yt_dlp/extractor/videomore.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_str,
   6 )
   7 from ..utils import (
   8     int_or_none,
   9     parse_qs,
  10 )
  11
  12
  13 class VideomoreBaseIE(InfoExtractor):
  14     _API_BASE_URL = 'https://more.tv/api/v3/web/'
  15     _VALID_URL_BASE = r'https?://(?:videomore\.ru|more\.tv)/'
  16
  17     def _download_page_data(self, display_id):
  18         return self._download_json(
  19             self._API_BASE_URL + 'PageData', display_id, query={
  20                 'url': '/' + display_id,
  21             })['attributes']['response']['data']
  22
  23     def _track_url_result(self, track):
  24         track_vod = track['trackVod']
  25         video_url = track_vod.get('playerLink') or track_vod['link']
  26         return self.url_result(
  27             video_url, VideomoreIE.ie_key(), track_vod.get('hubId'))
  28
  29
  30 class VideomoreIE(InfoExtractor):
  31     IE_NAME = 'videomore'
  32     _VALID_URL = r'''(?x)
  33                     videomore:(?P<sid>\d+)$|
  34                     https?://
  35                         (?:
  36                             videomore\.ru/
  37                             (?:
  38                                 embed|
  39                                 [^/]+/[^/]+
  40                             )/|
  41                             (?:
  42                                 (?:player\.)?videomore\.ru|
  43                                 siren\.more\.tv/player
  44                             )/[^/]*\?.*?\btrack_id=|
  45                             odysseus\.more.tv/player/(?P<partner_id>\d+)/
  46                         )
  47                         (?P<id>\d+)
  48                         (?:[/?#&]|\.(?:xml|json)|$)
  49                     '''
  50     _TESTS = [{
  51         'url': 'http://videomore.ru/kino_v_detalayah/5_sezon/367617',
  52         'md5': '44455a346edc0d509ac5b5a5b531dc35',
  53         'info_dict': {
  54             'id': '367617',
  55             'ext': 'flv',
  56             'title': 'Кино в деталях 5 сезон В гостях Алексей Чумаков и Юлия Ковальчук',
  57             'series': 'Кино в деталях',
  58             'episode': 'В гостях Алексей Чумаков и Юлия Ковальчук',
  59             'thumbnail': r're:^https?://.*\.jpg',
  60             'duration': 2910,
  61             'view_count': int,
  62             'comment_count': int,
  63             'age_limit': 16,
  64         },
  65         'skip': 'The video is not available for viewing.',
  66     }, {
  67         'url': 'http://videomore.ru/embed/259974',
  68         'info_dict': {
  69             'id': '259974',
  70             'ext': 'mp4',
  71             'title': 'Молодежка 2 сезон 40 серия',
  72             'series': 'Молодежка',
  73             'season': '2 сезон',
  74             'episode': '40 серия',
  75             'thumbnail': r're:^https?://.*\.jpg',
  76             'duration': 2789,
  77             'view_count': int,
  78             'age_limit': 16,
  79         },
  80         'params': {
  81             'skip_download': True,
  82         },
  83     }, {
  84         'url': 'http://videomore.ru/molodezhka/sezon_promo/341073',
  85         'info_dict': {
  86             'id': '341073',
  87             'ext': 'flv',
  88             'title': 'Промо Команда проиграла из-за Бакина?',
  89             'episode': 'Команда проиграла из-за Бакина?',
  90             'thumbnail': r're:^https?://.*\.jpg',
  91             'duration': 29,
  92             'age_limit': 16,
  93             'view_count': int,
  94         },
  95         'params': {
  96             'skip_download': True,
  97         },
  98         'skip': 'The video is not available for viewing.',
  99     }, {
 100         'url': 'http://videomore.ru/elki_3?track_id=364623',
 101         'only_matching': True,
 102     }, {
 103         'url': 'http://videomore.ru/embed/364623',
 104         'only_matching': True,
 105     }, {
 106         'url': 'http://videomore.ru/video/tracks/364623.xml',
 107         'only_matching': True,
 108     }, {
 109         'url': 'http://videomore.ru/video/tracks/364623.json',
 110         'only_matching': True,
 111     }, {
