2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
35 class RaiBaseIE(InfoExtractor
):
36 _UUID_RE
= r
'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
37 _GEO_COUNTRIES
= ['IT']
40 def _extract_relinker_info(self
, relinker_url
, video_id
):
41 if not re
.match(r
'https?://', relinker_url
):
42 return {'formats': [{'url': relinker_url}
]}
49 for platform
in ('mon', 'flash', 'native'):
50 relinker
= self
._download
_xml
(
51 relinker_url
, video_id
,
52 note
='Downloading XML metadata for platform %s' % platform
,
53 transform_source
=fix_xml_ampersands
,
54 query
={'output': 45, 'pl': platform}
,
55 headers
=self
.geo_verification_headers())
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'):
83 if ext
== 'm3u8' or 'format=m3u8' in media_url
or platform
== 'mon':
84 formats
.extend(self
._extract
_m
3u8_formats
(
85 media_url
, video_id
, 'mp4', 'm3u8_native',
86 m3u8_id
='hls', fatal
=False))
87 elif ext
== 'f4m' or platform
== 'flash':
88 manifest_url
= update_url_query(
89 media_url
.replace('manifest#live_hds.f4m', 'manifest.f4m'),
90 {'hdcore': '3.7.0', 'plugin': 'aasp-3.7.0.39.44'}
)
91 formats
.extend(self
._extract
_f
4m
_formats
(
92 manifest_url
, video_id
, f4m_id
='hds', fatal
=False))
94 bitrate
= int_or_none(xpath_text(relinker
, 'bitrate'))
97 'tbr': bitrate
if bitrate
> 0 else None,
98 'format_id': 'http-%d' % bitrate
if bitrate
> 0 else 'http',
101 if not formats
and geoprotection
is True:
102 self
.raise_geo_restricted(countries
=self
._GEO
_COUNTRIES
, metadata_available
=True)
104 formats
.extend(self
._create
_http
_urls
(relinker_url
, formats
))
106 return dict((k
, v
) for k
, v
in {
108 'duration': duration
,
110 }.items() if v
is not None)
112 def _create_http_urls(self
, relinker_url
, fmts
):
113 _RELINKER_REG
= r
'https?://(?P<host>[^/]+?)/(?:i/)?(?P<extra>[^/]+?)/(?P<path>.+?)/(?P<id>\d+)(?:_(?P<quality>[\d\,]+))?(?:\.mp4|/playlist\.m3u8).+?'
114 _MP4_TMPL
= '%s&overrideUserAgentRule=mp4-%s'
126 '5000': [1920, 1080],
127 '10000': [1920, 1080],
131 resp
= self
._request
_webpage
(
132 HEADRequest(url
), None, headers
={'User-Agent': 'Rai'}
,
133 fatal
=False, errnote
=False, note
=False)
139 return False if resp
.url
== url
else resp
.url
142 # filter out audio-only formats
143 fmts
= [f
for f
in fmts
if not f
.get('vcodec') == 'none']
145 def get_format_info(tbr
):
147 br
= int_or_none(tbr
)
148 if len(fmts
) == 1 and not br
:
149 br
= fmts
[0].get('tbr')
151 tbr
= compat_str(math
.floor(br
/ 100) * 100)
155 # try extracting info from available m3u8 formats
159 br_limit
= math
.floor(br
/ 100)
160 if br_limit
- 1 <= math
.floor(f
['tbr'] / 100) <= br_limit
+ 1:
161 format_copy
= f
.copy()
163 'width': format_copy
.get('width'),
164 'height': format_copy
.get('height'),
165 'tbr': format_copy
.get('tbr'),
166 'vcodec': format_copy
.get('vcodec'),
167 'acodec': format_copy
.get('acodec'),
168 'fps': format_copy
.get('fps'),
169 'format_id': 'https-%s' % tbr
,
170 } if format_copy
else {
171 'width': _QUALITY
[tbr
][0],
172 'height': _QUALITY
[tbr
][1],
173 'format_id': 'https-%s' % tbr
,
177 loc
= test_url(_MP4_TMPL
% (relinker_url
, '*'))
178 if not isinstance(loc
, compat_str
):
183 test_url(relinker_url
) or '')
187 available_qualities
= mobj
.group('quality').split(',') if mobj
.group('quality') else ['*']
188 available_qualities
= [i
for i
in available_qualities
if i
]
191 for q
in available_qualities
