]>
Commit | Line | Data |
---|---|---|
1 | import itertools | |
2 | import random | |
3 | import re | |
4 | ||
5 | from .common import InfoExtractor | |
6 | from ..compat import compat_str | |
7 | from ..networking.exceptions import HTTPError | |
8 | from ..utils import ( | |
9 | ExtractorError, | |
10 | determine_ext, | |
11 | int_or_none, | |
12 | parse_duration, | |
13 | parse_iso8601, | |
14 | str_or_none, | |
15 | try_get, | |
16 | url_or_none, | |
17 | urljoin, | |
18 | ) | |
19 | ||
20 | ||
21 | class NRKBaseIE(InfoExtractor): | |
22 | _GEO_COUNTRIES = ['NO'] | |
23 | _CDN_REPL_REGEX = r'''(?x):// | |
24 | (?: | |
25 | nrkod\d{1,2}-httpcache0-47115-cacheod0\.dna\.ip-only\.net/47115-cacheod0| | |
26 | nrk-od-no\.telenorcdn\.net| | |
27 | minicdn-od\.nrk\.no/od/nrkhd-osl-rr\.netwerk\.no/no | |
28 | )/''' | |
29 | ||
30 | def _extract_nrk_formats(self, asset_url, video_id): | |
31 | if re.match(r'https?://[^/]+\.akamaihd\.net/i/', asset_url): | |
32 | return self._extract_akamai_formats(asset_url, video_id) | |
33 | asset_url = re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only)&?', '', asset_url) | |
34 | formats = self._extract_m3u8_formats( | |
35 | asset_url, video_id, 'mp4', 'm3u8_native', fatal=False) | |
36 | if not formats and re.search(self._CDN_REPL_REGEX, asset_url): | |
37 | formats = self._extract_m3u8_formats( | |
38 | re.sub(self._CDN_REPL_REGEX, '://nrk-od-%02d.akamaized.net/no/' % random.randint(0, 99), asset_url), | |
39 | video_id, 'mp4', 'm3u8_native', fatal=False) | |
40 | return formats | |
41 | ||
42 | def _raise_error(self, data): | |
43 | MESSAGES = { | |
44 | 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet', | |
45 | 'ProgramRightsHasExpired': 'Programmet har gått ut', | |
46 | 'NoProgramRights': 'Ikke tilgjengelig', | |
47 | 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge', | |
48 | } | |
49 | message_type = data.get('messageType', '') | |
50 | # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked* | |
51 | if 'IsGeoBlocked' in message_type or try_get(data, lambda x: x['usageRights']['isGeoBlocked']) is True: | |
52 | self.raise_geo_restricted( | |
53 | msg=MESSAGES.get('ProgramIsGeoBlocked'), | |
54 | countries=self._GEO_COUNTRIES) | |
55 | message = data.get('endUserMessage') or MESSAGES.get(message_type, message_type) | |
56 | raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True) | |
57 | ||
58 | def _call_api(self, path, video_id, item=None, note=None, fatal=True, query=None): | |
59 | return self._download_json( | |
60 | urljoin('https://psapi.nrk.no/', path), | |
61 | video_id, note or 'Downloading %s JSON' % item, | |
62 | fatal=fatal, query=query) | |
63 | ||
64 | ||
65 | class NRKIE(NRKBaseIE): | |
66 | _VALID_URL = r'''(?x) | |
67 | (?: | |
68 | nrk:| | |
69 | https?:// | |
70 | (?: | |
71 | (?:www\.)?nrk\.no/video/(?:PS\*|[^_]+_)| | |
72 | v8[-.]psapi\.nrk\.no/mediaelement/ | |
73 | ) | |
74 | ) | |
75 | (?P<id>[^?\#&]+) | |
76 | ''' | |
77 | ||
78 | _TESTS = [{ | |
79 | # video | |
80 | 'url': 'http://www.nrk.no/video/PS*150533', | |
81 | 'md5': 'f46be075326e23ad0e524edfcb06aeb6', | |
82 | 'info_dict': { | |
83 | 'id': '150533', | |
84 | 'ext': 'mp4', | |
85 | 'title': 'Dompap og andre fugler i Piip-Show', | |
86 | 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f', | |
87 | 'duration': 262, | |
88 | } | |
89 | }, { | |
90 | # audio | |
91 | 'url': 'http://www.nrk.no/video/PS*154915', | |
92 | # MD5 is unstable | |
93 | 'info_dict': { | |
94 | 'id': '154915', | |
95 | 'ext': 'mp4', | |
96 | 'title': 'Slik høres internett ut når du er blind', | |
97 | 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568', | |
98 | 'duration': 20, | |
99 | } | |
100 | }, { | |
101 | 'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9', | |
102 | 'only_matching': True, | |
103 | }, { | |
104 | 'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70', | |
105 | 'only_matching': True, | |
106 | }, { | |
107 | 'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9', | |
108 | 'only_matching': True, | |
109 | }, { | |
