diff options
Diffstat (limited to 'yt_dlp/extractor/dplay.py')
| -rw-r--r-- | yt_dlp/extractor/dplay.py | 469 |
1 files changed, 327 insertions, 142 deletions
diff --git a/yt_dlp/extractor/dplay.py b/yt_dlp/extractor/dplay.py index 525c8e243..f5d6540c0 100644 --- a/yt_dlp/extractor/dplay.py +++ b/yt_dlp/extractor/dplay.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals import json +import uuid from .common import InfoExtractor from ..compat import compat_HTTPError @@ -11,12 +12,172 @@ from ..utils import ( float_or_none, int_or_none, strip_or_none, + try_get, unified_timestamp, ) -class DPlayIE(InfoExtractor): +class DPlayBaseIE(InfoExtractor): _PATH_REGEX = r'/(?P<id>[^/]+/[^/?#]+)' + _auth_token_cache = {} + + def _get_auth(self, disco_base, display_id, realm, needs_device_id=True): + key = (disco_base, realm) + st = self._get_cookies(disco_base).get('st') + token = (st and st.value) or self._auth_token_cache.get(key) + + if not token: + query = {'realm': realm} + if needs_device_id: + query['deviceId'] = uuid.uuid4().hex + token = self._download_json( + disco_base + 'token', display_id, 'Downloading token', + query=query)['data']['attributes']['token'] + + # Save cache only if cookies are not being set + if not self._get_cookies(disco_base).get('st'): + self._auth_token_cache[key] = token + + return f'Bearer {token}' + + def _process_errors(self, e, geo_countries): + info = self._parse_json(e.cause.read().decode('utf-8'), None) + error = info['errors'][0] + error_code = error.get('code') + if error_code == 'access.denied.geoblocked': + self.raise_geo_restricted(countries=geo_countries) + elif error_code in ('access.denied.missingpackage', 'invalid.token'): + raise ExtractorError( + 'This video is only available for registered users. You may want to use --cookies.', expected=True) + raise ExtractorError(info['errors'][0]['detail'], expected=True) + + def _update_disco_api_headers(self, headers, disco_base, display_id, realm): + headers['Authorization'] = self._get_auth(disco_base, display_id, realm, False) + + def _download_video_playback_info(self, disco_base, video_id, headers): + streaming = self._download_json( + disco_base + 'playback/videoPlaybackInfo/' + video_id, + video_id, headers=headers)['data']['attributes']['streaming'] + streaming_list = [] + for format_id, format_dict in streaming.items(): + streaming_list.append({ + 'type': format_id, + 'url': format_dict.get('url'), + }) + return streaming_list + + def _get_disco_api_info(self, url, display_id, disco_host, realm, country, domain=''): + geo_countries = [country.upper()] + self._initialize_geo_bypass({ + 'countries': geo_countries, + }) + disco_base = 'https://%s/' % disco_host + headers = { + 'Referer': url, + } + self._update_disco_api_headers(headers, disco_base, display_id, realm) + try: + video = self._download_json( + disco_base + 'content/videos/' + display_id, display_id, + headers=headers, query={ + 'fields[channel]': 'name', + 'fields[image]': 'height,src,width', + 'fields[show]': 'name', + 'fields[tag]': 'name', + 'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration', + 'include': 'images,primaryChannel,show,tags' + }) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: + self._process_errors(e, geo_countries) + raise + video_id = video['data']['id'] + info = video['data']['attributes'] + title = info['name'].strip() + formats = [] + subtitles = {} + try: + streaming = self._download_video_playback_info( + disco_base, video_id, headers) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + self._process_errors(e, geo_countries) + raise + for format_dict in streaming: + if not isinstance(format_dict, dict): + continue + format_url = format_dict.get('url') + if not format_url: + continue + format_id = format_dict.get('type') + ext = determine_ext(format_url) + if format_id == 'dash' or ext == 'mpd': + dash_fmts, dash_subs = self._extract_mpd_formats_and_subtitles( + format_url, display_id, mpd_id='dash', fatal=False) + formats.extend(dash_fmts) + subtitles = self._merge_subtitles(subtitles, dash_subs) + elif format_id == 'hls' or ext == 'm3u8': + m3u8_fmts, m3u8_subs = self._extract_m3u8_formats_and_subtitles( + format_url, display_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False) + formats.extend(m3u8_fmts) + subtitles = self._merge_subtitles(subtitles, m3u8_subs) + else: + formats.append({ + 