[youtube] Add ability to authenticate with cookies

[youtube-dl] / youtube_dl / extractor / nhk.py

diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py
index 90e935351d10b7647edccaedb61b37dec061ae6c..5c8cd76dcd8ac43542796fe16f15830f749a67a1 100644 (file)
--- a/youtube_dl/extractor/nhk.py
+++ b/youtube_dl/extractor/nhk.py
@@ -1,29 +1,51 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import ExtractorError
 
 
 class NhkVodIE(InfoExtractor):
-    _VALID_URL = r'http://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>.+)\.html'
-    _TESTS = [{
-        'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815.html',
+    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>[^/]+/[^/?#&]+)'
+    _TEST = {
+        # Videos available only for a limited period of time. Visit
+        # http://www3.nhk.or.jp/nhkworld/en/vod/ for working samples.
+        'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815',
         'info_dict': {
             'id': 'A1bnNiNTE6nY3jLllS-BIISfcC_PpvF5',
             'ext': 'flv',
-            'title': '[nhkworld]VOD;2009-251-2016;TOKYO FASHION EXPRESS;The Kimono as Global Fashion;en',
+            'title': 'TOKYO FASHION EXPRESS - The Kimono as Global Fashion',
+            'description': 'md5:db338ee6ce8204f415b754782f819824',
+            'series': 'TOKYO FASHION EXPRESS',
+            'episode': 'The Kimono as Global Fashion',
         },
-        'params': {
-            'skip_download': True  # Videos available only for a limited period of time.
-        },
-    }]
+        'skip': 'Videos available only for a limited period of time',
+    }
+    _API_URL = 'http://api.nhk.or.jp/nhkworld/vodesdlist/v1/all/all/all.json?apikey=EJfK8jdS57GqlupFgAfAAwr573q01y6k'
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
 
-        embed_code = self._search_regex(
-            r'''nw_vod_ooplayer\('movie-area', '([^']+)'\);''',
-            webpage,
-            'ooyala embed code')
+        data = self._download_json(self._API_URL, video_id)
+
+        try:
+            episode = next(
+                e for e in data['data']['episodes']
+                if e.get('url') and video_id in e['url'])
+        except StopIteration:
+            raise ExtractorError('Unable to find episode')
+
+        embed_code = episode['vod_id']
+
+        title = episode.get('sub_title_clean') or episode['sub_title']
+        description = episode.get('description_clean') or episode.get('description')
+        series = episode.get('title_clean') or episode.get('title')
 
-        return self.url_result('ooyala:' + embed_code, 'Ooyala')
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'Ooyala',
+            'url': 'ooyala:%s' % embed_code,
+            'title': '%s - %s' % (series, title) if series and title else title,
+            'description': description,
+            'series': series,
+            'episode': title,
+        }