]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/orf.py
[version] update
[yt-dlp.git] / yt_dlp / extractor / orf.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import functools
5 import re
6
7 from .common import InfoExtractor
8 from ..utils import (
9 clean_html,
10 determine_ext,
11 float_or_none,
12 HEADRequest,
13 InAdvancePagedList,
14 int_or_none,
15 join_nonempty,
16 orderedSet,
17 remove_end,
18 smuggle_url,
19 str_or_none,
20 strip_jsonp,
21 unescapeHTML,
22 unified_strdate,
23 unsmuggle_url,
24 url_or_none,
25 )
26
27
28 class ORFTVthekIE(InfoExtractor):
29 IE_NAME = 'orf:tvthek'
30 IE_DESC = 'ORF TVthek'
31 _VALID_URL = r'(?P<url>https?://tvthek\.orf\.at/(?:(?:[^/]+/){2}){1,2}(?P<id>\d+))(/[^/]+/(?P<vid>\d+))?(?:$|[?#])'
32
33 _TESTS = [{
34 'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079',
35 'info_dict': {
36 'id': '14121079',
37 },
38 'playlist_count': 11,
39 'params': {'noplaylist': True}
40 }, {
41 'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079/Umfrage-Welches-Tier-ist-Sebastian-Kurz/15083150',
42 'info_dict': {
43 'id': '14121079',
44 },
45 'playlist_count': 1,
46 'params': {'playlist_items': '5'}
47 }, {
48 'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079/Umfrage-Welches-Tier-ist-Sebastian-Kurz/15083150',
49 'info_dict': {
50 'id': '14121079',
51 'playlist_count': 1
52 },
53 'playlist': [{
54 'info_dict': {
55 'id': '15083150',
56 'ext': 'mp4',
57 'description': 'md5:7be1c485425f5f255a5e4e4815e77d04',
58 'thumbnail': 'https://api-tvthek.orf.at/uploads/media/segments/0130/59/824271ea35cd8931a0fb08ab316a5b0a1562342c.jpeg',
59 'title': 'Umfrage: Welches Tier ist Sebastian Kurz?',
60 }
61 }],
62 'playlist_count': 1,
63 'params': {'noplaylist': True, 'skip_download': 'm3u8'}
64 }, {
65 'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
66 'playlist': [{
67 'md5': '2942210346ed779588f428a92db88712',
68 'info_dict': {
69 'id': '8896777',
70 'ext': 'mp4',
71 'title': 'Aufgetischt: Mit der Steirischen Tafelrunde',
72 'description': 'md5:c1272f0245537812d4e36419c207b67d',
73 'duration': 2668,
74 'upload_date': '20141208',
75 },
76 }],
77 'skip': 'Blocked outside of Austria / Germany',
78 }, {
79 'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256',
80 'info_dict': {
81 'id': '7982259',
82 'ext': 'mp4',
83 'title': 'Best of Ingrid Thurnher',
84 'upload_date': '20140527',
85 'description': 'Viele Jahre war Ingrid Thurnher das "Gesicht" der ZIB 2. Vor ihrem Wechsel zur ZIB 2 im Jahr 1995 moderierte sie unter anderem "Land und Leute", "Österreich-Bild" und "Niederösterreich heute".',
86 },
87 'params': {
88 'skip_download': True, # rtsp downloads
89 },
90 'skip': 'Blocked outside of Austria / Germany',
91 }, {
92 'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141',
93 'only_matching': True,
94 }, {
95 'url': 'http://tvthek.orf.at/profile/Universum/35429',
96 'only_matching': True,
97 }]
98
99 def _pagefunc(self, url, data_jsb, n, *, image=None):
100 sd = data_jsb[n]
101 video_id, title = str(sd['id']), sd['title']
102 formats = []
103 for fd in sd['sources']:
104 src = url_or_none(fd.get('src'))
105 if not src:
106 continue
107 format_id = join_nonempty('delivery', 'quality', 'quality_string', from_dict=fd)
108 ext = determine_ext(src)
109 if ext == 'm3u8':
110 m3u8_formats = self._extract_m3u8_formats(
111 src, video_id, 'mp4', m3u8_id=format_id, fatal=False, note=f'Downloading {format_id} m3u8 manifest')
112 if any('/geoprotection' in f['url'] for f in m3u8_formats):
113 self.raise_geo_restricted()
114 formats.extend(m3u8_formats)
115 elif ext == 'f4m':
116 formats.extend(self._extract_f4m_formats(
117 src, video_id, f4m_id=format_id, fatal=False))
118 elif ext == 'mpd':
119 formats.extend(self._extract_mpd_formats(
120 src, video_id, mpd_id=format_id, fatal=False, note=f'Downloading {format_id} mpd manifest'))
121 else:
122 formats.append({
123 'format_id': format_id,
124 'url': src,
125 'protocol': fd.get('protocol'),
126 })
127
128 # Check for geoblocking.
