diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 3ab0f5efa..aa6ea13e2 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -1387,15 +1387,15 @@ ) from .noz import NozIE from .npo import ( - NPOIE, + NPO3IE, + NTRIE, VPROIE, - WNLIE, AndereTijdenIE, HetKlokhuisIE, - NPOLiveIE, - NPORadioFragmentIE, NPORadioIE, + NPOStartIE, SchoolTVIE, + ZappIE, ) from .npr import NprIE from .nrk import ( diff --git a/yt_dlp/extractor/npo.py b/yt_dlp/extractor/npo.py index 178fd98bf..31aa7be80 100644 --- a/yt_dlp/extractor/npo.py +++ b/yt_dlp/extractor/npo.py @@ -1,606 +1,438 @@ -import random +import json import re -import urllib.parse + +from yt_dlp.utils._utils import ExtractorError +from yt_dlp.utils.traversal import traverse_obj from .common import InfoExtractor from ..utils import ( determine_ext, int_or_none, - merge_dicts, orderedSet, - str_or_none, - try_call, - unified_timestamp, - url_or_none, - urlencode_postdata, ) -class NPOIE(InfoExtractor): - IE_NAME = 'npo' - IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl' - _VALID_URL = r'''(?x) - (?: - npo:| - https?:// - (?:www\.)? - (?: - npo\.nl/(?:[^/]+/)*| - (?:ntr|npostart)\.nl/(?:[^/]+/){2,}| - omroepwnl\.nl/video/fragment/[^/]+__| - (?:zapp|npo3)\.nl/(?:[^/]+/){2,} - ) - ) - (?P[^/?#]+) - ''' +class NPOBaseIE(InfoExtractor): + def _extract_product_id_information(self, product_id): + token = self._download_json( + f'https://npo.nl/start/api/domain/player-token?productId={product_id}', product_id, + 'Downloading token')['token'] + return self._extract_info_from_token(product_id, token) - _TESTS = [{ - 'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719', - 'md5': '4b3f9c429157ec4775f2c9cb7b911016', - 'info_dict': { - 'id': 'VPWON_1220719', - 'ext': 'm4v', - 'title': 'Nieuwsuur', - 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.', - 'upload_date': '20140622', - }, - 'skip': 'Video was removed', - }, { - 'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800', - 'md5': 'da50a5787dbfc1603c4ad80f31c5120b', - 'info_dict': { - 'id': 'VARA_101191800', - 'ext': 'm4v', - 'title': 'De Mega Mike & Mega Thomas show: The best of.', - 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4', - 'upload_date': '20090227', - 'duration': 2400, - }, - 'skip': 'Video was removed', - }, { - 'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289', - 'md5': '1b279c0547f6b270e014c576415268c5', - 'info_dict': { - 'id': 'VPWON_1169289', - 'ext': 'mp4', - 'title': 'Zwart geld: de toekomst komt uit Afrika', - 'description': 'md5:dffaf3d628a9c36f78ca48d834246261', - 'upload_date': '20130225', - 'duration': 3000, - 'creator': 'NED2', - 'series': 'Tegenlicht', - 'timestamp': 1361822340, - 'thumbnail': 'https://images.npo.nl/tile/1280x720/142854.jpg', - 'episode': 'Zwart geld: de toekomst komt uit Afrika', - 'episode_number': 18, - }, - }, { - 'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706', - 'info_dict': { - 'id': 'WO_VPRO_043706', - 'ext': 'mp4', - 'title': 'De nieuwe mens - Deel 1', - 'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b', - 'duration': 4680, - 'episode': 'De nieuwe mens - Deel 1', - 'thumbnail': 'https://images.npo.nl/tile/1280x720/6289.jpg', - 'timestamp': 1279716057, - 'series': 'De nieuwe mens - Deel 1', - 'upload_date': '20100721', - }, - 'params': { - 'skip_download': True, - }, - }, { - # non asf in streams - 'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771', - 'info_dict': { - 'id': 'WO_NOS_762771', - 'ext': 'mp4', - 'title': 'Hoe gaat Europa verder na Parijs?', - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'Video was removed', - }, { - 'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content', - 'info_dict': { - 'id': 'VPWON_1233944', - 'ext': 'mp4', - 