1 from __future__ import unicode_literals
5 from .common import InfoExtractor
22 class NPOBaseIE(InfoExtractor):
23 def _get_token(self, video_id):
24 return self._download_json(
25 'http://ida.omroep.nl/app.php/auth', video_id,
26 note='Downloading token')['token']
29 class NPOIE(NPOBaseIE):
31 IE_DESC = 'npo.nl and ntr.nl'
38 npo\.nl/(?!(?:live|radio)/)(?:[^/]+/){2}|
39 ntr\.nl/(?:[^/]+/){2,}|
40 omroepwnl\.nl/video/fragment/[^/]+__|
48 'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
49 'md5': '4b3f9c429157ec4775f2c9cb7b911016',
51 'id': 'VPWON_1220719',
54 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
55 'upload_date': '20140622',
58 'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
59 'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
61 'id': 'VARA_101191800',
63 'title': 'De Mega Mike & Mega Thomas show: The best of.',
64 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
65 'upload_date': '20090227',
69 'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
70 'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
72 'id': 'VPWON_1169289',
74 'title': 'Tegenlicht: Zwart geld. De toekomst komt uit Afrika',
75 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
76 'upload_date': '20130225',
80 'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
82 'id': 'WO_VPRO_043706',
84 'title': 'De nieuwe mens - Deel 1',
85 'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
89 'skip_download': True,
93 'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
95 'id': 'WO_NOS_762771',
97 'title': 'Hoe gaat Europa verder na Parijs?',
100 'skip_download': True,
103 'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
105 'id': 'VPWON_1233944',
107 'title': 'Aap, poot, pies',
108 'description': 'md5:c9c8005d1869ae65b858e82c01a91fde',
109 'upload_date': '20150508',
113 'skip_download': True,
116 'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
118 'id': 'POW_00996502',
120 'title': '''"Dit is wel een 'landslide'..."''',
121 'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
122 'upload_date': '20150508',
126 'skip_download': True,
130 'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437',
132 'id': 'RBX_FUNX_6683215',
134 'title': 'Jouw Stad Rotterdam',
135 'description': 'md5:db251505244f097717ec59fabc372d9f',
138 'skip_download': True,
141 'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
142 'only_matching': True,
144 'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
145 'only_matching': True,
147 'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
148 'only_matching': True,
151 'url': 'npo:LI_NL1_4188102',
152 'only_matching': True,
154 'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373',
155 'only_matching': True,
158 def _real_extract(self, url):
159 video_id = self._match_id(url)
160 return self._get_info(video_id)
162 def _get_info(self, video_id):
163 metadata = self._download_json(
164 'http://e.omroep.nl/metadata/%s' % video_id,
166 # We have to remove the javascript callback
167 transform_source=strip_jsonp,
170 # For some videos actual video id (prid) is different (e.g. for
171 # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698
172 # video id is POMS_WNL_853698 but prid is POW_00996502)
173 video_id = metadata.get('prid') or video_id
175 # titel is too generic in some cases so utilize aflevering_titel as well
176 # when available (e.g. http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html)
177 title = metadata['titel']
