1 from __future__ import unicode_literals
5 from .common import InfoExtractor
28 class NPOBaseIE(InfoExtractor):
29 def _get_token(self, video_id):
30 return self._download_json(
31 'http://ida.omroep.nl/app.php/auth', video_id,
32 note='Downloading token')['token']
35 class NPOIE(NPOBaseIE):
37 IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl'
45 (?:ntr|npostart)\.nl/(?:[^/]+/){2,}|
46 omroepwnl\.nl/video/fragment/[^/]+__|
47 (?:zapp|npo3)\.nl/(?:[^/]+/){2,}
54 'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
55 'md5': '4b3f9c429157ec4775f2c9cb7b911016',
57 'id': 'VPWON_1220719',
60 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
61 'upload_date': '20140622',
64 'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
65 'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
67 'id': 'VARA_101191800',
69 'title': 'De Mega Mike & Mega Thomas show: The best of.',
70 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
71 'upload_date': '20090227',
75 'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
76 'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
78 'id': 'VPWON_1169289',
80 'title': 'Tegenlicht: Zwart geld. De toekomst komt uit Afrika',
81 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
82 'upload_date': '20130225',
86 'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
88 'id': 'WO_VPRO_043706',
90 'title': 'De nieuwe mens - Deel 1',
91 'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
95 'skip_download': True,
99 'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
101 'id': 'WO_NOS_762771',
103 'title': 'Hoe gaat Europa verder na Parijs?',
106 'skip_download': True,
109 'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
111 'id': 'VPWON_1233944',
113 'title': 'Aap, poot, pies',
114 'description': 'md5:c9c8005d1869ae65b858e82c01a91fde',
115 'upload_date': '20150508',
119 'skip_download': True,
122 'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
124 'id': 'POW_00996502',
126 'title': '''"Dit is wel een 'landslide'..."''',
127 'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
128 'upload_date': '20150508',
132 'skip_download': True,
136 'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437',
138 'id': 'RBX_FUNX_6683215',
140 'title': 'Jouw Stad Rotterdam',
141 'description': 'md5:db251505244f097717ec59fabc372d9f',
144 'skip_download': True,
147 'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
148 'only_matching': True,
150 'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
151 'only_matching': True,
153 'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
154 'only_matching': True,
156 'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870',
157 'only_matching': True,
160 'url': 'npo:LI_NL1_4188102',
161 'only_matching': True,
163 'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373',
164 'only_matching': True,
166 'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927',
167 'only_matching': True,
169 'url': 'https://www.npostart.nl/broodje-gezond-ei/28-05-2018/KN_1698996',
170 'only_matching': True,
172 'url': 'https://npo.nl/KN_1698996',
173 'only_matching': True,
177 def suitable(cls, url):
178 return (False if any(ie.suitable(url)
179 for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE))
180 else super(NPOIE, cls).suitable(url))
182 def _real_extract(self, url):
183 video_id = self._match_id(url)
184 return self._get_info(url, video_id) or self._get_old_info(video_id)
186 def _get_info(self, url, video_id):
187 token = self._download_json(
188 'https://www.npostart.nl/api/token', video_id,
189 'Downloading token', headers={
191 'X-Requested-With': 'XMLHttpRequest',
194 player = self._download_json(
195 'https://www.npostart.nl/player/%s' % video_id, video_id,
196 'Downloading player JSON', data=urlencode_postdata({
204 player_token = player['token']
209 for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'):
210 streams = self._download_json(
211 'https://start-player.npo.nl/video/%s/streams' % video_id,
212 video_id, 'Downloading %s profile JSON' % profile, fatal=False,
216 'tokenId': player_token,
217 'streamType': 'broadcast',
221 stream = streams.get('stream')
222 if not isinstance(stream, dict):
224 stream_url = url_or_none(stream.get('src'))
225 if not stream_url or stream_url in format_urls:
