3 from .common
import InfoExtractor
32 class RaiBaseIE(InfoExtractor
):
33 _UUID_RE
= r
'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
34 _GEO_COUNTRIES
= ['IT']
37 def _extract_relinker_info(self
, relinker_url
, video_id
, audio_only
=False):
38 if not re
.match(r
'https?://', relinker_url
):
39 return {'formats': [{'url': relinker_url}
]}
46 for platform
in ('mon', 'flash', 'native'):
47 relinker
= self
._download
_xml
(
48 relinker_url
, video_id
,
49 note
=f
'Downloading XML metadata for platform {platform}',
50 transform_source
=fix_xml_ampersands
,
51 query
={'output': 45, 'pl': platform}
,
52 headers
=self
.geo_verification_headers())
54 if xpath_text(relinker
, './license_url', default
='{}') != '{}':
55 self
.report_drm(video_id
)
58 geoprotection
= xpath_text(
59 relinker
, './geoprotection', default
=None) == 'Y'
63 relinker
, './is_live', default
=None) == 'Y'
65 duration
= parse_duration(xpath_text(
66 relinker
, './duration', default
=None))
68 url_elem
= find_xpath_attr(relinker
, './url', 'type', 'content')
72 media_url
= url_elem
.text
74 # This does not imply geo restriction (e.g.
75 # http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html)
76 if '/video_no_available.mp4' in media_url
:
79 ext
= determine_ext(media_url
)
80 if (ext
== 'm3u8' and platform
!= 'mon') or (ext
== 'f4m' and platform
!= 'flash'):
88 'format_id': 'http-mp3',
91 elif ext
== 'm3u8' or 'format=m3u8' in media_url
or platform
== 'mon':
92 formats
.extend(self
._extract
_m
3u8_formats
(
93 media_url
, video_id
, 'mp4', 'm3u8_native',
94 m3u8_id
='hls', fatal
=False))
95 elif ext
== 'f4m' or platform
== 'flash':
96 manifest_url
= update_url_query(
97 media_url
.replace('manifest#live_hds.f4m', 'manifest.f4m'),
98 {'hdcore': '3.7.0', 'plugin': 'aasp-3.7.0.39.44'}
)
99 formats
.extend(self
._extract
_f
4m
_formats
(
100 manifest_url
, video_id
, f4m_id
='hds', fatal
=False))
102 bitrate
= int_or_none(xpath_text(relinker
, 'bitrate'))
105 'tbr': bitrate
if bitrate
> 0 else None,
106 'format_id': f
'http-{bitrate if bitrate > 0 else "http"}',
109 if not formats
and geoprotection
is True:
110 self
.raise_geo_restricted(countries
=self
._GEO
_COUNTRIES
, metadata_available
=True)
113 formats
.extend(self
._create
_http
_urls
(relinker_url
, formats
))
117 'duration': duration
,
121 def _create_http_urls(self
, relinker_url
, fmts
):
122 _RELINKER_REG
= r
'https?://(?P<host>[^/]+?)/(?:i/)?(?P<extra>[^/]+?)/(?P<path>.+?)/(?P<id>\w+)(?:_(?P<quality>[\d\,]+))?(?:\.mp4|/playlist\.m3u8).+?'