129 # There is a property is_geoprotection, but that's always false
130 geo_str = sd.get('geoprotection_string')
131 http_url = next(
132 (f['url'] for f in formats if re.match(r'^https?://.*\.mp4$', f['url'])),
133 None) if geo_str else None
134 if http_url:
135 self._request_webpage(
136 HEADRequest(http_url), video_id, fatal=False, note='Testing for geoblocking',
137 errnote=f'This video seems to be blocked outside of {geo_str}. You may want to try the streaming-* formats')
138
139 self._sort_formats(formats)
140
141 subtitles = {}
142 for sub in sd.get('subtitles', []):
143 sub_src = sub.get('src')
144 if not sub_src:
145 continue
146 subtitles.setdefault(sub.get('lang', 'de-AT'), []).append({
147 'url': sub_src,
148 })
149
150 upload_date = unified_strdate(sd.get('created_date'))
151
152 thumbnails = []
153 preview = sd.get('preview_image_url')
154 if preview:
155 thumbnails.append({
156 'id': 'preview',
157 'url': preview,
158 'preference': 0,
159 })
160 image = sd.get('image_full_url') or image
161 if image:
162 thumbnails.append({
163 'id': 'full',
164 'url': image,
165 'preference': 1,
166 })
167
168 yield {
169 'id': video_id,
170 'title': title,
171 'webpage_url': smuggle_url(f'{url}/part/{video_id}', {'force_noplaylist': True}),
172 'formats': formats,
173 'subtitles': subtitles,
174 'description': sd.get('description'),
175 'duration': int_or_none(sd.get('duration_in_seconds')),
176 'upload_date': upload_date,
177 'thumbnails': thumbnails,
178 }
179
180 def _real_extract(self, url):
181 url, smuggled_data = unsmuggle_url(url)
182 playlist_id, video_id, base_url = self._match_valid_url(url).group('id', 'vid', 'url')
183 webpage = self._download_webpage(url, playlist_id)
184
185 data_jsb = self._parse_json(
186 self._search_regex(
187 r'<div[^>]+class=(["\']).*?VideoPlaylist.*?\1[^>]+data-jsb=(["\'])(?P<json>.+?)\2',
188 webpage, 'playlist', group='json'),
189 playlist_id, transform_source=unescapeHTML)['playlist']['videos']
190
191 if not self._yes_playlist(playlist_id, video_id, smuggled_data):
192 data_jsb = [sd for sd in data_jsb if str(sd.get('id')) == video_id]
193
194 playlist_count = len(data_jsb)
195 image = self._og_search_thumbnail(webpage) if playlist_count == 1 else None
196
197 page_func = functools.partial(self._pagefunc, base_url, data_jsb, image=image)
198 return {
199 '_type': 'playlist',
200 'entries': InAdvancePagedList(page_func, playlist_count, 1),
201 'id': playlist_id,
202 }
203
204
205 class ORFRadioIE(InfoExtractor):
206 def _real_extract(self, url):
207 mobj = self._match_valid_url(url)
208 show_date = mobj.group('date')
209 show_id = mobj.group('show')
210
211 data = self._download_json(
212 'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s'
213 % (self._API_STATION, show_id, show_date), show_id)
214
215 entries = []
216 for info in data['streams']:
217 loop_stream_id = str_or_none(info.get('loopStreamId'))
218 if not loop_stream_id:
219 continue
220 title = str_or_none(data.get('title'))
221 if not title:
222 continue
223 start = int_or_none(info.get('start'), scale=1000)
224 end = int_or_none(info.get('end'), scale=1000)
225 duration = end - start if end and start else None
226 entries.append({
227 'id': loop_stream_id.replace('.mp3', ''),
228 'url': 'https://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id),
229 'title': title,
230 'description': clean_html(data.get('subtitle')),
231 'duration': duration,
232 'timestamp': start,
233 'ext': 'mp3',
234 'series': data.get('programTitle'),
235 })
236
237 return {
238 '_type': 'playlist',
239 'id': show_id,