110 | 'url': 'https://www.nrk.no/video/dompap-og-andre-fugler-i-piip-show_150533', | |
111 | 'only_matching': True, | |
112 | }, { | |
113 | 'url': 'https://www.nrk.no/video/humor/kommentatorboksen-reiser-til-sjos_d1fda11f-a4ad-437a-a374-0398bc84e999', | |
114 | 'only_matching': True, | |
115 | }, { | |
116 | # podcast | |
117 | 'url': 'nrk:l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8', | |
118 | 'only_matching': True, | |
119 | }, { | |
120 | 'url': 'nrk:podcast/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8', | |
121 | 'only_matching': True, | |
122 | }, { | |
123 | # clip | |
124 | 'url': 'nrk:150533', | |
125 | 'only_matching': True, | |
126 | }, { | |
127 | 'url': 'nrk:clip/150533', | |
128 | 'only_matching': True, | |
129 | }, { | |
130 | # program | |
131 | 'url': 'nrk:MDDP12000117', | |
132 | 'only_matching': True, | |
133 | }, { | |
134 | 'url': 'nrk:program/ENRK10100318', | |
135 | 'only_matching': True, | |
136 | }, { | |
137 | # direkte | |
138 | 'url': 'nrk:nrk1', | |
139 | 'only_matching': True, | |
140 | }, { | |
141 | 'url': 'nrk:channel/nrk1', | |
142 | 'only_matching': True, | |
143 | }] | |
144 | ||
145 | def _real_extract(self, url): | |
146 | video_id = self._match_id(url).split('/')[-1] | |
147 | ||
148 | def call_playback_api(item, query=None): | |
149 | try: | |
150 | return self._call_api(f'playback/{item}/program/{video_id}', video_id, item, query=query) | |
151 | except ExtractorError as e: | |
152 | if isinstance(e.cause, HTTPError) and e.cause.status == 400: | |
153 | return self._call_api(f'playback/{item}/{video_id}', video_id, item, query=query) | |
154 | raise | |
155 | ||
156 | # known values for preferredCdn: akamai, iponly, minicdn and telenor | |
157 | manifest = call_playback_api('manifest', {'preferredCdn': 'akamai'}) | |
158 | ||
159 | video_id = try_get(manifest, lambda x: x['id'], compat_str) or video_id | |
160 | ||
161 | if manifest.get('playability') == 'nonPlayable': | |
162 | self._raise_error(manifest['nonPlayable']) | |
163 | ||
164 | playable = manifest['playable'] | |
165 | ||
166 | formats = [] | |
167 | for asset in playable['assets']: | |
168 | if not isinstance(asset, dict): | |
169 | continue | |
170 | if asset.get('encrypted'): | |
171 | continue | |
172 | format_url = url_or_none(asset.get('url')) | |
173 | if not format_url: | |
174 | continue | |
175 | asset_format = (asset.get('format') or '').lower() | |
176 | if asset_format == 'hls' or determine_ext(format_url) == 'm3u8': | |
177 | formats.extend(self._extract_nrk_formats(format_url, video_id)) | |
178 | elif asset_format == 'mp3': | |
179 | formats.append({ | |
180 | 'url': format_url, | |
181 | 'format_id': asset_format, | |
182 | 'vcodec': 'none', | |
183 | }) | |
184 | ||
185 | data = call_playback_api('metadata') | |
186 | ||
187 | preplay = data['preplay'] | |
188 | titles = preplay['titles'] | |
189 | title = titles['title'] | |
190 | alt_title = titles.get('subtitle') | |
191 | ||
192 | description = try_get(preplay, lambda x: x['description'].replace('\r', '\n')) | |
193 | duration = parse_duration(playable.get('duration')) or parse_duration(data.get('duration')) | |
194 | ||
195 | thumbnails = [] | |
196 | for image in try_get( | |
197 | preplay, lambda x: x['poster']['images'], list) or []: | |
198 | if not isinstance(image, dict): | |
199 | continue | |
200 | image_url = url_or_none(image.get('url')) | |
201 | if not image_url: | |
202 | continue | |
203 | thumbnails.append({ | |
204 | 'url': image_url, | |
205 | 'width': int_or_none(image.get('pixelWidth')), | |
206 | 'height': int_or_none(image.get('pixelHeight')), | |
207 | }) | |
208 | ||
209 | subtitles = {} | |
210 | for sub in try_get(playable, lambda x: x['subtitles'], list) or []: | |
211 | if not isinstance(sub, dict): | |
212 | continue | |
213 | sub_url = url_or_none(sub.get('webVtt')) | |
214 | if not sub_url: | |
215 | continue | |
216 | sub_key = str_or_none(sub.get('language')) or 'nb' | |
217 | sub_type = str_or_none(sub.get('type')) | |
218 | if sub_type: | |
219 | sub_key += '-%s' % sub_type | |
