yt_dlp/extractor/zingmp3.py

   1 import functools
   2 import hashlib
   3 import hmac
   4 import json
   5 import urllib.parse
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     OnDemandPagedList,
  10     int_or_none,
  11     traverse_obj,
  12     urljoin,
  13 )
  14
  15
  16 class ZingMp3BaseIE(InfoExtractor):
  17     _VALID_URL_TMPL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<type>(?:%s))/[^/?#]+/(?P<id>\w+)(?:\.html|\?)'
  18     _GEO_COUNTRIES = ['VN']
  19     _DOMAIN = 'https://zingmp3.vn'
  20     _PER_PAGE = 50
  21     _API_SLUGS = {
  22         # Audio/video
  23         'bai-hat': '/api/v2/page/get/song',
  24         'embed': '/api/v2/page/get/song',
  25         'video-clip': '/api/v2/page/get/video',
  26         'lyric': '/api/v2/lyric/get/lyric',
  27         'song-streaming': '/api/v2/song/get/streaming',
  28         # Playlist
  29         'playlist': '/api/v2/page/get/playlist',
  30         'album': '/api/v2/page/get/playlist',
  31         # Chart
  32         'zing-chart': '/api/v2/page/get/chart-home',
  33         'zing-chart-tuan': '/api/v2/page/get/week-chart',
  34         'moi-phat-hanh': '/api/v2/page/get/newrelease-chart',
  35         'the-loai-video': '/api/v2/video/get/list',
  36         # User
  37         'info-artist': '/api/v2/page/get/artist',
  38         'user-list-song': '/api/v2/song/get/list',
  39         'user-list-video': '/api/v2/video/get/list',
  40     }
  41
  42     def _api_url(self, url_type, params):
  43         api_slug = self._API_SLUGS[url_type]
  44         params.update({'ctime': '1'})
  45         sha256 = hashlib.sha256(
  46             ''.join(f'{k}={v}' for k, v in sorted(params.items())).encode()).hexdigest()
  47         data = {
  48             **params,
  49             'apiKey': '88265e23d4284f25963e6eedac8fbfa3',
  50             'sig': hmac.new(
  51                 b'2aa2d1c561e809b267f3638c4a307aab', f'{api_slug}{sha256}'.encode(), hashlib.sha512).hexdigest(),
  52         }
  53         return f'{self._DOMAIN}{api_slug}?{urllib.parse.urlencode(data)}'
  54
  55     def _call_api(self, url_type, params, display_id=None, **kwargs):
  56         resp = self._download_json(
  57             self._api_url(url_type, params), display_id or params.get('id'),
  58             note=f'Downloading {url_type} JSON metadata', **kwargs)
  59         return (resp or {}).get('data') or {}
  60
  61     def _real_initialize(self):
  62         if not self._cookies_passed:
  63             self._request_webpage(
  64                 self._api_url('bai-hat', {'id': ''}), None, note='Updating cookies')
  65
  66     def _parse_items(self, items):
  67         for url in traverse_obj(items, (..., 'link')) or []:
  68             yield self.url_result(urljoin(self._DOMAIN, url))
  69
  70
  71 class ZingMp3IE(ZingMp3BaseIE):
  72     _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'bai-hat|video-clip|embed'
  73     IE_NAME = 'zingmp3'
  74     IE_DESC = 'zingmp3.vn'
  75     _TESTS = [{
  76         'url': 'https://mp3.zing.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
  77         'md5': 'ead7ae13693b3205cbc89536a077daed',
  78         'info_dict': {
  79             'id': 'ZWZB9WAB',
  80             'title': 'Xa Mãi Xa',
  81             'ext': 'mp3',
  82             'thumbnail': r're:^https?://.+\.jpg',
  83             'subtitles': {
  84                 'origin': [{
  85                     'ext': 'lrc',
  86                 }]
  87             },
  88             'duration': 255,
  89             'track': 'Xa Mãi Xa',
  90             'artist': 'Bảo Thy',
  91             'album': 'Special Album',
  92             'album_artist': 'Bảo Thy',
  93         },
  94     }, {
  95         'url': 'https://zingmp3.vn/video-clip/Suong-Hoa-Dua-Loi-K-ICM-RYO/ZO8ZF7C7.html',
  96         'md5': '3c2081e79471a2f4a3edd90b70b185ea',
  97         'info_dict': {
  98             'id': 'ZO8ZF7C7',
  99             'title': 'Sương Hoa Đưa Lối',
 100             'ext': 'mp4',
 101             'thumbnail': r're:^https?://.+\.jpg',
 102             'duration': 207,
