4 from .common
import InfoExtractor
26 class ORFTVthekIE(InfoExtractor
):
27 IE_NAME
= 'orf:tvthek'
28 IE_DESC
= 'ORF TVthek'
29 _VALID_URL
= r
'(?P<url>https?://tvthek\.orf\.at/(?:(?:[^/]+/){2}){1,2}(?P<id>\d+))(/[^/]+/(?P<vid>\d+))?(?:$|[?#])'
32 'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079',
37 'params': {'noplaylist': True}
39 'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079/Umfrage-Welches-Tier-ist-Sebastian-Kurz/15083150',
44 'params': {'playlist_items': '5'}
46 'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079/Umfrage-Welches-Tier-ist-Sebastian-Kurz/15083150',
55 'description': 'md5:7be1c485425f5f255a5e4e4815e77d04',
56 'thumbnail': 'https://api-tvthek.orf.at/uploads/media/segments/0130/59/824271ea35cd8931a0fb08ab316a5b0a1562342c.jpeg',
57 'title': 'Umfrage: Welches Tier ist Sebastian Kurz?',
61 'params': {'noplaylist': True, 'skip_download': 'm3u8'}
63 'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
65 'md5': '2942210346ed779588f428a92db88712',
69 'title': 'Aufgetischt: Mit der Steirischen Tafelrunde',
70 'description': 'md5:c1272f0245537812d4e36419c207b67d',
72 'upload_date': '20141208',
75 'skip': 'Blocked outside of Austria / Germany',
77 'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256',
81 'title': 'Best of Ingrid Thurnher',
82 'upload_date': '20140527',
83 '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 'skip_download': True, # rtsp downloads
88 'skip': 'Blocked outside of Austria / Germany',
90 'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141',
91 'only_matching': True,
93 'url': 'http://tvthek.orf.at/profile/Universum/35429',
94 'only_matching': True,
97 def _pagefunc(self
, url
, data_jsb
, n
, *, image
=None):
99 video_id
, title
= str(sd
['id']), sd
['title']
101 for fd
in sd
['sources']:
102 src
= url_or_none(fd
.get('src'))
105 format_id
= join_nonempty('delivery', 'quality', 'quality_string', from_dict
=fd
)
106 ext
= determine_ext(src
)
108 m3u8_formats
= self
._extract
_m
3u8_formats
(
109 src
, video_id
, 'mp4', m3u8_id
=format_id
, fatal
=False, note
=f
'Downloading {format_id} m3u8 manifest')
110 if any('/geoprotection' in f
['url'] for f
in m3u8_formats
):
111 self
.raise_geo_restricted()
112 formats
.extend(m3u8_formats
)
114 formats
.extend(self
._extract
_f
4m
_formats
(
115 src
, video_id
, f4m_id
=format_id
, fatal
=False))
117 formats
.extend(self
._extract
_mpd
_formats
(
118 src
, video_id
, mpd_id
=format_id
, fatal
=False, note
=f
'Downloading {format_id} mpd manifest'))
121 'format_id': format_id
,
123 'protocol': fd
.get('protocol'),
126 # Check for geoblocking.
127 # There is a property is_geoprotection, but that's always false
128 geo_str
= sd
.get('geoprotection_string')
130 (f
['url'] for f
in formats
if re
.match(r
'^https?://.*\.mp4$', f
['url'])),
131 None) if geo_str
else None
133 self
._request
_webpage
(
134 HEADRequest(http_url
), video_id
, fatal
=False, note
='Testing for geoblocking',
135 errnote
=f
'This video seems to be blocked outside of {geo_str}. You may want to try the streaming-* formats')
138 for sub
in sd
.get('subtitles', []):
139 sub_src
= sub
.get('src')
142 subtitles
.setdefault(sub
.get('lang', 'de-AT'), []).append({
146 upload_date
= unified_strdate(sd
.get('created_date'))
149 preview
= sd
.get('preview_image_url')
156 image
= sd
.get('image_full_url') or image
167 'webpage_url': smuggle_url(f
'{url}/part/{video_id}', {'force_noplaylist': True}
),
169 'subtitles': subtitles
,
170 'description': sd
.get('description'),
171 'duration': int_or_none(sd
.get('duration_in_seconds')),
172 'upload_date': upload_date
,
173 'thumbnails': thumbnails
