yt_dlp/extractor/zee5.py

   1 import json
   2 import time
   3 import uuid
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     jwt_decode_hs256,
  11     parse_age_limit,
  12     str_or_none,
  13     try_call,
  14     try_get,
  15     unified_strdate,
  16     unified_timestamp,
  17     url_or_none,
  18 )
  19
  20
  21 class Zee5IE(InfoExtractor):
  22     _VALID_URL = r'''(?x)
  23                      (?:
  24                         zee5:|
  25                         https?://(?:www\.)?zee5\.com/(?:[^#?]+/)?
  26                         (?:
  27                             (?:tv-shows|kids|web-series|zee5originals)(?:/[^#/?]+){3}
  28                             |(?:movies|kids|videos|news|music-videos)/(?!kids-shows)[^#/?]+
  29                         )/(?P<display_id>[^#/?]+)/
  30                      )
  31                      (?P<id>[^#/?]+)/?(?:$|[?#])
  32                      '''
  33     _TESTS = [{
  34         'url': 'https://www.zee5.com/movies/details/adavari-matalaku-ardhale-verule/0-0-movie_1143162669',
  35         'info_dict': {
  36             'id': '0-0-movie_1143162669',
  37             'ext': 'mp4',
  38             'display_id': 'adavari-matalaku-ardhale-verule',
  39             'title': 'Adavari Matalaku Ardhale Verule',
  40             'duration': 9360,
  41             'description': compat_str,
  42             'alt_title': 'Adavari Matalaku Ardhale Verule',
  43             'uploader': 'Zee Entertainment Enterprises Ltd',
  44             'release_date': '20070427',
  45             'upload_date': '20070427',
  46             'timestamp': 1177632000,
  47             'thumbnail': r're:^https?://.*\.jpg$',
  48             'episode_number': 0,
  49             'episode': 'Episode 0',
  50             'tags': list
  51         },
  52         'params': {
  53             'format': 'bv',
  54         },
  55     }, {
  56         'url': 'https://www.zee5.com/kids/kids-shows/bandbudh-aur-budbak/0-6-1899/yoga-se-hoga-bandbudh-aur-budbak/0-1-239839',
  57         'info_dict': {
  58             'id': '0-1-239839',
  59             'ext': 'mp4',
  60             'display_id': 'yoga-se-hoga-bandbudh-aur-budbak',
  61             'title': 'Yoga Se Hoga-Bandbudh aur Budbak',
  62             'duration': 659,
  63             'description': compat_str,
  64             'alt_title': 'Yoga Se Hoga-Bandbudh aur Budbak',
  65             'uploader': 'Zee Entertainment Enterprises Ltd',
  66             'release_date': '20150101',
  67             'upload_date': '20150101',
  68             'timestamp': 1420070400,
  69             'thumbnail': r're:^https?://.*\.jpg$',
  70             'series': 'Bandbudh Aur Budbak',
  71             'season_number': 1,
  72             'episode_number': 1,
  73             'episode': 'Episode 1',
  74             'season': 'Season 1',
  75             'tags': list,
  76         },
  77         'params': {
  78             'format': 'bv',
  79         },
  80     }, {
  81         'url': 'https://www.zee5.com/hi/tv-shows/details/kundali-bhagya/0-6-366/kundali-bhagya-march-08-2021/0-1-manual_7g9jv1os7730?country=IN',
  82         'only_matching': True
  83     }, {
  84         'url': 'https://www.zee5.com/global/hi/tv-shows/details/kundali-bhagya/0-6-366/kundali-bhagya-march-08-2021/0-1-manual_7g9jv1os7730',
  85         'only_matching': True
  86     }, {
  87         'url': 'https://www.zee5.com/web-series/details/mithya/0-6-4z587408/maine-dekhi-hai-uski-mrityu/0-1-6z587412',
  88         'only_matching': True
  89     }, {
  90         'url': 'https://www.zee5.com/kids/kids-movies/maya-bommalu/0-0-movie_1040370005',
  91         'only_matching': True
  92     }, {
  93         'url': 'https://www.zee5.com/news/details/jana-sena-chief-pawan-kalyan-shows-slippers-to-ysrcp-leaders/0-0-newsauto_6ettj4242oo0',
  94         'only_matching': True
  95     }, {
  96         'url': 'https://www.zee5.com/music-videos/details/adhento-gaani-vunnapaatuga-jersey-nani-shraddha-srinath/0-0-56973',
  97         'only_matching': True
  98     }]
  99     _DEVICE_ID = str(uuid.uuid4())
 100     _USER_TOKEN = None
 101     _LOGIN_HINT = 'Use "--username <mobile_number>" to login using otp or "--username token" and "--password <user_token>" to login using user token.'
