):
             if key in self:
                 self[key] = filter(lambda x: x.lower() != 'home', self[key])
+        #0092999
+        if '_director' in self:
+            self['creator'] = self.pop('_director')
 
         if 'series' in self:
             if 'episodeTitle' in self:

From f1fee4612640308920b58d7984ea81adf534da32 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Tue, 18 Oct 2011 14:25:13 +0200
Subject: [PATCH 08/14] episodes without director where series does not have a
 creator, fix euro entity

---
 ox/html.py     | 6 +++++-
 ox/web/imdb.py | 4 ++++
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/ox/html.py b/ox/html.py
index fb36574..8170918 100644
--- a/ox/html.py
+++ b/ox/html.py
@@ -137,6 +137,8 @@ def decodeHtml(html):
     """
     >>> decodeHtml('me &amp; you and &#36;&#38;%')
     u'me & you and $&%'
+    >>> decodeHtml('&#x80;')
+    u'€'
     """
     if type(html) != unicode:
         html = unicode(html)[:]
@@ -146,7 +148,9 @@ def decodeHtml(html):
         uchr = lambda value: value > 255 and unichr(value) or chr(value)
     def entitydecode(match, uchr=uchr):
         entity = match.group(1)
-        if entity.startswith('#x'):
+        if entity == '#x80':
+            return u'€'
+        elif entity.startswith('#x'):
             return uchr(int(entity[2:], 16))
         elif entity.startswith('#'):
             return uchr(int(entity[1:]))
diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index 3696b8a..ad97bf4 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -356,6 +356,10 @@ class Imdb(SiteParser):
             for key in ['creator', 'year', 'country']:
                 if key in series:
                     self[key] = series[key]
+
+            if not 'director' in self and 'director' in series:
+                self['director'] = series['director']
+
             if 'originalTitle' in self:
                 del self['originalTitle']
         else:

From 71abfcc3078402ceeaac34fcbcadc73941163335 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Tue, 18 Oct 2011 14:33:45 +0200
Subject: [PATCH 09/14] directors are creators

---
 ox/web/imdb.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index ad97bf4..a9e9e2f 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -353,13 +353,13 @@ class Imdb(SiteParser):
                     self['episode%s'%key] = self[key.lower()]
             series = Imdb(self['series'])
 
+            if not 'creator' in series and 'director' in series:
+                series['creator'] = series['director']
+
             for key in ['creator', 'year', 'country']:
                 if key in series:
                     self[key] = series[key]
 
-            if not 'director' in self and 'director' in series:
-                self['director'] = series['director']
-
             if 'originalTitle' in self:
                 del self['originalTitle']
         else:

From 3e7b463ac8d2a0e9362655edd6f6eb75e312e375 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Tue, 18 Oct 2011 14:45:00 +0200
Subject: [PATCH 10/14]  International (Spanish

---
 ox/web/imdb.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index a9e9e2f..3147e9c 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -279,7 +279,7 @@ class Imdb(SiteParser):
             if 'working title' in t[1].lower(): return False
             if 'complete title' in t[1].lower(): return False
             if t[1].lower() == 'usa': return True
-            if 'international' in t[1].lower(): return True
+            #if 'international' in t[1].lower(): return True
             #fails if orignial is english... Japan (English title)
             #if 'english title' in t[1].lower(): return True
             return False

From 23ea669b7d200f7a51fab3841141b7a497b055bd Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Tue, 18 Oct 2011 14:57:31 +0200
Subject: [PATCH 11/14] cleanup summary

---
 ox/web/imdb.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index 3147e9c..1e7fc49 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -377,6 +377,8 @@ class Imdb(SiteParser):
         if 'releaseDate' in self:
             if isinstance(self['releaseDate'], list):
                 self['releaseDate'] = min(self['releaseDate'])
+        if 'summary' in self:
+            self['summary'] = self['summary'].split('</p')[0].strip()
 
 class ImdbCombined(Imdb):
     def __init__(self, id, timeout=-1):

From f0a7aba8b0a35a3b156863249e7cc14552aa0281 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Tue, 18 Oct 2011 15:30:16 +0200
Subject: [PATCH 12/14] _

---
 ox/web/imdb.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index 1e7fc49..1274a96 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -530,8 +530,8 @@ def getMoviePoster(imdbId):
     'http://ia.media-imdb.com/images/M/MV5BMjA3NzMyMzU1MV5BMl5BanBnXkFtZTcwNjc1ODUwMg@@._V1._SX594_SY755_.jpg'
     '''
     info = ImdbCombined(imdbId)
-    if 'poster_id' in info:
-        url = "http://www.imdb.com/rg/action-box-title/primary-photo/media/rm%s/tt%s" % (info['poster_id'], imdbId)
+    if 'posterId' in info:
+        url = "http://www.imdb.com/rg/action-box-title/primary-photo/media/rm%s/tt%s" % (info['posterId'], imdbId)
         data = readUrl(url)
         poster = findRe(data, 'img id="primary-img".*?src="(.*?)"')
         return poster

From 60d8c6bc05e6572af685e2ae3d8f2fd1a4a545bf Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Tue, 18 Oct 2011 15:50:16 +0200
Subject: [PATCH 13/14] not everybody can be

---
 ox/web/imdb.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index 1274a96..bfb1cba 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -355,6 +355,8 @@ class Imdb(SiteParser):
 
             if not 'creator' in series and 'director' in series:
                 series['creator'] = series['director']
+                if len(series['creator']) > 10:
+                    series['creator'] = series['director'][:1]
 
             for key in ['creator', 'year', 'country']:
                 if key in series:

From c8dc06d68265e265957a44bde0d85ce78480cb68 Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Tue, 18 Oct 2011 16:15:07 +0200
Subject: [PATCH 14/14] take International (English title)

---
 ox/web/imdb.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ox/web/imdb.py b/ox/web/imdb.py
index bfb1cba..c3c2338 100644
--- a/ox/web/imdb.py
+++ b/ox/web/imdb.py
@@ -279,7 +279,7 @@ class Imdb(SiteParser):
             if 'working title' in t[1].lower(): return False
             if 'complete title' in t[1].lower(): return False
             if t[1].lower() == 'usa': return True
-            #if 'international' in t[1].lower(): return True
+            if 'international (english title)' in t[1].lower(): return True
             #fails if orignial is english... Japan (English title)
             #if 'english title' in t[1].lower(): return True
             return False