yt_dlp/extractor/cineverse.py

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