'title': 'Aap, poot, pies', - 'description': 'md5:4b46b1b9553b4c036a04d2a532a137e6', - 'upload_date': '20150508', - 'duration': 599, - 'episode': 'Aap, poot, pies', - 'thumbnail': 'https://images.poms.omroep.nl/image/s1280/c1280x720/608118.jpg', - 'timestamp': 1431064200, - 'series': 'Aap, poot, pies', - }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698', - 'info_dict': { - 'id': 'POW_00996502', - 'ext': 'm4v', - 'title': '''"Dit is wel een 'landslide'..."''', - 'description': 'md5:f8d66d537dfb641380226e31ca57b8e8', - 'upload_date': '20150508', - 'duration': 462, - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'Video was removed', - }, { - # audio - 'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437', - 'info_dict': { - 'id': 'RBX_FUNX_6683215', - 'ext': 'mp3', - 'title': 'Jouw Stad Rotterdam', - 'description': 'md5:db251505244f097717ec59fabc372d9f', - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'Video was removed', - }, { - 'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547', - 'only_matching': True, - }, { - 'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118', - 'only_matching': True, - }, { - 'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990', - 'only_matching': True, - }, { - 'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870', - 'only_matching': True, - }, { - # live stream - 'url': 'npo:LI_NL1_4188102', - 'only_matching': True, - }, { - 'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373', - 'only_matching': True, - }, { - 'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927', - 'only_matching': True, - }, { - 'url': 'https://www.npostart.nl/broodje-gezond-ei/28-05-2018/KN_1698996', - 'only_matching': True, - }, { - 'url': 'https://npo.nl/KN_1698996', - 'only_matching': True, - }, { - 'url': 'https://www.npo3.nl/the-genius/21-11-2022/VPWON_1341105', - 'info_dict': { - 'id': 'VPWON_1341105', - 'ext': 'mp4', - 'duration': 2658, - 'series': 'The Genius', - 'description': 'md5:db02f1456939ca63f7c408f858044e94', - 'title': 'The Genius', - 'timestamp': 1669062000, - 'creator': 'NED3', - 'episode': 'The Genius', - 'thumbnail': 'https://images.npo.nl/tile/1280x720/1827650.jpg', - 'episode_number': 8, - 'upload_date': '20221121', - }, - 'params': { - 'skip_download': True, - }, - }] - - @classmethod - def suitable(cls, url): - return (False if any(ie.suitable(url) - for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE)) - else super().suitable(url)) - - def _real_extract(self, url): - video_id = self._match_id(url) - if urllib.parse.urlparse(url).netloc in ['www.ntr.nl', 'ntr.nl']: - player = self._download_json( - f'https://www.ntr.nl/ajax/player/embed/{video_id}', video_id, - 'Downloading player JSON', query={ - 'parameters[elementId]': f'npo{random.randint(0, 999)}', - 'parameters[sterReferralUrl]': url, - 'parameters[autoplay]': 0, - }) - else: - self._request_webpage( - 'https://www.npostart.nl/api/token', video_id, - 'Downloading token', headers={ - 'Referer': url, - 'X-Requested-With': 'XMLHttpRequest', - }) - player = self._download_json( - f'https://www.npostart.nl/player/{video_id}', video_id, - 'Downloading player JSON', data=urlencode_postdata({ - 'autoplay': 0, - 'share': 1, - 'pageUrl': url, - 'hasAdConsent': 0, - }), headers={ - 'x-xsrf-token': try_call(lambda: urllib.parse.unquote( - self._get_cookies('https://www.npostart.nl')['XSRF-TOKEN'].value)), - }) - - player_token = player['token'] - - drm = False - format_urls = set() + def _extract_info_from_token(self, video_id, token): + data = { + 'id': video_id, + } formats = [] - for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'): - streams = self._download_json( - f'https://start-player.npo.nl/video/{video_id}/streams', - video_id, f'Downloading {profile} profile JSON', fatal=False, - query={ - 'profile': profile, - 'quality': 'npoplus', - 'tokenId': player_token, - 'streamType': 'broadcast', - }, data=b'') # endpoint requires POST - if not streams: - continue - stream = streams.get('stream') - if not isinstance(stream, dict): - continue - stream_url = url_or_none(stream.get('src')) - if not stream_url or stream_url in format_urls: - continue - format_urls.add(stream_url) - if stream.get('protection') is not None or stream.get('keySystemOptions') is not None: - drm = True - continue - stream_type = stream.get('type') + thumbnails = [] + subtitles = {} + for profile_name in ('dash', 'hls', 'smooth'): + profile = self._download_json( + 'https://prod.npoplayer.nl/stream-link', + video_id, + f'Downloading profile {profile_name} JSON', + data=json.dumps({'profileName': profile_name}).encode(), + headers={'Authorization': token}, + fatal=False, + ) + metadata = profile.get('metadata') + if metadata is not None: + duration = metadata.get('duration') + thumbnail = metadata.get('poster') + data['title'] = metadata.get('title') + data['description'] = metadata.get('description') + data['channel_id'] = metadata.get('channel') + data['uploader_id'] = metadata.get('channel') + data['genres'] = metadata.get('genres') + if duration: + data['duration'] = duration / 1000 + if thumbnail and not any(thumb['url'] == thumbnail for thumb in thumbnails): + thumbnails.append({ + 'url': thumbnail, + }) + raw_subtitles = traverse_obj(profile, ('assets', 'subtitles')) + stream_url = traverse_obj(profile, ('stream', 'streamURL')) stream_ext = determine_ext(stream_url) - if stream_type == 'application/dash+xml' or stream_ext == 'mpd': + if stream_ext == 'mpd': formats.extend(self._extract_mpd_formats( - stream_url, video_id, mpd_id='dash', fatal=False)) - elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8': + stream_url, video_id=video_id, mpd_id='dash', fatal=False)) + elif stream_ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - stream_url, video_id, ext='mp4', + stream_url, video_id=video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) elif re.search(r'\.isml?/Manifest', stream_url): formats.extend(self._extract_ism_formats( - stream_url, video_id, ism_id='mss', fatal=False)) + stream_url, video_id=video_id, ism_id='mss', fatal=False)) else: formats.append({ 'url': stream_url, }) - - if not formats: - if not self.get_param('allow_unplayable_formats') and drm: - self.report_drm(video_id) - - info = { - 'id': video_id, - 'title': video_id, - 'formats': formats, - } - - embed_url = url_or_none(player.get('embedUrl')) - if embed_url: - webpage = self._download_webpage( - embed_url, video_id, 'Downloading embed page', fatal=False) - if webpage: - video = self._parse_json( - self._search_regex( - r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video', - default='{}'), video_id) - if video: - title = video.get('episodeTitle') - subtitles = {} - subtitles_list = video.get('subtitles') - if isinstance(subtitles_list, list): - for cc in subtitles_list: - cc_url = url_or_none(cc.get('src')) - if not cc_url: - continue - lang = str_or_none(cc.get('language')) or 'nl' - subtitles.setdefault(lang, []).append({ - 'url': cc_url, - }) - return merge_dicts({ - 'title': title, - 'description': video.get('description'), - 'thumbnail': url_or_none( - video.get('still_image_url') or video.get('orig_image_url')), - 'duration': int_or_none(video.get('duration')), - 'timestamp': unified_timestamp(video.get('broadcastDate')), - 'creator': video.get('channel'), - 'series': video.get('title'), - 'episode': title, - 'episode_number': int_or_none(video.get('episodeNumber')), - 'subtitles': subtitles, - }, info) - - return info + if (raw_subtitles): + for subtitle in raw_subtitles: + tag = subtitle.get('iso') + if tag not in subtitles: + subtitles[tag] = [] + if not any(sub['url'] == subtitle['location'] for sub in subtitles[tag]): + subtitles[tag].append({ + 'url': subtitle.get('location'), + 'name': subtitle.get('name'), + }) + data['formats'] = formats + data['subtitles'] = subtitles + data['thumbnails'] = thumbnails + return data -class NPOLiveIE(InfoExtractor): - IE_NAME = 'npo.nl:live' - _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P[^/?