123 _MP4_TMPL
= '%s&overrideUserAgentRule=mp4-%s'
135 '5000': [1920, 1080],
136 '10000': [1920, 1080],
140 resp
= self
._request
_webpage
(
141 HEADRequest(url
), None, headers
={'User-Agent': 'Rai'}
,
142 fatal
=False, errnote
=False, note
=False)
148 return False if resp
.url
== url
else resp
.url
151 # filter out audio-only formats
152 fmts
= [f
for f
in fmts
if not f
.get('vcodec') == 'none']
154 def get_format_info(tbr
):
156 br
= int_or_none(tbr
)
157 if len(fmts
) == 1 and not br
:
158 br
= fmts
[0].get('tbr')
160 tbr
= compat_str(math
.floor(br
/ 100) * 100)
164 # try extracting info from available m3u8 formats
168 br_limit
= math
.floor(br
/ 100)
169 if br_limit
- 1 <= math
.floor(f
['tbr'] / 100) <= br_limit
+ 1:
170 format_copy
= f
.copy()
172 'width': format_copy
.get('width'),
173 'height': format_copy
.get('height'),
174 'tbr': format_copy
.get('tbr'),
175 'vcodec': format_copy
.get('vcodec'),
176 'acodec': format_copy
.get('acodec'),
177 'fps': format_copy
.get('fps'),
178 'format_id': f
'https-{tbr}',
179 } if format_copy
else {
180 'width': _QUALITY
[tbr
][0],
181 'height': _QUALITY
[tbr
][1],
182 'format_id': f
'https-{tbr}',
186 loc
= test_url(_MP4_TMPL
% (relinker_url
, '*'))
187 if not isinstance(loc
, compat_str
):
192 test_url(relinker_url
) or '')
196 available_qualities
= mobj
.group('quality').split(',') if mobj
.group('quality') else ['*']
197 available_qualities
= [i
for i
in available_qualities
if i
]
200 for q
in available_qualities
:
202 'url': _MP4_TMPL
% (relinker_url
, q
),
211 def _extract_subtitles(url
, video_data
):
215 subtitles_array
= video_data
.get('subtitlesArray') or []
216 for k
in ('subtitles', 'subtitlesUrl'):
217 subtitles_array
.append({'url': video_data.get(k)}
)
218 for subtitle
in subtitles_array
:
219 sub_url
= subtitle
.get('url')
220 if sub_url
and isinstance(sub_url
, compat_str
):
221 sub_lang
= subtitle
.get('language') or 'it'
222 sub_url
= urljoin(url
, sub_url
)
223 sub_ext
= determine_ext(sub_url
, SRT_EXT
)
224 subtitles
.setdefault(sub_lang
, []).append({
228 if STL_EXT
== sub_ext
:
229 subtitles
[sub_lang
].append({
231 'url': sub_url
[:-len(STL_EXT
)] + SRT_EXT
,
236 class RaiPlayIE(RaiBaseIE
):
237 _VALID_URL
= rf
'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>{RaiBaseIE._UUID_RE}))\.(?:html|json)'
239 'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
240 'md5': '8970abf8caf8aef4696e7b1f2adfc696',
242 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
244 'title': 'Report del 07/04/2014',
245 'alt_title': 'St 2013/14 - Report - Espresso nel caffè - 07/04/2014',
246 'description': 'md5:d730c168a58f4bb35600fc2f881ec04e',
247 'thumbnail': r
're:^https?://.*\.jpg$',
248 'uploader': 'Rai Gulp',
255 'release_year': 2022,
256 'episode': 'Espresso nel caffè - 07/04/2014',
257 'timestamp': 1396919880,
258 'upload_date': '20140408',
261 'skip_download': True,
264 # 1080p direct mp4 url
265 'url': 'https://www.raiplay.it/video/2021/11/Blanca-S1E1-Senza-occhi-b1255a4a-8e72-4a2f-b9f3-fc1308e00736.html',
266 'md5': 'aeda7243115380b2dd5e881fd42d949a',
268 'id': 'b1255a4a-8e72-4a2f-b9f3-fc1308e00736',
270 'title': 'Blanca - S1E1 - Senza occhi',
271 'alt_title': 'St 1 Ep 1 - Blanca - Senza occhi',
272 'description': 'md5:75f95d5c030ec8bac263b1212322e28c',
273 'thumbnail': r