,
176 def _real_extract(self
, url
):
177 url
, smuggled_data
= unsmuggle_url(url
)
178 playlist_id
, video_id
, base_url
= self
._match
_valid
_url
(url
).group('id', 'vid', 'url')
179 webpage
= self
._download
_webpage
(url
, playlist_id
)
181 data_jsb
= self
._parse
_json
(
183 r
'<div[^>]+class=(["\']).*?VideoPlaylist
.*?\
1[^
>]+data
-jsb
=(["\'])(?P<json>.+?)\2',
184 webpage, 'playlist', group='json'),
185 playlist_id, transform_source=unescapeHTML)['playlist']['videos']
187 if not self._yes_playlist(playlist_id, video_id, smuggled_data):
188 data_jsb = [sd for sd in data_jsb if str(sd.get('id')) == video_id]
190 playlist_count = len(data_jsb)
191 image = self._og_search_thumbnail(webpage) if playlist_count == 1 else None
193 page_func = functools.partial(self._pagefunc, base_url, data_jsb, image=image)
196 'entries': InAdvancePagedList(page_func, playlist_count, 1),
201 class ORFRadioIE(InfoExtractor):
202 IE_NAME = 'orf:radio'
205 'fm4': ('fm4', 'fm4', 'orffm4'),
206 'noe': ('noe', 'oe2n', 'orfnoe'),
207 'wien': ('wie', 'oe2w', 'orfwie'),
208 'burgenland': ('bgl', 'oe2b', 'orfbgl'),
209 'ooe': ('ooe', 'oe2o', 'orfooe'),
210 'steiermark': ('stm', 'oe2st', 'orfstm'),
211 'kaernten': ('ktn', 'oe2k', 'orfktn'),
212 'salzburg': ('sbg', 'oe2s', 'orfsbg'),
213 'tirol': ('tir', 'oe2t', 'orftir'),
214 'vorarlberg': ('vbg', 'oe2v', 'orfvbg'),
215 'oe3': ('oe3', 'oe3', 'orfoe3'),
216 'oe1': ('oe1', 'oe1', 'orfoe1'),
218 _STATION_RE = '|'.join(map(re.escape, STATION_INFO.keys()))
220 _VALID_URL = rf'''(?x)
222 (?P<station>{_STATION_RE})\.orf\.at/player|
223 radiothek\.orf\.at/(?P<station2>{_STATION_RE})
224 )/(?P<date>[0-9]+)/(?P<show>\w+)'''
227 'url': 'https://radiothek.orf.at/ooe/20220801/OGMO',
230 'title': 'Guten Morgen OÖ',
231 'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
234 'md5': 'f33147d954a326e338ea52572c2810e8',
236 'id': '2022-08-01_0459_tl_66_7DaysMon1_319062',
238 'title': 'Guten Morgen OÖ',
239 'upload_date': '20220801',
241 'timestamp': 1659322789,
242 'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
246 'url': 'https://ooe.orf.at/player/20220801/OGMO',
249 'title': 'Guten Morgen OÖ',
250 'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
253 'md5': 'f33147d954a326e338ea52572c2810e8',
255 'id': '2022-08-01_0459_tl_66_7DaysMon1_319062',
257 'title': 'Guten Morgen OÖ',
258 'upload_date': '20220801',
260 'timestamp': 1659322789,
261 'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
265 'url': 'http://fm4.orf.at/player/20170107/4CC',
266 'only_matching': True,
268 'url': 'https://noe.orf.at/player/20200423/NGM',
269 'only_matching': True,
271 'url': 'https://wien.orf.at/player/20200423/WGUM',
272 'only_matching': True,
274 'url': 'https://burgenland.orf.at/player/20200423/BGM',
275 'only_matching': True,
277 'url': 'https://steiermark.orf.at/player/20200423/STGMS',
278 'only_matching': True,
280 'url': 'https://kaernten.orf.at/player/20200423/KGUMO',
281 'only_matching': True,
283 'url': 'https://salzburg.orf.at/player/20200423/SGUM',
284 'only_matching': True,
286 'url': 'https://tirol.orf.at/player/20200423/TGUMO',
287 'only_matching': True,
289 'url': 'https://vorarlberg.orf.at/player/20200423/VGUM',
290 'only_matching': True,
292 'url': 'https://oe3.orf.at/player/20200424/3WEK',
293 'only_matching': True,
295 'url': 'http://oe1.orf.at/player/20170108/456544',
296 'md5': '34d8a6e67ea888293741c86a099b745b',
298 'id': '2017-01-08_0759_tl_51_7DaysSun6_256141',
300 'title': 'Morgenjournal',
302 'timestamp': 1483858796,
303 'upload_date': '20170108',
305 'skip': 'Shows from ORF radios are only available for 7 days.'