#&]+))?' +class NPOStartIE(NPOBaseIE): + IE_NAME = 'npo.nl:start' + _VALID_URL = r'https?://(?:www\.)?npo\.nl/start/serie/(?:[^/]+/){2}(?P[^/?#&]+)' _TESTS = [{ - 'url': 'http://www.npo.nl/live/npo-1', + 'url': 'https://npo.nl/start/serie/vpro-tegenlicht/seizoen-11/zwart-geld-de-toekomst-komt-uit-afrika/afspelen', + 'md5': '8c30593a81ac80d65b531eaf2a92ac02', 'info_dict': { - 'id': 'LI_NL1_4188102', - 'display_id': 'npo-1', + 'id': 'VPWON_1169289', 'ext': 'mp4', - 'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', - 'is_live': True, + 'title': 'Zwart geld: de toekomst komt uit Afrika', + 'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1', + 'duration': 3000, + 'uploader_id': 'NED2', + 'series': 'VPRO Tegenlicht', + 'timestamp': 1361822340, + 'thumbnail': 'https://assets-start.npo.nl/resources/2023/06/30/d9879593-1944-4249-990c-1561dac14d8e.jpg', + 'episode': 'Zwart geld: de toekomst komt uit Afrika', + 'episode_number': 18, + 'channel_id': 'NED2', + 'genres': [], + 'release_date': '20130225', + 'release_timestamp': 1361822340, + 'season': 'Season 11', + 'season_id': 'df5e2334-e07a-4301-b3d3-8e224d8c1f07', + 'season_number': 11, + 'series_id': '6727dcdf-4bd2-477c-bf96-1ead69fad6c9', + 'upload_date': '20130225', }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'http://www.npo.nl/live', - 'only_matching': True, - }, { - 'url': 'https://www.npostart.nl/live/npo-1', - 'only_matching': True, }] def _real_extract(self, url): - display_id = self._match_id(url) or 'npo-1' + slug = self._match_id(url) + metadata = self._download_json(f'https://npo.nl/start/api/domain/program-detail?slug={slug}', video_id=slug, note='Downloading program details JSON') + video_id = metadata['productId'] + data = self._extract_product_id_information(video_id) + thumbnails = [] + for image in metadata.get('images'): + thumbnails.append({ + 'id': image.get('guid'), + 'url': image.get('url'), + }) + break - webpage = self._download_webpage(url, display_id) - - live_id = self._search_regex( - [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id') - - return { - '_type': 'url_transparent', - 'url': f'npo:{live_id}', - 'ie_key': NPOIE.ie_key(), - 'id': live_id, - 'display_id': display_id, - } + data['title'] = metadata.get('title') or data.get('title') + data['episode'] = metadata.get('title') or data.get('title') + data['episode_number'] = int_or_none(metadata.get('programKey')) + data['duration'] = int_or_none(metadata.get('durationInSeconds'), default=data.get('duration')) + data['description'] = traverse_obj(metadata, ('synopsis', 'long')) or traverse_obj(metadata, ('synopsis', 'short')) or traverse_obj(metadata, ('synopsis', 'brief')) or data.get('description') + data['thumbnails'] = thumbnails + data['genres'] = metadata.get('genres') or data.get('genres') + data['series'] = traverse_obj(metadata, ('series', 'title')) + data['series_id'] = traverse_obj(metadata, ('series', 'guid')) + data['season_number'] = int_or_none(traverse_obj(metadata, ('season', 'seasonKey'))) + data['season_id'] = traverse_obj(metadata, ('season', 'guid')) + data['release_timestamp'] = int_or_none(metadata.get('firstBroadcastDate')) + data['timestamp'] = int_or_none(metadata.get('publishedDateTime')) + return data -class NPORadioIE(InfoExtractor): +class NPORadioIE(NPOBaseIE): IE_NAME = 'npo.nl:radio' - _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P[^/]+)' + _VALID_URL = r'https?://(?:www\.)