yt_dlp/extractor/zee5.py

   1 import json
   2 import random
   3 import string
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     parse_age_limit,
  11     str_or_none,
  12     try_get,
  13     unified_strdate,
  14     unified_timestamp,
  15     url_or_none,
  16 )
  17
  18
  19 class Zee5IE(InfoExtractor):
  20     _VALID_URL = r'''(?x)
  21                      (?:
  22                         zee5:|
  23                         https?://(?:www\.)?zee5\.com/(?:[^#?]+/)?
  24                         (?:
  25                             (?:tv-shows|kids|web-series|zee5originals)(?:/[^#/?]+){3}
  26                             |(?:movies|kids|videos|news|music-videos)/(?!kids-shows)[^#/?]+
  27                         )/(?P<display_id>[^#/?]+)/
  28                      )
  29                      (?P<id>[^#/?]+)/?(?:$|[?#])
  30                      '''
  31     _TESTS = [{
  32         'url': 'https://www.zee5.com/movies/details/adavari-matalaku-ardhale-verule/0-0-movie_1143162669',
  33         'info_dict': {
  34             'id': '0-0-movie_1143162669',
  35             'ext': 'mp4',
  36             'display_id': 'adavari-matalaku-ardhale-verule',
  37             'title': 'Adavari Matalaku Ardhale Verule',
  38             'duration': 9360,
  39             'description': compat_str,
  40             'alt_title': 'Adavari Matalaku Ardhale Verule',
  41             'uploader': 'Zee Entertainment Enterprises Ltd',
  42             'release_date': '20070427',
  43             'upload_date': '20070427',
  44             'timestamp': 1177632000,
  45             'thumbnail': r're:^https?://.*\.jpg$',
  46             'episode_number': 0,
  47             'episode': 'Episode 0',
  48             'tags': list
  49         },
  50         'params': {
  51             'format': 'bv',
  52         },
  53     }, {
  54         'url': 'https://www.zee5.com/kids/kids-shows/bandbudh-aur-budbak/0-6-1899/yoga-se-hoga-bandbudh-aur-budbak/0-1-239839',
  55         'info_dict': {
  56             'id': '0-1-239839',
  57             'ext': 'mp4',
  58             'display_id': 'yoga-se-hoga-bandbudh-aur-budbak',
  59             'title': 'Yoga Se Hoga-Bandbudh aur Budbak',
  60             'duration': 659,
  61             'description': compat_str,
  62             'alt_title': 'Yoga Se Hoga-Bandbudh aur Budbak',
  63             'uploader': 'Zee Entertainment Enterprises Ltd',
  64             'release_date': '20150101',
  65             'upload_date': '20150101',
  66             'timestamp': 1420070400,
  67             'thumbnail': r're:^https?://.*\.jpg$',
  68             'series': 'Bandbudh Aur Budbak',
  69             'season_number': 1,
  70             'episode_number': 1,
  71             'episode': 'Episode 1',
  72             'season': 'Season 1',
  73             'tags': list,
  74         },
  75         'params': {
  76             'format': 'bv',
  77         },
  78     }, {
  79         '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',
  80         'only_matching': True
  81     }, {
  82         'url': 'https://www.zee5.com/global/hi/tv-shows/details/kundali-bhagya/0-6-366/kundali-bhagya-march-08-2021/0-1-manual_7g9jv1os7730',
  83         'only_matching': True
  84     }, {
  85         'url': 'https://www.zee5.com/web-series/details/mithya/0-6-4z587408/maine-dekhi-hai-uski-mrityu/0-1-6z587412',
  86         'only_matching': True
  87     }, {
  88         'url': 'https://www.zee5.com/kids/kids-movies/maya-bommalu/0-0-movie_1040370005',
  89         'only_matching': True
  90     }, {
  91         'url': 'https://www.zee5.com/news/details/jana-sena-chief-pawan-kalyan-shows-slippers-to-ysrcp-leaders/0-0-newsauto_6ettj4242oo0',
  92         'only_matching': True
  93     }, {
  94         'url': 'https://www.zee5.com/music-videos/details/adhento-gaani-vunnapaatuga-jersey-nani-shraddha-srinath/0-0-56973',
  95         'only_matching': True
  96     }]
  97     _DETAIL_API_URL = 'https://spapi.zee5.com/singlePlayback/getDetails/secure?content_id={}&device_id={}&platform_name=desktop_web&country=IN&check_parental_control=false'
  98     _DEVICE_ID = ''.join(random.choices(string.ascii_letters + string.digits, k=20)).ljust(32, '0')
  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
 104     def _perform_login(self, username, password):
 105         if len(username) == 10 and username.isdigit() and self._USER_TOKEN is None:
 106             self.report_login()