'url': format_url, + 'format_id': format_id, + }) + self._sort_formats(formats) + + creator = series = None + tags = [] + thumbnails = [] + included = video.get('included') or [] + if isinstance(included, list): + for e in included: + attributes = e.get('attributes') + if not attributes: + continue + e_type = e.get('type') + if e_type == 'channel': + creator = attributes.get('name') + elif e_type == 'image': + src = attributes.get('src') + if src: + thumbnails.append({ + 'url': src, + 'width': int_or_none(attributes.get('width')), + 'height': int_or_none(attributes.get('height')), + }) + if e_type == 'show': + series = attributes.get('name') + elif e_type == 'tag': + name = attributes.get('name') + if name: + tags.append(name) + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': strip_or_none(info.get('description')), + 'duration': float_or_none(info.get('videoDuration'), 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')), + 'creator': creator, + 'tags': tags, + 'thumbnails': thumbnails, + 'formats': formats, + 'subtitles': subtitles, + 'http_headers': { + 'referer': domain, + }, + } + + +class DPlayIE(DPlayBaseIE): _VALID_URL = r'''(?x)https?:// (?P<domain> (?:www\.)?(?P<host>d @@ -26,7 +187,7 @@ class DPlayIE(InfoExtractor): ) )| (?P<subdomain_country>es|it)\.dplay\.com - )/[^/]+''' + _PATH_REGEX + )/[^/]+''' + DPlayBaseIE._PATH_REGEX _TESTS = [{ # non geo restricted, via secure api, unsigned download hls URL @@ -150,138 +311,6 @@ class DPlayIE(InfoExtractor): 'only_matching': True, }] - def _process_errors(self, e, geo_countries): - info = self._parse_json(e.cause.read().decode('utf-8'), None) - error = info['errors'][0] - error_code = error.get('code') - if error_code == 'access.denied.geoblocked': - self.raise_geo_restricted(countries=geo_countries) - elif error_code in ('access.denied.missingpackage', 'invalid.token'): - raise ExtractorError( - 'This video is only available for registered users. You may want to use --cookies.', expected=True) - raise ExtractorError(info['errors'][0]['detail'], expected=True) - - def _update_disco_api_headers(self, headers, disco_base, display_id, realm): - headers['Authorization'] = 'Bearer ' + self._download_json( - disco_base + 'token', display_id, 'Downloading token', - query={ - 'realm': realm, - })['data']['attributes']['token'] - - def _download_video_playback_info(self, disco_base, video_id, headers): - streaming = self._download_json( - disco_base + 'playback/videoPlaybackInfo/' + video_id, - video_id, headers=headers)['data']['attributes']['streaming'] - streaming_list = [] - for format_id, format_dict in streaming.items(): - streaming_list.append({ - 'type': format_id, - 'url': format_dict.get('url'), - }) - return streaming_list - - def _get_disco_api_info(self, url, display_id, disco_host, realm, country): - geo_countries = [country.upper()] - self._initialize_geo_bypass({ - 'countries': geo_countries, - }) - disco_base = 'https://%s/' % disco_host - headers = { - 'Referer': url, - } - self._update_disco_api_headers(headers, disco_base, display_id, realm) - try: - video = self._download_json( - disco_base + 'content/videos/' + display_id, display_id, - headers=headers, query={ - 'fields[channel]': 'name', - 'fields[image]': 'height,src,width', - 'fields[show]': 'name', - 'fields[tag]': 'name', - 'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration', - 'include': 'images,primaryChannel,show,tags' - }) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: - self._process_errors(e, geo_countries) - raise - video_id = video['data']['id'] - info = video['data']['attributes'] - title = info['name'].strip() - formats = [] - try: - streaming = self._download_video_playback_info( - disco_base, video_id, headers) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - self._process_errors(e, geo_countries) - raise - for format_dict in streaming: - if not isinstance(format_dict, dict): - continue - format_url = format_dict.get('url') - if not format_url: - continue - format_id = format_dict.get('type') - 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) - - creator = series = None - tags = [] - thumbnails = [] - included = video.get('included') or [] - if isinstance(included, list): - for e in included: - attributes = e.get('attributes') - if not attributes: - continue - e_type = e.get('type') - if e_type == 'channel': - creator = attributes.get('name') - elif