220 | subtitles.setdefault(sub_key, []).append({ | |
221 | 'url': sub_url, | |
222 | }) | |
223 | ||
224 | legal_age = try_get( | |
225 | data, lambda x: x['legalAge']['body']['rating']['code'], compat_str) | |
226 | # https://en.wikipedia.org/wiki/Norwegian_Media_Authority | |
227 | age_limit = None | |
228 | if legal_age: | |
229 | if legal_age == 'A': | |
230 | age_limit = 0 | |
231 | elif legal_age.isdigit(): | |
232 | age_limit = int_or_none(legal_age) | |
233 | ||
234 | is_series = try_get(data, lambda x: x['_links']['series']['name']) == 'series' | |
235 | ||
236 | info = { | |
237 | 'id': video_id, | |
238 | 'title': title, | |
239 | 'alt_title': alt_title, | |
240 | 'description': description, | |
241 | 'duration': duration, | |
242 | 'thumbnails': thumbnails, | |
243 | 'age_limit': age_limit, | |
244 | 'formats': formats, | |
245 | 'subtitles': subtitles, | |
246 | 'timestamp': parse_iso8601(try_get(manifest, lambda x: x['availability']['onDemand']['from'], str)) | |
247 | } | |
248 | ||
249 | if is_series: | |
250 | series = season_id = season_number = episode = episode_number = None | |
251 | programs = self._call_api( | |
252 | 'programs/%s' % video_id, video_id, 'programs', fatal=False) | |
253 | if programs and isinstance(programs, dict): | |
254 | series = str_or_none(programs.get('seriesTitle')) | |
255 | season_id = str_or_none(programs.get('seasonId')) | |
256 | season_number = int_or_none(programs.get('seasonNumber')) | |
257 | episode = str_or_none(programs.get('episodeTitle')) | |
258 | episode_number = int_or_none(programs.get('episodeNumber')) | |
259 | if not series: | |
260 | series = title | |
261 | if alt_title: | |
262 | title += ' - %s' % alt_title | |
263 | if not season_number: | |
264 | season_number = int_or_none(self._search_regex( | |
265 | r'Sesong\s+(\d+)', description or '', 'season number', | |
266 | default=None)) | |
267 | if not episode: | |
268 | episode = alt_title if is_series else None | |
269 | if not episode_number: | |
270 | episode_number = int_or_none(self._search_regex( | |
271 | r'^(\d+)\.', episode or '', 'episode number', | |
272 | default=None)) | |
273 | if not episode_number: | |
274 | episode_number = int_or_none(self._search_regex( | |
275 | r'\((\d+)\s*:\s*\d+\)', description or '', | |
276 | 'episode number', default=None)) | |
277 | info.update({ | |
278 | 'title': title, | |
279 | 'series': series, | |
280 | 'season_id': season_id, | |
281 | 'season_number': season_number, | |
282 | 'episode': episode, | |
283 | 'episode_number': episode_number, | |
284 | }) | |
285 | ||
286 | return info | |
287 | ||
288 | ||
289 | class NRKTVIE(InfoExtractor): | |
290 | IE_DESC = 'NRK TV and NRK Radio' | |
291 | _EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})' | |
292 | _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:[^/]+/)*%s' % _EPISODE_RE | |
293 | _TESTS = [{ | |
294 | 'url': 'https://tv.nrk.no/program/MDDP12000117', | |
295 | 'md5': 'c4a5960f1b00b40d47db65c1064e0ab1', | |
296 | 'info_dict': { | |
297 | 'id': 'MDDP12000117', | |
298 | 'ext': 'mp4', | |
299 | 'title': 'Alarm Trolltunga', | |
300 | 'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce', | |
301 | 'duration': 2223.44, | |
302 | 'age_limit': 6, | |
303 | 'subtitles': { | |
304 | 'nb-nor': [{ | |
305 | 'ext': 'vtt', | |
306 | }], | |
307 | 'nb-ttv': [{ | |
308 | 'ext': 'vtt', | |
309 | }] | |
310 | }, | |
311 | }, | |
312 | }, { | |
313 | 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', | |
314 | 'md5': '8d40dab61cea8ab0114e090b029a0565', | |
315 | 'info_dict': { | |
316 | 'id': 'MUHH48000314', | |
317 | 'ext': 'mp4', | |
318 | 'title': '20 spørsmål - 23. mai 2014', | |
319 | 'alt_title': '23. mai 2014', | |
320 | 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', | |
321 | 'duration': 1741, | |
322 | 'series': '20 spørsmål', | |
323 | 'episode': '23. mai 2014', | |
324 | 'age_limit': 0, | |
325 | }, | |
326 | }, { | |
327 | 'url': 'https://tv.nrk.no/program/mdfp15000514', | |
328 | 'info_dict': { | |
329 | 'id': 'MDFP15000514', | |