 102     _NETRC_MACHINE = 'zee5'
 103     _GEO_COUNTRIES = ['IN']
 104     _USER_COUNTRY = None
 105
 106     def _perform_login(self, username, password):
 107         if len(username) == 10 and username.isdigit() and self._USER_TOKEN is None:
 108             self.report_login()
 109             otp_request_json = self._download_json(f'https://b2bapi.zee5.com/device/sendotp_v1.php?phoneno=91{username}',
 110                                                    None, note='Sending OTP')
 111             if otp_request_json['code'] == 0:
 112                 self.to_screen(otp_request_json['message'])
 113             else:
 114                 raise ExtractorError(otp_request_json['message'], expected=True)
 115             otp_code = self._get_tfa_info('OTP')
 116             otp_verify_json = self._download_json(f'https://b2bapi.zee5.com/device/verifyotp_v1.php?phoneno=91{username}&otp={otp_code}&guest_token={self._DEVICE_ID}&platform=web',
 117                                                   None, note='Verifying OTP', fatal=False)
 118             if not otp_verify_json:
 119                 raise ExtractorError('Unable to verify OTP.', expected=True)
 120             self._USER_TOKEN = otp_verify_json.get('token')
 121             if not self._USER_TOKEN:
 122                 raise ExtractorError(otp_request_json['message'], expected=True)
 123         elif username.lower() == 'token' and try_call(lambda: jwt_decode_hs256(password)):
 124             self._USER_TOKEN = password
 125         else:
 126             raise ExtractorError(self._LOGIN_HINT, expected=True)
 127
 128         token = jwt_decode_hs256(self._USER_TOKEN)
 129         if token.get('exp', 0) <= int(time.time()):
 130             raise ExtractorError('User token has expired', expected=True)
 131         self._USER_COUNTRY = token.get('current_country')
 132
 133     def _real_extract(self, url):
 134         video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
 135         access_token_request = self._download_json(
 136             'https://launchapi.zee5.com/launch?platform_name=web_app',
 137             video_id, note='Downloading access token')['platform_token']
 138         data = {
 139             'x-access-token': access_token_request['token']
 140         }
 141         if self._USER_TOKEN:
 142             data['Authorization'] = 'bearer %s' % self._USER_TOKEN
 143         else:
 144             data['X-Z5-Guest-Token'] = self._DEVICE_ID
 145
 146         json_data = self._download_json(
 147             'https://spapi.zee5.com/singlePlayback/getDetails/secure', video_id, query={
 148                 'content_id': video_id,
 149                 'device_id': self._DEVICE_ID,
 150                 'platform_name': 'desktop_web',
 151                 'country': self._USER_COUNTRY or self.get_param('geo_bypass_country') or 'IN',
 152                 'check_parental_control': False,
 153             }, headers={'content-type': 'application/json'}, data=json.dumps(data).encode('utf-8'))
 154         asset_data = json_data['assetDetails']
 155         show_data = json_data.get('showDetails', {})
 156         if 'premium' in asset_data['business_type']:
 157             raise ExtractorError('Premium content is DRM protected.', expected=True)
 158         if not asset_data.get('hls_url'):
 159             self.raise_login_required(self._LOGIN_HINT, metadata_available=True, method=None)
 160         formats, m3u8_subs = self._extract_m3u8_formats_and_subtitles(asset_data['hls_url'], video_id, 'mp4', fatal=False)
 161
 162         subtitles = {}
 163         for sub in asset_data.get('subtitle_url', []):
 164             sub_url = sub.get('url')
 165             if not sub_url:
 166                 continue
 167             subtitles.setdefault(sub.get('language', 'en'), []).append({
 168                 'url': self._proto_relative_url(sub_url),
 169             })
 170         subtitles = self._merge_subtitles(subtitles, m3u8_subs)
 171         return {
 172             'id': video_id,
 173             'display_id': display_id,
 174             'title': asset_data['title'],
 175             'formats': formats,
 176             'subtitles': subtitles,
 177             'duration': int_or_none(asset_data.get('duration')),
 178             'description': str_or_none(asset_data.get('description')),
 179             'alt_title': str_or_none(asset_data.get('original_title')),
 180             'uploader': str_or_none(asset_data.get('content_owner')),
 181             'age_limit': parse_age_limit(asset_data.get('age_rating')),
 182             'release_date': unified_strdate(asset_data.get('release_date')),
 183             'timestamp': unified_timestamp(asset_data.get('release_date')),
 184             'thumbnail': url_or_none(asset_data.get('image_url')),
 185             'series': str_or_none(asset_data.get('tvshow_name')),
 186             'season': try_get(show_data, lambda x: x['seasons']['title'], str),
 187             'season_number': int_or_none(try_get(show_data, lambda x: x['seasons'][0]['orderid'])),
 188             'episode_number': int_or_none(try_get(asset_data, lambda x: x['orderid'])),
 189             'tags': try_get(asset_data, lambda x: x['tags'], list)
 190         }
 191
 192
 193 class Zee5SeriesIE(InfoExtractor):
 194     IE_NAME = 'zee5:series'
 195     _VALID_URL = r'''(?x)
 196                      (?:
 197                         zee5:series:|
 198                         https?://(?:www\.)?zee5\.com/(?:[^#?]+/)?
