]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/npo.py
New upstream version 2019.01.16
[youtubedl] / youtube_dl / extractor / npo.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..compat import (
7 compat_HTTPError,
8 compat_str,
9 )
10 from ..utils import (
11 determine_ext,
12 ExtractorError,
13 fix_xml_ampersands,
14 int_or_none,
15 orderedSet,
16 parse_duration,
17 qualities,
18 strip_jsonp,
19 unified_strdate,
20 )
21
22
23 class NPOBaseIE(InfoExtractor):
24 def _get_token(self, video_id):
25 return self._download_json(
26 'http://ida.omroep.nl/app.php/auth', video_id,
27 note='Downloading token')['token']
28
29
30 class NPOIE(NPOBaseIE):
31 IE_NAME = 'npo'
32 IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl'
33 _VALID_URL = r'''(?x)
34 (?:
35 npo:|
36 https?://
37 (?:www\.)?
38 (?:
39 npo\.nl/(?:[^/]+/)*|
40 (?:ntr|npostart)\.nl/(?:[^/]+/){2,}|
41 omroepwnl\.nl/video/fragment/[^/]+__|
42 (?:zapp|npo3)\.nl/(?:[^/]+/){2,}
43 )
44 )
45 (?P<id>[^/?#]+)
46 '''
47
48 _TESTS = [{
49 'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
50 'md5': '4b3f9c429157ec4775f2c9cb7b911016',
51 'info_dict': {
52 'id': 'VPWON_1220719',
53 'ext': 'm4v',
54 'title': 'Nieuwsuur',
55 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
56 'upload_date': '20140622',
57 },
58 }, {
59 'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
60 'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
61 'info_dict': {
62 'id': 'VARA_101191800',
63 'ext': 'm4v',
64 'title': 'De Mega Mike & Mega Thomas show: The best of.',
65 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
66 'upload_date': '20090227',
67 'duration': 2400,
68 },
69 }, {
70 'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
71 'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
72 'info_dict': {
73 'id': 'VPWON_1169289',
74 'ext': 'm4v',
75 'title': 'Tegenlicht: Zwart geld. De toekomst komt uit Afrika',
76 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
77 'upload_date': '20130225',
78 'duration': 3000,
79 },
80 }, {
81 'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
82 'info_dict': {
83 'id': 'WO_VPRO_043706',
84 'ext': 'm4v',
85 'title': 'De nieuwe mens - Deel 1',
86 'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
87 'duration': 4680,
88 },
89 'params': {
90 'skip_download': True,
91 }
92 }, {
93 # non asf in streams
94 'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
95 'info_dict': {
96 'id': 'WO_NOS_762771',
97 'ext': 'mp4',
98 'title': 'Hoe gaat Europa verder na Parijs?',
99 },
100 'params': {
101 'skip_download': True,
102 }
103 }, {
104 'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
105 'info_dict': {
106 'id': 'VPWON_1233944',
107 'ext': 'm4v',
108 'title': 'Aap, poot, pies',
109 'description': 'md5:c9c8005d1869ae65b858e82c01a91fde',
110 'upload_date': '20150508',
111 'duration': 599,
112 },
113 'params': {
114 'skip_download': True,
115 }
116 }, {
117 'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
118 'info_dict': {
119 'id': 'POW_00996502',
120 'ext': 'm4v',
121 'title': '''"Dit is wel een 'landslide'..."''',
122 'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
123 'upload_date': '20150508',
124 'duration': 462,
125 },
126 'params': {
127 'skip_download': True,
128 }
129 }, {
130 # audio
131 'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437',
132 'info_dict': {
133 'id': 'RBX_FUNX_6683215',
134 'ext': 'mp3',
135 'title': 'Jouw Stad Rotterdam',
136 'description': 'md5:db251505244f097717ec59fabc372d9f',
137 },
138 'params': {
139 'skip_download': True,
140 }
141 }, {
142 'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
143 'only_matching': True,
144 }, {
145 'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
146 'only_matching': True,
147 }, {
148 'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
149 'only_matching': True,
150 }, {
151 'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870',
152 'only_matching': True,
153 }, {
154 # live stream
155 'url': 'npo:LI_NL1_4188102',
156 'only_matching': True,
157 }, {
158 'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373',
159 'only_matching': True,
160 }, {
161 'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927',
162 'only_matching': True,
163 }, {
164 'url': 'https://www.npostart.nl/broodje-gezond-ei/28-05-2018/KN_1698996',
165 'only_matching': True,
166 }, {
167 'url': 'https://npo.nl/KN_1698996',
168 'only_matching': True,
169 }]
170
171 @classmethod
172 def suitable(cls, url):
173 return (False if any(ie.suitable(url)
174 for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE))