330 | 'ext': 'mp4', | |
331 | 'title': 'Kunnskapskanalen - Grunnlovsjubiléet - Stor ståhei for ingenting', | |
332 | 'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db', | |
333 | 'duration': 4605.08, | |
334 | 'series': 'Kunnskapskanalen', | |
335 | 'episode': 'Grunnlovsjubiléet - Stor ståhei for ingenting', | |
336 | 'age_limit': 0, | |
337 | }, | |
338 | 'params': { | |
339 | 'skip_download': True, | |
340 | }, | |
341 | }, { | |
342 | # single playlist video | |
343 | 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2', | |
344 | 'info_dict': { | |
345 | 'id': 'MSPO40010515', | |
346 | 'ext': 'mp4', | |
347 | 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015', | |
348 | 'description': 'md5:c03aba1e917561eface5214020551b7a', | |
349 | 'age_limit': 0, | |
350 | }, | |
351 | 'params': { | |
352 | 'skip_download': True, | |
353 | }, | |
354 | 'expected_warnings': ['Failed to download m3u8 information'], | |
355 | 'skip': 'particular part is not supported currently', | |
356 | }, { | |
357 | 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015', | |
358 | 'info_dict': { | |
359 | 'id': 'MSPO40010515', | |
360 | 'ext': 'mp4', | |
361 | 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015', | |
362 | 'description': 'md5:c03aba1e917561eface5214020551b7a', | |
363 | 'age_limit': 0, | |
364 | }, | |
365 | 'expected_warnings': ['Failed to download m3u8 information'], | |
366 | 'skip': 'Ikke tilgjengelig utenfor Norge', | |
367 | }, { | |
368 | 'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13', | |
369 | 'info_dict': { | |
370 | 'id': 'KMTE50001317', | |
371 | 'ext': 'mp4', | |
372 | 'title': 'Anno - 13. episode', | |
373 | 'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa', | |
374 | 'duration': 2340, | |
375 | 'series': 'Anno', | |
376 | 'episode': '13. episode', | |
377 | 'season_number': 3, | |
378 | 'episode_number': 13, | |
379 | 'age_limit': 0, | |
380 | }, | |
381 | 'params': { | |
382 | 'skip_download': True, | |
383 | }, | |
384 | }, { | |
385 | 'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017', | |
386 | 'info_dict': { | |
387 | 'id': 'MUHH46000317', | |
388 | 'ext': 'mp4', | |
389 | 'title': 'Nytt på Nytt 27.01.2017', | |
390 | 'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b', | |
391 | 'duration': 1796, | |
392 | 'series': 'Nytt på nytt', | |
393 | 'episode': '27.01.2017', | |
394 | 'age_limit': 0, | |
395 | }, | |
396 | 'params': { | |
397 | 'skip_download': True, | |
398 | }, | |
399 | 'skip': 'ProgramRightsHasExpired', | |
400 | }, { | |
401 | 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#', | |
402 | 'only_matching': True, | |
403 | }, { | |
404 | 'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller', | |
405 | 'only_matching': True, | |
406 | }, { | |
407 | 'url': 'https://radio.nrk.no/serie/dagsnytt/sesong/201507/NPUB21019315', | |
408 | 'only_matching': True, | |
409 | }] | |
410 | ||
411 | def _real_extract(self, url): | |
412 | video_id = self._match_id(url) | |
413 | return self.url_result( | |
414 | 'nrk:%s' % video_id, ie=NRKIE.ie_key(), video_id=video_id) | |
415 | ||
416 | ||
417 | class NRKTVEpisodeIE(InfoExtractor): | |
418 | _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/(?P<season_number>\d+)/episode/(?P<episode_number>\d+))' | |
419 | _TESTS = [{ | |
420 | 'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2', | |
421 | 'info_dict': { | |
422 | 'id': 'MUHH36005220', | |
423 | 'ext': 'mp4', | |
424 | 'title': 'Hellums kro - 2. Kro, krig og kjærlighet', | |
425 | 'description': 'md5:ad92ddffc04cea8ce14b415deef81787', | |
426 | 'duration': 1563.92, | |
427 | 'series': 'Hellums kro', | |
428 | 'season_number': 1, | |
429 | 'episode_number': 2, | |
430 | 'episode': '2. Kro, krig og kjærlighet', | |
431 | 'age_limit': 6, | |
432 | }, | |
433 | 'params': { | |
434 | 'skip_download': True, | |
435 | }, | |
436 | }, { | |
437 | 'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8', | |
438 | 'info_dict': { | |
439 | 'id': 'MSUI14000816', | |
440 | 'ext': 'mp4', | |
441 | 'title': 'Backstage - 8. episode', | |