178 sub_title = metadata.get('aflevering_titel')
179 if sub_title and sub_title != title:
180 title += ': %s' % sub_title
182 token = self._get_token(video_id)
187 quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
188 items = self._download_json(
189 'http://ida.omroep.nl/app.php/%s' % video_id, video_id,
190 'Downloading formats JSON', query={
194 for num, item in enumerate(items):
195 item_url = item.get('url')
196 if not item_url or item_url in urls:
199 format_id = self._search_regex(
200 r'video/ida/([^/]+)', item_url, 'format id',
203 def add_format_url(format_url):
206 'format_id': format_id,
207 'quality': quality(format_id),
210 # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
211 if item.get('contentType') in ('url', 'audio'):
212 add_format_url(item_url)
216 stream_info = self._download_json(
217 item_url + '&type=json', video_id,
218 'Downloading %s stream JSON'
219 % item.get('label') or item.get('format') or format_id or num)
220 except ExtractorError as ee:
221 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
222 error = (self._parse_json(
223 ee.cause.read().decode(), video_id,
224 fatal=False) or {}).get('errorstring')
226 raise ExtractorError(error, expected=True)
228 # Stream URL instead of JSON, example: npo:LI_NL1_4188102
229 if isinstance(stream_info, compat_str):
230 if not stream_info.startswith('http'):
232 video_url = stream_info
235 video_url = stream_info.get('url')
236 if not video_url or video_url in urls:
239 if determine_ext(video_url) == 'm3u8':
240 formats.extend(self._extract_m3u8_formats(
241 video_url, video_id, ext='mp4',
242 entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
244 add_format_url(video_url)
246 is_live = metadata.get('medium') == 'live'
249 for num, stream in enumerate(metadata.get('streams', [])):
250 stream_url = stream.get('url')
251 if not stream_url or stream_url in urls:
254 # smooth streaming is not supported
255 stream_type = stream.get('type', '').lower()
256 if stream_type in ['ss', 'ms']:
258 if stream_type == 'hds':
259 f4m_formats = self._extract_f4m_formats(
260 stream_url, video_id, fatal=False)
261 # f4m downloader downloads only piece of live stream
262 for f4m_format in f4m_formats:
263 f4m_format['preference'] = -1
264 formats.extend(f4m_formats)
265 elif stream_type == 'hls':
266 formats.extend(self._extract_m3u8_formats(
267 stream_url, video_id, ext='mp4', fatal=False))
268 # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
269 elif '.asf' in stream_url:
270 asx = self._download_xml(
271 stream_url, video_id,
272 'Downloading stream %d ASX playlist' % num,
273 transform_source=fix_xml_ampersands, fatal=False)
276 ref = asx.find('./ENTRY/Ref')
279 video_url = ref.get('href')
280 if not video_url or video_url in urls:
285 'ext': stream.get('formaat', 'asf'),
286 'quality': stream.get('kwaliteit'),
292 'quality': stream.get('kwaliteit'),
295 self._sort_formats(formats)
298 if metadata.get('tt888') == 'ja':
301 'url': 'http://tt888.omroep.nl/tt888/%s' % video_id,
306 'title': self._live_title(title) if is_live else title,
307 'description': metadata.get('info'),
308 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
309 'upload_date': unified_strdate(metadata.get('gidsdatum')),
310 'duration': parse_duration(metadata.get('tijdsduur')),
312 'subtitles': subtitles,
317 class NPOLiveIE(NPOBaseIE):
318 IE_NAME = 'npo.nl:live'
319 _VALID_URL = r'https?://(?:www\.)?npo\.nl/live(?:/(?P<id>[^/?#&]+))?'