're:^https?://.*\.jpg$',
277 'season': 'Season 1',
279 'release_year': 2021,
281 'episode': 'Senza occhi',
282 'timestamp': 1637318940,
283 'upload_date': '20211119',
286 'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
287 'only_matching': True,
289 # subtitles at 'subtitlesArray' key (see #27698)
290 'url': 'https://www.raiplay.it/video/2020/12/Report---04-01-2021-2e90f1de-8eee-4de4-ac0e-78d21db5b600.html',
291 'only_matching': True,
294 'url': 'https://www.raiplay.it/video/2021/06/Lo-straordinario-mondo-di-Zoey-S2E1-Lo-straordinario-ritorno-di-Zoey-3ba992de-2332-41ad-9214-73e32ab209f4.html',
295 'only_matching': True,
298 def _real_extract(self
, url
):
299 base
, video_id
= self
._match
_valid
_url
(url
).groups()
301 media
= self
._download
_json
(
302 base
+ '.json', video_id
, 'Downloading video JSON')
304 if not self
.get_param('allow_unplayable_formats'):
307 (lambda x
: x
['rights_management']['rights']['drm'],
308 lambda x
: x
['program_info']['rights_management']['rights']['drm']),
310 self
.report_drm(video_id
)
312 title
= media
['name']
313 video
= media
['video']
315 relinker_info
= self
._extract
_relinker
_info
(video
['content_url'], video_id
)
316 self
._sort
_formats
(relinker_info
['formats'])
319 for _
, value
in media
.get('images', {}).items():
322 'url': urljoin(url
, value
),
325 date_published
= media
.get('date_published')
326 time_published
= media
.get('time_published')
327 if date_published
and time_published
:
328 date_published
+= ' ' + time_published
330 subtitles
= self
._extract
_subtitles
(url
, video
)
332 program_info
= media
.get('program_info') or {}
333 season
= media
.get('season')
335 alt_title
= join_nonempty(media
.get('subtitle'), media
.get('toptitle'), delim
=' - ')
338 'id': remove_start(media
.get('id'), 'ContentItem-') or video_id
,
339 'display_id': video_id
,
341 'alt_title': strip_or_none(alt_title
or None),
342 'description': media
.get('description'),
343 'uploader': strip_or_none(media
.get('channel') or None),
344 'creator': strip_or_none(media
.get('editor') or None),
345 'duration': parse_duration(video
.get('duration')),
346 'timestamp': unified_timestamp(date_published
),
347 'thumbnails': thumbnails
,
348 'series': program_info
.get('name'),
349 'season_number': int_or_none(season
),
350 'season': season
if (season
and not season
.isdigit()) else None,
351 'episode': media
.get('episode_title'),
352 'episode_number': int_or_none(media
.get('episode')),
353 'subtitles': subtitles
,
354 'release_year': int_or_none(traverse_obj(media
, ('track_info', 'edit_year'))),
359 class RaiPlayLiveIE(RaiPlayIE
):
360 _VALID_URL
= r
'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))'
362 'url': 'http://www.raiplay.it/dirette/rainews24',
364 'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c',
365 'display_id': 'rainews24',
367 'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
368 'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497',
369 'uploader': 'Rai News 24',
370 'creator': 'Rai News 24',
372 'live_status': 'is_live',
373 'upload_date': '20090502',
374 'timestamp': 1241276220,
377 'skip_download': True,
382 class RaiPlayPlaylistIE(InfoExtractor
):
383 _VALID_URL
= r
'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))(?:/(?P<extra_id>[^?#&]+))?'