442 | 'description': 'md5:de6ca5d5a2d56849e4021f2bf2850df4', | |
443 | 'duration': 1320, | |
444 | 'series': 'Backstage', | |
445 | 'season_number': 1, | |
446 | 'episode_number': 8, | |
447 | 'episode': '8. episode', | |
448 | 'age_limit': 0, | |
449 | }, | |
450 | 'params': { | |
451 | 'skip_download': True, | |
452 | }, | |
453 | 'skip': 'ProgramRightsHasExpired', | |
454 | }] | |
455 | ||
456 | def _real_extract(self, url): | |
457 | display_id, season_number, episode_number = self._match_valid_url(url).groups() | |
458 | ||
459 | webpage = self._download_webpage(url, display_id) | |
460 | ||
461 | info = self._search_json_ld(webpage, display_id, default={}) | |
462 | nrk_id = info.get('@id') or self._html_search_meta( | |
463 | 'nrk:program-id', webpage, default=None) or self._search_regex( | |
464 | r'data-program-id=["\'](%s)' % NRKTVIE._EPISODE_RE, webpage, | |
465 | 'nrk id') | |
466 | assert re.match(NRKTVIE._EPISODE_RE, nrk_id) | |
467 | ||
468 | info.update({ | |
469 | '_type': 'url', | |
470 | 'id': nrk_id, | |
471 | 'url': 'nrk:%s' % nrk_id, | |
472 | 'ie_key': NRKIE.ie_key(), | |
473 | 'season_number': int(season_number), | |
474 | 'episode_number': int(episode_number), | |
475 | }) | |
476 | return info | |
477 | ||
478 | ||
479 | class NRKTVSerieBaseIE(NRKBaseIE): | |
480 | def _extract_entries(self, entry_list): | |
481 | if not isinstance(entry_list, list): | |
482 | return [] | |
483 | entries = [] | |
484 | for episode in entry_list: | |
485 | nrk_id = episode.get('prfId') or episode.get('episodeId') | |
486 | if not nrk_id or not isinstance(nrk_id, compat_str): | |
487 | continue | |
488 | entries.append(self.url_result( | |
489 | 'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id)) | |
490 | return entries | |
491 | ||
492 | _ASSETS_KEYS = ('episodes', 'instalments',) | |
493 | ||
494 | def _extract_assets_key(self, embedded): | |
495 | for asset_key in self._ASSETS_KEYS: | |
496 | if embedded.get(asset_key): | |
497 | return asset_key | |
498 | ||
499 | @staticmethod | |
500 | def _catalog_name(serie_kind): | |
501 | return 'podcast' if serie_kind in ('podcast', 'podkast') else 'series' | |
502 | ||
503 | def _entries(self, data, display_id): | |
504 | for page_num in itertools.count(1): | |
505 | embedded = data.get('_embedded') or data | |
506 | if not isinstance(embedded, dict): | |
507 | break | |
508 | assets_key = self._extract_assets_key(embedded) | |
509 | if not assets_key: | |
510 | break | |
511 | # Extract entries | |
512 | entries = try_get( | |
513 | embedded, | |
514 | (lambda x: x[assets_key]['_embedded'][assets_key], | |
515 | lambda x: x[assets_key]), | |
516 | list) | |
517 | for e in self._extract_entries(entries): | |
518 | yield e | |
519 | # Find next URL | |
520 | next_url_path = try_get( | |
521 | data, | |
522 | (lambda x: x['_links']['next']['href'], | |
523 | lambda x: x['_embedded'][assets_key]['_links']['next']['href']), | |
524 | compat_str) | |
525 | if not next_url_path: | |
526 | break | |
527 | data = self._call_api( | |
528 | next_url_path, display_id, | |
529 | note='Downloading %s JSON page %d' % (assets_key, page_num), | |
530 | fatal=False) | |
531 | if not data: | |
532 | break | |
533 | ||
534 | ||
535 | class NRKTVSeasonIE(NRKTVSerieBaseIE): | |
536 | _VALID_URL = r'''(?x) | |
537 | https?:// | |
538 | (?P<domain>tv|radio)\.nrk\.no/ | |
539 | (?P<serie_kind>serie|pod[ck]ast)/ | |
540 | (?P<serie>[^/]+)/ | |
541 | (?: | |
542 | (?:sesong/)?(?P<id>\d+)| | |
543 | sesong/(?P<id_2>[^/?#&]+) | |
544 | ) | |
545 | ''' | |
546 | _TESTS = [{ | |
547 | 'url': 'https://tv.nrk.no/serie/backstage/sesong/1', | |
548 | 'info_dict': { | |
549 | 'id': 'backstage/1', | |
550 | 'title': 'Sesong 1', | |
551 | }, | |
552 | 'playlist_mincount': 30, | |
553 | }, { | |
554 | # no /sesong/ in path | |
555 | 'url': 'https://tv.nrk.no/serie/lindmo/2016', | |
556 | 'info_dict': { | |
557 | 'id': 'lindmo/2016', | |
558 | 'title': '2016', | |
559 | }, | |
560 | 'playlist_mincount': 29, | |
561 | }, { | |
562 | # weird nested _embedded in catalog JSON response | |
