diff options
Diffstat (limited to 'youtube_dl/extractor/videomore.py')
| -rw-r--r-- | youtube_dl/extractor/videomore.py | 276 |
1 files changed, 177 insertions, 99 deletions
diff --git a/youtube_dl/extractor/videomore.py b/youtube_dl/extractor/videomore.py index 04e95c66e..e0c10aa5b 100644 --- a/youtube_dl/extractor/videomore.py +++ b/youtube_dl/extractor/videomore.py @@ -4,51 +4,83 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, + compat_str, + compat_urllib_parse_urlparse, +) from ..utils import ( + ExtractorError, int_or_none, - parse_age_limit, - parse_iso8601, - xpath_text, ) +class VideomoreBaseIE(InfoExtractor): + _API_BASE_URL = 'https://more.tv/api/v3/web/' + _VALID_URL_BASE = r'https?://(?:videomore\.ru|more\.tv)/' + + def _download_page_data(self, display_id): + return self._download_json( + self._API_BASE_URL + 'PageData', display_id, query={ + 'url': '/' + display_id, + })['attributes']['response']['data'] + + def _track_url_result(self, track): + track_vod = track['trackVod'] + video_url = track_vod.get('playerLink') or track_vod['link'] + return self.url_result( + video_url, VideomoreIE.ie_key(), track_vod.get('hubId')) + + class VideomoreIE(InfoExtractor): IE_NAME = 'videomore' - _VALID_URL = r'videomore:(?P<sid>\d+)$|https?://videomore\.ru/(?:(?:embed|[^/]+/[^/]+)/|[^/]+\?.*\btrack_id=)(?P<id>\d+)(?:[/?#&]|\.(?:xml|json)|$)' + _VALID_URL = r'''(?x) + videomore:(?P<sid>\d+)$| + https?:// + (?: + videomore\.ru/ + (?: + embed| + [^/]+/[^/]+ + )/| + (?: + (?:player\.)?videomore\.ru| + siren\.more\.tv/player + )/[^/]*\?.*?\btrack_id=| + odysseus\.more.tv/player/(?P<partner_id>\d+)/ + ) + (?P<id>\d+) + (?:[/?#&]|\.(?:xml|json)|$) + ''' _TESTS = [{ 'url': 'http://videomore.ru/kino_v_detalayah/5_sezon/367617', - 'md5': '70875fbf57a1cd004709920381587185', + 'md5': '44455a346edc0d509ac5b5a5b531dc35', 'info_dict': { 'id': '367617', 'ext': 'flv', - 'title': 'В гостях Алексей Чумаков и Юлия Ковальчук', - 'description': 'В гостях – лучшие романтические комедии года, «Выживший» Иньярриту и «Стив Джобс» Дэнни Бойла.', + 'title': 'Кино в деталях 5 сезон В гостях Алексей Чумаков и Юлия Ковальчук', 'series': 'Кино в деталях', 'episode': 'В гостях Алексей Чумаков и Юлия Ковальчук', - 'episode_number': None, - 'season': 'Сезон 2015', - 'season_number': 5, - 'thumbnail': 're:^https?://.*\.jpg', + 'thumbnail': r're:^https?://.*\.jpg', 'duration': 2910, - 'age_limit': 16, 'view_count': int, + 'comment_count': int, + 'age_limit': 16, }, + 'skip': 'The video is not available for viewing.', }, { 'url': 'http://videomore.ru/embed/259974', 'info_dict': { 'id': '259974', - 'ext': 'flv', - 'title': '80 серия', - 'description': '«Медведей» ждет решающий матч. Макеев выясняет отношения со Стрельцовым. Парни узнают подробности прошлого Макеева.', + 'ext': 'mp4', + 'title': 'Молодежка 2 сезон 40 серия', 'series': 'Молодежка', - 'episode': '80 серия', - 'episode_number': 40, 'season': '2 сезон', - 'season_number': 2, - 'thumbnail': 're:^https?://.*\.jpg', - 'duration': 2809, - 'age_limit': 16, + 'episode': '40 серия', + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 2789, 'view_count': int, + 'age_limit': 16, }, 'params': { 'skip_download': True, @@ -58,14 +90,9 @@ class VideomoreIE(InfoExtractor): 'info_dict': { 'id': '341073', 'ext': 'flv', - 'title': 'Команда проиграла из-за Бакина?', - 'description': 'Молодежка 3 сезон скоро', - 'series': 'Молодежка', + 'title': 'Промо Команда проиграла из-за Бакина?', 'episode': 'Команда проиграла из-за Бакина?', - 'episode_number': None, - 'season': 'Промо', - 'season_number': 99, - 'thumbnail': 're:^https?://.*\.jpg', + 'thumbnail': r're:^https?://.*\.jpg', 'duration': 29, 'age_limit': 16, 'view_count': int, @@ -73,6 +100,7 @@ class VideomoreIE(InfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'The video is not available for viewing.', }, { 'url': 'http://videomore.ru/elki_3?track_id=364623', 'only_matching': True, @@ -91,69 +119,101 @@ class VideomoreIE(InfoExtractor): }, { 'url': 'videomore:367617', 'only_matching': True, + }, { + 'url': 'https://player.videomore.ru/?partner_id=97&track_id=736234&autoplay=0&userToken=', + 'only_matching': True, + }, { + 'url': 'https://odysseus.more.tv/player/1788/352317', + 'only_matching': True, + }, { + 'url': 'https://siren.more.tv/player/config?track_id=352317&partner_id=1788&user_token=', + 'only_matching': True, }] + _GEO_BYPASS = False @staticmethod def _extract_url(webpage): mobj = re.search( - r'<object[^>]+data=(["\'])https?://videomore.ru/player\.swf\?.