240 'title': data.get('title'),
241 'description': clean_html(data.get('subtitle')),
242 'entries': entries,
243 }
244
245
246 class ORFFM4IE(ORFRadioIE):
247 IE_NAME = 'orf:fm4'
248 IE_DESC = 'radio FM4'
249 _VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>4\w+)'
250 _API_STATION = 'fm4'
251 _LOOP_STATION = 'fm4'
252
253 _TEST = {
254 'url': 'http://fm4.orf.at/player/20170107/4CC',
255 'md5': '2b0be47375432a7ef104453432a19212',
256 'info_dict': {
257 'id': '2017-01-07_2100_tl_54_7DaysSat18_31295',
258 'ext': 'mp3',
259 'title': 'Solid Steel Radioshow',
260 'description': 'Die Mixshow von Coldcut und Ninja Tune.',
261 'duration': 3599,
262 'timestamp': 1483819257,
263 'upload_date': '20170107',
264 },
265 'skip': 'Shows from ORF radios are only available for 7 days.',
266 'only_matching': True,
267 }
268
269
270 class ORFNOEIE(ORFRadioIE):
271 IE_NAME = 'orf:noe'
272 IE_DESC = 'Radio Niederösterreich'
273 _VALID_URL = r'https?://(?P<station>noe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
274 _API_STATION = 'noe'
275 _LOOP_STATION = 'oe2n'
276
277 _TEST = {
278 'url': 'https://noe.orf.at/player/20200423/NGM',
279 'only_matching': True,
280 }
281
282
283 class ORFWIEIE(ORFRadioIE):
284 IE_NAME = 'orf:wien'
285 IE_DESC = 'Radio Wien'
286 _VALID_URL = r'https?://(?P<station>wien)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
287 _API_STATION = 'wie'
288 _LOOP_STATION = 'oe2w'
289
290 _TEST = {
291 'url': 'https://wien.orf.at/player/20200423/WGUM',
292 'only_matching': True,
293 }
294
295
296 class ORFBGLIE(ORFRadioIE):
297 IE_NAME = 'orf:burgenland'
298 IE_DESC = 'Radio Burgenland'
299 _VALID_URL = r'https?://(?P<station>burgenland)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
300 _API_STATION = 'bgl'
301 _LOOP_STATION = 'oe2b'
302
303 _TEST = {
304 'url': 'https://burgenland.orf.at/player/20200423/BGM',
305 'only_matching': True,
306 }
307
308
309 class ORFOOEIE(ORFRadioIE):
310 IE_NAME = 'orf:oberoesterreich'
311 IE_DESC = 'Radio Oberösterreich'
312 _VALID_URL = r'https?://(?P<station>ooe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
313 _API_STATION = 'ooe'
314 _LOOP_STATION = 'oe2o'
315
316 _TEST = {
317 'url': 'https://ooe.orf.at/player/20200423/OGMO',
318 'only_matching': True,
319 }
320
321
322 class ORFSTMIE(ORFRadioIE):
323 IE_NAME = 'orf:steiermark'
324 IE_DESC = 'Radio Steiermark'
325 _VALID_URL = r'https?://(?P<station>steiermark)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
326 _API_STATION = 'stm'
327 _LOOP_STATION = 'oe2st'
328
329 _TEST = {
330 'url': 'https://steiermark.orf.at/player/20200423/STGMS',
331 'only_matching': True,
332 }
333
334
335 class ORFKTNIE(ORFRadioIE):
336 IE_NAME = 'orf:kaernten'
337 IE_DESC = 'Radio Kärnten'
338 _VALID_URL = r'https?://(?P<station>kaernten)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
339 _API_STATION = 'ktn'
340 _LOOP_STATION = 'oe2k'
341
342 _TEST = {
343 'url': 'https://kaernten.orf.at/player/20200423/KGUMO',
344 'only_matching': True,
345 }
346
347
348 class ORFSBGIE(ORFRadioIE):
349 IE_NAME = 'orf:salzburg'
350 IE_DESC = 'Radio Salzburg'
351 _VALID_URL = r'https?://(?P<station>salzburg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
352 _API_STATION = 'sbg'
353 _LOOP_STATION = 'oe2s'
354
355 _TEST = {
356 'url': 'https://salzburg.orf.at/player/20200423/SGUM',
357 'only_matching': True,
358 }
359
360
361 class ORFTIRIE(ORFRadioIE):
362 IE_NAME = 'orf:tirol'
363 IE_DESC = 'Radio Tirol'
364 _VALID_URL = r'https?://(?P<station>tirol)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
365 _API_STATION = 'tir'