 112         'url': 'http://videomore.ru/video/tracks/158031/quotes/33248',
 113         'only_matching': True,
 114     }, {
 115         'url': 'videomore:367617',
 116         'only_matching': True,
 117     }, {
 118         'url': 'https://player.videomore.ru/?partner_id=97&track_id=736234&autoplay=0&userToken=',
 119         'only_matching': True,
 120     }, {
 121         'url': 'https://odysseus.more.tv/player/1788/352317',
 122         'only_matching': True,
 123     }, {
 124         'url': 'https://siren.more.tv/player/config?track_id=352317&partner_id=1788&user_token=',
 125         'only_matching': True,
 126     }]
 127     _GEO_BYPASS = False
 128
 129     @staticmethod
 130     def _extract_url(webpage):
 131         mobj = re.search(
 132             r'<object[^>]+data=(["\'])https?://videomore\.ru/player\.swf\?.*config=(?P<url>https?://videomore\.ru/(?:[^/]+/)+\d+\.xml).*\1',
 133             webpage)
 134         if not mobj:
 135             mobj = re.search(
 136                 r'<iframe[^>]+src=([\'"])(?P<url>https?://videomore\.ru/embed/\d+)',
 137                 webpage)
 138
 139         if mobj:
 140             return mobj.group('url')
 141
 142     def _real_extract(self, url):
 143         mobj = self._match_valid_url(url)
 144         video_id = mobj.group('sid') or mobj.group('id')
 145         partner_id = mobj.group('partner_id') or parse_qs(url).get('partner_id', [None])[0] or '97'
 146
 147         item = self._download_json(
 148             'https://siren.more.tv/player/config', video_id, query={
 149                 'partner_id': partner_id,
 150                 'track_id': video_id,
 151             })['data']['playlist']['items'][0]
 152
 153         title = item.get('title')
 154         series = item.get('project_name')
 155         season = item.get('season_name')
 156         episode = item.get('episode_name')
 157         if not title:
 158             title = []
 159             for v in (series, season, episode):
 160                 if v:
 161                     title.append(v)
 162             title = ' '.join(title)
 163
 164         streams = item.get('streams') or []
 165         for protocol in ('DASH', 'HLS'):
 166             stream_url = item.get(protocol.lower() + '_url')
 167             if stream_url:
 168                 streams.append({'protocol': protocol, 'url': stream_url})
 169
 170         formats = []
 171         for stream in streams:
 172             stream_url = stream.get('url')
 173             if not stream_url:
 174                 continue
 175             protocol = stream.get('protocol')
 176             if protocol == 'DASH':
 177                 formats.extend(self._extract_mpd_formats(
 178                     stream_url, video_id, mpd_id='dash', fatal=False))
 179             elif protocol == 'HLS':
 180                 formats.extend(self._extract_m3u8_formats(
 181                     stream_url, video_id, 'mp4', 'm3u8_native',
 182                     m3u8_id='hls', fatal=False))
 183             elif protocol == 'MSS':
 184                 formats.extend(self._extract_ism_formats(
 185                     stream_url, video_id, ism_id='mss', fatal=False))
 186
 187         if not formats:
 188             error = item.get('error')
 189             if error:
 190                 if error in ('Данное видео недоступно для просмотра на территории этой страны', 'Данное видео доступно для просмотра только на территории России'):
 191                     self.raise_geo_restricted(countries=['RU'], metadata_available=True)
 192                 self.raise_no_formats(error, expected=True)
 193         self._sort_formats(formats)
 194
 195         return {
 196             'id': video_id,
 197             'title': title,
 198             'series': series,
 199             'season': season,
 200             'episode': episode,
 201             'thumbnail': item.get('thumbnail_url'),
 202             'duration': int_or_none(item.get('duration')),
 203             'view_count': int_or_none(item.get('views')),
 204             'age_limit': int_or_none(item.get('min_age')),
 205             'formats': formats,
 206         }
 207
 208
 209 class VideomoreVideoIE(VideomoreBaseIE):
 210     IE_NAME = 'videomore:video'