*config=(?P<url>https?://videomore\.ru/(?:[^/]+/)+\d+\.xml).*\1', + r'<object[^>]+data=(["\'])https?://videomore\.ru/player\.swf\?.*config=(?P<url>https?://videomore\.ru/(?:[^/]+/)+\d+\.xml).*\1', webpage) + if not mobj: + mobj = re.search( + r'<iframe[^>]+src=([\'"])(?P<url>https?://videomore\.ru/embed/\d+)', + webpage) + if mobj: return mobj.group('url') def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('sid') or mobj.group('id') + partner_id = mobj.group('partner_id') or compat_parse_qs(compat_urllib_parse_urlparse(url).query).get('partner_id', [None])[0] or '97' - video = self._download_xml( - 'http://videomore.ru/video/tracks/%s.xml' % video_id, - video_id, 'Downloading video XML') + item = self._download_json( + 'https://siren.more.tv/player/config', video_id, query={ + 'partner_id': partner_id, + 'track_id': video_id, + })['data']['playlist']['items'][0] - video_url = xpath_text(video, './/video_url', 'video url', fatal=True) - formats = self._extract_f4m_formats(video_url, video_id, f4m_id='hds') - self._sort_formats(formats) + title = item.get('title') + series = item.get('project_name') + season = item.get('season_name') + episode = item.get('episode_name') + if not title: + title = [] + for v in (series, season, episode): + if v: + title.append(v) + title = ' '.join(title) + + streams = item.get('streams') or [] + for protocol in ('DASH', 'HLS'): + stream_url = item.get(protocol.lower() + '_url') + if stream_url: + streams.append({'protocol': protocol, 'url': stream_url}) - data = self._download_json( - 'http://videomore.ru/video/tracks/%s.json' % video_id, - video_id, 'Downloading video JSON') - - title = data.get('title') or data['project_title'] - description = data.get('description') or data.get('description_raw') - timestamp = parse_iso8601(data.get('published_at')) - duration = int_or_none(data.get('duration')) - view_count = int_or_none(data.get('views')) - age_limit = parse_age_limit(data.get('min_age')) - thumbnails = [{ - 'url': thumbnail, - } for thumbnail in data.get('big_thumbnail_urls', [])] - - series = data.get('project_title') - episode = data.get('title') - episode_number = int_or_none(data.get('episode_of_season') or None) - season = data.get('season_title') - season_number = int_or_none(data.get('season_pos') or None) + formats = [] + for stream in streams: + stream_url = stream.get('url') + if not stream_url: + continue + protocol = stream.get('protocol') + if protocol == 'DASH': + formats.extend(self._extract_mpd_formats( + stream_url, video_id, mpd_id='dash', fatal=False)) + elif protocol == 'HLS': + formats.extend(self._extract_m3u8_formats( + stream_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + elif protocol == 'MSS': + formats.extend(self._extract_ism_formats( + stream_url, video_id, ism_id='mss', fatal=False)) + + if not formats: + error = item.get('error') + if error: + if error in ('Данное видео недоступно для просмотра на территории этой страны', 'Данное видео доступно для просмотра только на территории России'): + self.raise_geo_restricted(countries=['RU']) + raise ExtractorError(error, expected=True) + self._sort_formats(formats) return { 'id': video_id, 'title': title, - 'description': description, 'series': series, - 'episode': episode, - 'episode_number': episode_number, 'season': season, - 'season_number': season_number, - 'thumbnails': thumbnails, - 'timestamp': timestamp, - 'duration': duration, - 'view_count': view_count, - 'age_limit': age_limit, + 'episode': episode, + 'thumbnail': item.get('thumbnail_url'), + 'duration': int_or_none(item.get('duration')), + 'view_count': int_or_none(item.get('views')), + 'age_limit': int_or_none(item.get('min_age')), 'formats': formats, } -class VideomoreVideoIE(InfoExtractor): +class VideomoreVideoIE(VideomoreBaseIE): IE_NAME = 'videomore:video' - _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)[/?