From 29724e7b07ac35d5a82e64808699fa7879e3afd9 Mon Sep 17 00:00:00 2001 From: Bart Broere Date: Fri, 1 Mar 2024 13:24:48 +0100 Subject: [PATCH] Delete all broken extractors Re-implementing these is quicker for the cases where that's even still possible --- youtube_dl/extractor/extractors.py | 12 +- youtube_dl/extractor/npo.py | 425 +---------------------------- 2 files changed, 9 insertions(+), 428 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 29b655c94..dabcd60cb 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -847,17 +847,7 @@ from .nowness import ( NownessSeriesIE, ) from .noz import NozIE -from .npo import ( - AndereTijdenIE, - NPOIE, - NPOLiveIE, - NPORadioIE, - NPORadioFragmentIE, - SchoolTVIE, - HetKlokhuisIE, - VPROIE, - WNLIE, -) +from .npo import NPOIE from .npr import NprIE from .nrk import ( NRKIE, diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index 918768035..f1d9c87ba 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -27,45 +27,22 @@ from ..utils import ( ) -class NPOBaseIE(InfoExtractor): - 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'] - - -class NPOIE(NPOBaseIE): +class NPOIE(InfoExtractor): IE_NAME = 'npo' - # TODO find out if all hosts still work: - IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl' + IE_DESC = 'npo.nl' _VALID_URL = r'''(?x) (?: npo:| https?:// (?:www\.)? (?: - npo\.nl/(?:[^/]+/)*| - (?:ntr|npostart)\.nl/(?:[^/]+/){2,}| - omroepwnl\.nl/video/fragment/[^/]+__| - (?:zapp|npo3)\.nl/(?:[^/]+/){2,} + npo\.nl/(?:[^/]+/)* ) ) (?P[^/?#]+) ''' _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 gone', - }, { 'url': 'https://npo.nl/start/serie/zembla/seizoen-2015/wie-is-de-mol-2/', # TODO other test attributes }, { @@ -91,110 +68,13 @@ class NPOIE(NPOBaseIE): '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, - }, - 'skip': 'Video gone', - }, { - # 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 gone', - }, { - '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, - }, - 'skip': 'Video gone', - }, { - '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 gone', - }, { - # 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, - 'skip': 'Video gone', - }, { - 'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118', - 'only_matching': True, - 'skip': 'Video gone', - }, { - 'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990', - 'only_matching': True, - 'skip': 'Video gone', - }, { - 'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870', - 'only_matching': True, - 'skip': 'Video gone', - }, { - # 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) @@ -505,295 +385,6 @@ class NPOIE(NPOBaseIE): 'is_live': is_live, } - -class NPOLiveIE(NPOBaseIE): - IE_NAME = 'npo.nl:live' - _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P[^/?#&]+))?' - - _TESTS = [{ - 'url': 'http://www.npo.nl/live/npo-1', - '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}$', - 'is_live': True, - }, - 'params': { - 'skip_download': True, - } - }, { - 'url': 'http://www.npo.nl/live', - 'only_matching': True, - }, { - 'url': 'https://www.npostart.nl/live/npo-1', - 'only_matching': True, - }] - - def _real_extract(self, url): - display_id = self._match_id(url) or 'npo-1' - - webpage = self._download_webpage(url, display_id) - - live_id = self._search_regex( - [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id') - - return { - '_type': 'url_transparent', - 'url': 'npo:%s' % live_id, - 'ie_key': NPOIE.ie_key(), - 'id': live_id, - 'display_id': display_id, - } - - -class NPORadioIE(InfoExtractor): - IE_NAME = 'npo.nl:radio' - _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P[^/]+)' - - _TEST = { - 'url': 'http://www.npo.nl/radio/radio-1', - 'info_dict': { - 'id': 'radio-1', - 'ext': 'mp3', - 'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', - 'is_live': True, - }, - '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') - - 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': self._live_title(title), - 'acodec': codec, - 'ext': codec, - 'is_live': True, - } - - -class NPORadioFragmentIE(InfoExtractor): - IE_NAME = 'npo.nl:radio:fragment' - _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P\d+)' - - _TEST = { - 'url': 'http://www.npo.nl/radio/radio-5/fragment/174356', - 'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2', - 'info_dict': { - 'id': '174356', - 'ext': 'mp3', - 'title': 'Jubileumconcert Willeke Alberti', - }, - } - - def _real_extract(self, url): - audio_id = self._match_id(url) - - webpage = self._download_webpage(url, audio_id) - - title = self._html_search_regex( - r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id, - webpage, 'title') - - audio_url = self._search_regex( - r"data-streams='([^']+)'", webpage, 'audio url') - - return { - 'id': audio_id, - 'url': audio_url, - 'title': title, - } - - -class NPODataMidEmbedIE(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': 'npo:%s' % video_id, - 'display_id': display_id - } - - -class SchoolTVIE(NPODataMidEmbedIE): - IE_NAME = 'schooltv' - _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P[^/?#&]+)' - - _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 - } - } - - -class HetKlokhuisIE(NPODataMidEmbedIE): - IE_NAME = 'hetklokhuis' - _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P[^/?#&]+)' - - _TEST = { - 'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven', - 'info_dict': { - 'id': 'VPWON_1260528', - 'display_id': 'Zwaartekrachtsgolven', - 'ext': 'm4v', - 'title': 'Het Klokhuis: Zwaartekrachtsgolven', - 'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48', - 'upload_date': '20170223', - }, - '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): - 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', - }, - }, - { - 'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html', - 'info_dict': { - 'id': 'sergio-herman', - 'title': 'sergio herman: fucking perfect', - }, - 'playlist_count': 2, - 'skip': 'Video gone', - }, - { - # 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, - 'skip': 'Video gone', - }, - { - '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+' - - _TESTS = [{ - 'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515', - 'info_dict': { - 'id': 'vandaag-de-dag-6-mei', - 'title': 'Vandaag de Dag 6 mei', - }, - 'playlist_count': 4, - }] - - -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=["\'](.+?)["\']' - - _TESTS = [{ - 'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem', - 'info_dict': { - 'id': 'Duitse-soldaten-over-de-Slag-bij-Arnhem', - 'title': 'Duitse soldaten over de Slag bij Arnhem', - }, - 'playlist_count': 3, - }] - ############################################################### # Description of the new process of getting to the stream # ###############################################################