385 'url': 'https://www.raiplay.it/programmi/nondirloalmiocapo/',
387 'id': 'nondirloalmiocapo',
388 'title': 'Non dirlo al mio capo',
389 'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b',
391 'playlist_mincount': 12,
393 'url': 'https://www.raiplay.it/programmi/nondirloalmiocapo/episodi/stagione-2/',
395 'id': 'nondirloalmiocapo',
396 'title': 'Non dirlo al mio capo - Stagione 2',
397 'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b',
399 'playlist_mincount': 12,
402 def _real_extract(self
, url
):
403 base
, playlist_id
, extra_id
= self
._match
_valid
_url
(url
).groups()
405 program
= self
._download
_json
(
406 base
+ '.json', playlist_id
, 'Downloading program JSON')
409 extra_id
= extra_id
.upper().rstrip('/')
411 playlist_title
= program
.get('name')
413 for b
in (program
.get('blocks') or []):
414 for s
in (b
.get('sets') or []):
416 if extra_id
!= join_nonempty(
417 b
.get('name'), s
.get('name'), delim
='/').replace(' ', '-').upper():
419 playlist_title
= join_nonempty(playlist_title
, s
.get('name'), delim
=' - ')
424 medias
= self
._download
_json
(
425 f
'{base}/{s_id}.json', s_id
,
426 'Downloading content set JSON', fatal
=False)
429 for m
in (medias
.get('items') or []):
430 path_id
= m
.get('path_id')
433 video_url
= urljoin(url
, path_id
)
434 entries
.append(self
.url_result(
435 video_url
, ie
=RaiPlayIE
.ie_key(),
436 video_id
=RaiPlayIE
._match
_id
(video_url
)))
438 return self
.playlist_result(
439 entries
, playlist_id
, playlist_title
,
440 try_get(program
, lambda x
: x
['program_info']['description']))
443 class RaiPlaySoundIE(RaiBaseIE
):
444 _VALID_URL
= rf
'(?P<base>https?://(?:www\.)?raiplaysound\.it/.+?-(?P<id>{RaiBaseIE._UUID_RE}))\.(?:html|json)'
446 'url': 'https://www.raiplaysound.it/audio/2021/12/IL-RUGGITO-DEL-CONIGLIO-1ebae2a7-7cdb-42bb-842e-fe0d193e9707.html',
447 'md5': '8970abf8caf8aef4696e7b1f2adfc696',
449 'id': '1ebae2a7-7cdb-42bb-842e-fe0d193e9707',
451 'title': 'Il Ruggito del Coniglio del 10/12/2021',
452 'alt_title': 'md5:0e6476cd57858bb0f3fcc835d305b455',
453 'description': 'md5:2a17d2107e59a4a8faa0e18334139ee2',
454 'thumbnail': r
're:^https?://.*\.jpg$',
455 'uploader': 'rai radio 2',
457 'series': 'Il Ruggito del Coniglio',
458 'episode': 'Il Ruggito del Coniglio del 10/12/2021',
459 'creator': 'rai radio 2',
460 'timestamp': 1638346620,
461 'upload_date': '20211201',
464 'skip_download': True,
468 def _real_extract(self
, url
):
469 base
, audio_id
= self
._match
_valid
_url
(url
).group('base', 'id')
470 media
= self
._download
_json
(f
'{base}.json', audio_id
, 'Downloading audio JSON')
471 uid
= try_get(media
, lambda x
: remove_start(remove_start(x
['uniquename'], 'ContentItem-'), 'Page-'))
475 relinkers
= set(traverse_obj(media
, (('downloadable_audio', 'audio', ('live', 'cards', 0, 'audio')), 'url')))
477 info
= self
._extract
_relinker
_info
(r
, audio_id
, True)
478 formats
.extend(info
.get('formats'))
480 date_published
= try_get(media
, (lambda x
: f
'{x["create_date"]} {x.get("create_time") or ""}',
481 lambda x
: x
['live']['create_date']))
483 podcast_info
= traverse_obj(media