#&]*$' + _VALID_URL = VideomoreBaseIE._VALID_URL_BASE + r'(?P<id>(?:(?:[^/]+/){2})?[^/?#&]+)(?:/*|[?#&].*?)$' _TESTS = [{ # single video with og:video:iframe 'url': 'http://videomore.ru/elki_3', @@ -162,7 +222,7 @@ class VideomoreVideoIE(InfoExtractor): 'ext': 'flv', 'title': 'Ёлки 3', 'description': '', - 'thumbnail': 're:^https?://.*\.jpg', + 'thumbnail': r're:^https?://.*\.jpg', 'duration': 5579, 'age_limit': 6, 'view_count': int, @@ -170,10 +230,25 @@ class VideomoreVideoIE(InfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'Requires logging in', }, { # season single series with og:video:iframe 'url': 'http://videomore.ru/poslednii_ment/1_sezon/14_seriya', - 'only_matching': True, + 'info_dict': { + 'id': '352317', + 'ext': 'mp4', + 'title': 'Последний мент 1 сезон 14 серия', + 'series': 'Последний мент', + 'season': '1 сезон', + 'episode': '14 серия', + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 2464, + 'age_limit': 16, + 'view_count': int, + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'http://videomore.ru/sejchas_v_seti/serii_221-240/226_vypusk', 'only_matching': True, @@ -185,7 +260,7 @@ class VideomoreVideoIE(InfoExtractor): 'ext': 'flv', 'title': '1 серия. Здравствуй, Аквавилль!', 'description': 'md5:c6003179538b5d353e7bcd5b1372b2d7', - 'thumbnail': 're:^https?://.*\.jpg', + 'thumbnail': r're:^https?://.*\.jpg', 'duration': 754, 'age_limit': 6, 'view_count': int, @@ -193,6 +268,13 @@ class VideomoreVideoIE(InfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'redirects to https://more.tv/' + }, { + 'url': 'https://videomore.ru/molodezhka/6_sezon/29_seriya?utm_so', + 'only_matching': True, + }, { + 'url': 'https://more.tv/poslednii_ment/1_sezon/14_seriya', + 'only_matching': True, }] @classmethod @@ -201,44 +283,40 @@ class VideomoreVideoIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) + return self._track_url_result(self._download_page_data(display_id)) - webpage = self._download_webpage(url, display_id) - - video_url = self._og_search_property( - 'video:iframe', webpage, 'video url', default=None) - - if not video_url: - video_id = self._search_regex( - (r'config\s*:\s*["\']https?://videomore\.ru/video/tracks/(\d+)\.xml', - r'track-id=["\'](\d+)', - r'xcnt_product_id\s*=\s*(\d+)'), webpage, 'video id') - video_url = 'videomore:%s' % video_id - - return self.url_result(video_url, VideomoreIE.ie_key()) - -class VideomoreSeasonIE(InfoExtractor): +class VideomoreSeasonIE(VideomoreBaseIE): IE_NAME = 'videomore:season' - _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)[/?#&]*$' + _VALID_URL = VideomoreBaseIE._VALID_URL_BASE + r'(?!embed)(?P<id>[^/]+/[^/?#&]+)(?:/*|[?#&].*?)$' _TESTS = [{ - 'url': 'http://videomore.ru/molodezhka/sezon_promo', + 'url': 'http://videomore.ru/molodezhka/film_o_filme', 'info_dict': { - 'id': 'molodezhka/sezon_promo', - 'title': 'Молодежка Промо', + 'id': 'molodezhka/film_o_filme', + 'title': 'Фильм о фильме', }, - 'playlist_mincount': 12, + 'playlist_mincount': 3, + }, { + 'url': 'http://videomore.ru/molodezhka/sezon_promo?utm_so', + 'only_matching': True, + }, { + 'url': 'https://more.tv/molodezhka/film_o_filme', + 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return (False if (VideomoreIE.suitable(url) or VideomoreVideoIE.suitable(url)) + else super(VideomoreSeasonIE, cls).suitable(url)) + def _real_extract(self, url): display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - title = self._og_search_title(webpage) - - entries = [ - self.url_result(item) for item in re.findall( - r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"' - % display_id, webpage)] - - return self.playlist_result(entries, display_id, title) + season = self._download_page_data(display_id) + season_id = compat_str(season['id']) + tracks = self._download_json( + self._API_BASE_URL + 'seasons/%s/tracks' % season_id, + season_id)['data'] + entries = [] + for track in tracks: + entries.append(self._track_url_result(track)) + return self.playlist_result(entries, display_id, season.get('title')) |