563 | 'url': 'https://radio.nrk.no/serie/dickie-dick-dickens/sesong/1', | |
564 | 'info_dict': { | |
565 | 'id': 'dickie-dick-dickens/1', | |
566 | 'title': 'Sesong 1', | |
567 | }, | |
568 | 'playlist_mincount': 11, | |
569 | }, { | |
570 | # 841 entries, multi page | |
571 | 'url': 'https://radio.nrk.no/serie/dagsnytt/sesong/201509', | |
572 | 'info_dict': { | |
573 | 'id': 'dagsnytt/201509', | |
574 | 'title': 'September 2015', | |
575 | }, | |
576 | 'playlist_mincount': 841, | |
577 | }, { | |
578 | # 180 entries, single page | |
579 | 'url': 'https://tv.nrk.no/serie/spangas/sesong/1', | |
580 | 'only_matching': True, | |
581 | }, { | |
582 | 'url': 'https://radio.nrk.no/podkast/hele_historien/sesong/diagnose-kverulant', | |
583 | 'info_dict': { | |
584 | 'id': 'hele_historien/diagnose-kverulant', | |
585 | 'title': 'Diagnose kverulant', | |
586 | }, | |
587 | 'playlist_mincount': 3, | |
588 | }, { | |
589 | 'url': 'https://radio.nrk.no/podkast/loerdagsraadet/sesong/202101', | |
590 | 'only_matching': True, | |
591 | }] | |
592 | ||
593 | @classmethod | |
594 | def suitable(cls, url): | |
595 | return (False if NRKTVIE.suitable(url) or NRKTVEpisodeIE.suitable(url) or NRKRadioPodkastIE.suitable(url) | |
596 | else super(NRKTVSeasonIE, cls).suitable(url)) | |
597 | ||
598 | def _real_extract(self, url): | |
599 | mobj = self._match_valid_url(url) | |
600 | domain = mobj.group('domain') | |
601 | serie_kind = mobj.group('serie_kind') | |
602 | serie = mobj.group('serie') | |
603 | season_id = mobj.group('id') or mobj.group('id_2') | |
604 | display_id = '%s/%s' % (serie, season_id) | |
605 | ||
606 | data = self._call_api( | |
607 | '%s/catalog/%s/%s/seasons/%s' | |
608 | % (domain, self._catalog_name(serie_kind), serie, season_id), | |
609 | display_id, 'season', query={'pageSize': 50}) | |
610 | ||
611 | title = try_get(data, lambda x: x['titles']['title'], compat_str) or display_id | |
612 | return self.playlist_result( | |
613 | self._entries(data, display_id), | |
614 | display_id, title) | |
615 | ||
616 | ||
617 | class NRKTVSeriesIE(NRKTVSerieBaseIE): | |
618 | _VALID_URL = r'https?://(?P<domain>(?:tv|radio)\.nrk|(?:tv\.)?nrksuper)\.no/(?P<serie_kind>serie|pod[ck]ast)/(?P<id>[^/]+)' | |
619 | _TESTS = [{ | |
620 | # new layout, instalments | |
621 | 'url': 'https://tv.nrk.no/serie/groenn-glede', | |
622 | 'info_dict': { | |
623 | 'id': 'groenn-glede', | |
624 | 'title': 'Grønn glede', | |
625 | 'description': 'md5:7576e92ae7f65da6993cf90ee29e4608', | |
626 | }, | |
627 | 'playlist_mincount': 90, | |
628 | }, { | |
629 | # new layout, instalments, more entries | |
630 | 'url': 'https://tv.nrk.no/serie/lindmo', | |
631 | 'only_matching': True, | |
632 | }, { | |
633 | 'url': 'https://tv.nrk.no/serie/blank', | |
634 | 'info_dict': { | |
635 | 'id': 'blank', | |
636 | 'title': 'Blank', | |
637 | 'description': 'md5:7664b4e7e77dc6810cd3bca367c25b6e', | |
638 | }, | |
639 | 'playlist_mincount': 30, | |
640 | }, { | |
641 | # new layout, seasons | |
642 | 'url': 'https://tv.nrk.no/serie/backstage', | |
643 | 'info_dict': { | |
644 | 'id': 'backstage', | |
645 | 'title': 'Backstage', | |
646 | 'description': 'md5:63692ceb96813d9a207e9910483d948b', | |
647 | }, | |
648 | 'playlist_mincount': 60, | |
649 | }, { | |
650 | # old layout | |
651 | 'url': 'https://tv.nrksuper.no/serie/labyrint', | |
652 | 'info_dict': { | |
653 | 'id': 'labyrint', | |
654 | 'title': 'Labyrint', | |
655 | 'description': 'I Daidalos sin undersjøiske Labyrint venter spennende oppgaver, skumle robotskapninger og slim.', | |
656 | }, | |
657 | 'playlist_mincount': 3, | |
658 | }, { | |
659 | 'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene', | |
660 | 'only_matching': True, | |
661 | }, { | |
662 | 'url': 'https://tv.nrk.no/serie/saving-the-human-race', | |
663 | 'only_matching': True, | |
664 | }, { | |
665 | 'url': 'https://tv.nrk.no/serie/postmann-pat', | |
666 | 'only_matching': True, | |
667 | }, { | |
668 | 'url': 'https://radio.nrk.no/serie/dickie-dick-dickens', | |
669 | 'info_dict': { | |