, 'podcast_info', ('live', 'cards', 0)) or {}
485 'url': urljoin(url
, thumb_url
),
486 } for thumb_url
in (podcast_info
.get('images') or {}).values() if thumb_url
]
490 'id': uid
or audio_id
,
491 'display_id': audio_id
,
492 'title': traverse_obj(media
, 'title', 'episode_title'),
493 'alt_title': traverse_obj(media
, ('track_info', 'media_name'), expected_type
=strip_or_none
),
494 'description': media
.get('description'),
495 'uploader': traverse_obj(media
, ('track_info', 'channel'), expected_type
=strip_or_none
),
496 'creator': traverse_obj(media
, ('track_info', 'editor'), expected_type
=strip_or_none
),
497 'timestamp': unified_timestamp(date_published
),
498 'thumbnails': thumbnails
,
499 'series': podcast_info
.get('title'),
500 'season_number': int_or_none(media
.get('season')),
501 'episode': media
.get('episode_title'),
502 'episode_number': int_or_none(media
.get('episode')),
507 class RaiPlaySoundLiveIE(RaiPlaySoundIE
):
508 _VALID_URL
= r
'(?P<base>https?://(?:www\.)?raiplaysound\.it/(?P<id>[^/?#&]+)$)'
510 'url': 'https://www.raiplaysound.it/radio2',
512 'id': 'b00a50e6-f404-4af6-8f8c-ff3b9af73a44',
513 'display_id': 'radio2',
515 'title': r
're:Rai Radio 2 \d+-\d+-\d+ \d+:\d+',
516 'thumbnail': r
're:https://www.raiplaysound.it/dl/img/.+?png',
517 'uploader': 'rai radio 2',
518 'series': 'Rai Radio 2',
519 'creator': 'raiplaysound',
521 'live_status': 'is_live',
524 'skip_download': 'live',
529 class RaiPlaySoundPlaylistIE(InfoExtractor
):
530 _VALID_URL
= r
'(?P<base>https?://(?:www\.)?raiplaysound\.it/(?:programmi|playlist|audiolibri)/(?P<id>[^/?#&]+))(?:/(?P<extra_id>[^?#&]+))?'
532 'url': 'https://www.raiplaysound.it/programmi/ilruggitodelconiglio',
534 'id': 'ilruggitodelconiglio',
535 'title': 'Il Ruggito del Coniglio',
536 'description': 'md5:1bbaf631245a7ab1ec4d9fbb3c7aa8f3',
538 'playlist_mincount': 65,
540 'url': 'https://www.raiplaysound.it/programmi/ilruggitodelconiglio/puntate/prima-stagione-1995',
542 'id': 'ilruggitodelconiglio_puntate_prima-stagione-1995',
543 'title': 'Prima Stagione 1995',
548 def _real_extract(self
, url
):
549 base
, playlist_id
, extra_id
= self
._match
_valid
_url
(url
).group('base', 'id', 'extra_id')
551 program
= self
._download
_json
(url
, playlist_id
, 'Downloading program JSON')
554 extra_id
= extra_id
.rstrip('/')
555 playlist_id
+= '_' + extra_id
.replace('/', '_')
556 path
= next(c
['path_id'] for c
in program
.get('filters') or [] if extra_id
in c
.get('weblink'))
557 program
= self
._download
_json
(
558 urljoin('https://www.raiplaysound.it', path
), playlist_id
, 'Downloading program secondary JSON')
561 self
.url_result(urljoin(base
, c
['path_id']), ie
=RaiPlaySoundIE
.ie_key())
562 for c
in traverse_obj(program
, 'cards', ('block', 'cards')) or []
565 return self
.playlist_result(entries
, playlist_id
, program
.get('title'),
566 traverse_obj(program
, ('podcast_info', 'description')))
569 class RaiIE(RaiBaseIE
):
570 _VALID_URL
= rf
'https?://[^/]+\.(?:rai\.(?:it|tv))/.+?-(?P<id>{RaiBaseIE._UUID_RE})(?:-.+?)?\.html'
572 # var uniquename = "ContentItem-..."
573 # data-id="ContentItem-..."
