1 from __future__ import unicode_literals
5 from .common import InfoExtractor
15 class NPOBaseIE(InfoExtractor):
16 def _get_token(self, video_id):
17 token_page = self._download_webpage(
18 'http://ida.omroep.nl/npoplayer/i.js',
19 video_id, note='Downloading token')
20 token = self._search_regex(
21 r'npoplayer\.token = "(.+?)"', token_page, 'token')
22 # Decryption algorithm extracted from http://npoplayer.omroep.nl/csjs/npoplayer-min.js
25 for i in range(5, len(token_l) - 4):
26 if token_l[i].isdigit():
31 if first is None or second is None:
35 token_l[first], token_l[second] = token_l[second], token_l[first]
37 return ''.join(token_l)
40 class NPOIE(NPOBaseIE):
42 IE_DESC = 'npo.nl and ntr.nl'
49 npo\.nl/(?!live|radio)(?:[^/]+/){2}|
50 ntr\.nl/(?:[^/]+/){2,}|
51 omroepwnl\.nl/video/fragment/[^/]+__
59 'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
60 'md5': '4b3f9c429157ec4775f2c9cb7b911016',
62 'id': 'VPWON_1220719',
65 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
66 'upload_date': '20140622',
70 'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
71 'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
73 'id': 'VARA_101191800',
75 'title': 'De Mega Mike & Mega Thomas show',
76 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
77 'upload_date': '20090227',
82 'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
83 'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
85 'id': 'VPWON_1169289',
87 'title': 'Tegenlicht',
88 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
89 'upload_date': '20130225',
94 'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
96 'id': 'WO_VPRO_043706',
98 'title': 'De nieuwe mens - Deel 1',
99 'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
103 # mplayer mms download
104 'skip_download': True,
109 'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
110 'md5': 'b3da13de374cbe2d5332a7e910bef97f',
112 'id': 'WO_NOS_762771',
114 'title': 'Hoe gaat Europa verder na Parijs?',
118 'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
119 'md5': '01c6a2841675995da1f0cf776f03a9c3',
121 'id': 'VPWON_1233944',
123 'title': 'Aap, poot, pies',
124 'description': 'md5:c9c8005d1869ae65b858e82c01a91fde',
125 'upload_date': '20150508',
130 'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
131 'md5': 'd30cd8417b8b9bca1fdff27428860d08',
133 'id': 'POW_00996502',
135 'title': '''"Dit is wel een 'landslide'..."''',
136 'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
137 'upload_date': '20150508',
143 def _real_extract(self, url):
144 video_id = self._match_id(url)
145 return self._get_info(video_id)
147 def _get_info(self, video_id):
148 metadata = self._download_json(
149 'http://e.omroep.nl/metadata/%s' % video_id,
151 # We have to remove the javascript callback
152 transform_source=strip_jsonp,
155 # For some videos actual video id (prid) is different (e.g. for
156 # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698
157 # video id is POMS_WNL_853698 but prid is POW_00996502)
158 video_id = metadata.get('prid') or video_id
160 token = self._get_token(video_id)
164 pubopties = metadata.get('pubopties')
166 quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
167 for format_id in pubopties:
168 format_info = self._download_json(
169 'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s'
170 % (video_id, format_id, token),
171 video_id, 'Downloading %s JSON' % format_id)
172 if format_info.get('error_code', 0) or format_info.get('errorcode', 0):
174 streams = format_info.get('streams')
176 video_info = self._download_json(
177 streams[0] + '&type=json',
178 video_id, 'Downloading %s stream JSON' % format_id)
180 video_info = format_info
181 video_url = video_info.get('url')
184 if format_id == 'adaptive':
185 formats.extend(self._extract_m3u8_formats(video_url, video_id))
189 'format_id': format_id,
190 'quality': quality(format_id),
193 streams = metadata.get('streams')
195 for i, stream in enumerate(streams):
196 stream_url = stream.get('url')
199 if '.asf' not in stream_url:
202 'quality': stream.get('kwaliteit'),
205 asx = self._download_xml(
206 stream_url, video_id,
207 'Downloading stream %d ASX playlist' % i,
208 transform_source=fix_xml_ampersands)
209 ref = asx.find('./ENTRY/Ref')
212 video_url = ref.get('href')
217 'ext': stream.get('formaat', 'asf'),
218 'quality': stream.get('kwaliteit'),
221 self._sort_formats(formats)
224 if metadata.get('tt888') == 'ja':
227 'url': 'http://e.omroep.nl/tt888/%s' % video_id,
232 # prefer aflevering_titel if any since titel may be too generic, e.g.
