yt_dlp/extractor/videomore.py

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