227 format_urls.add(stream_url)
228 if stream.get('protection') is not None or stream.get('keySystemOptions') is not None:
231 stream_type = stream.get('type')
232 stream_ext = determine_ext(stream_url)
233 if stream_type == 'application/dash+xml' or stream_ext == 'mpd':
234 formats.extend(self._extract_mpd_formats(
235 stream_url, video_id, mpd_id='dash', fatal=False))
236 elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8':
237 formats.extend(self._extract_m3u8_formats(
238 stream_url, video_id, ext='mp4',
239 entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
240 elif re.search(r'\.isml?/Manifest', stream_url):
241 formats.extend(self._extract_ism_formats(
242 stream_url, video_id, ism_id='mss', fatal=False))
250 raise ExtractorError('This video is DRM protected.', expected=True)
253 self._sort_formats(formats)
261 embed_url = url_or_none(player.get('embedUrl'))
263 webpage = self._download_webpage(
264 embed_url, video_id, 'Downloading embed page', fatal=False)
266 video = self._parse_json(
268 r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video',
269 default='{}'), video_id)
271 title = video.get('episodeTitle')
273 subtitles_list = video.get('subtitles')
274 if isinstance(subtitles_list, list):
275 for cc in subtitles_list:
276 cc_url = url_or_none(cc.get('src'))
279 lang = str_or_none(cc.get('language')) or 'nl'
280 subtitles.setdefault(lang, []).append({
285 'description': video.get('description'),
286 'thumbnail': url_or_none(
287 video.get('still_image_url') or video.get('orig_image_url')),
288 'duration': int_or_none(video.get('duration')),
289 'timestamp': unified_timestamp(video.get('broadcastDate')),
290 'creator': video.get('channel'),
291 'series': video.get('title'),
293 'episode_number': int_or_none(video.get('episodeNumber')),
294 'subtitles': subtitles,
299 def _get_old_info(self, video_id):
300 metadata = self._download_json(
301 'http://e.omroep.nl/metadata/%s' % video_id,
303 # We have to remove the javascript callback
304 transform_source=strip_jsonp,
307 error = metadata.get('error')
309 raise ExtractorError(error, expected=True)
311 # For some videos actual video id (prid) is different (e.g. for
312 # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698
313 # video id is POMS_WNL_853698 but prid is POW_00996502)
314 video_id = metadata.get('prid') or video_id
316 # titel is too generic in some cases so utilize aflevering_titel as well
317 # when available (e.g. http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html)
318 title = metadata['titel']
319 sub_title = metadata.get('aflevering_titel')
320 if sub_title and sub_title != title:
321 title += ': %s' % sub_title
323 token = self._get_token(video_id)
328 def is_legal_url(format_url):
329 return format_url and format_url not in urls and re.match(
330 r'^(?:https?:)?//', format_url)
332 QUALITY_LABELS = ('Laag', 'Normaal', 'Hoog')
333 QUALITY_FORMATS = ('adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std')
335 quality_from_label = qualities(QUALITY_LABELS)
336 quality_from_format_id = qualities(QUALITY_FORMATS)
337 items = self._download_json(
338 'http://ida.omroep.nl/app.php/%s' % video_id, video_id,
339 'Downloading formats JSON', query={
343 for num, item in enumerate(items):
344 item_url = item.get('url')
345 if not is_legal_url(item_url):
348 format_id = self._search_regex(
349 r'video/ida/([^/]+)', item_url, 'format id',
352 item_label = item.get('label')
354 def add_format_url(format_url):
355 width = int_or_none(self._search_regex(
356 r'(\d+)[xX]\d+', format_url, 'width', default=None))
357 height = int_or_none(self._search_regex(
358 r'\d+[xX](\d+)', format_url, 'height', default=None))
359 if item_label in QUALITY_LABELS:
360 quality = quality_from_label(item_label)
362 elif item_label in QUALITY_FORMATS:
363 quality = quality_from_format_id(format_id)
366 quality, f_id = [None] * 2
375 # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
376 if item.get('contentType') in ('url', 'audio'):
377 add_format_url(item_url)
381 stream_info = self._download_json(
382 item_url + '&type=json', video_id,
383 'Downloading %s stream JSON'
384 % item_label or item.get('format') or format_id or num)
385 except ExtractorError as ee:
386 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