 211     _VALID_URL = VideomoreBaseIE._VALID_URL_BASE + r'(?P<id>(?:(?:[^/]+/){2})?[^/?#&]+)(?:/*|[?#&].*?)$'
 212     _TESTS = [{
 213         # single video with og:video:iframe
 214         'url': 'http://videomore.ru/elki_3',
 215         'info_dict': {
 216             'id': '364623',
 217             'ext': 'flv',
 218             'title': 'Ёлки 3',
 219             'description': '',
 220             'thumbnail': r're:^https?://.*\.jpg',
 221             'duration': 5579,
 222             'age_limit': 6,
 223             'view_count': int,
 224         },
 225         'params': {
 226             'skip_download': True,
 227         },
 228         'skip': 'Requires logging in',
 229     }, {
 230         # season single series with og:video:iframe
 231         'url': 'http://videomore.ru/poslednii_ment/1_sezon/14_seriya',
 232         'info_dict': {
 233             'id': '352317',
 234             'ext': 'mp4',
 235             'title': 'Последний мент 1 сезон 14 серия',
 236             'series': 'Последний мент',
 237             'season': '1 сезон',
 238             'episode': '14 серия',
 239             'thumbnail': r're:^https?://.*\.jpg',
 240             'duration': 2464,
 241             'age_limit': 16,
 242             'view_count': int,
 243         },
 244         'params': {
 245             'skip_download': True,
 246         },
 247     }, {
 248         'url': 'http://videomore.ru/sejchas_v_seti/serii_221-240/226_vypusk',
 249         'only_matching': True,
 250     }, {
 251         # single video without og:video:iframe
 252         'url': 'http://videomore.ru/marin_i_ego_druzya',
 253         'info_dict': {
 254             'id': '359073',
 255             'ext': 'flv',
 256             'title': '1 серия. Здравствуй, Аквавилль!',
 257             'description': 'md5:c6003179538b5d353e7bcd5b1372b2d7',
 258             'thumbnail': r're:^https?://.*\.jpg',
 259             'duration': 754,
 260             'age_limit': 6,
 261             'view_count': int,
 262         },
 263         'params': {
 264             'skip_download': True,
 265         },
 266         'skip': 'redirects to https://more.tv/'
 267     }, {
 268         'url': 'https://videomore.ru/molodezhka/6_sezon/29_seriya?utm_so',
 269         'only_matching': True,
 270     }, {
 271         'url': 'https://more.tv/poslednii_ment/1_sezon/14_seriya',
 272         'only_matching': True,
 273     }]
 274
 275     @classmethod
 276     def suitable(cls, url):
 277         return False if VideomoreIE.suitable(url) else super(VideomoreVideoIE, cls).suitable(url)
 278
 279     def _real_extract(self, url):
 280         display_id = self._match_id(url)
 281         return self._track_url_result(self._download_page_data(display_id))
 282
 283
 284 class VideomoreSeasonIE(VideomoreBaseIE):
 285     IE_NAME = 'videomore:season'
 286     _VALID_URL = VideomoreBaseIE._VALID_URL_BASE + r'(?!embed)(?P<id>[^/]+/[^/?#&]+)(?:/*|[?#&].*?)$'
 287     _TESTS = [{
 288         'url': 'http://videomore.ru/molodezhka/film_o_filme',
 289         'info_dict': {
 290             'id': 'molodezhka/film_o_filme',
 291             'title': 'Фильм о фильме',
 292         },
 293         'playlist_mincount': 3,
 294     }, {
 295         'url': 'http://videomore.ru/molodezhka/sezon_promo?utm_so',
 296         'only_matching': True,
 297     }, {
 298         'url': 'https://more.tv/molodezhka/film_o_filme',
 299         'only_matching': True,
 300     }]
 301
 302     @classmethod
 303     def suitable(cls, url):
 304         return (False if (VideomoreIE.suitable(url) or VideomoreVideoIE.suitable(url))
 305                 else super(VideomoreSeasonIE, cls).suitable(url))
 306
 307     def _real_extract(self, url):
 308         display_id = self._match_id(url)
 309         season = self._download_page_data(display_id)
 310         season_id = compat_str(season['id'])
 311         tracks = self._download_json(
 312             self._API_BASE_URL + 'seasons/%s/tracks' % season_id,
 313             season_id)['data']
 314         entries = []
 315         for track in tracks:
 316             entries.append(self._track_url_result(track))
 317         return self.playlist_result(entries, display_id, season.get('title'))