?nporadio(?P\d)\.nl(?:/[^/]+)*/(?P[^/]+)?' - _TEST = { - 'url': 'http://www.npo.nl/radio/radio-1', + _TESTS = [{ + 'url': 'https://www.nporadio1.nl/', 'info_dict': { - 'id': 'radio-1', - 'ext': 'mp3', - 'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'id': 'live', + 'ext': 'mp4', + 'title': r're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'live_status': 'is_live', + 'thumbnail': r're:^https?://.*\.jpg', + 'description': 'Live programmering', 'is_live': True, }, 'params': { 'skip_download': True, }, - } - - @classmethod - def suitable(cls, url): - return False if NPORadioFragmentIE.suitable(url) else super().suitable(url) - - @staticmethod - def _html_get_attribute_regex(attribute): - return rf'{attribute}\s*=\s*\'([^\']+)\'' + }, + { + 'url': 'https://www.nporadio1.nl/nieuws/binnenland/15bcad75-22c5-4226-a3fe-d54a76175da3/utrecht-zet-rolmodellen-in-voor-bewustwording-mentale-gezondheid', + 'md5': '8ad04123febc07716f45e324d7fb792d', + 'info_dict': { + 'id': 'utrecht-zet-rolmodellen-in-voor-bewustwording-mentale-gezondheid', + 'ext': 'mp4', + 'duration': 262, + 'channel_id': 'RAD1', + 'description': 'md5:7d36b72407e757e6c748a6cdf27c7628', + 'title': 'Utrecht zet rolmodellen in voor bewustzijn mentale gezondheid ', + 'genres': ['Informatief'], + 'uploader_id': 'RAD1', + 'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2217026', + }, + }, + { + 'url': 'https://www.nporadio2.nl/fragmenten/janwillemstartop/9d35b8fb-a07b-41f9-9cc5-a9c89dd60dbb/2024-10-10-nancy-zet-zich-in-voor-daklozen-voor-mij-was-het-op-het-randje', + 'md5': '432b0e106082ffaa0e31c4549db09b0c', + 'info_dict': { + 'id': '2024-10-10-nancy-zet-zich-in-voor-daklozen-voor-mij-was-het-op-het-randje', + 'ext': 'mp4', + 'genres': ['Muziek'], + 'title': 'Nancy zet zich in voor daklozen: "Voor mij was het op het randje" ', + 'duration': 235, + 'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2216783', + 'description': 'md5:26925e8bd2c715b160cc864efa731583', + 'uploader_id': 'RAD2', + 'channel_id': 'RAD2', + }, + }, + { + 'url': 'https://www.nporadio2.nl/uitzendingen/dit-is-tannaz/9bc1ab7e-77f6-4444-986b-1cd7c25ff4bf/2024-10-11-dit-is-tannaz', + 'md5': 'a1212f4d2fe361aafcced5bcd3cf939b', + 'info_dict': { + 'id': '2024-10-11-dit-is-tannaz', + 'ext': 'mp3', + 'uploader_id': 'RAD2', + 'genres': ['Muziek'], + 'title': 'Dit is Tannaz', + 'channel_id': 'RAD2', + 'description': 'md5:3f2b5dad3e965ae7915a5f9a5a2decc5', + 'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2190854', + 'duration': 7200.026, + }, + }] def _real_extract(self, url): - video_id = self._match_id(url) + parsed = self._match_valid_url(url) + video_id = parsed.group('id') or 'live' - webpage = self._download_webpage(url, video_id) - - title = self._html_search_regex( - self._html_get_attribute_regex('data-channel'), webpage, 'title') - - stream = self._parse_json( - self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'), - video_id) - - codec = stream.get('codec') - - return { - 'id': video_id, - 'url': stream['url'], - 'title': title, - 'acodec': codec, - 'ext': codec, - 'is_live': True, - } + if video_id == 'live': + radio_number = parsed.group('n') + token_url = self._download_json(f'https://www.nporadio{radio_number}.nl/api/player/npo-radio-{radio_number}', video_id)['tokenUrl'] + else: + props = self._search_nextjs_data(self._download_webpage(url, video_id), video_id)['props']['pageProps'] + token_url = traverse_obj(props, ('article', 'content', 0, 'value', 'player', 