e_type == 'image': - src = attributes.get('src') - if src: - thumbnails.append({ - 'url': src, - 'width': int_or_none(attributes.get('width')), - 'height': int_or_none(attributes.get('height')), - }) - if e_type == 'show': - series = attributes.get('name') - elif e_type == 'tag': - name = attributes.get('name') - if name: - tags.append(name) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': strip_or_none(info.get('description')), - 'duration': float_or_none(info.get('videoDuration'), 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')), - 'creator': creator, - 'tags': tags, - 'thumbnails': thumbnails, - 'formats': formats, - } - def _real_extract(self, url): mobj = self._match_valid_url(url) display_id = mobj.group('id') @@ -289,11 +318,11 @@ class DPlayIE(InfoExtractor): country = mobj.group('country') or mobj.group('subdomain_country') or mobj.group('plus_country') host = 'disco-api.' + domain if domain[0] == 'd' else 'eu2-prod.disco-api.com' return self._get_disco_api_info( - url, display_id, host, 'dplay' + country, country) + url, display_id, host, 'dplay' + country, country, domain) -class HGTVDeIE(DPlayIE): - _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayIE._PATH_REGEX +class HGTVDeIE(DPlayBaseIE): + _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayBaseIE._PATH_REGEX _TESTS = [{ 'url': 'https://de.hgtv.com/sendungen/tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette/', 'info_dict': { @@ -318,8 +347,8 @@ class HGTVDeIE(DPlayIE): url, display_id, 'eu1-prod.disco-api.com', 'hgtv', 'de') -class DiscoveryPlusIE(DPlayIE): - _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?:\w{2}/)?video' + DPlayIE._PATH_REGEX +class DiscoveryPlusIE(DPlayBaseIE): + _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?:\w{2}/)?video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ 'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family', 'info_dict': { @@ -369,7 +398,7 @@ class DiscoveryPlusIE(DPlayIE): class ScienceChannelIE(DiscoveryPlusIE): - _VALID_URL = r'https?://(?:www\.)?sciencechannel\.com/video' + DPlayIE._PATH_REGEX + _VALID_URL = r'https?://(?:www\.)?sciencechannel\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ 'url': 'https://www.sciencechannel.com/video/strangest-things-science-atve-us/nazi-mystery-machine', 'info_dict': { @@ -389,7 +418,7 @@ class ScienceChannelIE(DiscoveryPlusIE): class DIYNetworkIE(DiscoveryPlusIE): - _VALID_URL = r'https?://(?:watch\.)?diynetwork\.com/video' + DPlayIE._PATH_REGEX + _VALID_URL = r'https?://(?:watch\.)?diynetwork\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ 'url': 'https://watch.diynetwork.com/video/pool-kings-diy-network/bringing-beach-life-to-texas', 'info_dict': { @@ -409,7 +438,7 @@ class DIYNetworkIE(DiscoveryPlusIE): class AnimalPlanetIE(DiscoveryPlusIE): - _VALID_URL = r'https?://(?:www\.)?animalplanet\.com/video' + DPlayIE._PATH_REGEX + _VALID_URL = r'https?://(?:www\.)?animalplanet\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ 'url': 'https://www.animalplanet.com/video/north-woods-law-animal-planet/squirrel-showdown', 'info_dict': { @@ -426,3 +455,159 @@ class AnimalPlanetIE(DiscoveryPlusIE): _PRODUCT = 'apl' _API_URL = 'us1-prod-direct.animalplanet.com' + + +class DiscoveryPlusIndiaIE(DPlayBaseIE): + _VALID_URL = r'https?://(?:www\.)?discoveryplus\.in/videos?' + DPlayBaseIE._PATH_REGEX + _TESTS = [{ + 'url': 'https://www.discoveryplus.in/videos/how-do-they-do-it/fugu-and-more?seasonId=8&type=EPISODE', + 'info_dict': { + 'id': '27104', + 'ext': 'mp4', + 'display_id': 'how-do-they-do-it/fugu-and-more', + 'title': 'Fugu and More', + 'description': 'The Japanese catch, prepare and eat the deadliest fish on the planet.', + 'duration': 1319, + 'timestamp': 1582309800, + 'upload_date': '20200221', + 'series': 'How Do They Do It?', + 'season_number': 8, + 'episode_number': 2, + 'creator': 'Discovery Channel', + }, + 'params': { + 'skip_download': True, + } + }] + + def _update_disco_api_headers(self, headers, disco_base, display_id, realm): + headers.update({ + 'x-disco-params': 'realm=%s' % realm, + 'x-disco-client': 'WEB:UNKNOWN:dplus-india:17.0.0', + 'Authorization': self._get_auth(disco_base, display_id, realm), + }) + + def _download_video_playback_info(self, disco_base, video_id, headers): + return self._download_json( + disco_base + 'playback/v3/videoPlaybackInfo', + video_id, headers=headers, data=json.dumps({ + 'deviceInfo': { + 'adBlocker': False, + }, + 'videoId': video_id, + }).encode('utf-8'))['data']['attributes']['streaming'] + + def _real_extract(self, url): + display_id = self._match_id(url) + return self._get_disco_api_info( + url, display_id, 'ap2-prod-direct.discoveryplus.in', 'dplusindia', 'in', 'https://www.discoveryplus.in/') + + +class DiscoveryNetworksDeIE(DPlayBaseIE): + _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:tlc|dmax)\.de|dplay\.co\.uk)/(?:programme|show|sendungen)/(?P<programme>[^/]+)/(?:video/)?