366 _LOOP_STATION = 'oe2t'
367
368 _TEST = {
369 'url': 'https://tirol.orf.at/player/20200423/TGUMO',
370 'only_matching': True,
371 }
372
373
374 class ORFVBGIE(ORFRadioIE):
375 IE_NAME = 'orf:vorarlberg'
376 IE_DESC = 'Radio Vorarlberg'
377 _VALID_URL = r'https?://(?P<station>vorarlberg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
378 _API_STATION = 'vbg'
379 _LOOP_STATION = 'oe2v'
380
381 _TEST = {
382 'url': 'https://vorarlberg.orf.at/player/20200423/VGUM',
383 'only_matching': True,
384 }
385
386
387 class ORFOE3IE(ORFRadioIE):
388 IE_NAME = 'orf:oe3'
389 IE_DESC = 'Radio Österreich 3'
390 _VALID_URL = r'https?://(?P<station>oe3)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
391 _API_STATION = 'oe3'
392 _LOOP_STATION = 'oe3'
393
394 _TEST = {
395 'url': 'https://oe3.orf.at/player/20200424/3WEK',
396 'only_matching': True,
397 }
398
399
400 class ORFOE1IE(ORFRadioIE):
401 IE_NAME = 'orf:oe1'
402 IE_DESC = 'Radio Österreich 1'
403 _VALID_URL = r'https?://(?P<station>oe1)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
404 _API_STATION = 'oe1'
405 _LOOP_STATION = 'oe1'
406
407 _TEST = {
408 'url': 'http://oe1.orf.at/player/20170108/456544',
409 'md5': '34d8a6e67ea888293741c86a099b745b',
410 'info_dict': {
411 'id': '2017-01-08_0759_tl_51_7DaysSun6_256141',
412 'ext': 'mp3',
413 'title': 'Morgenjournal',
414 'duration': 609,
415 'timestamp': 1483858796,
416 'upload_date': '20170108',
417 },
418 'skip': 'Shows from ORF radios are only available for 7 days.'
419 }
420
421
422 class ORFIPTVIE(InfoExtractor):
423 IE_NAME = 'orf:iptv'
424 IE_DESC = 'iptv.ORF.at'
425 _VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
426
427 _TEST = {
428 'url': 'http://iptv.orf.at/stories/2275236/',
429 'md5': 'c8b22af4718a4b4af58342529453e3e5',
430 'info_dict': {
431 'id': '350612',
432 'ext': 'flv',
433 'title': 'Weitere Evakuierungen um Vulkan Calbuco',
434 'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
435 'duration': 68.197,
436 'thumbnail': r're:^https?://.*\.jpg$',
437 'upload_date': '20150425',
438 },
439 }
440
441 def _real_extract(self, url):
442 story_id = self._match_id(url)
443
444 webpage = self._download_webpage(
445 'http://iptv.orf.at/stories/%s' % story_id, story_id)
446
447 video_id = self._search_regex(
448 r'data-video(?:id)?="(\d+)"', webpage, 'video id')
449
450 data = self._download_json(
451 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
452 video_id)[0]
453
454 duration = float_or_none(data['duration'], 1000)
455
456 video = data['sources']['default']
457 load_balancer_url = video['loadBalancerUrl']
458 abr = int_or_none(video.get('audioBitrate'))
459 vbr = int_or_none(video.get('bitrate'))
460 fps = int_or_none(video.get('videoFps'))
461 width = int_or_none(video.get('videoWidth'))
462 height = int_or_none(video.get('videoHeight'))
463 thumbnail = video.get('preview')
464
465 rendition = self._download_json(
466 load_balancer_url, video_id, transform_source=strip_jsonp)
467
468 f = {
469 'abr': abr,
470 'vbr': vbr,
471 'fps': fps,
472 'width': width,
473 'height': height,
474 }
475
476 formats = []
477 for format_id, format_url in rendition['redirect'].items():
478 if format_id == 'rtmp':
479 ff = f.copy()
480 ff.update({
481 'url': format_url,
482 'format_id': format_id,
483 })
484 formats.append(ff)
485 elif determine_ext(format_url) == 'f4m':
486 formats.extend(self._extract_f4m_formats(
487 format_url, video_id, f4m_id=format_id))
488 elif determine_ext(format_url) == 'm3u8':
489 formats.extend(self._extract_m3u8_formats(
490 format_url, video_id, 'mp4', m3u8_id=format_id))
