diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index a56a7c52f..c68c1d849 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -848,14 +848,13 @@ from .nowness import ( from .noz import NozIE from .npo import ( AndereTijdenIE, + BNNVaraIE, NPOIE, - NPOLiveIE, - NPORadioIE, - NPORadioFragmentIE, + ONIE, SchoolTVIE, HetKlokhuisIE, VPROIE, - WNLIE, + ZAPPIE, ) from .npr import NprIE from .nrk import ( diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index e525ad928..4dbab16ab 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -1,767 +1,331 @@ +# coding: utf-8 from __future__ import unicode_literals +import json import re from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_str, -) -from ..utils import ( - determine_ext, - ExtractorError, - fix_xml_ampersands, - int_or_none, - merge_dicts, - orderedSet, - parse_duration, - qualities, - str_or_none, - strip_jsonp, - unified_strdate, - unified_timestamp, - url_or_none, - urlencode_postdata, -) - - -class NPOBaseIE(InfoExtractor): - def _get_token(self, video_id): - return self._download_json( - 'http://ida.omroep.nl/app.php/auth', video_id, - note='Downloading token')['token'] +from ..utils import ExtractorError -class NPOIE(NPOBaseIE): +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[^/?#]+) - ''' + IE_DESC = 'npo.nl' + _VALID_URL = r'https?://(?:www\.)?npo\.nl/start/serie/' _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', - }, - }, { - '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, - }, - }, { - 'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289', - 'md5': 'f8065e4e5a7824068ed3c7e783178f2c', + 'url': 'https://npo.nl/start/serie/zembla/seizoen-2015/wie-is-de-mol-2/', + 'md5': 'f9ce9c43cc8bc3b8138df1562b99c379', 'info_dict': { - 'id': 'VPWON_1169289', + 'description': 'Wie is de mol? (2)', + 'duration': 2439, 'ext': 'm4v', - 'title': 'Tegenlicht: Zwart geld. De toekomst komt uit Afrika', - 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea', - 'upload_date': '20130225', - 'duration': 3000, - }, - }, { - 'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706', - 'info_dict': { - 'id': 'WO_VPRO_043706', - 'ext': 'm4v', - 'title': 'De nieuwe mens - Deel 1', - 'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b', - 'duration': 4680, - }, - 'params': { - 'skip_download': True, + 'id': 'wie-is-de-mol-2', + 'thumbnail': 'https://assets-start.npo.nl/resources/2023/07/01/e723c3cf-3e42-418a-9ba5-f6dbb64b516a.jpg', + 'title': 'Wie is de mol? (2)' } }, { - # non asf in streams - 'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771', + 'url': 'https://npo.nl/start/serie/vpro-tegenlicht/seizoen-11/zwart-geld-de-toekomst-komt-uit-afrika', + 'md5': 'c84d054219c4888ed53b4ee3d01b2d93', 'info_dict': { - 'id': 'WO_NOS_762771', + 'id': 'zwart-geld-de-toekomst-komt-uit-afrika', + 'title': 'Zwart geld: de toekomst komt uit Afrika', 'ext': 'mp4', - 'title': 'Hoe gaat Europa verder na Parijs?', + 'description': 'Zwart geld: de toekomst komt uit Afrika', + 'thumbnail': 'https://assets-start.npo.nl/resources/2023/06/30/d9879593-1944-4249-990c-1561dac14d8e.jpg', + 'duration': 3000 }, - 'params': { - 'skip_download': True, - } - }, { - 'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content', - 'info_dict': { - 'id': 'VPWON_1233944', - 'ext': 'm4v', - 'title': 'Aap, poot, pies', - 'description': 'md5:c9c8005d1869ae65b858e82c01a91fde', - 'upload_date': '20150508', - 'duration': 599, - }, - '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, - } - }, { - # 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, - } - }, { - '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, }] - @classmethod - def suitable(cls, url): - return (False if any(ie.suitable(url) - for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE)) - else super(NPOIE, cls).suitable(url)) + def _get_token(self, video_id): + return self._download_json( + 'https://npo.nl/start/api/domain/player-token?productId=%s' % video_id, + video_id, + note='Downloading token')['token'] def _real_extract(self, url): - video_id = self._match_id(url) - return self._get_info(url, video_id) or