175 else super(NPOIE, cls).suitable(url))
176
177 def _real_extract(self, url):
178 video_id = self._match_id(url)
179 return self._get_info(video_id)
180
181 def _get_info(self, video_id):
182 metadata = self._download_json(
183 'http://e.omroep.nl/metadata/%s' % video_id,
184 video_id,
185 # We have to remove the javascript callback
186 transform_source=strip_jsonp,
187 )
188
189 error = metadata.get('error')
190 if error:
191 raise ExtractorError(error, expected=True)
192
193 # For some videos actual video id (prid) is different (e.g. for
194 # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698
195 # video id is POMS_WNL_853698 but prid is POW_00996502)
196 video_id = metadata.get('prid') or video_id
197
198 # titel is too generic in some cases so utilize aflevering_titel as well
199 # when available (e.g. http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html)
200 title = metadata['titel']
201 sub_title = metadata.get('aflevering_titel')
202 if sub_title and sub_title != title:
203 title += ': %s' % sub_title
204
205 token = self._get_token(video_id)
206
207 formats = []
208 urls = set()
209
210 def is_legal_url(format_url):
211 return format_url and format_url not in urls and re.match(
212 r'^(?:https?:)?//', format_url)
213
214 QUALITY_LABELS = ('Laag', 'Normaal', 'Hoog')
215 QUALITY_FORMATS = ('adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std')
216
217 quality_from_label = qualities(QUALITY_LABELS)
218 quality_from_format_id = qualities(QUALITY_FORMATS)
219 items = self._download_json(
220 'http://ida.omroep.nl/app.php/%s' % video_id, video_id,
221 'Downloading formats JSON', query={
222 'adaptive': 'yes',
223 'token': token,
224 })['items'][0]
225 for num, item in enumerate(items):
226 item_url = item.get('url')
227 if not is_legal_url(item_url):
228 continue
229 urls.add(item_url)
230 format_id = self._search_regex(
231 r'video/ida/([^/]+)', item_url, 'format id',
232 default=None)
233
234 item_label = item.get('label')
235
236 def add_format_url(format_url):
237 width = int_or_none(self._search_regex(
238 r'(\d+)[xX]\d+', format_url, 'width', default=None))
239 height = int_or_none(self._search_regex(
240 r'\d+[xX](\d+)', format_url, 'height', default=None))
241 if item_label in QUALITY_LABELS:
242 quality = quality_from_label(item_label)
243 f_id = item_label
244 elif item_label in QUALITY_FORMATS:
245 quality = quality_from_format_id(format_id)
246 f_id = format_id
247 else:
248 quality, f_id = [None] * 2
249 formats.append({
250 'url': format_url,
251 'format_id': f_id,
252 'width': width,
253 'height': height,
254 'quality': quality,
255 })
256
257 # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
258 if item.get('contentType') in ('url', 'audio'):
259 add_format_url(item_url)
260 continue
261
262 try:
263 stream_info = self._download_json(
264 item_url + '&type=json', video_id,
265 'Downloading %s stream JSON'
266 % item_label or item.get('format') or format_id or num)
267 except ExtractorError as ee:
268 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
269 error = (self._parse_json(
270 ee.cause.read().decode(), video_id,
271 fatal=False) or {}).get('errorstring')
272 if error:
273 raise ExtractorError(error, expected=True)
274 raise
275 # Stream URL instead of JSON, example: npo:LI_NL1_4188102
276 if isinstance(stream_info, compat_str):
277 if not stream_info.startswith('http'):
278 continue
279 video_url = stream_info
280 # JSON
281 else:
282 video_url = stream_info.get('url')
283 if not video_url or video_url in urls:
284 continue
285 urls.add(video_url)
286 if determine_ext(video_url) == 'm3u8':
287 formats.extend(self._extract_m3u8_formats(
288 video_url, video_id, ext='mp4',
289 entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
290 else:
291 add_format_url(video_url)
292
293 is_live = metadata.get('medium') == 'live'
294
295 if not is_live:
296 for num, stream in enumerate(metadata.get('streams', [])):
297 stream_url = stream.get('url')
298 if not is_legal_url(stream_url):
299 continue
300 urls.add(stream_url)
301 # smooth streaming is not supported
302 stream_type = stream.get('type', '').lower()
303 if stream_type in ['ss', 'ms']:
304 continue
305 if stream_type == 'hds':
306 f4m_formats = self._extract_f4m_formats(
307 stream_url, video_id, fatal=False)
308 # f4m downloader downloads only piece of live stream
309 for f4m_format in f4m_formats:
310 f4m_format['preference'] = -1
311 formats.extend(f4m_formats)
312 elif stream_type == 'hls':
313 formats.extend(self._extract_m3u8_formats(
314 stream_url, video_id, ext='mp4', fatal=False))