:
193 'url': _MP4_TMPL
% (relinker_url
, q
),
197 fmt
.update(get_format_info(q
))
202 def _extract_subtitles(url
, video_data
):
206 subtitles_array
= video_data
.get('subtitlesArray') or []
207 for k
in ('subtitles', 'subtitlesUrl'):
208 subtitles_array
.append({'url': video_data.get(k)}
)
209 for subtitle
in subtitles_array
:
210 sub_url
= subtitle
.get('url')
211 if sub_url
and isinstance(sub_url
, compat_str
):
212 sub_lang
= subtitle
.get('language') or 'it'
213 sub_url
= urljoin(url
, sub_url
)
214 sub_ext
= determine_ext(sub_url
, SRT_EXT
)
215 subtitles
.setdefault(sub_lang
, []).append({
219 if STL_EXT
== sub_ext
:
220 subtitles
[sub_lang
].append({
222 'url': sub_url
[:-len(STL_EXT
)] + SRT_EXT
,
227 class RaiPlayIE(RaiBaseIE
):
228 _VALID_URL
= r
'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s))\.(?:html|json)' % RaiBaseIE
._UUID
_RE
230 'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
231 'md5': '8970abf8caf8aef4696e7b1f2adfc696',
233 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
235 'title': 'Report del 07/04/2014',
236 'alt_title': 'St 2013/14 - Report - Espresso nel caffè - 07/04/2014',
237 'description': 'md5:d730c168a58f4bb35600fc2f881ec04e',
238 'thumbnail': r
're:^https?://.*\.jpg$',
239 'uploader': 'Rai Gulp',
248 'skip_download': True,
251 # 1080p direct mp4 url
252 'url': 'https://www.raiplay.it/video/2021/11/Blanca-S1E1-Senza-occhi-b1255a4a-8e72-4a2f-b9f3-fc1308e00736.html',
253 'md5': 'aeda7243115380b2dd5e881fd42d949a',
255 'id': 'b1255a4a-8e72-4a2f-b9f3-fc1308e00736',
257 'title': 'Blanca - S1E1 - Senza occhi',
258 'alt_title': 'St 1 Ep 1 - Blanca - Senza occhi',
259 'description': 'md5:75f95d5c030ec8bac263b1212322e28c',
260 'thumbnail': r
're:^https?://.*\.jpg$',
264 'season': 'Season 1',
267 'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
268 'only_matching': True,
270 # subtitles at 'subtitlesArray' key (see #27698)
271 'url': 'https://www.raiplay.it/video/2020/12/Report---04-01-2021-2e90f1de-8eee-4de4-ac0e-78d21db5b600.html',
272 'only_matching': True,
275 'url': 'https://www.raiplay.it/video/2020/09/Lo-straordinario-mondo-di-Zoey-S1E1-Lo-straordinario-potere-di-Zoey-ed493918-1d32-44b7-8454-862e473d00ff.html',
276 'only_matching': True,
279 def _real_extract(self
, url
):
280 base
, video_id
= self
._match
_valid
_url
(url
).groups()
282 media
= self
._download
_json
(
283 base
+ '.json', video_id
, 'Downloading video JSON')
285 if not self
.get_param('allow_unplayable_formats'):
288 (lambda x
: x
['rights_management']['rights']['drm'],
289 lambda x
: x
['program_info']['rights_management']['rights']['drm']),
291 self
.report_drm(video_id
)
293 title
= media
['name']
294 video
= media
['video']
296 relinker_info
= self
._extract
_relinker
_info
(video
['content_url'], video_id
)
297 self
._sort
_formats
(relinker_info
['formats'])
300 for _
, value
in media
.get('images', {}).items():
303 'url': urljoin(url
, value
),
306 date_published
= media
.get('date_published')
307 time_published
= media
.get('time_published')
308 if date_published
and time_published
:
309 date_published
+= ' ' + time_published
311 subtitles
= self
._extract
_subtitles
(url
, video
)
313 program_info
= media
.get('program_info') or {}
314 season
= media
.get('season')
316 alt_title
= join_nonempty(media
.get('subtitle'), media
.get('toptitle'), delim
=' - ')
319 'id': remove_start(media
.get('id'), 'ContentItem-') or video_id
