yt_dlp/extractor/zingmp3.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import hashlib
   5 import hmac
   6 import urllib.parse
   7
   8 from .common import InfoExtractor
   9 from ..utils import (
  10     int_or_none,
  11     traverse_obj,
  12     HEADRequest,
  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     _SLUG_API = {
  21         'bai-hat': '/api/v2/page/get/song',
  22         'embed': '/api/v2/page/get/song',
  23         'video-clip': '/api/v2/page/get/video',
  24         'playlist': '/api/v2/page/get/playlist',
  25         'album': '/api/v2/page/get/playlist',
  26         'lyric': '/api/v2/lyric/get/lyric',
  27         'song_streaming': '/api/v2/song/get/streaming',
  28     }
  29
  30     _API_KEY = '88265e23d4284f25963e6eedac8fbfa3'
  31     _SECRET_KEY = b'2aa2d1c561e809b267f3638c4a307aab'
  32
  33     def _extract_item(self, item, song_id, type_url, fatal):
  34         item_id = item.get('encodeId') or song_id
  35         title = item.get('title') or item.get('alias')
  36
  37         if type_url == 'video-clip':
  38             source = item.get('streaming')
  39         else:
  40             api = self.get_api_with_signature(name_api=self._SLUG_API.get('song_streaming'), param={'id': item_id})
  41             source = self._download_json(api, video_id=item_id).get('data')
  42
  43         formats = []
  44         for k, v in (source or {}).items():
  45             if not v:
  46                 continue
  47             if k in ('mp4', 'hls'):
  48                 for res, video_url in v.items():
  49                     if not video_url:
  50                         continue
  51                     if k == 'hls':
  52                         formats.extend(self._extract_m3u8_formats(
  53                             video_url, item_id, 'mp4',
  54                             'm3u8_native', m3u8_id=k, fatal=False))
  55                     elif k == 'mp4':
  56                         formats.append({
  57                             'format_id': 'mp4-' + res,
  58                             'url': video_url,
  59                             'height': int_or_none(self._search_regex(
  60                                 r'^(\d+)p', res, 'resolution', default=None)),
  61                         })
  62                 continue
  63             elif v == 'VIP':
  64                 continue
  65             formats.append({
  66                 'ext': 'mp3',
  67                 'format_id': k,
  68                 'tbr': int_or_none(k),
  69                 'url': self._proto_relative_url(v),
  70                 'vcodec': 'none',
  71             })
  72         if not formats:
  73             if not fatal:
  74                 return
  75             msg = item.get('msg')
  76             if msg == 'Sorry, this content is not available in your country.':
  77                 self.raise_geo_restricted(countries=self._GEO_COUNTRIES, metadata_available=True)
  78             self.raise_no_formats(msg, expected=True)
  79         self._sort_formats(formats)
  80
  81         lyric = item.get('lyric')
  82         if not lyric:
  83             api = self.get_api_with_signature(name_api=self._SLUG_API.get("lyric"), param={'id': item_id})
  84             info_lyric = self._download_json(api, video_id=item_id)
  85             lyric = traverse_obj(info_lyric, ('data', 'file'))
  86         subtitles = {
  87             'origin': [{
  88                 'url': lyric,
  89             }],
  90         } if lyric else None
  91
  92         album = item.get('album') or {}
  93
  94         return {
  95             'id': item_id,
  96             'title': title,
  97             'formats': formats,
  98             'thumbnail': traverse_obj(item, 'thumbnail', 'thumbnailM'),
  99             'subtitles': subtitles,
 100             'duration': int_or_none(item.get('duration')),
 101             'track': title,
 102             'artist': traverse_obj(item, 'artistsNames', 'artists_names'),
 103             'album': traverse_obj(album, 'name', 'title'),
 104             'album_artist': traverse_obj(album, 'artistsNames', 'artists_names'),
 105         }
 106