 199                         (?:tv-shows|web-series|kids|zee5originals)/(?!kids-movies)(?:[^#/?]+/){2}
 200                      )
 201                      (?P<id>[^#/?]+)(?:/episodes)?/?(?:$|[?#])
 202                      '''
 203     _TESTS = [{
 204         'url': 'https://www.zee5.com/kids/kids-shows/bandbudh-aur-budbak/0-6-1899',
 205         'playlist_mincount': 156,
 206         'info_dict': {
 207             'id': '0-6-1899',
 208         },
 209     }, {
 210         'url': 'https://www.zee5.com/tv-shows/details/bhabi-ji-ghar-par-hai/0-6-199',
 211         'playlist_mincount': 1500,
 212         'info_dict': {
 213             'id': '0-6-199',
 214         },
 215     }, {
 216         'url': 'https://www.zee5.com/tv-shows/details/agent-raghav-crime-branch/0-6-965',
 217         'playlist_mincount': 24,
 218         'info_dict': {
 219             'id': '0-6-965',
 220         },
 221     }, {
 222         'url': 'https://www.zee5.com/ta/tv-shows/details/nagabhairavi/0-6-3201',
 223         'playlist_mincount': 3,
 224         'info_dict': {
 225             'id': '0-6-3201',
 226         },
 227     }, {
 228         'url': 'https://www.zee5.com/global/hi/tv-shows/details/khwaabon-ki-zamin-par/0-6-270',
 229         'playlist_mincount': 150,
 230         'info_dict': {
 231             'id': '0-6-270',
 232         },
 233     }, {
 234         'url': 'https://www.zee5.com/tv-shows/details/chala-hawa-yeu-dya-ladies-zindabaad/0-6-2943/episodes',
 235         'only_matching': True,
 236     }, {
 237         'url': 'https://www.zee5.com/web-series/details/mithya/0-6-4z587408',
 238         'only_matching': True,
 239     }]
 240
 241     def _entries(self, show_id):
 242         access_token_request = self._download_json(
 243             'https://launchapi.zee5.com/launch?platform_name=web_app',
 244             show_id, note='Downloading access token')['platform_token']
 245         headers = {
 246             'X-Access-Token': access_token_request['token'],
 247             'Referer': 'https://www.zee5.com/',
 248         }
 249         show_url = f'https://gwapi.zee5.com/content/tvshow/{show_id}?translation=en&country=IN'
 250
 251         page_num = 0
 252         show_json = self._download_json(show_url, video_id=show_id, headers=headers)
 253         for season in show_json.get('seasons') or []:
 254             season_id = try_get(season, lambda x: x['id'], compat_str)
 255             next_url = f'https://gwapi.zee5.com/content/tvshow/?season_id={season_id}&type=episode&translation=en&country=IN&on_air=false&asset_subtype=tvshow&page=1&limit=100'
 256             while next_url:
 257                 page_num += 1
 258                 episodes_json = self._download_json(
 259                     next_url, video_id=show_id, headers=headers,
 260                     note='Downloading JSON metadata page %d' % page_num)
 261                 for episode in try_get(episodes_json, lambda x: x['episode'], list) or []:
 262                     video_id = episode.get('id')
 263                     yield self.url_result(
 264                         'zee5:%s' % video_id,
 265                         ie=Zee5IE.ie_key(), video_id=video_id)
 266                 next_url = url_or_none(episodes_json.get('next_episode_api'))
 267
 268     def _real_extract(self, url):
 269         show_id = self._match_id(url)
 270         return self.playlist_result(self._entries(show_id), playlist_id=show_id)