308 def _entries(self, data, station):
309 _, loop_station, old_ie = self.STATION_INFO[station]
310 for info in data['streams']:
311 item_id = info.get('loopStreamId')
314 video_id = item_id.replace('.mp3', '')
318 'url': f'https://loopstream01.apa.at/?channel={loop_station}&id={item_id}',
319 '_old_archive_ids': [make_archive_id(old_ie, video_id)],
320 'title': data.get('title'),
321 'description': clean_html(data.get('subtitle')),
322 'duration': try_call(lambda: (info['end'] - info['start']) / 1000),
323 'timestamp': int_or_none(info.get('start'), scale=1000),
324 'series': data.get('programTitle'),
327 def _real_extract(self, url):
328 station, station2, show_date, show_id = self._match_valid_url(url).group('station', 'station2', 'date', 'show')
329 api_station, _, _ = self.STATION_INFO[station or station2]
330 data = self._download_json(
331 f'http://audioapi.orf.at/{api_station}/api/json/current/broadcast/{show_id}/{show_date}', show_id)
333 return self.playlist_result(
334 self._entries(data, station or station2), show_id, data.get('title'), clean_html(data.get('subtitle')))
337 class ORFIPTVIE(InfoExtractor):
339 IE_DESC = 'iptv.ORF.at'
340 _VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
343 'url': 'http://iptv.orf.at/stories/2275236/',
344 'md5': 'c8b22af4718a4b4af58342529453e3e5',
348 'title': 'Weitere Evakuierungen um Vulkan Calbuco',
349 'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
351 'thumbnail': r're:^https?://.*\.jpg$',
352 'upload_date': '20150425',
356 def _real_extract(self, url):
357 story_id = self._match_id(url)
359 webpage = self._download_webpage(
360 'http://iptv.orf.at/stories/%s' % story_id, story_id)
362 video_id = self._search_regex(
363 r'data-video(?:id)?="(\d
+)"', webpage, 'video id')
365 data = self._download_json(
366 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
369 duration = float_or_none(data['duration'], 1000)
371 video = data['sources']['default']
372 load_balancer_url = video['loadBalancerUrl']
373 abr = int_or_none(video.get('audioBitrate'))
374 vbr = int_or_none(video.get('bitrate'))
375 fps = int_or_none(video.get('videoFps'))
376 width = int_or_none(video.get('videoWidth'))
377 height = int_or_none(video.get('videoHeight'))
378 thumbnail = video.get('preview')
380 rendition = self._download_json(
381 load_balancer_url, video_id, transform_source=strip_jsonp)
392 for format_id, format_url in rendition['redirect'].items():
393 if format_id == 'rtmp':
397 'format_id': format_id,
400 elif determine_ext(format_url) == 'f4m':
401 formats.extend(self._extract_f4m_formats(
402 format_url, video_id, f4m_id=format_id))
403 elif determine_ext(format_url) == 'm3u8':
404 formats.extend(self._extract_m3u8_formats(
405 format_url, video_id, 'mp4', m3u8_id=format_id))
409 title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at')
410 description = self._og_search_description(webpage)
411 upload_date = unified_strdate(self._html_search_meta(
412 'dc.date', webpage, 'upload date'))
417 'description': description,
418 'duration': duration,
419 'thumbnail': thumbnail,
420 'upload_date': upload_date,
425 class ORFFM4StoryIE(InfoExtractor):
426 IE_NAME = 'orf:fm4:story'
427 IE_DESC = 'fm4.orf.at stories'
428 _VALID_URL = r'https?://fm4\.orf\.at/stories/(?P<id>\d+)'
431 'url': 'http://fm4.orf.at/stories/2865738/',
433 'md5': 'e1c2c706c45c7b34cf478bbf409907ca',
437 'title': 'Manu Delago und Inner Tongue live',
438 '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.',
440 'thumbnail': r're:^https?://.*\.jpg$',
441 'upload_date': '20170913',
444 'md5': 'c6dd2179731f86f4f55a7b49899d515f',
448 'title': 'Manu Delago und Inner Tongue live (2)',
450 'thumbnail': r're:^https?://.*\.jpg$',
451 'upload_date': '20170913',
452 '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.',
457 def _real_extract(self, url):
458 story_id = self._match_id(url)
459 webpage = self._download_webpage(url, story_id)
462 all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d
+)"', webpage))
463 for idx, video_id in enumerate(all_ids):
464 data = self._download_json(
465 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
468 duration = float_or_none(data['duration'], 1000)
470 video = data['sources']['q8c']
471 load_balancer_url = video['loadBalancerUrl']
472 abr = int_or_none(video.get('audioBitrate'))
473 vbr = int_or_none(video.get('bitrate'))
474 fps = int_or_none(video.get('videoFps'))
475 width = int_or_none(video.get('videoWidth'))
476 height = int_or_none(video.get('videoHeight'))
477 thumbnail = video.get('preview')
479 rendition = self._download_json(
480 load_balancer_url, video_id, transform_source=strip_jsonp)
491 for format_id, format_url in rendition['redirect'].items():
492 if format_id == 'rtmp':
496 'format_id': format_id,
499 elif determine_ext(format_url) == 'f4m':
500 formats.extend(self._extract_f4m_formats(
501 format_url, video_id, f4m_id=format_id))
502 elif determine_ext(format_url) == 'm3u8':
503 formats.extend(self._extract_m3u8_formats(
504 format_url, video_id, 'mp4', m3u8_id=format_id))
508 title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at')
510 # Titles are duplicates, make them unique
511 title += ' (' + str(idx + 1) + ')'
512 description = self._og_search_description(webpage)
513 upload_date = unified_strdate(self._html_search_meta(
514 'dc.date', webpage, 'upload date'))
519 'description': description,
520 'duration': duration,
521 'thumbnail': thumbnail,
522 'upload_date': upload_date,
526 return self.playlist_result(entries)