[extractor/zingmp3]: add live radio extractor

yt_dlp/extractor/_extractors.py

@@ -2588,6 +2588,9 @@
     ZingMp3ChartMusicVideoIE,
     ZingMp3UserIE,
     ZingMp3HubIE,
+    ZingMp3LiveRadioIE,
+    ZingMp3PodcastEpisodeIE,
+    ZingMp3PodcastIE,
 )
 from .zoom import ZoomIE
 from .zype import ZypeIE

yt_dlp/extractor/zingmp3.py

@@ -5,7 +5,15 @@
 import urllib.parse
 
 from .common import InfoExtractor
-from ..utils import int_or_none, traverse_obj, try_call, urljoin
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    join_nonempty,
+    try_call,
+    urljoin,
+    url_or_none
+)
+from ..utils.traversal import traverse_obj
 
 
 class ZingMp3BaseIE(InfoExtractor):
@@ -20,9 +28,17 @@ class ZingMp3BaseIE(InfoExtractor):
         'video-clip': '/api/v2/page/get/video',
         'lyric': '/api/v2/lyric/get/lyric',
         'song-streaming': '/api/v2/song/get/streaming',
+        'liveradio': '/api/v2/livestream/get/info',
+        'eps': '/api/v2/page/get/podcast-episode',
+        'episode-streaming': '/api/v2/podcast/episode/get/streaming',
         # Playlist
         'playlist': '/api/v2/page/get/playlist',
         'album': '/api/v2/page/get/playlist',
+        'pgr': '/api/v2/page/get/podcast-program',
+        'pgr-list': '/api/v2/podcast/episode/get/list',
+        'cgr': '/api/v2/page/get/podcast-category',
+        'cgr-list': '/api/v2/podcast/program/get/list-by-cate',
+        'cgrs': '/api/v2/page/get/podcast-categories',
         # Chart
         'zing-chart': '/api/v2/page/get/chart-home',
         'zing-chart-tuan': '/api/v2/page/get/week-chart',
@@ -33,6 +49,10 @@ class ZingMp3BaseIE(InfoExtractor):
         'user-list-song': '/api/v2/song/get/list',
         'user-list-video': '/api/v2/video/get/list',
         'hub': '/api/v2/page/get/hub-detail',
+        'new-release': '/api/v2/chart/get/new-release',
+        'top100': '/api/v2/page/get/top-100',
+        'podcast-new': '/api/v2/podcast/program/get/list-by-type',
+        'top-podcast': '/api/v2/podcast/program/get/top-episode',
     }
 
     def _api_url(self, url_type, params):
@@ -78,7 +98,7 @@ def _paged_list(self, _id, url_type):
 
 
 class ZingMp3IE(ZingMp3BaseIE):
-    _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'bai-hat|video-clip|embed'
+    _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'bai-hat|video-clip|embed|eps'
     IE_NAME = 'zingmp3'
     IE_DESC = 'zingmp3.vn'
     _TESTS = [{
@@ -102,7 +122,7 @@ class ZingMp3IE(ZingMp3BaseIE):
         },
     }, {
         'url': 'https://zingmp3.vn/video-clip/Suong-Hoa-Dua-Loi-K-ICM-RYO/ZO8ZF7C7.html',
-        'md5': '3c2081e79471a2f4a3edd90b70b185ea',
+        'md5': '92c6e7a019f06b4682a6c35ae5785fab',
         'info_dict': {
             'id': 'ZO8ZF7C7',
             'title': 'Sương Hoa Đưa Lối',
@@ -128,6 +148,20 @@ class ZingMp3IE(ZingMp3BaseIE):
             'album': 'Người Yêu Tôi Lạnh Lùng Sắt Đá (Single)',
             'album_artist': 'Mr. Siro',
         },
+    }, {
+        'url': 'https://zingmp3.vn/eps/Cham-x-Ban-Noi-Goi-La-Nha/ZZD9ACWI.html',
+        'md5': 'd52f9f63e2631e004e4f15188eedcf80',
+        'info_dict': {
+            'id': 'ZZD9ACWI',
+            'title': 'Chạm x Bạn - Nơi Gọi Là Nhà',
+            'ext': 'mp3',
+            'duration': 3716,
+            'thumbnail': r're:^https?://.+\.jpg',
+            'track': 'Chạm x Bạn - Nơi Gọi Là Nhà',
+            'artist': 'On Air',
+            'album': 'Top Podcast',
+            'album_artist': 'On Air',
+        },
     }, {
         'url': 'https://zingmp3.vn/embed/song/ZWZEI76B?start=false',
         'only_matching': True,
@@ -147,6 +181,8 @@ def _real_extract(self, url):
                 'http://api.mp3.zing.vn/api/mobile/video/getvideoinfo', item_id,
                 query={'requestdata': json.dumps({'id': item_id})},
                 note='Downloading mp4 JSON metadata').get('source')
+        elif url_type == 'eps':
+            source = self._call_api('episode-streaming', {'id': item_id})
         else:
             source = self._call_api('song-streaming', {'id': item_id})
 
