X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/99a6f8745584b59fe0fa1f5e81f6c3667bd3fb2b..6a680aa147c68717d8224546bf1bcbb737b78ac7:/youtube_dl/extractor/dplay.py diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py index a08dace..ebf5951 100644 --- a/youtube_dl/extractor/dplay.py +++ b/youtube_dl/extractor/dplay.py @@ -21,12 +21,13 @@ from ..utils import ( unified_strdate, unified_timestamp, update_url_query, + urljoin, USER_AGENTS, ) class DPlayIE(InfoExtractor): - _VALID_URL = r'https?://(?Pwww\.(?Pdplay\.(?Pdk|se|no)))/(?:videoer/)?(?P[^/]+/[^/?#]+)' + _VALID_URL = r'https?://(?Pwww\.(?Pdplay\.(?Pdk|se|no)))/(?:video(?:er|s)/)?(?P[^/]+/[^/?#]+)' _TESTS = [{ # non geo restricted, via secure api, unsigned download hls URL @@ -89,17 +90,91 @@ class DPlayIE(InfoExtractor): 'skip_download': True, }, }, { - # geo restricted, bypassable via X-Forwarded-For + 'url': 'https://www.dplay.dk/videoer/singleliv/season-5-episode-3', 'only_matching': True, + }, { + 'url': 'https://www.dplay.se/videos/sofias-anglar/sofias-anglar-1001', + 'only_matching': True, }] + def _get_disco_api_info(self, url, display_id, disco_host, realm): + disco_base = 'https://' + disco_host + token = self._download_json( + '%s/token' % disco_base, display_id, 'Downloading token', + query={ + 'realm': realm, + })['data']['attributes']['token'] + headers = { + 'Referer': url, + 'Authorization': 'Bearer ' + token, + } + video = self._download_json( + '%s/content/videos/%s' % (disco_base, display_id), display_id, + headers=headers, query={ + 'include': 'show' + }) + video_id = video['data']['id'] + info = video['data']['attributes'] + title = info['name'] + formats = [] + for format_id, format_dict in self._download_json( + '%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id), + display_id, headers=headers)['data']['attributes']['streaming'].items(): + if not isinstance(format_dict, dict): + continue + format_url = format_dict.get('url') + if not format_url: + continue + ext = determine_ext(format_url) + if format_id == 'dash' or ext == 'mpd': + formats.extend(self._extract_mpd_formats( + format_url, display_id, mpd_id='dash', fatal=False)) + elif format_id == 'hls' or ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, display_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False)) + else: + formats.append({ + 'url': format_url, + 'format_id': format_id, + }) + self._sort_formats(formats) + + series = None + try: + included = video.get('included') + if isinstance(included, list): + show = next(e for e in included if e.get('type') == 'show') + series = try_get( + show, lambda x: x['attributes']['name'], compat_str) + except StopIteration: + pass + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': info.get('description'), + 'duration': float_or_none( + info.get('videoDuration'), scale=1000), + 'timestamp': unified_timestamp(info.get('publishStart')), + 'series': series, + 'season_number': int_or_none(info.get('seasonNumber')), + 'episode_number': int_or_none(info.get('episodeNumber')), + 'age_limit': int_or_none(info.get('minimum_age')), + 'formats': formats, + } + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) display_id = mobj.group('id') domain = mobj.group('domain') - self._initialize_geo_bypass([mobj.group('country').upper()]) + self._initialize_geo_bypass({ + 'countries': [mobj.group('country').upper()], + }) webpage = self._download_webpage(url, display_id) @@ -108,72 +183,8 @@ class DPlayIE(InfoExtractor): if not video_id: host = mobj.group('host') - disco_base = 'https://disco-api.%s' % host - self._download_json( - '%s/token' % disco_base, display_id, 'Downloading token', - query={ - 'realm': host.replace('.', ''), - }) - video = self._download_json( - '%s/content/videos/%s' % (disco_base, display_id), display_id, - headers={ - 'Referer': url, - 'x-disco-client': 'WEB:UNKNOWN:dplay-client:0.0.1', - }, query={ - 'include': 'show' - }) - video_id = video['data']['id'] - info = video['data']['attributes'] - title = info['name'] - formats = [] - for format_id, format_dict in self._download_json( - '%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id), - display_id)['data']['attributes']['streaming'].items(): - if not isinstance(format_dict, dict): - continue - format_url = format_dict.get('url') - if not format_url: - continue - ext = determine_ext(format_url) - if format_id == 'dash' or ext == 'mpd': - formats.extend(self._extract_mpd_formats( - format_url, display_id, mpd_id='dash', fatal=False)) - elif format_id == 'hls' or ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - format_url, display_id, 'mp4', - entry_protocol='m3u8_native', m3u8_id='hls', - fatal=False)) - else: - formats.append({ - 'url': format_url, - 'format_id': format_id, - }) - self._sort_formats(formats) - - series = None - try: - included = video.get('included') - if isinstance(included, list): - show = next(e for e in included if e.get('type') == 'show') - series = try_get( - show, lambda x: x['attributes']['name'], compat_str) - except StopIteration: - pass - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': info.get('description'), - 'duration': float_or_none( - info.get('videoDuration'), scale=1000), - 'timestamp': unified_timestamp(info.get('publishStart')), - 'series': series, - 'season_number': int_or_none(info.get('seasonNumber')), - 'episode_number': int_or_none(info.get('episodeNumber')), - 'age_limit': int_or_none(info.get('minimum_age')), - 'formats': formats, - } + return self._get_disco_api_info( + url, display_id, 'disco-api.' + host, host.replace('.', '')) info = self._download_json( 'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id), @@ -300,9 +311,11 @@ class DPlayItIE(InfoExtractor): if not info: info_url = self._search_regex( - r'url\s*[:=]\s*["\']((?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)', - webpage, 'info url') + (r'playback_json_url\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', + r'url\s*[:=]\s*["\'](?P(?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)'), + webpage, 'info url', group='url') + info_url = urljoin(url, info_url) video_id = info_url.rpartition('/')[-1] try: @@ -312,6 +325,8 @@ class DPlayItIE(InfoExtractor): 'dplayit_token').value, 'Referer': url, }) + if isinstance(info, compat_str): + info = self._parse_json(info, display_id) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403): info = self._parse_json(e.cause.read().decode('utf-8'), display_id) @@ -327,6 +342,7 @@ class DPlayItIE(InfoExtractor): formats = self._extract_m3u8_formats( hls_url, display_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls') + self._sort_formats(formats) series = self._html_search_regex( r'(?s)]+class=["\'].*?\bshow_title\b.*?["\'][^>]*>(.+?)',