491 else:
492 continue
493 self._sort_formats(formats)
494
495 title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at')
496 description = self._og_search_description(webpage)
497 upload_date = unified_strdate(self._html_search_meta(
498 'dc.date', webpage, 'upload date'))
499
500 return {
501 'id': video_id,
502 'title': title,
503 'description': description,
504 'duration': duration,
505 'thumbnail': thumbnail,
506 'upload_date': upload_date,
507 'formats': formats,
508 }
509
510
511 class ORFFM4StoryIE(InfoExtractor):
512 IE_NAME = 'orf:fm4:story'
513 IE_DESC = 'fm4.orf.at stories'
514 _VALID_URL = r'https?://fm4\.orf\.at/stories/(?P<id>\d+)'
515
516 _TEST = {
517 'url': 'http://fm4.orf.at/stories/2865738/',
518 'playlist': [{
519 'md5': 'e1c2c706c45c7b34cf478bbf409907ca',
520 'info_dict': {
521 'id': '547792',
522 'ext': 'flv',
523 'title': 'Manu Delago und Inner Tongue live',
524 'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
525 'duration': 1748.52,
526 'thumbnail': r're:^https?://.*\.jpg$',
527 'upload_date': '20170913',
528 },
529 }, {
530 'md5': 'c6dd2179731f86f4f55a7b49899d515f',
531 'info_dict': {
532 'id': '547798',
533 'ext': 'flv',
534 'title': 'Manu Delago und Inner Tongue live (2)',
535 'duration': 1504.08,
536 'thumbnail': r're:^https?://.*\.jpg$',
537 'upload_date': '20170913',
538 'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
539 },
540 }],
541 }
542
543 def _real_extract(self, url):
544 story_id = self._match_id(url)
545 webpage = self._download_webpage(url, story_id)
546
547 entries = []
548 all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage))
549 for idx, video_id in enumerate(all_ids):
550 data = self._download_json(
551 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
552 video_id)[0]
553
554 duration = float_or_none(data['duration'], 1000)
555
556 video = data['sources']['q8c']
557 load_balancer_url = video['loadBalancerUrl']
558 abr = int_or_none(video.get('audioBitrate'))
559 vbr = int_or_none(video.get('bitrate'))
560 fps = int_or_none(video.get('videoFps'))
561 width = int_or_none(video.get('videoWidth'))
562 height = int_or_none(video.get('videoHeight'))
563 thumbnail = video.get('preview')
564
565 rendition = self._download_json(
566 load_balancer_url, video_id, transform_source=strip_jsonp)
567
568 f = {
569 'abr': abr,
570 'vbr': vbr,
571 'fps': fps,
572 'width': width,
573 'height': height,
574 }
575
576 formats = []
577 for format_id, format_url in rendition['redirect'].items():
578 if format_id == 'rtmp':
579 ff = f.copy()
580 ff.update({
581 'url': format_url,
582 'format_id': format_id,
583 })
584 formats.append(ff)
585 elif determine_ext(format_url) == 'f4m':
586 formats.extend(self._extract_f4m_formats(
587 format_url, video_id, f4m_id=format_id))
588 elif determine_ext(format_url) == 'm3u8':
589 formats.extend(self._extract_m3u8_formats(
590 format_url, video_id, 'mp4', m3u8_id=format_id))
591 else:
592 continue
593 self._sort_formats(formats)
594
595 title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at')
596 if idx >= 1:
597 # Titles are duplicates, make them unique
598 title += ' (' + str(idx + 1) + ')'
599 description = self._og_search_description(webpage)
600 upload_date = unified_strdate(self._html_search_meta(
601 'dc.date', webpage, 'upload date'))
602
603 entries.append({
604 'id': video_id,
605 'title': title,
606 'description': description,
607 'duration': duration,
608 'thumbnail': thumbnail,
609 'upload_date': upload_date,
610 'formats': formats,
611 })
612
613 return self.playlist_result(entries)