@@ -189,9 +225,10 @@ def _real_extract(self, url):
             'thumbnail': traverse_obj(item, 'thumbnail', 'thumbnailM'),
             'duration': int_or_none(item.get('duration')),
             'track': traverse_obj(item, 'title', 'alias'),
-            'artist': traverse_obj(item, 'artistsNames', 'artists_names'),
-            'album': traverse_obj(item, ('album', ('name', 'title')), get_all=False),
-            'album_artist': traverse_obj(item, ('album', ('artistsNames', 'artists_names')), get_all=False),
+            'artist': traverse_obj(item, 'artistsNames', 'artists_names', ('artists', 0, 'name')),
+            'album': traverse_obj(item, ('album', ('name', 'title')), ('genres', 0, 'name'), get_all=False),
+            'album_artist': traverse_obj(item, ('album', ('artistsNames', 'artists_names')),
+                                         ('artists', 0, 'name'), get_all=False),
             'formats': formats,
             'subtitles': {'origin': [{'url': lyric}]} if lyric else None,
         }
@@ -200,12 +237,12 @@ def _real_extract(self, url):
 class ZingMp3AlbumIE(ZingMp3BaseIE):
     _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'album|playlist'
     _TESTS = [{
-        'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
+        'url': 'https://zingmp3.vn/album/Ca-Phe-Quan-Quen-Hoang-Dung-My-Anh-Da-LAB-Thinh-Suy/ZOC7WUZC.html',
         'info_dict': {
-            'id': 'ZWZBWDAF',
-            'title': 'Lâu Đài Tình Ái',
+            'id': 'ZOC7WUZC',
+            'title': 'Cà Phê Quán Quen',
         },
-        'playlist_mincount': 9,
+        'playlist_mincount': 10,
     }, {
         'url': 'https://zingmp3.vn/album/Nhung-Bai-Hat-Hay-Nhat-Cua-Mr-Siro-Mr-Siro/ZWZAEZZD.html',
         'info_dict': {
@@ -231,7 +268,7 @@ def _real_extract(self, url):
 
 
 class ZingMp3ChartHomeIE(ZingMp3BaseIE):
-    _VALID_URL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<id>(?:zing-chart|moi-phat-hanh))/?(?:[#?]|$)'
+    _VALID_URL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<id>(?:zing-chart|moi-phat-hanh|top100|podcast-discover))/?(?:[#?]|$)'
     _TESTS = [{
         'url': 'https://zingmp3.vn/zing-chart',
         'info_dict': {
@@ -244,13 +281,34 @@ class ZingMp3ChartHomeIE(ZingMp3BaseIE):
             'id': 'moi-phat-hanh',
         },
         'playlist_mincount': 100,
+    }, {
+        'url': 'https://zingmp3.vn/top100',
+        'info_dict': {
+            'id': 'top100',
+        },
+        'playlist_mincount': 50,
+    }, {
+        'url': 'https://zingmp3.vn/podcast-discover',
+        'info_dict': {
+            'id': 'podcast-discover',
+        },
+        'playlist_mincount': 4,
     }]
     IE_NAME = 'zingmp3:chart-home'
 
     def _real_extract(self, url):
         url_type = self._match_id(url)
-        data = self._call_api(url_type, {'id': url_type})
-        items = traverse_obj(data, ('RTChart', 'items') if url_type == 'zing-chart' else 'items')
+        params = {'id': url_type}
+        if url_type == 'podcast-discover':
+            params['type'] = 'discover'
+        data = self._call_api(url_type, params)
+        items = []
+        if url_type == 'top100':
+            items.extend(traverse_obj(data, (..., 'items', ..., {dict})))
+        elif url_type == 'zing-chart':
+            items.extend(traverse_obj(data, ('RTChart', 'items', ..., {dict})))
+        else:
+            items.extend(traverse_obj(data, ('items', ..., {dict})))
         return self.playlist_result(self._parse_items(items), url_type)
 