 103             'track': 'Sương Hoa Đưa Lối',
 104             'artist': 'K-ICM, RYO',
 105             'album': 'Sương Hoa Đưa Lối (Single)',
 106             'album_artist': 'K-ICM, RYO',
 107         },
 108     }, {
 109         'url': 'https://zingmp3.vn/bai-hat/Nguoi-Yeu-Toi-Lanh-Lung-Sat-Da-Mr-Siro/ZZ6IW7OU.html',
 110         'md5': '3e9f7a9bd0d965573dbff8d7c68b629d',
 111         'info_dict': {
 112             'id': 'ZZ6IW7OU',
 113             'title': 'Người Yêu Tôi Lạnh Lùng Sắt Đá',
 114             'ext': 'mp3',
 115             'thumbnail': r're:^https?://.+\.jpg',
 116             'duration': 303,
 117             'track': 'Người Yêu Tôi Lạnh Lùng Sắt Đá',
 118             'artist': 'Mr. Siro',
 119             'album': 'Người Yêu Tôi Lạnh Lùng Sắt Đá (Single)',
 120             'album_artist': 'Mr. Siro',
 121         },
 122     }, {
 123         'url': 'https://zingmp3.vn/embed/song/ZWZEI76B?start=false',
 124         'only_matching': True,
 125     }, {
 126         'url': 'https://zingmp3.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
 127         'only_matching': True,
 128     }]
 129
 130     def _real_extract(self, url):
 131         song_id, url_type = self._match_valid_url(url).group('id', 'type')
 132         item = self._call_api(url_type, {'id': song_id})
 133
 134         item_id = item.get('encodeId') or song_id
 135         if url_type == 'video-clip':
 136             source = item.get('streaming')
 137             source['mp4'] = self._download_json(
 138                 'http://api.mp3.zing.vn/api/mobile/video/getvideoinfo', item_id,
 139                 query={'requestdata': json.dumps({'id': item_id})},
 140                 note='Downloading mp4 JSON metadata').get('source')
 141         else:
 142             source = self._call_api('song-streaming', {'id': item_id})
 143
 144         formats = []
 145         for k, v in (source or {}).items():
 146             if not v or v == 'VIP':
 147                 continue
 148             if k not in ('mp4', 'hls'):
 149                 formats.append({
 150                     'ext': 'mp3',
 151                     'format_id': k,
 152                     'tbr': int_or_none(k),
 153                     'url': self._proto_relative_url(v),
 154                     'vcodec': 'none',
 155                 })
 156                 continue
 157             for res, video_url in v.items():
 158                 if not video_url:
 159                     continue
 160                 if k == 'hls':
 161                     formats.extend(self._extract_m3u8_formats(video_url, item_id, 'mp4', m3u8_id=k, fatal=False))
 162                     continue
 163                 formats.append({
 164                     'format_id': f'mp4-{res}',
 165                     'url': video_url,
 166                     'height': int_or_none(res),
 167                 })
 168
 169         if not formats and item.get('msg') == 'Sorry, this content is not available in your country.':
 170             self.raise_geo_restricted(countries=self._GEO_COUNTRIES, metadata_available=True)
 171         self._sort_formats(formats)
 172
 173         lyric = item.get('lyric') or self._call_api('lyric', {'id': item_id}, fatal=False).get('file')
 174
 175         return {
 176             'id': item_id,
 177             'title': traverse_obj(item, 'title', 'alias'),
 178             'thumbnail': traverse_obj(item, 'thumbnail', 'thumbnailM'),
 179             'duration': int_or_none(item.get('duration')),
 180             'track': traverse_obj(item, 'title', 'alias'),
 181             'artist': traverse_obj(item, 'artistsNames', 'artists_names'),
 182             'album': traverse_obj(item, ('album', ('name', 'title')), get_all=False),
 183             'album_artist': traverse_obj(item, ('album', ('artistsNames', 'artists_names')), get_all=False),
 184             'formats': formats,
 185             'subtitles': {'origin': [{'url': lyric}]} if lyric else None,
 186         }
 187
 188
 189 class ZingMp3AlbumIE(ZingMp3BaseIE):
 190     _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'album|playlist'