 107     def _real_initialize(self):
 108         if not self.get_param('cookiefile') and not self.get_param('cookiesfrombrowser'):
 109             self._request_webpage(HEADRequest(self._DOMAIN), None, note='Updating cookies')
 110
 111     def _real_extract(self, url):
 112         song_id, type_url = self._match_valid_url(url).group('id', 'type')
 113
 114         api = self.get_api_with_signature(name_api=self._SLUG_API[type_url], param={'id': song_id})
 115
 116         return self._process_data(self._download_json(api, song_id)['data'], song_id, type_url)
 117
 118     def get_api_with_signature(self, name_api, param):
 119         sha256 = hashlib.sha256(''.join(f'{k}={v}' for k, v in param.items()).encode('utf-8')).hexdigest()
 120
 121         data = {
 122             'apiKey': self._API_KEY,
 123             'sig': hmac.new(self._SECRET_KEY, f'{name_api}{sha256}'.encode('utf-8'), hashlib.sha512).hexdigest(),
 124             **param,
 125         }
 126         return f'{self._DOMAIN}{name_api}?{urllib.parse.urlencode(data)}'
 127
 128
 129 class ZingMp3IE(ZingMp3BaseIE):
 130     _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'bai-hat|video-clip|embed'
 131     _TESTS = [{
 132         'url': 'https://mp3.zing.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
 133         'md5': 'ead7ae13693b3205cbc89536a077daed',
 134         'info_dict': {
 135             'id': 'ZWZB9WAB',
 136             'title': 'Xa Mãi Xa',
 137             'ext': 'mp3',
 138             'thumbnail': r're:^https?://.+\.jpg',
 139             'subtitles': {
 140                 'origin': [{
 141                     'ext': 'lrc',
 142                 }]
 143             },
 144             'duration': 255,
 145             'track': 'Xa Mãi Xa',
 146             'artist': 'Bảo Thy',
 147             'album': 'Special Album',
 148             'album_artist': 'Bảo Thy',
 149         },
 150     }, {
 151         'url': 'https://zingmp3.vn/video-clip/Suong-Hoa-Dua-Loi-K-ICM-RYO/ZO8ZF7C7.html',
 152         'md5': 'c7f23d971ac1a4f675456ed13c9b9612',
 153         'info_dict': {
 154             'id': 'ZO8ZF7C7',
 155             'title': 'Sương Hoa Đưa Lối',
 156             'ext': 'mp4',
 157             'thumbnail': r're:^https?://.+\.jpg',
 158             'duration': 207,
 159             'track': 'Sương Hoa Đưa Lối',
 160             'artist': 'K-ICM, RYO',
 161             'album': 'Sương Hoa Đưa Lối (Single)',
 162             'album_artist': 'K-ICM, RYO',
 163         },
 164     }, {
 165         'url': 'https://zingmp3.vn/embed/song/ZWZEI76B?start=false',
 166         'only_matching': True,
 167     }, {
 168         'url': 'https://zingmp3.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
 169         'only_matching': True,
 170     }]
 171     IE_NAME = 'zingmp3'
 172     IE_DESC = 'zingmp3.vn'
 173
 174     def _process_data(self, data, song_id, type_url):
 175         return self._extract_item(data, song_id, type_url, True)
 176
 177
 178 class ZingMp3AlbumIE(ZingMp3BaseIE):
 179     _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'album|playlist'
 180     _TESTS = [{
 181         'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
 182         'info_dict': {
 183             '_type': 'playlist',
 184             'id': 'ZWZBWDAF',
 185             'title': 'Lâu Đài Tình Ái',
 186         },
 187         'playlist_count': 9,
 188     }, {
 189         'url': 'http://mp3.zing.vn/playlist/Duong-Hong-Loan-apollobee/IWCAACCB.html',
 190         'only_matching': True,
 191     }, {
 192         'url': 'https://zingmp3.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
 193         'only_matching': True,
 194     }]
 195     IE_NAME = 'zingmp3:album'
 196
 197     def _process_data(self, data, song_id, type_url):
 198         def entries():
 199             for item in traverse_obj(data, ('song', 'items')) or []:
 200                 entry = self._extract_item(item, song_id, type_url, False)
 201                 if entry:
 202                     yield entry
 203
 204         return self.playlist_result(entries(), traverse_obj(data, 'id', 'encodeId'),
 205                                     traverse_obj(data, 'name', 'title'))