self._get_old_info(video_id) - - def _get_info(self, url, video_id): - token = self._download_json( - 'https://www.npostart.nl/api/token', video_id, - 'Downloading token', headers={ - 'Referer': url, - 'X-Requested-With': 'XMLHttpRequest', - })['token'] - - player = self._download_json( - 'https://www.npostart.nl/player/%s' % video_id, video_id, - 'Downloading player JSON', data=urlencode_postdata({ - 'autoplay': 0, - 'share': 1, - 'pageUrl': url, - 'hasAdConsent': 0, - '_token': token, - })) - - player_token = player['token'] - - drm = False - format_urls = set() - formats = [] - for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'): - streams = self._download_json( - 'https://start-player.npo.nl/video/%s/streams' % video_id, - video_id, 'Downloading %s profile JSON' % profile, fatal=False, - query={ - 'profile': profile, - 'quality': 'npo', - 'tokenId': player_token, - 'streamType': 'broadcast', - }) - 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') - stream_ext = determine_ext(stream_url) - if stream_type == 'application/dash+xml' or 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': - formats.extend(self._extract_m3u8_formats( - stream_url, 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)) - else: - formats.append({ - 'url': stream_url, - }) - - if not formats: - if drm: - raise ExtractorError('This video is DRM protected.', expected=True) - return + # Remove /afspelen and/or any trailing `/`s + url = re.sub(r'/(?:afspelen)?/*$', '', url) + slug = url.split('/')[-1] + + program_metadata = self._download_json('https://npo.nl/start/api/domain/program-detail', + slug, query={'slug': slug}) + product_id = program_metadata.get('productId') + images = program_metadata.get('images') + thumbnail = None + for image in images: + thumbnail = image.get('url') + break + title = program_metadata.get('title') + descriptions = program_metadata.get('description', {}) + description = descriptions.get('long') or descriptions.get('short') or descriptions.get('brief') + duration = program_metadata.get('durationInSeconds') + + if not product_id: + raise ExtractorError('No productId found for slug: %s' % slug) + + formats = self._extract_formats_by_product_id(product_id, slug, url) - self._sort_formats(formats) - - info = { - 'id': video_id, - 'title': video_id, + return { + 'id': slug, 'formats': formats, + 'title': title or slug, + 'description': description or title or slug, + 'thumbnail': thumbnail, + 'duration': duration, } - 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 - - def _get_old_info(self, video_id): - metadata = self._download_json( - 'http://e.omroep.nl/metadata/%s' % video_id, - video_id, - # We have to remove the javascript callback - transform_source=strip_jsonp, - ) - - error = metadata.get('error') - if error: - raise ExtractorError(error, expected=True) - - # For some videos actual video id (prid) is different (e.g. for - # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698 - # video id is POMS_WNL_853698 but prid is POW_00996502) - video_id = metadata.get('prid') or video_id - - # titel is too generic in some cases so utilize aflevering_titel as well - # when available (e.g. http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html) - title = metadata['titel'] - sub_title = metadata.get('aflevering_titel') - if sub_title and sub_title != title: - title += ': %s' % sub_title - - token = self._get_token(video_id) - + def _extract_formats_by_product_id(self, product_id, slug, url=None): + token = self._get_token(product_id) formats = [] - urls = set() - - def is_legal_url(format_url): - return format_url and format_url not in urls and re.match( - r'^(?:https?:)?