 
@@ -334,7 +392,7 @@ def _real_extract(self, url):
 
 
 class ZingMp3UserIE(ZingMp3BaseIE):
-    _VALID_URL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<user>[^/]+)/(?P<type>bai-hat|single|album|video)/?(?:[?#]|$)'
+    _VALID_URL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<user>[^/]+)/(?P<type>bai-hat|single|album|video|song)/?(?:[?#]|$)'
     IE_NAME = 'zingmp3:user'
     _TESTS = [{
         'url': 'https://zingmp3.vn/Mr-Siro/bai-hat',
@@ -368,6 +426,18 @@ class ZingMp3UserIE(ZingMp3BaseIE):
             'description': 'md5:5bdcf45e955dc1b8d7f518f322ffef36',
         },
         'playlist_mincount': 15,
+    }, {
+        'url': 'https://zingmp3.vn/new-release/song',
+        'info_dict': {
+            'id': 'new-release-song',
+        },
+        'playlist_mincount': 50,
+    }, {
+        'url': 'https://zingmp3.vn/new-release/album',
+        'info_dict': {
+            'id': 'new-release-album',
+        },
+        'playlist_mincount': 20,
     }]
 
     def _fetch_page(self, user_id, url_type, page):
@@ -380,20 +450,28 @@ def _fetch_page(self, user_id, url_type, page):
         })
 
     def _real_extract(self, url):
-        user_alias, url_type = self._match_valid_url(url).group('user', 'type')
+        alias, url_type = self._match_valid_url(url).group('user', 'type')
         if not url_type:
             url_type = 'bai-hat'
 
-        user_info = self._call_api('info-artist', {}, user_alias, query={'alias': user_alias})
-        if url_type in ('bai-hat', 'video'):
-            entries = self._paged_list(user_info['id'], url_type)
+        user_info = self._call_api('info-artist', {}, alias, query={'alias': alias})
+
+        # Handle for new-release
+        if alias == 'new-release' and url_type in ('song', 'album'):
+            _id = f'{alias}-{url_type}'
+            return self.playlist_result(self._parse_items(
+                self._call_api('new-release', params={'type': url_type}, display_id=_id)), _id)
         else:
-            entries = self._parse_items(traverse_obj(user_info, (
-                'sections',
-                lambda _, v: v['sectionId'] == 'aAlbum' if url_type == 'album' else v['sectionId'] == 'aSingle',
-                'items', ...)))
-        return self.playlist_result(
-            entries, user_info['id'], f'{user_info.get("name")} - {url_type}', user_info.get('biography'))
+            # Handle for user/artist
+            if url_type in ('bai-hat', 'video'):
+                entries = self._paged_list(user_info['id'], url_type)
+            else:
+                section_id = 'aAlbum' if url_type == 'album' else 'aSingle'
+                entries = self._parse_items(traverse_obj(user_info, (
+                    'sections', lambda _, v: v['sectionId'] == section_id, 'items', ...)))
+            return self.playlist_result(
+                entries, user_info['id'], join_nonempty(user_info.get('name'), url_type, delim=' - '),
+                user_info.get('biography'))
 