(?P<alternate_id>[^/]+)' + + _TESTS = [{ + 'url': 'https://www.tlc.de/programme/breaking-amish/video/die-welt-da-drauen/DCB331270001100', + 'info_dict': { + 'id': '78867', + 'ext': 'mp4', + 'title': 'Die Welt da draußen', + 'description': 'md5:61033c12b73286e409d99a41742ef608', + 'timestamp': 1554069600, + 'upload_date': '20190331', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.dmax.de/programme/dmax-highlights/video/tuning-star-sidney-hoffmann-exklusiv-bei-dmax/191023082312316', + 'only_matching': True, + }, { + 'url': 'https://www.dplay.co.uk/show/ghost-adventures/video/hotel-leger-103620/EHD_280313B', + 'only_matching': True, + }, { + 'url': 'https://tlc.de/sendungen/breaking-amish/die-welt-da-drauen/', + 'only_matching': True, + }] + + def _real_extract(self, url): + domain, programme, alternate_id = self._match_valid_url(url).groups() + country = 'GB' if domain == 'dplay.co.uk' else 'DE' + realm = 'questuk' if country == 'GB' else domain.replace('.', '') + return self._get_disco_api_info( + url, '%s/%s' % (programme, alternate_id), + 'sonic-eu1-prod.disco-api.com', realm, country) + + +class DiscoveryPlusShowBaseIE(DPlayBaseIE): + + def _entries(self, show_name): + headers = { + 'x-disco-client': self._X_CLIENT, + 'x-disco-params': f'realm={self._REALM}', + 'referer': self._DOMAIN, + 'Authentication': self._get_auth(self._BASE_API, None, self._REALM), + } + show_json = self._download_json( + f'{self._BASE_API}cms/routes/{self._SHOW_STR}/{show_name}?include=default', + video_id=show_name, headers=headers)['included'][self._INDEX]['attributes']['component'] + show_id = show_json['mandatoryParams'].split('=')[-1] + season_url = self._BASE_API + 'content/videos?sort=episodeNumber&filter[seasonNumber]={}&filter[show.id]={}&page[size]=100&page[number]={}' + for season in show_json['filters'][0]['options']: + season_id = season['id'] + total_pages, page_num = 1, 0 + while page_num < total_pages: + season_json = self._download_json( + season_url.format(season_id, show_id, str(page_num + 1)), show_name, headers=headers, + note='Downloading season %s JSON metadata%s' % (season_id, ' page %d' % page_num if page_num else '')) + if page_num == 0: + total_pages = try_get(season_json, lambda x: x['meta']['totalPages'], int) or 1 + episodes_json = season_json['data'] + for episode in episodes_json: + video_id = episode['attributes']['path'] + yield self.url_result( + '%svideos/%s' % (self._DOMAIN, video_id), + ie=self._VIDEO_IE.ie_key(), video_id=video_id) + page_num += 1 + + def _real_extract(self, url): + show_name = self._match_valid_url(url).group('show_name') + return self.playlist_result(self._entries(show_name), playlist_id=show_name) + + +class DiscoveryPlusItalyShowIE(DiscoveryPlusShowBaseIE): + _VALID_URL = r'https?://(?:www\.)?discoveryplus\.it/programmi/(?P<show_name>[^/]+)/?(?:[?#]|$)' + _TESTS = [{ + 'url': 'https://www.discoveryplus.it/programmi/deal-with-it-stai-al-gioco', + 'playlist_mincount': 168, + 'info_dict': { + 'id': 'deal-with-it-stai-al-gioco', + }, + }] + + _BASE_API = 'https://disco-api.discoveryplus.it/' + _DOMAIN = 'https://www.discoveryplus.it/' + _X_CLIENT = 'WEB:UNKNOWN:dplay-client:2.6.0' + _REALM = 'dplayit' + _SHOW_STR = 'programmi' + _INDEX = 1 + _VIDEO_IE = DPlayIE + + +class DiscoveryPlusIndiaShowIE(DiscoveryPlusShowBaseIE): + _VALID_URL = r'https?://(?:www\.)?discoveryplus\.in/show/(?P<show_name>[^/]+)/?(?:[?#]|$)' + _TESTS = [{ + 'url': 'https://www.discoveryplus.in/show/how-do-they-do-it', + 'playlist_mincount': 140, + 'info_dict': { + 'id': 'how-do-they-do-it', + }, + }] + + _BASE_API = 'https://ap2-prod-direct.discoveryplus.in/' + _DOMAIN = 'https://www.discoveryplus.in/' + _X_CLIENT = 'WEB:UNKNOWN:dplus-india:prod' + _REALM = 'dplusindia' + _SHOW_STR = 'show' + _INDEX = 4 + _VIDEO_IE = DiscoveryPlusIndiaIE |