 191     _TESTS = [{
 192         'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
 193         'info_dict': {
 194             'id': 'ZWZBWDAF',
 195             'title': 'Lâu Đài Tình Ái',
 196         },
 197         'playlist_mincount': 9,
 198     }, {
 199         'url': 'https://zingmp3.vn/album/Nhung-Bai-Hat-Hay-Nhat-Cua-Mr-Siro-Mr-Siro/ZWZAEZZD.html',
 200         'info_dict': {
 201             'id': 'ZWZAEZZD',
 202             'title': 'Những Bài Hát Hay Nhất Của Mr. Siro',
 203         },
 204         'playlist_mincount': 49,
 205     }, {
 206         'url': 'http://mp3.zing.vn/playlist/Duong-Hong-Loan-apollobee/IWCAACCB.html',
 207         'only_matching': True,
 208     }, {
 209         'url': 'https://zingmp3.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
 210         'only_matching': True,
 211     }]
 212     IE_NAME = 'zingmp3:album'
 213
 214     def _real_extract(self, url):
 215         song_id, url_type = self._match_valid_url(url).group('id', 'type')
 216         data = self._call_api(url_type, {'id': song_id})
 217         return self.playlist_result(
 218             self._parse_items(traverse_obj(data, ('song', 'items'))),
 219             traverse_obj(data, 'id', 'encodeId'), traverse_obj(data, 'name', 'title'))
 220
 221
 222 class ZingMp3ChartHomeIE(ZingMp3BaseIE):
 223     _VALID_URL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<id>(?:zing-chart|moi-phat-hanh))/?(?:[#?]|$)'
 224     _TESTS = [{
 225         'url': 'https://zingmp3.vn/zing-chart',
 226         'info_dict': {
 227             'id': 'zing-chart',
 228         },
 229         'playlist_mincount': 100,
 230     }, {
 231         'url': 'https://zingmp3.vn/moi-phat-hanh',
 232         'info_dict': {
 233             'id': 'moi-phat-hanh',
 234         },
 235         'playlist_mincount': 100,
 236     }]
 237     IE_NAME = 'zingmp3:chart-home'
 238
 239     def _real_extract(self, url):
 240         url_type = self._match_id(url)
 241         data = self._call_api(url_type, {'id': url_type})
 242         items = traverse_obj(data, ('RTChart', 'items') if url_type == 'zing-chart' else 'items')
 243         return self.playlist_result(self._parse_items(items), url_type)
 244
 245
 246 class ZingMp3WeekChartIE(ZingMp3BaseIE):
 247     _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'zing-chart-tuan'
 248     IE_NAME = 'zingmp3:week-chart'
 249     _TESTS = [{
 250         'url': 'https://zingmp3.vn/zing-chart-tuan/Bai-hat-Viet-Nam/IWZ9Z08I.html',
 251         'info_dict': {
 252             'id': 'IWZ9Z08I',
 253             'title': 'zing-chart-vn',
 254         },
 255         'playlist_mincount': 10,
 256     }, {
 257         'url': 'https://zingmp3.vn/zing-chart-tuan/Bai-hat-US-UK/IWZ9Z0BW.html',
 258         'info_dict': {
 259             'id': 'IWZ9Z0BW',
 260             'title': 'zing-chart-us',
 261         },
 262         'playlist_mincount': 10,
 263     }, {
 264         'url': 'https://zingmp3.vn/zing-chart-tuan/Bai-hat-KPop/IWZ9Z0BO.html',
 265         'info_dict': {
 266             'id': 'IWZ9Z0BO',
 267             'title': 'zing-chart-korea',
 268         },
 269         'playlist_mincount': 10,
 270     }]
 271
 272     def _real_extract(self, url):
 273         song_id, url_type = self._match_valid_url(url).group('id', 'type')
 274         data = self._call_api(url_type, {'id': song_id})
 275         return self.playlist_result(
 276             self._parse_items(data['items']), song_id, f'zing-chart-{data.get("country", "")}')
 277
 278
 279 class ZingMp3ChartMusicVideoIE(ZingMp3BaseIE):
 280     _VALID_URL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<type>the-loai-video)/(?P<regions>[^/]+)/(?P<id>[^\.]+)'
 281     IE_NAME = 'zingmp3:chart-music-video'
 282     _TESTS = [{
 283         'url': 'https://zingmp3.vn/the-loai-video/Viet-Nam/IWZ9Z08I.html',
 284         'info_dict': {
 285             'id': 'IWZ9Z08I',
 286             'title': 'the-loai-video_Viet-Nam',
 287         },
 288         'playlist_mincount': 400,
 289     }, {
 290         'url': 'https://zingmp3.vn/the-loai-video/Au-My/IWZ9Z08O.html',