'tokenUrl')) or traverse_obj(props, ('fragmentDetail', 'bodyContent', 0, 'payload', 'player', 'tokenUrl')) or traverse_obj(props, ('radioBroadcast', 'showAssets', 0, 'player', 'tokenUrl')) + if token_url is None: + raise ExtractorError('Token url not found') + data = self._extract_info_from_token(video_id, self._download_json(token_url, video_id, 'Downloading token JSON')['playerToken']) + data['is_live'] = video_id == 'live' + return data -class NPORadioFragmentIE(InfoExtractor): - IE_NAME = 'npo.nl:radio:fragment' - _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P\d+)' +class NPO3IE(NPOBaseIE): + IE_NAME = 'npo.nl:npo3' + _VALID_URL = r'https?://(?:www\.)?npo\.nl/npo3/(?:[^/]+/){2}(?P[^/?#&]+)' _TEST = { - 'url': 'http://www.npo.nl/radio/radio-5/fragment/174356', - 'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2', + 'url': 'https://npo.nl/npo3/vlees-smakelijk/11-10-2024/WO_KN_20222563', + 'md5': 'e0cd5b96c712edea2e7f0700d348bc98', 'info_dict': { - 'id': '174356', - 'ext': 'mp3', - 'title': 'Jubileumconcert Willeke Alberti', + 'id': 'WO_KN_20222563', + 'ext': 'mp4', + 'description': 'md5:31f5ffff8c70af1635cbb93a8205e0c4', + 'duration': 1021.994, + 'title': 'Vlees smakelijk', + 'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2215940', + 'genres': ['Human Interest', 'Reality TV'], }, } def _real_extract(self, url): - audio_id = self._match_id(url) - - webpage = self._download_webpage(url, audio_id) - - title = self._html_search_regex( - rf'href="/radio/[^/]+/fragment/{audio_id}" title="([^"]+)"', - webpage, 'title') - - audio_url = self._search_regex( - r"data-streams='([^']+)'", webpage, 'audio url') - - return { - 'id': audio_id, - 'url': audio_url, - 'title': title, - } + return self._extract_product_id_information(self._match_id(url)) -class NPODataMidEmbedIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - video_id = self._search_regex( - r'data-mid=(["\'])(?P(?:(?!\1).)+)\1', webpage, 'video_id', group='id') - return { - '_type': 'url_transparent', - 'ie_key': 'NPO', - 'url': f'npo:{video_id}', - 'display_id': display_id, - } - - -class SchoolTVIE(NPODataMidEmbedIE): +class SchoolTVIE(NPOBaseIE): IE_NAME = 'schooltv' - _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video-item/(?P[^/?#&]+)' _TEST = { - 'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/', + 'url': 'https://schooltv.nl/video-item/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam', 'info_dict': { 'id': 'WO_NTR_429477', - 'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam', - 'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?', 'ext': 'mp4', - 'description': 'md5:abfa0ff690adb73fd0297fd033aaa631', - }, - 'params': { - # Skip because of m3u8 download - 'skip_download': True, + 'duration': 51.0, + 'genres': ['Jeugd'], + 'thumbnail': 'https://images.poms.omroep.nl/image/s1080/242560', + 'title': 'Ademhaling', + 'description': 'md5:db41d874d9ebe597686dda69e892ba49', }, } + def _real_extract(self, url): + video_id = self._search_regex(r'id=([a-zA-Z0-9_]+)', self._html_search_meta(('og:video', 'og:video:secure_url'), self._download_webpage(url, self._match_id(url))), 'video id') + return self._extract_info_from_token(video_id, self._download_json(f'https://api3.schooltv.nl/player/{video_id}', video_id, 'Downloading token JSON')['data']['token']) -class HetKlokhuisIE(NPODataMidEmbedIE): + +class HetKlokhuisIE(NPOBaseIE): IE_NAME = 'hetklokhuis' - _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/(?:[^/]+/)*(?P[^/?