 107             otp_request_json = self._download_json(f'https://b2bapi.zee5.com/device/sendotp_v1.php?phoneno=91{username}',
 108                                                    None, note='Sending OTP')
 109             if otp_request_json['code'] == 0:
 110                 self.to_screen(otp_request_json['message'])
 111             else:
 112                 raise ExtractorError(otp_request_json['message'], expected=True)
 113             otp_code = self._get_tfa_info('OTP')
 114             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',
 115                                                   None, note='Verifying OTP', fatal=False)
 116             if not otp_verify_json:
 117                 raise ExtractorError('Unable to verify OTP.', expected=True)
 118             self._USER_TOKEN = otp_verify_json.get('token')
 119             if not self._USER_TOKEN:
 120                 raise ExtractorError(otp_request_json['message'], expected=True)
 121         elif username.lower() == 'token' and len(password) > 1198:
 122             self._USER_TOKEN = password
 123         else:
 124             raise ExtractorError(self._LOGIN_HINT, expected=True)
 125
 126     def _real_extract(self, url):
 127         video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
 128         access_token_request = self._download_json(
 129             'https://useraction.zee5.com/token/platform_tokens.php?platform_name=web_app',
 130             video_id, note='Downloading access token')
 131         data = {
 132             'x-access-token': access_token_request['token']
 133         }
 134         if self._USER_TOKEN:
 135             data['Authorization'] = 'bearer %s' % self._USER_TOKEN
 136         else:
 137             data['X-Z5-Guest-Token'] = self._DEVICE_ID
 138
 139         json_data = self._download_json(
 140             self._DETAIL_API_URL.format(video_id, self._DEVICE_ID),
 141             video_id, headers={'content-type': 'application/json'}, data=json.dumps(data).encode('utf-8'))
 142         asset_data = json_data['assetDetails']
 143         show_data = json_data.get('showDetails', {})
 144         if 'premium' in asset_data['business_type']:
 145             raise ExtractorError('Premium content is DRM protected.', expected=True)
 146         if not asset_data.get('hls_url'):
 147             self.raise_login_required(self._LOGIN_HINT, metadata_available=True, method=None)
 148         formats, m3u8_subs = self._extract_m3u8_formats_and_subtitles(asset_data['hls_url'], video_id, 'mp4', fatal=False)
 149
 150         subtitles = {}
 151         for sub in asset_data.get('subtitle_url', []):
 152             sub_url = sub.get('url')
 153             if not sub_url:
 154                 continue
 155             subtitles.setdefault(sub.get('language', 'en'), []).append({
 156                 'url': self._proto_relative_url(sub_url),
 157             })
 158         subtitles = self._merge_subtitles(subtitles, m3u8_subs)
 159         return {
 160             'id': video_id,
 161             'display_id': display_id,
 162             'title': asset_data['title'],
 163             'formats': formats,
 164             'subtitles': subtitles,
 165             'duration': int_or_none(asset_data.get('duration')),
 166             'description': str_or_none(asset_data.get('description')),
 167             'alt_title': str_or_none(asset_data.get('original_title')),
 168             'uploader': str_or_none(asset_data.get('content_owner')),
 169             'age_limit': parse_age_limit(asset_data.get('age_rating')),
 170             'release_date': unified_strdate(asset_data.get('release_date')),
 171             'timestamp': unified_timestamp(asset_data.get('release_date')),
 172             'thumbnail': url_or_none(asset_data.get('image_url')),
 173             'series': str_or_none(asset_data.get('tvshow_name')),
 174             'season': try_get(show_data, lambda x: x['seasons']['title'], str),
 175             'season_number': int_or_none(try_get(show_data, lambda x: x['seasons'][0]['orderid'])),
 176             'episode_number': int_or_none(try_get(asset_data, lambda x: x['orderid'])),
 177             'tags': try_get(asset_data, lambda x: x['tags'], list)
 178         }
 179
 180
 181 class Zee5SeriesIE(InfoExtractor):
 182     IE_NAME = 'zee5:series'
 183     _VALID_URL = r'''(?x)
 184                      (?:
 185                         zee5:series:|
 186                         https?://(?:www\.)?zee5\.com/(?:[^#?]+/)?