315 # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
316 elif '.asf' in stream_url:
317 asx = self._download_xml(
318 stream_url, video_id,
319 'Downloading stream %d ASX playlist' % num,
320 transform_source=fix_xml_ampersands, fatal=False)
321 if not asx:
322 continue
323 ref = asx.find('./ENTRY/Ref')
324 if ref is None:
325 continue
326 video_url = ref.get('href')
327 if not video_url or video_url in urls:
328 continue
329 urls.add(video_url)
330 formats.append({
331 'url': video_url,
332 'ext': stream.get('formaat', 'asf'),
333 'quality': stream.get('kwaliteit'),
334 'preference': -10,
335 })
336 else:
337 formats.append({
338 'url': stream_url,
339 'quality': stream.get('kwaliteit'),
340 })
341
342 self._sort_formats(formats)
343
344 subtitles = {}
345 if metadata.get('tt888') == 'ja':
346 subtitles['nl'] = [{
347 'ext': 'vtt',
348 'url': 'http://tt888.omroep.nl/tt888/%s' % video_id,
349 }]
350
351 return {
352 'id': video_id,
353 'title': self._live_title(title) if is_live else title,
354 'description': metadata.get('info'),
355 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
356 'upload_date': unified_strdate(metadata.get('gidsdatum')),
357 'duration': parse_duration(metadata.get('tijdsduur')),
358 'formats': formats,
359 'subtitles': subtitles,
360 'is_live': is_live,
361 }
362
363
364 class NPOLiveIE(NPOBaseIE):
365 IE_NAME = 'npo.nl:live'
366 _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P<id>[^/?#&]+))?'
367
368 _TESTS = [{
369 'url': 'http://www.npo.nl/live/npo-1',
370 'info_dict': {
371 'id': 'LI_NL1_4188102',
372 'display_id': 'npo-1',
373 'ext': 'mp4',
374 'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
375 'is_live': True,
376 },
377 'params': {
378 'skip_download': True,
379 }
380 }, {
381 'url': 'http://www.npo.nl/live',
382 'only_matching': True,
383 }, {
384 'url': 'https://www.npostart.nl/live/npo-1',
385 'only_matching': True,
386 }]
387
388 def _real_extract(self, url):
389 display_id = self._match_id(url) or 'npo-1'
390
391 webpage = self._download_webpage(url, display_id)
392
393 live_id = self._search_regex(
394 [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')
395
396 return {
397 '_type': 'url_transparent',
398 'url': 'npo:%s' % live_id,
399 'ie_key': NPOIE.ie_key(),
400 'id': live_id,
401 'display_id': display_id,
402 }
403
404
405 class NPORadioIE(InfoExtractor):
406 IE_NAME = 'npo.nl:radio'
407 _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)'
408
409 _TEST = {
410 'url': 'http://www.npo.nl/radio/radio-1',
411 'info_dict': {
412 'id': 'radio-1',
413 'ext': 'mp3',
414 'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
415 'is_live': True,
416 },
417 'params': {
418 'skip_download': True,
419 }
420 }
421
422 @classmethod
423 def suitable(cls, url):
424 return False if NPORadioFragmentIE.suitable(url) else super(NPORadioIE, cls).suitable(url)
425
426 @staticmethod
427 def _html_get_attribute_regex(attribute):
428 return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)
429
430 def _real_extract(self, url):
431 video_id = self._match_id(url)
432
433 webpage = self._download_webpage(url, video_id)
434
435 title = self._html_search_regex(
436 self._html_get_attribute_regex('data-channel'), webpage, 'title')
437
438 stream = self._parse_json(
439 self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
440 video_id)
441
442 codec = stream.get('codec')
443
444 return {
445 'id': video_id,
446 'url': stream['url'],
447 'title': self._live_title(title),
448 'acodec': codec,
449 'ext': codec,
450 'is_live': True,
451 }
452
453
454 class NPORadioFragmentIE(InfoExtractor):
455 IE_NAME = 'npo.nl:radio:fragment'
456 _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
457
458 _TEST = {
459 'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
460 'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
461 'info_dict': {
462 'id': '174356',
463 'ext': 'mp3',
464 'title': 'Jubileumconcert Willeke Alberti',
465 },
466 }
467
468 def _real_extract(self, url):
469 audio_id = self._match_id(url)
470
471 webpage = self._download_webpage(url, audio_id)
472
473 title = self._html_search_regex(
474 r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id,
475 webpage, 'title')
476
477 audio_url = self._search_regex(
478 r"data-streams='([^']+)'", webpage, 'audio url')
479
480 return {
481 'id': audio_id,
482 'url': audio_url,
483 'title': title,
484 }
485
486
487 class NPODataMidEmbedIE(InfoExtractor):
488 def _real_extract(self, url):
489 display_id = self._match_id(url)
490 webpage = self._download_webpage(url, display_id)
491 video_id = self._search_regex(