#&]+)' _TEST = { - 'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven', + 'url': 'https://hetklokhuis.nl/dossier/142/zoek-het-uit/tv-uitzending/2987/aliens', + 'md5': '679d610017689ecc798b316b8daa34e7', 'info_dict': { - 'id': 'VPWON_1260528', - 'display_id': 'Zwaartekrachtsgolven', - 'ext': 'm4v', - 'title': 'Het Klokhuis: Zwaartekrachtsgolven', - 'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48', - 'upload_date': '20170223', - }, - 'params': { - 'skip_download': True, + 'id': 'VPWON_1225126', + 'ext': 'mp4', + 'duration': 852.27, + 'channel_id': 'NED3', + 'description': 'md5:17681c9644521344a0573e04c78912d7', + 'title': 'Aliens', + 'genres': ['Jeugd', 'Informatief'], + 'thumbnail': 'https://images.poms.omroep.nl/image/s1080/624824', + 'uploader_id': 'NED3', + 'series': 'Zoek Het Uit!', }, } + def _real_extract(self, url): + webpage = self._download_webpage(url, self._match_id(url)) + series, title = self._og_search_title(webpage).split(' - ') + video_id = self._html_search_regex(r'data-mid="([a-zA-Z0-9_]+)"', webpage, 'video id') + data = self._extract_info_from_token(video_id, self._download_json(f'https://api3.schooltv.nl/player/{video_id}', video_id, 'Downloading token JSON')['data']['token']) + data['series'] = series + data['title'] = title + return data + + +class ZappIE(NPOBaseIE): + IE_NAME = 'zapp.nl' + _VALID_URL = r'https?://(?:www\.)?zapp\.nl/programmas/(?:[^/]+/){2}(?P[^/?#&]+)' + + _TEST = { + 'url': 'https://www.zapp.nl/programmas/zappsport/gemist/POMS_AT_811523', + 'md5': 'faf6811abea03ba8a52298c97bd0146b', + 'info_dict': { + 'id': 'POMS_AT_811523', + 'ext': 'mp4', + 'genres': [], + 'uploader_id': 'NED3', + 'description': 'Kindersportprogramma waarin alle takken van sport voorbijkomen.', + 'channel_id': 'NED3', + 'thumbnail': 'https://images.poms.omroep.nl/image/s1080/586056', + 'duration': 900.0, + 'title': 'Running Team 2015 - aflevering 1', + }, + } + + def _real_extract(self, url): + return self._extract_product_id_information(self._match_id(url)) + + +class NPOPlaylistBaseIE(NPOBaseIE): + def _mid_result(self, mid, title, url): + token = self._download_token(mid, url) + data = self._extract_info_from_token(mid, token) + # The API returns the same title for every video so overwrite it with the video title + data['title'] = title + return data -class NPOPlaylistBaseIE(NPOIE): # XXX: Do not subclass from concrete IE def _real_extract(self, url): playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) - entries = [ - self.url_result(f'npo:{video_id}' if not video_id.startswith('http') else video_id) - for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage)) - ] - playlist_title = self._html_search_regex( self._PLAYLIST_TITLE_RE, webpage, 'playlist title', default=None) or self._og_search_title(webpage) + entries = [ + self._mid_result(video_id, playlist_title, url) + for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage)) + ] + return self.playlist_result(entries, playlist_id, playlist_title) class VPROIE(NPOPlaylistBaseIE): IE_NAME = 'vpro' - _VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P[^/]+)\.html' - _PLAYLIST_TITLE_RE = (r']+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)', - r']+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)') + _VALID_URL = r'https?://(?:www\.)?(?:vpro|2doc)\.nl/(?:[^/]+/)*(?P[^/.]+)' + _PLAYLIST_TITLE_RE = (r']+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)') _PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"' _TESTS = [ { - 'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html', - 'md5': 'f8065e4e5a7824068ed3c7e783178f2c', - 'info_dict': { - 'id': 'VPWON_1169289', - 'ext': 'm4v', - 'title': 'De toekomst komt uit Afrika', - 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea', - 'upload_date': '20130225', - }, - 'skip': 'Video gone', - }, - { - 'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html', + 'url': 'https://www.vpro.nl/programmas/3doc/2015/sergio-herman.html', 