233 # http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html
234 'title': metadata.get('aflevering_titel') or metadata['titel'],
235 'description': metadata.get('info'),
236 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
237 'upload_date': unified_strdate(metadata.get('gidsdatum')),
238 'duration': parse_duration(metadata.get('tijdsduur')),
240 'subtitles': subtitles,
244 class NPOLiveIE(NPOBaseIE):
245 IE_NAME = 'npo.nl:live'
246 _VALID_URL = r'https?://(?:www\.)?npo\.nl/live/(?P<id>.+)'
249 'url': 'http://www.npo.nl/live/npo-1',
251 'id': 'LI_NEDERLAND1_136692',
252 'display_id': 'npo-1',
254 'title': 're:^Nederland 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
255 'description': 'Livestream',
259 'skip_download': True,
263 def _real_extract(self, url):
264 display_id = self._match_id(url)
266 webpage = self._download_webpage(url, display_id)
268 live_id = self._search_regex(
269 r'data-prid="([^"]+)"', webpage, 'live id')
271 metadata = self._download_json(
272 'http://e.omroep.nl/metadata/%s' % live_id,
273 display_id, transform_source=strip_jsonp)
275 token = self._get_token(display_id)
279 streams = metadata.get('streams')
281 for stream in streams:
282 stream_type = stream.get('type').lower()
283 # smooth streaming is not supported
284 if stream_type in ['ss', 'ms']:
286 stream_info = self._download_json(
287 'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp'
288 % (stream.get('url'), token),
289 display_id, 'Downloading %s JSON' % stream_type)
290 if stream_info.get('error_code', 0) or stream_info.get('errorcode', 0):
292 stream_url = self._download_json(
293 stream_info['stream'], display_id,
294 'Downloading %s URL' % stream_type,
295 'Unable to download %s URL' % stream_type,
296 transform_source=strip_jsonp, fatal=False)
299 if stream_type == 'hds':
300 f4m_formats = self._extract_f4m_formats(stream_url, display_id)
301 # f4m downloader downloads only piece of live stream
302 for f4m_format in f4m_formats:
303 f4m_format['preference'] = -1
304 formats.extend(f4m_formats)
305 elif stream_type == 'hls':
306 formats.extend(self._extract_m3u8_formats(stream_url, display_id, 'mp4'))
313 self._sort_formats(formats)
317 'display_id': display_id,
318 'title': self._live_title(metadata['titel']),
319 'description': metadata['info'],
320 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
326 class NPORadioIE(InfoExtractor):
327 IE_NAME = 'npo.nl:radio'
328 _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)/?$'
331 'url': 'http://www.npo.nl/radio/radio-1',
335 'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
339 'skip_download': True,
344 def _html_get_attribute_regex(attribute):
345 return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)
347 def _real_extract(self, url):
348 video_id = self._match_id(url)
350 webpage = self._download_webpage(url, video_id)
352 title = self._html_search_regex(
353 self._html_get_attribute_regex('data-channel'), webpage, 'title')
355 stream = self._parse_json(
356 self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
359 codec = stream.get('codec')
363 'url': stream['url'],
364 'title': self._live_title(title),
371 class NPORadioFragmentIE(InfoExtractor):
372 IE_NAME = 'npo.nl:radio:fragment'
373 _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
376 'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
377 'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
381 'title': 'Jubileumconcert Willeke Alberti',
385 def _real_extract(self, url):
386 audio_id = self._match_id(url)
388 webpage = self._download_webpage(url, audio_id)
390 title = self._html_search_regex(
391 r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id,
394 audio_url = self._search_regex(
395 r"data-streams='([^']+)'", webpage, 'audio url')
405 _VALID_URL = r'https?://(?:www\.)?(?:tegenlicht\.)?vpro\.nl/(?:[^/]+/){2,}(?P<id>[^/]+)\.html'
409 'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
410 'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
412 'id': 'VPWON_1169289',
414 'title': 'De toekomst komt uit Afrika',
415 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
416 'upload_date': '20130225',
420 'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
422 'id': 'sergio-herman',
423 'title': 'Sergio Herman: Fucking perfect',
428 # playlist with youtube embed
429 'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
431 'id': 'education-education',
438 def _real_extract(self, url):
439 playlist_id = self._match_id(url)
441 webpage = self._download_webpage(url, playlist_id)
444 self.url_result('npo:%s' % video_id if not video_id.startswith('http') else video_id)
445 for video_id in re.findall(r'data-media-id="([^"]+)"', webpage)
448 playlist_title = self._search_regex(
449 r'<title>\s*([^>]+?)\s*-\s*Teledoc\s*-\s*VPRO\s*</title>',
450 webpage, 'playlist title', default=None) or self._og_search_title(webpage)
452 return self.playlist_result(entries, playlist_id, playlist_title)
455 class WNLIE(InfoExtractor):
456 _VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
459 'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
461 'id': 'vandaag-de-dag-6-mei',
462 'title': 'Vandaag de Dag 6 mei',
467 def _real_extract(self, url):
468 playlist_id = self._match_id(url)
470 webpage = self._download_webpage(url, playlist_id)
473 self.url_result('npo:%s' % video_id, 'NPO')
474 for video_id, part in re.findall(
475 r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>(Deel \d+)', webpage)
478 playlist_title = self._html_search_regex(
479 r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>',
480 webpage, 'playlist title')
482 return self.playlist_result(entries, playlist_id, playlist_title)