492 r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
493 return {
494 '_type': 'url_transparent',
495 'ie_key': 'NPO',
496 'url': 'npo:%s' % video_id,
497 'display_id': display_id
498 }
499
500
501 class SchoolTVIE(NPODataMidEmbedIE):
502 IE_NAME = 'schooltv'
503 _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
504
505 _TEST = {
506 'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
507 'info_dict': {
508 'id': 'WO_NTR_429477',
509 'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
510 'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
511 'ext': 'mp4',
512 'description': 'md5:abfa0ff690adb73fd0297fd033aaa631'
513 },
514 'params': {
515 # Skip because of m3u8 download
516 'skip_download': True
517 }
518 }
519
520
521 class HetKlokhuisIE(NPODataMidEmbedIE):
522 IE_NAME = 'hetklokhuis'
523 _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
524
525 _TEST = {
526 'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
527 'info_dict': {
528 'id': 'VPWON_1260528',
529 'display_id': 'Zwaartekrachtsgolven',
530 'ext': 'm4v',
531 'title': 'Het Klokhuis: Zwaartekrachtsgolven',
532 'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
533 'upload_date': '20170223',
534 },
535 'params': {
536 'skip_download': True
537 }
538 }
539
540
541 class NPOPlaylistBaseIE(NPOIE):
542 def _real_extract(self, url):
543 playlist_id = self._match_id(url)
544
545 webpage = self._download_webpage(url, playlist_id)
546
547 entries = [
548 self.url_result('npo:%s' % video_id if not video_id.startswith('http') else video_id)
549 for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
550 ]
551
552 playlist_title = self._html_search_regex(
553 self._PLAYLIST_TITLE_RE, webpage, 'playlist title',
554 default=None) or self._og_search_title(webpage)
555
556 return self.playlist_result(entries, playlist_id, playlist_title)
557
558
559 class VPROIE(NPOPlaylistBaseIE):
560 IE_NAME = 'vpro'
561 _VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
562 _PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)',
563 r'<h5[^>]+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)')
564 _PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
565
566 _TESTS = [
567 {
568 'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
569 'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
570 'info_dict': {
571 'id': 'VPWON_1169289',
572 'ext': 'm4v',
573 'title': 'De toekomst komt uit Afrika',
574 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
575 'upload_date': '20130225',
576 },
577 'skip': 'Video gone',
578 },
579 {
580 'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
581 'info_dict': {
582 'id': 'sergio-herman',
583 'title': 'sergio herman: fucking perfect',
584 },
585 'playlist_count': 2,
586 },
587 {
588 # playlist with youtube embed
589 'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
590 'info_dict': {
591 'id': 'education-education',
592 'title': 'education education',
593 },
594 'playlist_count': 2,
595 },
596 {
597 'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
598 'info_dict': {
599 'id': 'de-tegenprestatie',
600 'title': 'De Tegenprestatie',
601 },
602 'playlist_count': 2,
603 }, {
604 'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
605 'info_dict': {
606 'id': 'VARA_101375237',
607 'ext': 'm4v',
608 'title': 'MH17: Het verdriet van Nederland',
609 'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
610 'upload_date': '20150716',
611 },
612 'params': {
613 # Skip because of m3u8 download
614 'skip_download': True
615 },
616 }
617 ]
618
619
620 class WNLIE(NPOPlaylistBaseIE):
621 IE_NAME = 'wnl'
622 _VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
623 _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>'
624 _PLAYLIST_ENTRY_RE = r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+'
625
626 _TESTS = [{
627 'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
628 'info_dict': {
629 'id': 'vandaag-de-dag-6-mei',
630 'title': 'Vandaag de Dag 6 mei',
631 },
632 'playlist_count': 4,
633 }]
634
635
636 class AndereTijdenIE(NPOPlaylistBaseIE):
637 IE_NAME = 'anderetijden'
638 _VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P<id>[^/?#&]+)'
639 _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class=["\'].*?\bpage-title\b.*?["\'][^>]*>(.+?)</h1>'
640 _PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']'
641
642 _TESTS = [{
643 'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',
644 'info_dict': {
645 'id': 'Duitse-soldaten-over-de-Slag-bij-Arnhem',
646 'title': 'Duitse soldaten over de Slag bij Arnhem',
647 },
648 'playlist_count': 3,
649 }]