670 | 'id': 'dickie-dick-dickens', | |
671 | 'title': 'Dickie Dick Dickens', | |
672 | 'description': 'md5:19e67411ffe57f7dce08a943d7a0b91f', | |
673 | }, | |
674 | 'playlist_mincount': 8, | |
675 | }, { | |
676 | 'url': 'https://nrksuper.no/serie/labyrint', | |
677 | 'only_matching': True, | |
678 | }, { | |
679 | 'url': 'https://radio.nrk.no/podkast/ulrikkes_univers', | |
680 | 'info_dict': { | |
681 | 'id': 'ulrikkes_univers', | |
682 | }, | |
683 | 'playlist_mincount': 10, | |
684 | }, { | |
685 | 'url': 'https://radio.nrk.no/podkast/ulrikkes_univers/nrkno-poddkast-26588-134079-05042018030000', | |
686 | 'only_matching': True, | |
687 | }] | |
688 | ||
689 | @classmethod | |
690 | def suitable(cls, url): | |
691 | return ( | |
692 | False if any(ie.suitable(url) | |
693 | for ie in (NRKTVIE, NRKTVEpisodeIE, NRKRadioPodkastIE, NRKTVSeasonIE)) | |
694 | else super(NRKTVSeriesIE, cls).suitable(url)) | |
695 | ||
696 | def _real_extract(self, url): | |
697 | site, serie_kind, series_id = self._match_valid_url(url).groups() | |
698 | is_radio = site == 'radio.nrk' | |
699 | domain = 'radio' if is_radio else 'tv' | |
700 | ||
701 | size_prefix = 'p' if is_radio else 'embeddedInstalmentsP' | |
702 | series = self._call_api( | |
703 | '%s/catalog/%s/%s' | |
704 | % (domain, self._catalog_name(serie_kind), series_id), | |
705 | series_id, 'serie', query={size_prefix + 'ageSize': 50}) | |
706 | titles = try_get(series, [ | |
707 | lambda x: x['titles'], | |
708 | lambda x: x[x['type']]['titles'], | |
709 | lambda x: x[x['seriesType']]['titles'], | |
710 | ]) or {} | |
711 | ||
712 | entries = [] | |
713 | entries.extend(self._entries(series, series_id)) | |
714 | embedded = series.get('_embedded') or {} | |
715 | linked_seasons = try_get(series, lambda x: x['_links']['seasons']) or [] | |
716 | embedded_seasons = embedded.get('seasons') or [] | |
717 | if len(linked_seasons) > len(embedded_seasons): | |
718 | for season in linked_seasons: | |
719 | season_url = urljoin(url, season.get('href')) | |
720 | if not season_url: | |
721 | season_name = season.get('name') | |
722 | if season_name and isinstance(season_name, compat_str): | |
723 | season_url = 'https://%s.nrk.no/serie/%s/sesong/%s' % (domain, series_id, season_name) | |
724 | if season_url: | |
725 | entries.append(self.url_result( | |
726 | season_url, ie=NRKTVSeasonIE.ie_key(), | |
727 | video_title=season.get('title'))) | |
728 | else: | |
729 | for season in embedded_seasons: | |
730 | entries.extend(self._entries(season, series_id)) | |
731 | entries.extend(self._entries( | |
732 | embedded.get('extraMaterial') or {}, series_id)) | |
733 | ||
734 | return self.playlist_result( | |
735 | entries, series_id, titles.get('title'), titles.get('subtitle')) | |
736 | ||
737 | ||
738 | class NRKTVDirekteIE(NRKTVIE): # XXX: Do not subclass from concrete IE | |
739 | IE_DESC = 'NRK TV Direkte and NRK Radio Direkte' | |
740 | _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)' | |
741 | ||
742 | _TESTS = [{ | |
743 | 'url': 'https://tv.nrk.no/direkte/nrk1', | |
744 | 'only_matching': True, | |
745 | }, { | |
746 | 'url': 'https://radio.nrk.no/direkte/p1_oslo_akershus', | |
747 | 'only_matching': True, | |
748 | }] | |
749 | ||
750 | ||
751 | class NRKRadioPodkastIE(InfoExtractor): | |
752 | _VALID_URL = r'https?://radio\.nrk\.no/pod[ck]ast/(?:[^/]+/)+(?P<id>l_[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' | |
753 | ||
754 | _TESTS = [{ | |
755 | 'url': 'https://radio.nrk.no/podkast/ulrikkes_univers/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8', | |
756 | 'md5': '8d40dab61cea8ab0114e090b029a0565', | |
757 | 'info_dict': { | |
758 | 'id': 'MUHH48000314AA', | |
759 | 'ext': 'mp4', | |
760 | 'title': '20 spørsmål 23.05.2014', | |
761 | 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', | |
762 | 'duration': 1741, | |
763 | 'series': '20 spørsmål', | |
764 | 'episode': '23.05.2014', | |
765 | }, | |
766 | }, { | |
767 | 'url': 'https://radio.nrk.no/podcast/ulrikkes_univers/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8', | |