//', format_url) - - QUALITY_LABELS = ('Laag', 'Normaal', 'Hoog') - QUALITY_FORMATS = ('adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std') - - quality_from_label = qualities(QUALITY_LABELS) - quality_from_format_id = qualities(QUALITY_FORMATS) - items = self._download_json( - 'http://ida.omroep.nl/app.php/%s' % video_id, video_id, - 'Downloading formats JSON', query={ - 'adaptive': 'yes', - 'token': token, - })['items'][0] - for num, item in enumerate(items): - item_url = item.get('url') - if not is_legal_url(item_url): - continue - urls.add(item_url) - format_id = self._search_regex( - r'video/ida/([^/]+)', item_url, 'format id', - default=None) - - item_label = item.get('label') - - def add_format_url(format_url): - width = int_or_none(self._search_regex( - r'(\d+)[xX]\d+', format_url, 'width', default=None)) - height = int_or_none(self._search_regex( - r'\d+[xX](\d+)', format_url, 'height', default=None)) - if item_label in QUALITY_LABELS: - quality = quality_from_label(item_label) - f_id = item_label - elif item_label in QUALITY_FORMATS: - quality = quality_from_format_id(format_id) - f_id = format_id - else: - quality, f_id = [None] * 2 - formats.append({ - 'url': format_url, - 'format_id': f_id, - 'width': width, - 'height': height, - 'quality': quality, - }) - - # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706 - if item.get('contentType') in ('url', 'audio'): - add_format_url(item_url) - continue - - try: - stream_info = self._download_json( - item_url + '&type=json', video_id, - 'Downloading %s stream JSON' - % item_label or item.get('format') or format_id or num) - except ExtractorError as ee: - if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404: - error = (self._parse_json( - ee.cause.read().decode(), video_id, - fatal=False) or {}).get('errorstring') - if error: - raise ExtractorError(error, expected=True) - raise - # Stream URL instead of JSON, example: npo:LI_NL1_4188102 - if isinstance(stream_info, compat_str): - if not stream_info.startswith('http'): - continue - video_url = stream_info - # JSON - else: - video_url = stream_info.get('url') - if not video_url or 'vodnotavailable.' in video_url or video_url in urls: - continue - urls.add(video_url) - if determine_ext(video_url) == 'm3u8': - formats.extend(self._extract_m3u8_formats( - video_url, video_id, ext='mp4', - entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) - else: - add_format_url(video_url) - - is_live = metadata.get('medium') == 'live' - - if not is_live: - for num, stream in enumerate(metadata.get('streams', [])): - stream_url = stream.get('url') - if not is_legal_url(stream_url): - continue - urls.add(stream_url) - # smooth streaming is not supported - stream_type = stream.get('type', '').lower() - if stream_type in ['ss', 'ms']: - continue - if stream_type == 'hds': - f4m_formats = self._extract_f4m_formats( - stream_url, video_id, fatal=False) - # f4m downloader downloads only piece of live stream - for f4m_format in f4m_formats: - f4m_format['preference'] = -1 - formats.extend(f4m_formats) - elif stream_type == 'hls': - formats.extend(self._extract_m3u8_formats( - stream_url, video_id, ext='mp4', fatal=False)) - # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706 - elif '.asf' in stream_url: - asx = self._download_xml( - stream_url, video_id, - 'Downloading stream %d ASX playlist' % num, - transform_source=fix_xml_ampersands, fatal=False) - if not asx: - continue - ref = asx.find('./ENTRY/Ref') - if ref is None: - continue - video_url = ref.get('href') - if not video_url or video_url in urls: - continue - urls.add(video_url) - formats.append({ - 'url': video_url, - 'ext': stream.get('formaat', 'asf'), - 'quality': stream.get('kwaliteit'), - 'preference': -10, - }) - else: - formats.append({ - 'url': stream_url, - 'quality': stream.get('kwaliteit'), - }) - - self._sort_formats(formats) - - subtitles = {} - if metadata.get('tt888') == 'ja': - subtitles['nl'] = [{ - 'ext': 'vtt', - 'url': 'http://tt888.omroep.nl/tt888/%s' % video_id, - }] + for profile in ( + 'dash', + # 'hls' is available too, but implementing it doesn't add much + # As far as I know 'dash' is always available + ): + stream_link = self._download_json( + 'https://prod.npoplayer.nl/stream-link', video_id=slug, + data=json.dumps({ + 'profileName': profile, + 'referrerUrl': url or '', + }).encode('utf8'), + headers={ + 'Authorization': token, + 'Content-Type': 'application/json', + }, + fatal=False, + ) + stream_url = stream_link.get('stream', {}).get('streamURL') + formats.extend(self._extract_mpd_formats(stream_url, slug, mpd_id='dash', fatal=False)) + return formats + + +class BNNVaraIE(NPOIE): + IE_NAME = 'bnnvara' + IE_DESC = 'bnnvara.nl' + _VALID_URL = r'https?://(?:www\.)