yt_dlp/extractor/cineverse.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     filter_dict,
   6     float_or_none,
   7     int_or_none,
   8     parse_age_limit,
   9     smuggle_url,
  10     traverse_obj,
  11     unsmuggle_url,
  12     url_or_none,
  13 )
  14
  15
  16 class CineverseBaseIE(InfoExtractor):
  17     _VALID_URL_BASE = r'https?://www\.(?P<host>{})'.format('|'.join(map(re.escape, (
  18         'cineverse.com',
  19         'asiancrush.com',
  20         'dovechannel.com',
  21         'screambox.com',
  22         'midnightpulp.com',
  23         'fandor.com',
  24         'retrocrush.tv',
  25     ))))
  26
  27
  28 class CineverseIE(CineverseBaseIE):
  29     _VALID_URL = rf'{CineverseBaseIE._VALID_URL_BASE}/watch/(?P<id>[A-Z0-9]+)'
  30     _TESTS = [{
  31         'url': 'https://www.asiancrush.com/watch/DMR00018919/Women-Who-Flirt',
  32         'skip': 'geo-blocked',
  33         'info_dict': {
  34             'title': 'Women Who Flirt',
  35             'ext': 'mp4',
  36             'id': 'DMR00018919',
  37             'modified_timestamp': 1678744575289,
  38             'cast': ['Xun Zhou', 'Xiaoming Huang', 'Yi-Lin Sie', 'Sonia Sui', 'Quniciren'],
  39             'duration': 5811.597,
  40             'description': 'md5:892fd62a05611d394141e8394ace0bc6',
  41             'age_limit': 13,
  42         },
  43     }, {
  44         'url': 'https://www.retrocrush.tv/watch/1000000023016/Archenemy! Crystal Bowie',
  45         'skip': 'geo-blocked',
  46         'info_dict': {
  47             'title': 'Archenemy! Crystal Bowie',
  48             'ext': 'mp4',
  49             'id': '1000000023016',
  50             'episode_number': 3,
  51             'season_number': 1,
  52             'cast': ['Nachi Nozawa', 'Yoshiko Sakakibara', 'Toshiko Fujita'],
  53             'age_limit': 0,
  54             'episode': 'Episode 3',
  55             'season': 'Season 1',
  56             'duration': 1485.067,
  57             'description': 'Cobra meets a beautiful bounty hunter by the name of Jane Royal.',
  58             'series': 'Space Adventure COBRA (Original Japanese)',
  59         },
  60     }]
  61
  62     def _real_extract(self, url):
  63         url, smuggled_data = unsmuggle_url(url, default={})
  64         self._initialize_geo_bypass({
  65             'countries': smuggled_data.get('geo_countries'),
  66         })
  67         video_id = self._match_id(url)
  68         html = self._download_webpage(url, video_id)
  69         idetails = self._search_nextjs_data(html, video_id)['props']['pageProps']['idetails']
  70
  71         err_code = idetails.get('err_code')
  72         if err_code == 1002:
  73             self.raise_login_required()
  74         elif err_code == 1200:
  75             self.raise_geo_restricted(
  76                 'This video is not available from your location due to geo restriction. '
  77                 'You may be able to bypass it by using the /details/ page instead of the /watch/ page',
  78                 countries=smuggled_data.get('geo_countries'))
  79
  80         return {
  81             'subtitles': filter_dict({
  82                 'en': traverse_obj(idetails, (('cc_url_vtt', 'subtitle_url'), {'url': {url_or_none}})) or None,
  83             }),
  84             'formats': self._extract_m3u8_formats(idetails['url'], video_id),
  85             **traverse_obj(idetails, {
  86                 'title': 'title',
  87                 'id': ('details', 'item_id'),
  88                 'description': ('details', 'description'),
  89                 'duration': ('duration', {float_or_none(scale=1000)}),
  90                 'cast': ('details', 'cast', {lambda x: x.split(', ')}),
  91                 'modified_timestamp': ('details', 'updated_by', 0, 'update_time', 'time', {int_or_none}),
  92                 'season_number': ('details', 'season', {int_or_none}),
  93                 'episode_number': ('details', 'episode', {int_or_none}),
  94                 'age_limit': ('details', 'rating_code', {parse_age_limit}),
  95                 'series': ('details', 'series_details', 'title'),
  96             }),
  97         }
  98
  99
 100 class CineverseDetailsIE(CineverseBaseIE):
 101     _VALID_URL = rf'{CineverseBaseIE._VALID_URL_BASE}/details/(?P<id>[A-Z0-9]+)'
 102     _TESTS = [{
 103         'url': 'https://www.retrocrush.tv/details/1000000023012/Space-Adventure-COBRA-(Original-Japanese)',
 104         'playlist_mincount': 30,
 105         'info_dict': {
 106             'title': 'Space Adventure COBRA (Original Japanese)',
 107             'id': '1000000023012',
 108         },
 109     }, {
 110         'url': 'https://www.asiancrush.com/details/NNVG4938/Hansel-and-Gretel',
 111         'info_dict': {
 112             'id': 'NNVG4938',
 113             'ext': 'mp4',
 114             'title': 'Hansel and Gretel',
 115             'description': 'md5:e3e4c35309c2e82aee044f972c2fb05d',
 116             'cast': ['Jeong-myeong Cheon', 'Eun Won-jae', 'Shim Eun-gyeong', 'Ji-hee Jin', 'Hee-soon Park', 'Lydia Park', 'Kyeong-ik Kim'],
 117             'duration': 7030.732,
 118         },
 119     }]
 120
 121     def _real_extract(self, url):
 122         host, series_id = self._match_valid_url(url).group('host', 'id')
 123         html = self._download_webpage(url, series_id)
 124         pageprops = self._search_nextjs_data(html, series_id)['props']['pageProps']
 125
 126         geo_countries = traverse_obj(pageprops, ('itemDetailsData', 'geo_country', {lambda x: x.split(', ')}))
 127         geoblocked = traverse_obj(pageprops, (
 128             'itemDetailsData', 'playback_err_msg')) == 'This title is not available in your location.'
 129
 130         def item_result(item):
 131             item_url = f'https://www.{host}/watch/{item["item_id"]}/{item["title"]}'
 132             if geoblocked:
 133                 item_url = smuggle_url(item_url, {'geo_countries': geo_countries})
 134             return self.url_result(item_url, CineverseIE)
 135
 136         season = traverse_obj(pageprops, ('seasonEpisodes', ..., 'episodes', lambda _, v: v['item_id'] and v['title']))
 137         if season:
 138             return self.playlist_result([item_result(ep) for ep in season], playlist_id=series_id,
 139                                         playlist_title=traverse_obj(pageprops, ('itemDetailsData', 'title')))
 140         return item_result(pageprops['itemDetailsData'])