 
 class ZingMp3HubIE(ZingMp3BaseIE):
@@ -403,7 +481,7 @@ class ZingMp3HubIE(ZingMp3BaseIE):
         'url': 'https://zingmp3.vn/hub/Nhac-Moi/IWZ9Z0CA.html',
         'info_dict': {
             'id': 'IWZ9Z0CA',
-            'title': 'Nhạc Mới',
+            'title': 'BXH Nhạc Mới',
             'description': 'md5:1cc31b68a6f746427b07b2756c22a558',
         },
         'playlist_mincount': 20,
@@ -424,3 +502,129 @@ def _real_extract(self, url):
             'sections', lambda _, v: v['sectionId'] == 'hub', 'items', ...)))
         return self.playlist_result(
             entries, song_id, hub_detail.get('title'), hub_detail.get('description'))
+
+
+class ZingMp3LiveRadioIE(ZingMp3BaseIE):
+    IE_NAME = 'zingmp3:liveradio'
+    _VALID_URL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<type>(?:liveradio))/(?P<id>\w+)(?:\.html|\?)'
+    _TESTS = [{
+        'url': 'https://zingmp3.vn/liveradio/IWZ979UB.html',
+        'info_dict': {
+            'id': 'IWZ979UB',
+            'title': r're:^V\-POP',
+            'description': 'md5:aa857f8a91dc9ce69e862a809e4bdc10',
+            'protocol': 'm3u8_native',
+            'ext': 'mp4',
+            'view_count': int,
+            'thumbnail': r're:^https?://.*\.jpg',
+            'like_count': int,
+            'live_status': 'is_live',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://zingmp3.vn/liveradio/IWZ97CWB.html',
+        'info_dict': {
+            'id': 'IWZ97CWB',
+            'title': r're:^Live\s247',
+            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+            'protocol': 'm3u8_native',
+            'ext': 'm4a',
+            'view_count': int,
+            'thumbnail': r're:^https?://.*\.jpg',
+            'like_count': int,
+            'live_status': 'is_live',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        url_type, live_radio_id = self._match_valid_url(url).group('type', 'id')
+        info = self._call_api(url_type, {'id': live_radio_id})
+        manifest_url = info.get('streaming')
+        if not manifest_url:
+            raise ExtractorError('This radio is offline.', expected=True)
+        fmts, subtitles = self._extract_m3u8_formats_and_subtitles(manifest_url, live_radio_id, fatal=False)
+        return {
+            'id': live_radio_id,
+            'is_live': True,
+            'formats': fmts,
+            'subtitles': subtitles,
+            **traverse_obj(info, {
+                'title': 'title',
+                'thumbnail': (('thumbnail', 'thumbnailM', 'thumbnailV', 'thumbnailH'), {url_or_none}),
+                'view_count': ('activeUsers', {int_or_none}),
+                'like_count': ('totalReaction', {int_or_none}),
+                'description': 'description',
+            }, get_all=False),
+        }
+
+
+class ZingMp3PodcastEpisodeIE(ZingMp3BaseIE):
+    IE_NAME = 'zingmp3:podcast-episode'
+    _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'pgr|cgr'
+    _TESTS = [{
+        'url': 'https://zingmp3.vn/pgr/Nhac-Moi-Moi-Ngay/68Z9W66B.html',
+        'info_dict': {
+            'id': '68Z9W66B',
+            'title': 'Nhạc Mới Mỗi Ngày',
+            'description': 'md5:2875dfa951f8e5356742f1610cf20691'
+        },
+        'playlist_mincount': 20,
+    }, {
+        'url': 'https://zingmp3.vn/cgr/Am-nhac/IWZ980AO.html',
+        'info_dict': {
+            'id': 'IWZ980AO',
+            'title': 'Âm nhạc'
+        },
+        'playlist_mincount': 2,
+    }]
+
+    def _fetch_page(self, eps_id, url_type, page):
+        return self._call_api(url_type, {
+            'id': eps_id,
+            'page': page,
+            'count': self._PER_PAGE
+        })
+
+    def _real_extract(self, url):
+        podcast_id, url_type = self._match_valid_url(url).group('id', 'type')
+        podcast_info = self._call_api(url_type, {'id': podcast_id})
+        entries = self._paged_list(podcast_id, 'pgr-list' if url_type == 'pgr' else 'cgr-list')
+        return self.playlist_result(
+            entries, podcast_id, podcast_info.get('title'), podcast_info.get('description'))
+
+
+class ZingMp3PodcastIE(ZingMp3BaseIE):
+    IE_NAME = 'zingmp3:podcast'
+    _VALID_URL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<id>(?:cgr|top-podcast|podcast-new))/?(?:[#?]|$)'
+    _TESTS = [{
+        'url': 'https://zingmp3.vn/cgr',
+        'info_dict': {
+            'id': 'cgr',
+        },
+        'playlist_mincount': 5,
+    }, {
+        'url': 'https://zingmp3.vn/top-podcast',
+        'info_dict': {
+            'id': 'top-podcast',
+        },
+        'playlist_mincount': 7,
+    }, {
+        'url': 'https://zingmp3.vn/podcast-new',
+        'info_dict': {
+            'id': 'podcast-new',
+        },
+        'playlist_mincount': 4,
+    }]
+
+    def _real_extract(self, url):
+        url_type = self._match_id(url)
+        params = {'id': url_type}
+        if url_type == 'podcast-new':
+            params['type'] = 'new'
+        items = self._call_api('cgrs' if url_type == 'cgr' else url_type, params)['items']
+        return self.playlist_result(self._parse_items(items), url_type)