 291         'info_dict': {
 292             'id': 'IWZ9Z08O',
 293             'title': 'the-loai-video_Au-My',
 294         },
 295         'playlist_mincount': 40,
 296     }, {
 297         'url': 'https://zingmp3.vn/the-loai-video/Han-Quoc/IWZ9Z08W.html',
 298         'info_dict': {
 299             'id': 'IWZ9Z08W',
 300             'title': 'the-loai-video_Han-Quoc',
 301         },
 302         'playlist_mincount': 30,
 303     }, {
 304         'url': 'https://zingmp3.vn/the-loai-video/Khong-Loi/IWZ9Z086.html',
 305         'info_dict': {
 306             'id': 'IWZ9Z086',
 307             'title': 'the-loai-video_Khong-Loi',
 308         },
 309         'playlist_mincount': 10,
 310     }]
 311
 312     def _fetch_page(self, song_id, url_type, page):
 313         return self._parse_items(self._call_api(url_type, {
 314             'id': song_id,
 315             'type': 'genre',
 316             'page': page + 1,
 317             'count': self._PER_PAGE
 318         }).get('items'))
 319
 320     def _real_extract(self, url):
 321         song_id, regions, url_type = self._match_valid_url(url).group('id', 'regions', 'type')
 322         return self.playlist_result(
 323             OnDemandPagedList(functools.partial(self._fetch_page, song_id, url_type), self._PER_PAGE),
 324             song_id, f'{url_type}_{regions}')
 325
 326
 327 class ZingMp3UserIE(ZingMp3BaseIE):
 328     _VALID_URL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?P<user>[^/]+)/(?P<type>bai-hat|single|album|video)/?(?:[?#]|$)'
 329     IE_NAME = 'zingmp3:user'
 330     _TESTS = [{
 331         'url': 'https://zingmp3.vn/Mr-Siro/bai-hat',
 332         'info_dict': {
 333             'id': 'IWZ98609',
 334             'title': 'Mr. Siro - bai-hat',
 335             'description': 'md5:85ab29bd7b21725c12bf76fd1d6922e5',
 336         },
 337         'playlist_mincount': 91,
 338     }, {
 339         'url': 'https://zingmp3.vn/Mr-Siro/album',
 340         'info_dict': {
 341             'id': 'IWZ98609',
 342             'title': 'Mr. Siro - album',
 343             'description': 'md5:85ab29bd7b21725c12bf76fd1d6922e5',
 344         },
 345         'playlist_mincount': 3,
 346     }, {
 347         'url': 'https://zingmp3.vn/Mr-Siro/single',
 348         'info_dict': {
 349             'id': 'IWZ98609',
 350             'title': 'Mr. Siro - single',
 351             'description': 'md5:85ab29bd7b21725c12bf76fd1d6922e5',
 352         },
 353         'playlist_mincount': 20,
 354     }, {
 355         'url': 'https://zingmp3.vn/Mr-Siro/video',
 356         'info_dict': {
 357             'id': 'IWZ98609',
 358             'title': 'Mr. Siro - video',
 359             'description': 'md5:85ab29bd7b21725c12bf76fd1d6922e5',
 360         },
 361         'playlist_mincount': 15,
 362     }]
 363
 364     def _fetch_page(self, user_id, url_type, page):
 365         url_type = 'user-list-song' if url_type == 'bai-hat' else 'user-list-video'
 366         return self._parse_items(self._call_api(url_type, {
 367             'id': user_id,
 368             'type': 'artist',
 369             'page': page + 1,
 370             'count': self._PER_PAGE
 371         }, query={'sort': 'new', 'sectionId': 'aSong'}).get('items'))
 372
 373     def _real_extract(self, url):
 374         user_alias, url_type = self._match_valid_url(url).group('user', 'type')
 375         if not url_type:
 376             url_type = 'bai-hat'
 377
 378         user_info = self._call_api('info-artist', {}, user_alias, query={'alias': user_alias})
 379         if url_type in ('bai-hat', 'video'):
 380             entries = OnDemandPagedList(
 381                 functools.partial(self._fetch_page, user_info['id'], url_type), self._PER_PAGE)
 382         else:
 383             entries = self._parse_items(traverse_obj(user_info, (
 384                 'sections', lambda _, v: v['link'] == f'/{user_alias}/{url_type}', 'items', ...)))
 385         return self.playlist_result(
 386             entries, user_info['id'], f'{user_info.get("name")} - {url_type}', user_info.get('biography'))