574 'url': 'https://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
576 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
578 'title': 'TG PRIMO TEMPO',
579 'thumbnail': r
're:^https?://.*\.jpg$',
581 'upload_date': '20140612',
583 'skip': 'This content is available only in Italy',
585 # with ContentItem in og:url
586 'url': 'https://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html',
587 'md5': '06345bd97c932f19ffb129973d07a020',
589 'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
591 'title': 'TG1 ore 20:00 del 03/11/2016',
592 'description': 'TG1 edizione integrale ore 20:00 del giorno 03/11/2016',
593 'thumbnail': r
're:^https?://.*\.jpg$',
595 'upload_date': '20161103'
599 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html',
600 'only_matching': True,
603 def _extract_from_content_id(self
, content_id
, url
):
604 media
= self
._download
_json
(
605 f
'https://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-{content_id}.html?json',
606 content_id
, 'Downloading video JSON')
608 title
= media
['name'].strip()
610 media_type
= media
['type']
611 if 'Audio' in media_type
:
614 'format_id': media
.get('formatoAudio'),
615 'url': media
['audioUrl'],
616 'ext': media
.get('formatoAudio'),
619 elif 'Video' in media_type
:
620 relinker_info
= self
._extract
_relinker
_info
(media
['mediaUri'], content_id
)
622 raise ExtractorError('not a media file')
624 self
._sort
_formats
(relinker_info
['formats'])
627 for image_type
in ('image', 'image_medium', 'image_300'):
628 thumbnail_url
= media
.get(image_type
)
631 'url': compat_urlparse
.urljoin(url
, thumbnail_url
),
634 subtitles
= self
._extract
_subtitles
(url
, media
)
639 'description': strip_or_none(media
.get('desc') or None),
640 'thumbnails': thumbnails
,
641 'uploader': strip_or_none(media
.get('author') or None),
642 'upload_date': unified_strdate(media
.get('date')),
643 'duration': parse_duration(media
.get('length')),
644 'subtitles': subtitles
,
648 def _real_extract(self
, url
):
649 video_id
= self
._match
_id
(url
)
651 webpage
= self
._download
_webpage
(url
, video_id
)
653 content_item_id
= None
655 content_item_url
= self
._html
_search
_meta
(
656 ('og:url', 'og:video', 'og:video:secure_url', 'twitter:url',
657 'twitter:player', 'jsonlink'), webpage
, default
=None)
659 content_item_id
= self
._search
_regex
(
660 rf
'ContentItem-({self._UUID_RE})', content_item_url
,
661 'content item id', default
=None)
663 if not content_item_id
:
664 content_item_id
= self
._search
_regex
(
667 (?:initEdizione|drawMediaRaiTV)\(|
668 <(?:[^>]+\bdata-id|var\s+uniquename)=|
672 (?:(?!\1).)*\bContentItem-(?P<id>{self._UUID_RE})
674 webpage
, 'content item id', default
=None, group
='id')
676 content_item_ids
= set()
678 content_item_ids
.add(content_item_id
)
679 if video_id
not in content_item_ids
:
680 content_item_ids
.add(video_id
)
682 for content_item_id
in content_item_ids
:
684 return self
._extract
_from
_content
_id
(content_item_id
, url
)
685 except GeoRestrictedError
:
687 except ExtractorError
:
690 relinker_url
= self
._proto
_relative
_url
(self
._search
_regex
(
699 //mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\?
700 (?:(?!\1).)*\bcont=(?:(?!\1).)+)\1
702 webpage, 'relinker URL', group='url'))
704 relinker_info = self._extract_relinker_info(
705 urljoin(url, relinker_url), video_id)
706 self._sort_formats(relinker_info['formats'])
708 title = self._search_regex(
709 r'var\s+videoTitolo\s*=\s*([\'"])(?P
<title
>[^
\'"]+)\1',
710 webpage, 'title', group='title',
711 default=None) or self._og_search_title(webpage)
720 class RaiNewsIE(RaiIE):
721 _VALID_URL = rf'https?://(www\.)?rainews\.it/(?!articoli)[^?#]+-(?P<id>{RaiBaseIE._UUID_RE})(?:-[^/?#]+)?\.html'
722 _EMBED_REGEX = [rf'<iframe[^>]+data-src="(?P
<url
>/iframe
/[^?
