Merge 2f0fd84ef6 into f3411af12e

Authored by: megumintyan

yt_dlp/extractor/digitalconcerthall.py

@@ -10,7 +10,7 @@
 
 class DigitalConcertHallIE(InfoExtractor):
     IE_DESC = 'DigitalConcertHall extractor'
-    _VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert)/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert|work)/(?P<id>[0-9]+)-?(?P<part>[0-9]+)?'
     _OAUTH_URL = 'https://api.digitalconcerthall.com/v2/oauth2/token'
     _ACCESS_TOKEN = None
     _NETRC_MACHINE = 'digitalconcerthall'
@@ -52,6 +52,16 @@ class DigitalConcertHallIE(InfoExtractor):
             'album_artist': 'Frank Peter Zimmermann / Benedikt von Bernstorff / Jakob von Bernstorff',
         },
         'params': {'skip_download': 'm3u8'},
+    }, {
+        'note': 'Concert with several works and an interview',
+        'url': 'https://www.digitalconcerthall.com/en/work/53785-1',
+        'info_dict': {
+            'id': '53785',
+            'album_artist': 'Berliner Philharmoniker / Kirill Petrenko',
+            'title': 'Kirill Petrenko conducts Mendelssohn and Shostakovich',
+        },
+        'params': {'skip_download': 'm3u8'},
+        'playlist_count': 1,
     }]
 
     def _perform_login(self, username, password):
@@ -119,7 +129,7 @@ def _entries(self, items, language, type_, **kwargs):
             }
 
     def _real_extract(self, url):
-        language, type_, video_id = self._match_valid_url(url).group('language', 'type', 'id')
+        language, type_, video_id, part = self._match_valid_url(url).group('language', 'type', 'id', 'part')
         if not language:
             language = 'en'
 
@@ -131,14 +141,21 @@ def _real_extract(self, url):
             **parse_resolution(thumbnail_url),
         }]
 
+        url = f'https://api.digitalconcerthall.com/v2/{type_}/{video_id}'
+        if type_ == 'work':
+            url = f'https://api.digitalconcerthall.com/v2/concert/{video_id}'
+
         vid_info = self._download_json(
-            f'https://api.digitalconcerthall.com/v2/{type_}/{video_id}', video_id, headers={
+            url, video_id, headers={
                 'Accept': 'application/json',
                 'Accept-Language': language,
             })
         album_artist = ' / '.join(traverse_obj(vid_info, ('_links', 'artist', ..., 'name')) or '')
         videos = [vid_info] if type_ == 'film' else traverse_obj(vid_info, ('_embedded', ..., ...))
 
+        if type_ == 'work':
+            videos = [videos[int(part) - 1]]
+
         return {
             '_type': 'playlist',
             'id': video_id,

yt_dlp/extractor/matchtv.py

@@ -1,51 +1,35 @@
-import random
-
 from .common import InfoExtractor
-from ..utils import xpath_text
 
 
 class MatchTVIE(InfoExtractor):
-    _VALID_URL = r'https?://matchtv\.ru(?:/on-air|/?#live-player)'
+    _VALID_URL = [
+        r'https?://matchtv\.ru/on-air/?(?:$|[?#])',
+        r'https?://video\.matchtv\.ru/iframe/channel/106/?(?:$|[?#])',
+    ]
     _TESTS = [{
-        'url': 'http://matchtv.ru/#live-player',
+        'url': 'http://matchtv.ru/on-air/',
         'info_dict': {
             'id': 'matchtv-live',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': r're:^Матч ТВ - Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
-            'is_live': True,
+            'live_status': 'is_live',
         },
         'params': {
             'skip_download': True,
         },
     }, {
-        'url': 'http://matchtv.ru/on-air/',
+        'url': 'https://video.matchtv.ru/iframe/channel/106',
         'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = 'matchtv-live'
-        video_url = self._download_json(
-            'http://player.matchtv.ntvplus.tv/player/smil', video_id,
-            query={
-                'ts': '',
-                'quality': 'SD',
-                'contentId': '561d2c0df7159b37178b4567',
-                'sign': '',
-                'includeHighlights': '0',
-                'userId': '',
-                'sessionId': random.randint(1, 1000000000),
-                'contentType': 'channel',
-                'timeShift': '0',
-                'platform': 'portal',
-            },
-            headers={
-                'Referer': 'http://player.matchtv.ntvplus.tv/embed-player/NTVEmbedPlayer.swf',
-            })['data']['videoUrl']
-        f4m_url = xpath_text(self._download_xml(video_url, video_id), './to')
-        formats = self._extract_f4m_formats(f4m_url, video_id)
+        webpage = self._download_webpage('https://video.matchtv.ru/iframe/channel/106', video_id)
+        video_url = self._html_search_regex(
+            r'data-config="config=(https?://[^?"]+)[?"]', webpage, 'video URL').replace('/feed/', '/media/') + '.m3u8'
         return {
             'id': video_id,
             'title': 'Матч ТВ - Прямой эфир',
             'is_live': True,
-            'formats': formats,
+            'formats': self._extract_m3u8_formats(video_url, video_id, 'mp4', live=True),
         }