imdb fixes

ox/web/imdb.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
-from __future__ import print_function
+from collections import defaultdict
 
 import json
 import re
@@ -17,7 +17,7 @@ from .. import cache
 from . siteparser import SiteParser
 from . import duckduckgo
 from ..utils import datetime
-from ..geo import normalize_country_name
+from ..geo import normalize_country_name, get_country_name
 
 
 def prepare_url(url, data=None, headers=cache.DEFAULT_HEADERS, timeout=cache.cache_timeout, valid=None, unicode=False):
@@ -176,18 +176,36 @@ def get_release_date(metadata):
         return min(dates)
 
 
+def get_entity_metadata(metadata):
+    data = {}
+    entity = metadata['props']['pageProps']['contentData']['entityMetadata']
+    data['title'] = entity['titleText']['text']
+    data['originalTitle'] = entity['originalTitleText']['text']
+    data['year'] = entity['releaseYear']['year']
+    data['plot'] = entity['plot']['plotText']['plainText']
+    data['country'] = [get_country_name(c['id']) for c in entity['countriesOfOrigin']['countries']]
+    data['poster'] = metadata['props']['pageProps']['contentData']['posterData']['image']['url']
+    return data
+
+
 def alternative_titles(metadata):
-    titles = []
+    titles = defaultdict(list)
     akas = get_category_by_id(metadata, 'akas')
+
+    skip = [
+        metadata['props']['pageProps']['contentData']['entityMetadata']['titleText']['text'],
+        metadata['props']['pageProps']['contentData']['entityMetadata']['originalTitleText']['text']
+    ]
     for row in akas['section']['items']:
         content = row['listContent'][0]
-        titles.append({
-            'title': content['text'],
-            'country': row['rowTitle'],
-        })
-        if content.get('subText'):
-            titles[-1]['subText'] = content['subText']
-    return titles
+        title = content['text']
+        country = row['rowTitle']
+        if title in skip:
+            continue
+        titles[title].append(country)
+        #if content.get('subText'):
+        #    titles[-1]['subText'] = content['subText']
+    return [kv for kv in titles.items()]
 
 
 '''