322 'url': 'http://www.npo.nl/live/npo-1',
324 'id': 'LI_NL1_4188102',
325 'display_id': 'npo-1',
327 'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
331 'skip_download': True,
334 'url': 'http://www.npo.nl/live',
335 'only_matching': True,
338 def _real_extract(self, url):
339 display_id = self._match_id(url) or 'npo-1'
341 webpage = self._download_webpage(url, display_id)
343 live_id = self._search_regex(
344 [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')
347 '_type': 'url_transparent',
348 'url': 'npo:%s' % live_id,
349 'ie_key': NPOIE.ie_key(),
351 'display_id': display_id,
355 class NPORadioIE(InfoExtractor):
356 IE_NAME = 'npo.nl:radio'
357 _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)/?$'
360 'url': 'http://www.npo.nl/radio/radio-1',
364 'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
368 'skip_download': True,
373 def _html_get_attribute_regex(attribute):
374 return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)
376 def _real_extract(self, url):
377 video_id = self._match_id(url)
379 webpage = self._download_webpage(url, video_id)
381 title = self._html_search_regex(
382 self._html_get_attribute_regex('data-channel'), webpage, 'title')
384 stream = self._parse_json(
385 self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
388 codec = stream.get('codec')
392 'url': stream['url'],
393 'title': self._live_title(title),
400 class NPORadioFragmentIE(InfoExtractor):
401 IE_NAME = 'npo.nl:radio:fragment'
402 _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
405 'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
406 'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
410 'title': 'Jubileumconcert Willeke Alberti',
414 def _real_extract(self, url):
415 audio_id = self._match_id(url)
417 webpage = self._download_webpage(url, audio_id)
419 title = self._html_search_regex(
420 r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id,
423 audio_url = self._search_regex(
424 r"data-streams='([^']+)'", webpage, 'audio url')
433 class NPODataMidEmbedIE(InfoExtractor):
434 def _real_extract(self, url):
435 display_id = self._match_id(url)
436 webpage = self._download_webpage(url, display_id)
437 video_id = self._search_regex(
438 r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
440 '_type': 'url_transparent',
442 'url': 'npo:%s' % video_id,
443 'display_id': display_id
447 class SchoolTVIE(NPODataMidEmbedIE):
449 _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
452 'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
454 'id': 'WO_NTR_429477',
455 'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
456 'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
458 'description': 'md5:abfa0ff690adb73fd0297fd033aaa631'
461 # Skip because of m3u8 download
462 'skip_download': True
467 class HetKlokhuisIE(NPODataMidEmbedIE):
468 IE_NAME = 'hetklokhuis'
469 _VALID_URL = r'https?://(?:www\.)?hetklokhuis.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
472 'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
474 'id': 'VPWON_1260528',
475 'display_id': 'Zwaartekrachtsgolven',
477 'title': 'Het Klokhuis: Zwaartekrachtsgolven',
478 'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
479 'upload_date': '20170223',
482 'skip_download': True
487 class NPOPlaylistBaseIE(NPOIE):
488 def _real_extract(self, url):
489 playlist_id = self._match_id(url)
491 webpage = self._download_webpage(url, playlist_id)
494 self.url_result('npo:%s' % video_id if not video_id.startswith('http') else video_id)
495 for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
498 playlist_title = self._html_search_regex(
499 self._PLAYLIST_TITLE_RE, webpage, 'playlist title',
500 default=None) or self._og_search_title(webpage)
502 return self.playlist_result(entries, playlist_id, playlist_title)
505 class VPROIE(NPOPlaylistBaseIE):
507 _VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
508 _PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)',
509 r'<h5[^>]+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)')
510 _PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
514 'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
515 'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
517 'id': 'VPWON_1169289',
519 'title': 'De toekomst komt uit Afrika',
520 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
521 'upload_date': '20130225',
523 'skip': 'Video gone',
526 'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
528 'id': 'sergio-herman',
529 'title': 'sergio herman: fucking perfect',
534 # playlist with youtube embed
535 'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
537 'id': 'education-education',
538 'title': 'education education',
543 'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
545 'id': 'de-tegenprestatie',
546 'title': 'De Tegenprestatie',
550 'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
552 'id': 'VARA_101375237',
554 'title': 'MH17: Het verdriet van Nederland',
555 'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
556 'upload_date': '20150716',
559 # Skip because of m3u8 download
560 'skip_download': True
566 class WNLIE(NPOPlaylistBaseIE):
568 _VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
569 _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>'
570 _PLAYLIST_ENTRY_RE = r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+'
573 'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
575 'id': 'vandaag-de-dag-6-mei',
576 'title': 'Vandaag de Dag 6 mei',
582 class AndereTijdenIE(NPOPlaylistBaseIE):
583 IE_NAME = 'anderetijden'
584 _VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P<id>[^/?#&]+)'
585 _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class=["\'].*?\bpage-title\b.*?["\'][^>]*>(.+?)</h1>'
586 _PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']'
589 'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',
591 'id': 'Duitse-soldaten-over-de-Slag-bij-Arnhem',
592 'title': 'Duitse soldaten over de Slag bij Arnhem',