'info_dict': { 'id': 'sergio-herman', - 'title': 'sergio herman: fucking perfect', - }, - 'playlist_count': 2, - }, - { - # playlist with youtube embed - 'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html', - 'info_dict': { - 'id': 'education-education', - 'title': 'education education', + 'title': 'Sergio Herman: Fucking Perfect', }, 'playlist_count': 2, }, { 'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html', + 'md5': '87a4cc5a62da942ca9270e4da1d2b8b5', 'info_dict': { - 'id': 'de-tegenprestatie', + 'id': 'VPWON_1223413', + 'ext': 'mp4', 'title': 'De Tegenprestatie', + 'duration': 2992.45, + 'genres': ['Documentaire'], + 'channel_id': 'NED2', + 'description': 'Er wordt van burgers steeds meer eigen verantwoordelijkheid en zelfredzaamheid gevraagd.', + 'uploader_id': 'NED2', + 'thumbnail': 'https://images.poms.omroep.nl/image/s1080/663342', }, - 'playlist_count': 2, }, { - 'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html', + 'url': 'https://www.2doc.nl/documentaires/2018/07/het-verdriet-van-nederland.html', + 'md5': '9ae67f6bdcb16a62f99e01198674fe10', 'info_dict': { 'id': 'VARA_101375237', - 'ext': 'm4v', - 'title': 'MH17: Het verdriet van Nederland', - 'description': 'md5:09e1a37c1fdb144621e22479691a9f18', - 'upload_date': '20150716', - }, - 'params': { - # Skip because of m3u8 download - 'skip_download': True, + 'ext': 'mp4', + 'uploader_id': 'NED1', + 'channel_id': 'NED1', + 'thumbnail': 'https://images.poms.omroep.nl/image/s1080/1608566', + 'duration': 4259.63, + 'genres': ['Documentaire'], + 'title': 'Het verdriet van Nederland', + 'description': 'md5:d19b745af196f6cb98daf50ac7cb01fc', }, }, ] + def _download_token(self, mid, url): + return self._download_json('https://rs.vpro.nl/v3/api/npoplayer/token', mid, 'Downloading token JSON', data=json.dumps({'mid': mid}).encode(), headers={ + 'Content-Type': 'application/json', + 'Referer': url, + })['token'] -class WNLIE(NPOPlaylistBaseIE): - IE_NAME = 'wnl' - _VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P[^/]+)__\d+' - _PLAYLIST_TITLE_RE = r'(?s)]+class="subject"[^>]*>(.+?)' - _PLAYLIST_ENTRY_RE = r']+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+' + +class NTRIE(NPOPlaylistBaseIE): + IE_NAME = 'ntr' + _VALID_URL = r'https?://(?:www\.)?ntr\.nl/(?:[^/]+/)+(?P[^/?#&]+)' + _PLAYLIST_TITLE_RE = r']*>\s*(.+)\s*' + _PLAYLIST_ENTRY_RE = r']+class=["\']npo_wrapper["\'][^>]+data-mid=["\'](.+?)["\']' _TESTS = [{ - 'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515', + 'url': 'https://ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944', + 'md5': '5b7b45c15750c9a74f8b70ea69f0b55a', 'info_dict': { - 'id': 'vandaag-de-dag-6-mei', - 'title': 'Vandaag de Dag 6 mei', + 'id': 'VPWON_1233944', + 'ext': 'mp4', + 'duration': 599.98, + 'channel_id': 'NED3', + 'genres': ['Jeugd', 'Serie'], + 'description': 'Appie en Aisia mogen beurtelings mee met hun vader Luc, die in de dierentuin werkt.', + 'uploader_id': 'NED3', + 'title': 'Aap, poot, pies', + 'thumbnail': 'https://images.poms.omroep.nl/image/s1080/608116', }, - 'playlist_count': 4, }] + def _download_token(self, mid, url): + return self._download_json(f'https://ntr.nl/ajax/player/embed/{mid}', mid, 'Downloading token JSON')['jwt'] -class AndereTijdenIE(NPOPlaylistBaseIE): + +class AndereTijdenIE(NTRIE): IE_NAME = 'anderetijden' _VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P[^/?#&]+)' _PLAYLIST_TITLE_RE = r'(?s)]+class=["\'].*?\bpage-title\b.*?["\'][^>]*>(.+?)' - _PLAYLIST_ENTRY_RE = r']+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']' + _PLAYLIST_ENTRY_RE = r']+class=["\']episode-container\s+episode-page["\'][^>]+data-mid=["\'](.+?)["\']' _TESTS = [{ 'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',