New upstream version 2020.06.16

[youtubedl] / youtube_dl / extractor / nhk.py

diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py
index 241412f9849645674c5369e4a5d46a6ca0709358..de6a707c4265c4fc61a57db117a432a95468ab54 100644 (file)
--- a/youtube_dl/extractor/nhk.py
+++ b/youtube_dl/extractor/nhk.py
@@ -6,10 +6,22 @@ from .common import InfoExtractor
 
 
 class NhkVodIE(InfoExtractor):
 
 
 class NhkVodIE(InfoExtractor):

-    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[a-z]+-\d{8}-\d+)'
+    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[^/]+?-\d{8}-\d+)'

     # Content available only for a limited period of time. Visit
     # https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
     _TESTS = [{
     # Content available only for a limited period of time. Visit
     # https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
     _TESTS = [{

+        # clip
+        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999011/',
+        'md5': '256a1be14f48d960a7e61e2532d95ec3',
+        'info_dict': {
+            'id': 'a95j5iza',
+            'ext': 'mp4',
+            'title': "Dining with the Chef - Chef Saito's Family recipe: MENCHI-KATSU",
+            'description': 'md5:5aee4a9f9d81c26281862382103b0ea5',
+            'timestamp': 1565965194,
+            'upload_date': '20190816',
+        },
+    }, {

         'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/',
         'only_matching': True,
     }, {
         'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/',
         'only_matching': True,
     }, {


@@ -18,8 +30,11 @@ class NhkVodIE(InfoExtractor):
     }, {
         'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/',
         'only_matching': True,
     }, {
         'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/',
         'only_matching': True,

+    }, {
+        'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/j_art-20150903-1/',
+        'only_matching': True,

     }]
     }]

-    _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sodesdlist/v7/episode/%s/%s/all%s.json'
+    _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7a/episode/%s/%s/all%s.json'

 
     def _real_extract(self, url):
         lang, m_type, episode_id = re.match(self._VALID_URL, url).groups()
 
     def _real_extract(self, url):
         lang, m_type, episode_id = re.match(self._VALID_URL, url).groups()


@@ -28,7 +43,10 @@ class NhkVodIE(InfoExtractor):
 
         is_video = m_type == 'video'
         episode = self._download_json(
 
         is_video = m_type == 'video'
         episode = self._download_json(

-            self._API_URL_TEMPLATE % ('v' if is_video else 'r', episode_id, lang, '/all' if is_video else ''),
+            self._API_URL_TEMPLATE % (
+                'v' if is_video else 'r',
+                'clip' if episode_id[:4] == '9999' else 'esd',
+                episode_id, lang, '/all' if is_video else ''),

             episode_id, query={'apikey': 'EJfK8jdS57GqlupFgAfAAwr573q01y6k'})['data']['episodes'][0]
         title = episode.get('sub_title_clean') or episode['sub_title']
 
             episode_id, query={'apikey': 'EJfK8jdS57GqlupFgAfAAwr573q01y6k'})['data']['episodes'][0]
         title = episode.get('sub_title_clean') or episode['sub_title']
 


@@ -60,22 +78,16 @@ class NhkVodIE(InfoExtractor):
         if is_video:
             info.update({
                 '_type': 'url_transparent',
         if is_video:
             info.update({
                 '_type': 'url_transparent',

-                'ie_key': 'Ooyala',
-                'url': 'ooyala:' + episode['vod_id'],
+                'ie_key': 'Piksel',
+                'url': 'https://player.piksel.com/v/refid/nhkworld/prefid/' + episode['vod_id'],

             })
         else:
             audio = episode['audio']
             audio_path = audio['audio']
             info['formats'] = self._extract_m3u8_formats(
             })
         else:
             audio = episode['audio']
             audio_path = audio['audio']
             info['formats'] = self._extract_m3u8_formats(

-                'https://nhks-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
-                episode_id, 'm4a', m3u8_id='hls', fatal=False)
-            for proto in ('rtmpt', 'rtmp'):
-                info['formats'].append({
-                    'ext': 'flv',
-                    'format_id': proto,
-                    'url': '%s://flv.nhk.or.jp/ondemand/mp4:flv%s' % (proto, audio_path),
-                    'vcodec': 'none',
-                })
+                'https://nhkworld-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
+                episode_id, 'm4a', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False)

             for f in info['formats']:
                 f['language'] = lang
         return info
             for f in info['formats']:
                 f['language'] = lang
         return info