#]+?{RaiBaseIE._UUID_RE}\.html)']
724 # new rainews player (#3911)
725 'url': 'https://www.rainews.it/rubriche/24mm/video/2022/05/24mm-del-29052022-12cf645d-1ffd-4220-b27c-07c226dbdecf.html',
727 'id': '12cf645d-1ffd-4220-b27c-07c226dbdecf',
729 'title': 'Puntata del 29/05/2022',
731 'upload_date': '20220529',
732 'uploader': 'rainews',
735 # old content with fallback method to extract media urls
736 'url': 'https://www.rainews.it/dl/rainews/media/Weekend-al-cinema-da-Hollywood-arriva-il-thriller-di-Tate-Taylor-La-ragazza-del-treno-1632c009-c843-4836-bb65-80c33084a64b.html',
738 'id': '1632c009-c843-4836-bb65-80c33084a64b',
740 'title': 'Weekend al cinema, da Hollywood arriva il thriller di Tate Taylor "La ragazza del treno"',
741 'description': 'I film in uscita questa settimana.',
742 'thumbnail': r
're:^https?://.*\.png$',
744 'upload_date': '20161103'
746 'expected_warnings': ['unable to extract player_data'],
749 'url': 'https://www.rainews.it/iframe/video/2022/07/euro2022-europei-calcio-femminile-italia-belgio-gol-0-1-video-4de06a69-de75-4e32-a657-02f0885f8118.html',
750 'only_matching': True,
753 def _real_extract(self
, url
):
754 video_id
= self
._match
_id
(url
)
756 webpage
= self
._download
_webpage
(url
, video_id
)
758 player_data
= self
._search
_json
(
759 r
'<rainews-player\s*data=\'', webpage, 'player_data
', video_id,
760 transform_source=clean_html, fatal=False)
761 track_info = player_data.get('track_info
')
762 relinker_url = traverse_obj(player_data, 'mediapolis
', 'content_url
')
765 # fallback on old implementation for some old content
767 return self._extract_from_content_id(video_id, url)
768 except GeoRestrictedError:
770 except ExtractorError as e:
771 raise ExtractorError('Relinker URL
not found
', cause=e)
773 relinker_info = self._extract_relinker_info(urljoin(url, relinker_url), video_id)
775 self._sort_formats(relinker_info['formats
'])
779 'title
': track_info.get('title
') or self._og_search_title(webpage),
780 'upload_date
': unified_strdate(track_info.get('date
')),
781 'uploader
': strip_or_none(track_info.get('editor
') or None),
786 class RaiSudtirolIE(RaiBaseIE):
787 _VALID_URL = r'https?
://raisudtirol\
.rai\
.it
/.+?media
=(?P
<id>[TP
]tv\d
+)'
789 'url
': 'https
://raisudtirol
.rai
.it
/la
/index
.php?media
=Ptv1619729460
',
791 'id': 'Ptv1619729460
',
793 'title
': 'Euro
: trasmisciun d
\'economia
- 29-04-2021 20:51',
794 'series
': 'Euro
: trasmisciun d
\'economia
',
795 'upload_date
': '20210429',
796 'thumbnail
': r're
:https
://raisudtirol\
.rai\
.it
/img
/.+?\
.jpg
',
797 'uploader
': 'raisudtirol
',
801 def _real_extract(self, url):
802 video_id = self._match_id(url)
803 webpage = self._download_webpage(url, video_id)
805 video_date = self._html_search_regex(r'<span
class="med_data">(.+?
)</span
>', webpage, 'video_date
', fatal=False)
806 video_title = self._html_search_regex(r'<span
class="med_title">(.+?
)</span
>', webpage, 'video_title
', fatal=False)
807 video_url = self._html_search_regex(r'sources
:\s
*\
[\{file:\s*"(.+?)"\}\
]', webpage, 'video_url
')
808 video_thumb = self._html_search_regex(r'image
: \'(.+?
)\'', webpage, 'video_thumb
', fatal=False)
812 'title
': join_nonempty(video_title, video_date, delim=' - '),
813 'series
': video_title,
814 'upload_date
': unified_strdate(video_date),
815 'thumbnail
': urljoin('https
://raisudtirol
.rai
.it
/', video_thumb),
816 'uploader
': 'raisudtirol
',
818 'format_id
': 'https
-mp4
',
819 'url
': self._proto_relative_url(video_url),