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