387 error = (self._parse_json(
388 ee.cause.read().decode(), video_id,
389 fatal=False) or {}).get('errorstring')
391 raise ExtractorError(error, expected=True)
393 # Stream URL instead of JSON, example: npo:LI_NL1_4188102
394 if isinstance(stream_info, compat_str):
395 if not stream_info.startswith('http'):
397 video_url = stream_info
400 video_url = stream_info.get('url')
401 if not video_url or 'vodnotavailable.' in video_url or video_url in urls:
404 if determine_ext(video_url) == 'm3u8':
405 formats.extend(self._extract_m3u8_formats(
406 video_url, video_id, ext='mp4',
407 entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
409 add_format_url(video_url)
411 is_live = metadata.get('medium') == 'live'
414 for num, stream in enumerate(metadata.get('streams', [])):
415 stream_url = stream.get('url')
416 if not is_legal_url(stream_url):
419 # smooth streaming is not supported
420 stream_type = stream.get('type', '').lower()
421 if stream_type in ['ss', 'ms']:
423 if stream_type == 'hds':
424 f4m_formats = self._extract_f4m_formats(
425 stream_url, video_id, fatal=False)
426 # f4m downloader downloads only piece of live stream
427 for f4m_format in f4m_formats:
428 f4m_format['preference'] = -1
429 formats.extend(f4m_formats)
430 elif stream_type == 'hls':
431 formats.extend(self._extract_m3u8_formats(
432 stream_url, video_id, ext='mp4', fatal=False))
433 # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
434 elif '.asf' in stream_url:
435 asx = self._download_xml(
436 stream_url, video_id,
437 'Downloading stream %d ASX playlist' % num,
438 transform_source=fix_xml_ampersands, fatal=False)
441 ref = asx.find('./ENTRY/Ref')
444 video_url = ref.get('href')
445 if not video_url or video_url in urls:
450 'ext': stream.get('formaat', 'asf'),
451 'quality': stream.get('kwaliteit'),
457 'quality': stream.get('kwaliteit'),
460 self._sort_formats(formats)
463 if metadata.get('tt888') == 'ja':
466 'url': 'http://tt888.omroep.nl/tt888/%s' % video_id,
471 'title': self._live_title(title) if is_live else title,
472 'description': metadata.get('info'),
473 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
474 'upload_date': unified_strdate(metadata.get('gidsdatum')),
475 'duration': parse_duration(metadata.get('tijdsduur')),
477 'subtitles': subtitles,
482 class NPOLiveIE(NPOBaseIE):
483 IE_NAME = 'npo.nl:live'
484 _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P<id>[^/?#&]+))?'
487 'url': 'http://www.npo.nl/live/npo-1',
489 'id': 'LI_NL1_4188102',
490 'display_id': 'npo-1',
492 'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
496 'skip_download': True,
499 'url': 'http://www.npo.nl/live',
500 'only_matching': True,
502 'url': 'https://www.npostart.nl/live/npo-1',
503 'only_matching': True,
506 def _real_extract(self, url):
507 display_id = self._match_id(url) or 'npo-1'
509 webpage = self._download_webpage(url, display_id)
511 live_id = self._search_regex(
512 [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')
515 '_type': 'url_transparent',
516 'url': 'npo:%s' % live_id,
517 'ie_key': NPOIE.ie_key(),
519 'display_id': display_id,
523 class NPORadioIE(InfoExtractor):
524 IE_NAME = 'npo.nl:radio'
525 _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)'
528 'url': 'http://www.npo.nl/radio/radio-1',
532 'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
536 'skip_download': True,
541 def suitable(cls, url):
542 return False if NPORadioFragmentIE.suitable(url) else super(NPORadioIE, cls).suitable(url)
545 def _html_get_attribute_regex(attribute):
546 return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)
548 def _real_extract(self, url):
549 video_id = self._match_id(url)
551 webpage = self._download_webpage(url, video_id)
553 title = self._html_search_regex(
554 self._html_get_attribute_regex('data-channel'), webpage, 'title')
556 stream = self._parse_json(
557 self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
560 codec = stream.get('codec')
564 'url': stream['url'],
565 'title': self._live_title(title),
572 class NPORadioFragmentIE(InfoExtractor):
573 IE_NAME = 'npo.nl:radio:fragment'
574 _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
577 'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
578 'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
