yt_dlp/extractor/zee5.py

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