?bnnvara\.nl/videos/[0-9]*' + _TESTS = [{ + 'url': 'https://www.bnnvara.nl/videos/27455', + 'md5': '392dd367877739e49b9e0a9a550b178a', + 'info_dict': { + 'id': 'VARA_101369808', + 'thumbnail': 'https://media.vara.nl/files/thumbnails/321291_custom_zembla__wie_is_de_mol_680x383.jpg', + 'title': 'Zembla - Wie is de mol?', + 'ext': 'mp4', + } + }] + + def _real_extract(self, url): + url = url.rstrip('/') + video_id = url.split('/')[-1] + + media = self._download_json('https://api.bnnvara.nl/bff/graphql', + video_id, + data=json.dumps( + { + 'operationName': 'getMedia', + 'variables': { + 'id': video_id, + 'hasAdConsent': False, + 'atInternetId': 70 + }, + 'query': 'query getMedia($id: ID!, $mediaUrl: String, $hasAdConsent: Boolean!, $atInternetId: Int) {\n player(\n id: $id\n mediaUrl: $mediaUrl\n hasAdConsent: $hasAdConsent\n atInternetId: $atInternetId\n ) {\n ... on PlayerSucces {\n brand {\n name\n slug\n broadcastsEnabled\n __typename\n }\n title\n programTitle\n pomsProductId\n broadcasters {\n name\n __typename\n }\n duration\n classifications {\n title\n imageUrl\n type\n __typename\n }\n image {\n title\n url\n __typename\n }\n cta {\n title\n url\n __typename\n }\n genres {\n name\n __typename\n }\n subtitles {\n url\n language\n __typename\n }\n sources {\n name\n url\n ratio\n __typename\n }\n type\n token\n __typename\n }\n ... on PlayerError {\n error\n __typename\n }\n __typename\n }\n}' + }).encode('utf8'), + headers={ + 'Content-Type': 'application/json', + }) + product_id = media.get('data', {}).get('player', {}).get('pomsProductId') + + formats = self._extract_formats_by_product_id(product_id, video_id) return { - 'id': video_id, - 'title': self._live_title(title) if is_live else title, - 'description': metadata.get('info'), - 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'], - 'upload_date': unified_strdate(metadata.get('gidsdatum')), - 'duration': parse_duration(metadata.get('tijdsduur')), + 'id': product_id, + 'title': media.get('data', {}).get('player', {}).get('title'), 'formats': formats, - 'subtitles': subtitles, - 'is_live': is_live, + 'thumbnail': media.get('data', {}).get('player', {}).get('image').get('url'), } -class NPOLiveIE(NPOBaseIE): - IE_NAME = 'npo.nl:live' - _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P[^/?#&]+))?' - +class ONIE(NPOIE): + IE_NAME = 'on' + IE_DESC = 'ongehoordnederland.tv' + _VALID_URL = r'https?://(?:www\.)?ongehoordnederland.tv/.*' _TESTS = [{ - 'url': 'http://www.npo.nl/live/npo-1', + 'url': 'https://ongehoordnederland.tv/2024/03/01/korte-clips/heeft-preppen-zin-betwijfel-dat-je-daar-echt-iets-aan-zult-hebben-bij-oorlog-lydia-daniel/', + 'md5': 'a85ebd50fa86fe5cbce654655f7dbb12', 'info_dict': { - 'id': 'LI_NL1_4188102', - 'display_id': 'npo-1', - 'ext': 'mp4', - 'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', - 'is_live': True, - }, - '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' - - webpage = self._download_webpage(url, display_id) + video_id = url.rstrip('/').split('/')[-1] + page, _ = self._download_webpage_handle(url, video_id) + results = re.findall("page: '(.+)'", page) + formats = [] + for result in results: + formats.extend(self._extract_formats_by_product_id(result, video_id)) - live_id = self._search_regex( - [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id') + if not formats: + raise ExtractorError('Could not find a POMS product id in the provided URL, ' + 'perhaps because all stream URLs are DRM protected.') return { - '_type': 'url_transparent', - 'url': 'npo:%s' % live_id, - 'ie_key': NPOIE.ie_key(), - 'id': live_id, - 'display_id': display_id, + 'id': video_id, + 'title': video_id, + 'formats': formats, } -class NPORadioIE(InfoExtractor): - IE_NAME = 'npo.nl:radio' - _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P[^/]+)' +class ZAPPIE(NPOIE): + IE_NAME = 'zapp' + IE_DESC = 'zapp.nl' + _VALID_URL = r'https?://(?:www\.)?zapp.nl/.