582 'title': 'Jubileumconcert Willeke Alberti',
586 def _real_extract(self, url):
587 audio_id = self._match_id(url)
589 webpage = self._download_webpage(url, audio_id)
591 title = self._html_search_regex(
592 r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id,
595 audio_url = self._search_regex(
596 r"data-streams='([^']+)'", webpage, 'audio url')
605 class NPODataMidEmbedIE(InfoExtractor):
606 def _real_extract(self, url):
607 display_id = self._match_id(url)
608 webpage = self._download_webpage(url, display_id)
609 video_id = self._search_regex(
610 r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
612 '_type': 'url_transparent',
614 'url': 'npo:%s' % video_id,
615 'display_id': display_id
619 class SchoolTVIE(NPODataMidEmbedIE):
621 _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
624 'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
626 'id': 'WO_NTR_429477',
627 'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
628 'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
630 'description': 'md5:abfa0ff690adb73fd0297fd033aaa631'
633 # Skip because of m3u8 download
634 'skip_download': True
639 class HetKlokhuisIE(NPODataMidEmbedIE):
640 IE_NAME = 'hetklokhuis'
641 _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
644 'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
646 'id': 'VPWON_1260528',
647 'display_id': 'Zwaartekrachtsgolven',
649 'title': 'Het Klokhuis: Zwaartekrachtsgolven',
650 'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
651 'upload_date': '20170223',
654 'skip_download': True
659 class NPOPlaylistBaseIE(NPOIE):
660 def _real_extract(self, url):
661 playlist_id = self._match_id(url)
663 webpage = self._download_webpage(url, playlist_id)
666 self.url_result('npo:%s' % video_id if not video_id.startswith('http') else video_id)
667 for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
670 playlist_title = self._html_search_regex(
671 self._PLAYLIST_TITLE_RE, webpage, 'playlist title',
672 default=None) or self._og_search_title(webpage)
674 return self.playlist_result(entries, playlist_id, playlist_title)
677 class VPROIE(NPOPlaylistBaseIE):
679 _VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
680 _PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)',
681 r'<h5[^>]+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)')
682 _PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
686 'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
687 'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
689 'id': 'VPWON_1169289',
691 'title': 'De toekomst komt uit Afrika',
692 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
693 'upload_date': '20130225',
695 'skip': 'Video gone',
698 'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
700 'id': 'sergio-herman',
701 'title': 'sergio herman: fucking perfect',
706 # playlist with youtube embed
707 'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
709 'id': 'education-education',
710 'title': 'education education',
715 'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
717 'id': 'de-tegenprestatie',
718 'title': 'De Tegenprestatie',
722 'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
724 'id': 'VARA_101375237',
726 'title': 'MH17: Het verdriet van Nederland',
727 'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
728 'upload_date': '20150716',
731 # Skip because of m3u8 download
732 'skip_download': True
738 class WNLIE(NPOPlaylistBaseIE):
740 _VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
741 _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>'
742 _PLAYLIST_ENTRY_RE = r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+'
745 'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
747 'id': 'vandaag-de-dag-6-mei',
748 'title': 'Vandaag de Dag 6 mei',
754 class AndereTijdenIE(NPOPlaylistBaseIE):
755 IE_NAME = 'anderetijden'
756 _VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P<id>[^/?#&]+)'
757 _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class=["\'].*?\bpage-title\b.*?["\'][^>]*>(.+?)</h1>'
758 _PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']'
761 'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',
763 'id': 'Duitse-soldaten-over-de-Slag-bij-Arnhem',
764 'title': 'Duitse soldaten over de Slag bij Arnhem',