test/test_utils.py

@@ -554,11 +554,6 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(url_or_none('http$://foo.de'), None)
         self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de')
         self.assertEqual(url_or_none('//foo.de'), '//foo.de')
-        self.assertEqual(url_or_none('s3://foo.de'), None)
-        self.assertEqual(url_or_none('rtmpte://foo.de'), 'rtmpte://foo.de')
-        self.assertEqual(url_or_none('mms://foo.de'), 'mms://foo.de')
-        self.assertEqual(url_or_none('rtspu://foo.de'), 'rtspu://foo.de')
-        self.assertEqual(url_or_none('ftps://foo.de'), 'ftps://foo.de')
 
     def test_parse_age_limit(self):
         self.assertEqual(parse_age_limit(None), None)

youtube_dl/extractor/yandexvideo.py

@@ -13,30 +13,26 @@ class YandexVideoIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            yandex\.ru(?:/(?:portal/(?:video|efir)|efir))?/?\?.*?stream_id=|
+                            yandex\.ru(?:/portal/(?:video|efir))?/?\?.*?stream_id=|
                             frontend\.vh\.yandex\.ru/player/
                         )
-                        (?P<id>(?:[\da-f]{32}|[\w-]{12}))
+                        (?P<id>[\da-f]+)
                     '''
     _TESTS = [{
-        'url': 'https://yandex.ru/portal/video?stream_id=4dbb36ec4e0526d58f9f2dc8f0ecf374',
+        'url': 'https://yandex.ru/portal/video?stream_id=4dbb262b4fe5cf15a215de4f34eee34d',
-        'md5': 'e02a05bfaf0d9615ef07ae3a10f4faf4',
+        'md5': '33955d7ae052f15853dc41f35f17581c',
         'info_dict': {
-            'id': '4dbb36ec4e0526d58f9f2dc8f0ecf374',
+            'id': '4dbb262b4fe5cf15a215de4f34eee34d',
             'ext': 'mp4',
-            'title': 'Русский Вудсток - главный рок-фест в истории СССР / вДудь',
+            'title': 'В Нью-Йорке баржи и теплоход оторвались от причала и расплылись по Гудзону',
-            'description': 'md5:7d6b8d4bc4a3b9a56499916c1ea5b5fa',
+            'description': '',
-            'thumbnail': r're:^https?://',
+            'thumbnail': r're:^https?://.*\.jpg$',
-            'timestamp': 1549972939,
+            'timestamp': 0,
-            'duration': 5575,
+            'duration': 30,
             'age_limit': 18,
-            'upload_date': '20190212',
-            'view_count': int,
-            'like_count': int,
-            'dislike_count': int,
         },
     }, {
-        'url': 'https://yandex.ru/portal/efir?stream_id=4dbb262b4fe5cf15a215de4f34eee34d&from=morda',
+        'url': 'https://yandex.ru/portal/efir?stream_id=4dbb36ec4e0526d58f9f2dc8f0ecf374&from=morda',
         'only_matching': True,
     }, {
         'url': 'https://yandex.ru/?stream_id=4dbb262b4fe5cf15a215de4f34eee34d',
@@ -56,85 +52,53 @@ class YandexVideoIE(InfoExtractor):
         # DASH with DRM
         'url': 'https://yandex.ru/portal/video?from=morda&stream_id=485a92d94518d73a9d0ff778e13505f8',
         'only_matching': True,
-    }, {
-        'url': 'https://yandex.ru/efir?stream_active=watching&stream_id=v7a2dZ-v5mSI&from_block=efir_newtab',
-        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         content = self._download_json(
-            # 'https://frontend.vh.yandex.ru/v23/player/%s.json' % video_id,
+            'https://frontend.vh.yandex.ru/v22/player/%s.json' % video_id,
-            # video_id, query={
+            video_id, query={
-            #     'stream_options': 'hires',
+                'stream_options': 'hires',
-            #     'disable_trackings': 1,
+                'disable_trackings': 1,
-            # })['content']
+            })['content']
-            'https://frontend.vh.yandex.ru/graphql', video_id, data=b'''{
-  player(content_id: "%s") {
-    computed_title
-    content_url
-    description
-    dislikes
-    duration
-    likes
-    program_title
-    release_date
-    release_date_ut
-    release_year
-    restriction_age
-    season
-    start_time
-    streams
-    thumbnail
-    title
-    views_count
-  }
-}''' % video_id.encode())['player']['content']['content']
 
-        title = content.get('title') or content['computed_title']
+        content_url = url_or_none(content.get('content_url')) or url_or_none(
+            content['streams'][0]['url'])
+        title = content.get('title') or content.get('computed_title')
 
-        formats = []
-        streams = content.get('streams') or []
-        streams.append({'url': content.get('content_url')})
-        for stream in streams:
-            content_url = url_or_none(stream.get('url'))
-            if not content_url:
-                continue
         ext = determine_ext(content_url)
-            if ext == 'ismc':
+
-                continue
+        if ext == 'm3u8':
-            elif ext == 'm3u8':
+            formats = self._extract_m3u8_formats(
-                formats.extend(self._extract_m3u8_formats(
+                content_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                    content_url, video_id, 'mp4',
+                m3u8_id='hls')
-                    'm3u8_native', m3u8_id='hls', fatal=False))
         elif ext == 'mpd':
-                formats.extend(self._extract_mpd_formats(
+            formats = self._extract_mpd_formats(
-                    content_url, video_id, mpd_id='dash', fatal=False))
+                content_url, video_id, mpd_id='dash')
         else:
-                formats.append({'url': content_url})
+            formats = [{'url': content_url}]
 
         self._sort_formats(formats)
 
+        description = content.get('description')
+        thumbnail = content.get('thumbnail')
         timestamp = (int_or_none(content.get('release_date'))
                      or int_or_none(content.get('release_date_ut'))
                      or int_or_none(content.get('start_time')))
-        season = content.get('season') or {}
+        duration = int_or_none(content.get('duration'))
+        series = content.get('program_title')
+        age_limit = int_or_none(content.get('restriction_age'))
 
         return {
             'id': video_id,
             'title': title,
-            'description': content.get('description'),
+            'description': description,
-            'thumbnail': content.get('thumbnail'),
+            'thumbnail': thumbnail,
             'timestamp': timestamp,
-            'duration': int_or_none(content.get('duration')),
+            'duration': duration,
-            'series': content.get('program_title'),
+            'series': series,
-            'age_limit': int_or_none(content.get('restriction_age')),
+            'age_limit': age_limit,
-            'view_count': int_or_none(content.get('views_count')),
-            'like_count': int_or_none(content.get('likes')),
-            'dislike_count': int_or_none(content.get('dislikes')),
-            'season_number': int_or_none(season.get('season_number')),
-            'season_id': season.get('id'),
-            'release_year': int_or_none(content.get('release_year')),
             'formats': formats,
         }

youtube_dl/utils.py

@@ -3640,7 +3640,7 @@ def url_or_none(url):
     if not url or not isinstance(url, compat_str):
         return None
     url = url.strip()
-    return url if re.match(r'^(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None
+    return url if re.match(r'^(?:[a-zA-Z][\da-zA-Z.+-]*:)?//', url) else None
 
 
 def parse_duration(s):