*' - _TEST = { - 'url': 'http://www.npo.nl/radio/radio-1', + _TESTS = [{ + 'url': 'https://www.zapp.nl/programmas/zappsport/gemist/POMS_AT_811523', + 'md5': '9eb2d8b6f88b72b6b986ea2c26a81588', '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}$', - 'is_live': True, + 'id': 'POMS_AT_811523', + 'title': 'POMS_AT_811523', }, - 'params': { - 'skip_download': True, - } - } - - @classmethod - def suitable(cls, url): - return False if NPORadioFragmentIE.suitable(url) else super(NPORadioIE, cls).suitable(url) - - @staticmethod - def _html_get_attribute_regex(attribute): - return r'{0}\s*=\s*\'([^\']+)\''.format(attribute) + }] def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - title = self._html_search_regex( - self._html_get_attribute_regex('data-channel'), webpage, 'title') + video_id = url.rstrip('/').split('/')[-1] - stream = self._parse_json( - self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'), - video_id) - - codec = stream.get('codec') + formats = self._extract_formats_by_product_id(video_id, video_id, url=url) return { 'id': video_id, - 'url': stream['url'], - 'title': self._live_title(title), - 'acodec': codec, - 'ext': codec, - 'is_live': True, + 'title': video_id, + 'formats': formats, } -class NPORadioFragmentIE(InfoExtractor): - IE_NAME = 'npo.nl:radio:fragment' - _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P\d+)' +class SchoolTVIE(NPOIE): + IE_NAME = 'schooltv' + IE_DESC = 'schooltv.nl' + _VALID_URL = r'https?://(?:www\.)?schooltv.nl/item/.*' - _TEST = { - 'url': 'http://www.npo.nl/radio/radio-5/fragment/174356', - 'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2', + _TESTS = [{ + 'url': 'https://schooltv.nl/item/zapp-music-challenge-2015-zapp-music-challenge-2015', + 'md5': 'e9ef151c4886994e2bea23593348cb14', 'info_dict': { - 'id': '174356', - 'ext': 'mp3', - 'title': 'Jubileumconcert Willeke Alberti', + 'id': 'zapp-music-challenge-2015-zapp-music-challenge-2015', + 'title': 'Zapp Music Challenge 2015 - Alain Clark & Yaell', + 'description': "Een nummer schrijven met de super bekende soulzanger en producer Alain Clark? Dat is de uitdaging voor de dertienjarige Yaell uit Delft. En als het dan echt goed is, mag hij het ook nog eens live gaan spelen op de speelplaats bij Giel Beelen! Muziek is heel erg belangrijk in het leven van Yaell. 'Als er geen muziek zou zijn, dan zou ik heel veel niet kunnen.' Hij is dan ook altijd aan het schrijven, vaak over zijn eigen leven. Maar soms is het best lastig om die teksten te verzinnen. Vindt hij de inspiratie om een hit te maken met Alain?" }, - } + }] def _real_extract(self, url): - audio_id = self._match_id(url) + video_id = url.rstrip('/').split('/')[-1] + + # TODO Find out how we could obtain this automatically + # Otherwise this extractor might break each time SchoolTV deploys a new release + build_id = 'b7eHUzAVO7wHXCopYxQhV' - webpage = self._download_webpage(url, audio_id) + metadata_url = 'https://schooltv.nl/_next/data/' \ + + build_id \ + + '/item/' \ + + video_id + '.json' - title = self._html_search_regex( - r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id, - webpage, 'title') + metadata = self._download_json(metadata_url, + video_id).get('pageProps', {}).get('data', {}) - audio_url = self._search_regex( - r"data-streams='([^']+)'", webpage, 'audio url') + formats = self._extract_formats_by_product_id(metadata.get('poms_mid'), video_id) + + if not formats: + raise ExtractorError('Could not find a POMS product id in the provided URL, ' + 'perhaps because all stream URLs are DRM protected.') return { - 'id': audio_id, - 'url': audio_url, - 'title': title, + 'id': video_id, + 'title': metadata.get('title', '') + ' - ' + metadata.get('subtitle', ''), + 'description': metadata.get('description') or metadata.get('short_description'), + 'formats': formats, } -class NPODataMidEmbedIE(InfoExtractor): +class NTRSubsiteIE(NPOIE): 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': 'npo:%s' % video_id, - 'display_id': display_id - } + video_id = url.rstrip('/').split('/')[-1] + page, _ = self._download_webpage_handle(url, video_id) + results = re.findall(r'data-mid="(.+_.