 187                         (?:tv-shows|web-series|kids|zee5originals)/(?!kids-movies)(?:[^#/?]+/){2}
 188                      )
 189                      (?P<id>[^#/?]+)(?:/episodes)?/?(?:$|[?#])
 190                      '''
 191     _TESTS = [{
 192         'url': 'https://www.zee5.com/kids/kids-shows/bandbudh-aur-budbak/0-6-1899',
 193         'playlist_mincount': 156,
 194         'info_dict': {
 195             'id': '0-6-1899',
 196         },
 197     }, {
 198         'url': 'https://www.zee5.com/tv-shows/details/bhabi-ji-ghar-par-hai/0-6-199',
 199         'playlist_mincount': 1500,
 200         'info_dict': {
 201             'id': '0-6-199',
 202         },
 203     }, {
 204         'url': 'https://www.zee5.com/tv-shows/details/agent-raghav-crime-branch/0-6-965',
 205         'playlist_mincount': 24,
 206         'info_dict': {
 207             'id': '0-6-965',
 208         },
 209     }, {
 210         'url': 'https://www.zee5.com/ta/tv-shows/details/nagabhairavi/0-6-3201',
 211         'playlist_mincount': 3,
 212         'info_dict': {
 213             'id': '0-6-3201',
 214         },
 215     }, {
 216         'url': 'https://www.zee5.com/global/hi/tv-shows/details/khwaabon-ki-zamin-par/0-6-270',
 217         'playlist_mincount': 150,
 218         'info_dict': {
 219             'id': '0-6-270',
 220         },
 221     }, {
 222         'url': 'https://www.zee5.com/tv-shows/details/chala-hawa-yeu-dya-ladies-zindabaad/0-6-2943/episodes',
 223         'only_matching': True,
 224     }, {
 225         'url': 'https://www.zee5.com/web-series/details/mithya/0-6-4z587408',
 226         'only_matching': True,
 227     }]
 228
 229     def _entries(self, show_id):
 230         access_token_request = self._download_json(
 231             'https://useraction.zee5.com/token/platform_tokens.php?platform_name=web_app',
 232             show_id, note='Downloading access token')
 233         headers = {
 234             'X-Access-Token': access_token_request['token'],
 235             'Referer': 'https://www.zee5.com/',
 236         }
 237         show_url = f'https://gwapi.zee5.com/content/tvshow/{show_id}?translation=en&country=IN'
 238
 239         page_num = 0
 240         show_json = self._download_json(show_url, video_id=show_id, headers=headers)
 241         for season in show_json.get('seasons') or []:
 242             season_id = try_get(season, lambda x: x['id'], compat_str)
 243             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'
 244             while next_url:
 245                 page_num += 1
 246                 episodes_json = self._download_json(
 247                     next_url, video_id=show_id, headers=headers,
 248                     note='Downloading JSON metadata page %d' % page_num)
 249                 for episode in try_get(episodes_json, lambda x: x['episode'], list) or []:
 250                     video_id = episode.get('id')
 251                     yield self.url_result(
 252                         'zee5:%s' % video_id,
 253                         ie=Zee5IE.ie_key(), video_id=video_id)
 254                 next_url = url_or_none(episodes_json.get('next_episode_api'))
 255
 256     def _real_extract(self, url):
 257         show_id = self._match_id(url)
 258         return self.playlist_result(self._entries(show_id), playlist_id=show_id)