768 | 'only_matching': True, | |
769 | }, { | |
770 | 'url': 'https://radio.nrk.no/podkast/ulrikkes_univers/sesong/1/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8', | |
771 | 'only_matching': True, | |
772 | }, { | |
773 | 'url': 'https://radio.nrk.no/podkast/hele_historien/sesong/bortfoert-i-bergen/l_774d1a2c-7aa7-4965-8d1a-2c7aa7d9652c', | |
774 | 'only_matching': True, | |
775 | }] | |
776 | ||
777 | def _real_extract(self, url): | |
778 | video_id = self._match_id(url) | |
779 | return self.url_result( | |
780 | 'nrk:%s' % video_id, ie=NRKIE.ie_key(), video_id=video_id) | |
781 | ||
782 | ||
783 | class NRKPlaylistBaseIE(InfoExtractor): | |
784 | def _extract_description(self, webpage): | |
785 | pass | |
786 | ||
787 | def _real_extract(self, url): | |
788 | playlist_id = self._match_id(url) | |
789 | ||
790 | webpage = self._download_webpage(url, playlist_id) | |
791 | ||
792 | entries = [ | |
793 | self.url_result('nrk:%s' % video_id, NRKIE.ie_key()) | |
794 | for video_id in re.findall(self._ITEM_RE, webpage) | |
795 | ] | |
796 | ||
797 | playlist_title = self._extract_title(webpage) | |
798 | playlist_description = self._extract_description(webpage) | |
799 | ||
800 | return self.playlist_result( | |
801 | entries, playlist_id, playlist_title, playlist_description) | |
802 | ||
803 | ||
804 | class NRKPlaylistIE(NRKPlaylistBaseIE): | |
805 | _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)' | |
806 | _ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"' | |
807 | _TESTS = [{ | |
808 | 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763', | |
809 | 'info_dict': { | |
810 | 'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763', | |
811 | 'title': 'Gjenopplev den historiske solformørkelsen', | |
812 | 'description': 'md5:c2df8ea3bac5654a26fc2834a542feed', | |
813 | }, | |
814 | 'playlist_count': 2, | |
815 | }, { | |
816 | 'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449', | |
817 | 'info_dict': { | |
818 | 'id': 'rivertonprisen-til-karin-fossum-1.12266449', | |
819 | 'title': 'Rivertonprisen til Karin Fossum', | |
820 | 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.', | |
821 | }, | |
822 | 'playlist_count': 2, | |
823 | }] | |
824 | ||
825 | def _extract_title(self, webpage): | |
826 | return self._og_search_title(webpage, fatal=False) | |
827 | ||
828 | def _extract_description(self, webpage): | |
829 | return self._og_search_description(webpage) | |
830 | ||
831 | ||
832 | class NRKTVEpisodesIE(NRKPlaylistBaseIE): | |
833 | _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)' | |
834 | _ITEM_RE = r'data-episode=["\']%s' % NRKTVIE._EPISODE_RE | |
835 | _TESTS = [{ | |
836 | 'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031', | |
837 | 'info_dict': { | |
838 | 'id': '69031', | |
839 | 'title': 'Nytt på nytt, sesong: 201210', | |
840 | }, | |
841 | 'playlist_count': 4, | |
842 | }] | |
843 | ||
844 | def _extract_title(self, webpage): | |
845 | return self._html_search_regex( | |
846 | r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False) | |
847 | ||
848 | ||
849 | class NRKSkoleIE(InfoExtractor): | |
850 | IE_DESC = 'NRK Skole' | |
851 | _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)' | |
852 | ||
853 | _TESTS = [{ | |
854 | 'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099', | |
855 | 'md5': '18c12c3d071953c3bf8d54ef6b2587b7', | |
856 | 'info_dict': { | |
857 | 'id': '6021', | |
858 | 'ext': 'mp4', | |
859 | 'title': 'Genetikk og eneggede tvillinger', | |
860 | 'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d', | |
861 | 'duration': 399, | |
862 | }, | |
863 | }, { | |
864 | 'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355', | |
865 | 'only_matching': True, | |
866 | }] | |
867 | ||
868 | def _real_extract(self, url): | |
869 | video_id = self._match_id(url) | |
870 | ||
871 | nrk_id = self._download_json( | |
872 | 'https://nrkno-skole-prod.kube.nrk.no/skole/api/media/%s' % video_id, | |
873 | video_id)['psId'] | |
874 | ||
875 | return self.url_result('nrk:%s' % nrk_id) |