+)"', page) + formats = [] + for result in results: + formats.extend(self._extract_formats_by_product_id(result, video_id)) + break -class SchoolTVIE(NPODataMidEmbedIE): - IE_NAME = 'schooltv' - _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P[^/?#&]+)' + if not formats: + raise ExtractorError('Could not find a POMS product id in the provided URL, ' + 'perhaps because all stream URLs are DRM protected.') - _TEST = { - 'url': 'http://www.schooltv.nl/video/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 + return { + 'id': video_id, + 'title': video_id, + 'formats': formats, } - } -class HetKlokhuisIE(NPODataMidEmbedIE): +class HetKlokhuisIE(NTRSubsiteIE): IE_NAME = 'hetklokhuis' - _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P[^/?#&]+)' - - _TEST = { - 'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven', + IE_DESC = 'hetklokhuis.nl' + _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/.*' + _TESTS = [{ + 'url': 'https://hetklokhuis.nl/dossier/142/zoek-het-uit/tv-uitzending/2987/aliens', + 'md5': '4664b54ed4e05183b1e4f2f4290d551e', 'info_dict': { - 'id': 'VPWON_1260528', - 'display_id': 'Zwaartekrachtsgolven', - 'ext': 'm4v', - 'title': 'Het Klokhuis: Zwaartekrachtsgolven', - 'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48', - 'upload_date': '20170223', + 'id': 'aliens', + 'title': 'aliens', }, - 'params': { - 'skip_download': True - } - } - - -class NPOPlaylistBaseIE(NPOIE): - def _real_extract(self, url): - playlist_id = self._match_id(url) - - webpage = self._download_webpage(url, playlist_id) - - entries = [ - self.url_result('npo:%s' % 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) - - return self.playlist_result(entries, playlist_id, playlist_title) + }] -class VPROIE(NPOPlaylistBaseIE): +class VPROIE(NPOIE): 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.*?["\'][^>]*>([^<]+)') - _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', - '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', - }, - 'playlist_count': 2, - }, - { - 'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html', - 'info_dict': { - 'id': 'de-tegenprestatie', - 'title': 'De Tegenprestatie', - }, - 'playlist_count': 2, - }, { - 'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html', - '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 - }, - } - ] - - -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+' - + IE_DESC = 'vpro.nl' + _VALID_URL = r'https?://(?:www\.)?vpro.nl/.*' _TESTS = [{ - 'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515', + 'url': 'https://www.vpro.nl/programmas/tegenlicht/kijk/afleveringen/2015-2016/offline-als-luxe.html', + 'md5': 'cf302e066b5313cfaf8d5adf50d64f13', 'info_dict': { - 'id': 'vandaag-de-dag-6-mei', - 'title': 'Vandaag de Dag 6 mei', + 'id': 'offline-als-luxe.html', + 'title': 'offline-als-luxe.html', + 'ext': 'm4v', }, - 'playlist_count': 4, }] + def _real_extract(self, url): + video_id = url.rstrip('/').split('/')[-1] + page, _ = self._download_webpage_handle(url, video_id) + results = re.findall(r'data-media-id="([a-zA-Z0-9_]+)"\s', page) + formats = [] + for result in results: + formats.extend(self._extract_formats_by_product_id(result, video_id)) + break # TODO find a better solution, VPRO pages can have multiple videos embedded -class AndereTijdenIE(NPOPlaylistBaseIE): - 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=["\'](.+?)["\']' + if not formats: + raise ExtractorError('Could not find a POMS product id in the provided URL, ' + 'perhaps because all stream URLs are DRM protected.') + return { + 'id': video_id, + 'title': video_id, + 'formats': formats, + } + + +class AndereTijdenIE(NTRSubsiteIE): + IE_NAME = 'anderetijden' + IE_DESC = 'anderetijden.nl' + _VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/.*' _TESTS = [{ - 'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem', + 'url': 'https://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem', + 'md5': '3d607b16e00b459156b4ab6e163dccd7', 'info_dict': { 'id': 'Duitse-soldaten-over-de-Slag-bij-Arnhem', - 'title': 'Duitse soldaten over de Slag bij Arnhem', + 'title': 'Duitse-soldaten-over-de-Slag-bij-Arnhem', }, - 'playlist_count': 3, }]