,
320 'display_id': video_id
,
321 'title': self
._live
_title
(title
) if relinker_info
.get(
322 'is_live') else title
,
323 'alt_title': strip_or_none(alt_title
),
324 'description': media
.get('description'),
325 'uploader': strip_or_none(media
.get('channel')),
326 'creator': strip_or_none(media
.get('editor') or None),
327 'duration': parse_duration(video
.get('duration')),
328 'timestamp': unified_timestamp(date_published
),
329 'thumbnails': thumbnails
,
330 'series': program_info
.get('name'),
331 'season_number': int_or_none(season
),
332 'season': season
if (season
and not season
.isdigit()) else None,
333 'episode': media
.get('episode_title'),
334 'episode_number': int_or_none(media
.get('episode')),
335 'subtitles': subtitles
,
338 info
.update(relinker_info
)
342 class RaiPlayLiveIE(RaiPlayIE
):
343 _VALID_URL
= r
'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))'
345 'url': 'http://www.raiplay.it/dirette/rainews24',
347 'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c',
348 'display_id': 'rainews24',
350 'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
351 'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497',
352 'uploader': 'Rai News 24',
353 'creator': 'Rai News 24',
357 'skip_download': True,
362 class RaiPlayPlaylistIE(InfoExtractor
):
363 _VALID_URL
= r
'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))'
365 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/',
367 'id': 'nondirloalmiocapo',
368 'title': 'Non dirlo al mio capo',
369 'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b',
371 'playlist_mincount': 12,
374 def _real_extract(self
, url
):
375 base
, playlist_id
= self
._match
_valid
_url
(url
).groups()
377 program
= self
._download
_json
(
378 base
+ '.json', playlist_id
, 'Downloading program JSON')
381 for b
in (program
.get('blocks') or []):
382 for s
in (b
.get('sets') or []):
386 medias
= self
._download
_json
(
387 '%s/%s.json' % (base
, s_id
), s_id
,
388 'Downloading content set JSON', fatal
=False)
391 for m
in (medias
.get('items') or []):
392 path_id
= m
.get('path_id')
395 video_url
= urljoin(url
, path_id
)
396 entries
.append(self
.url_result(
397 video_url
, ie
=RaiPlayIE
.ie_key(),
398 video_id
=RaiPlayIE
._match
_id
(video_url
)))
400 return self
.playlist_result(
401 entries
, playlist_id
, program
.get('name'),
402 try_get(program
, lambda x
: x
['program_info']['description']))
405 class RaiIE(RaiBaseIE
):
406 _VALID_URL
= r
'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE
._UUID
_RE
408 # var uniquename = "ContentItem-..."
409 # data-id="ContentItem-..."
410 'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
412 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
414 'title': 'TG PRIMO TEMPO',
415 'thumbnail': r
're:^https?://.*\.jpg$',
417 'upload_date': '20140612',
419 'skip': 'This content is available only in Italy',
421 # with ContentItem in many metas
422 'url': 'http://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',
424 'id': '1632c009-c843-4836-bb65-80c33084a64b',
426 'title': 'Weekend al cinema, da Hollywood arriva il thriller di Tate Taylor "La ragazza del treno"',
427 'description': 'I film in uscita questa settimana.',
428 'thumbnail': r
're:^https?://.*\.png$',
430 'upload_date': '20161103',
433 # with ContentItem in og:url
434 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html',
435 'md5': '06345bd97c932f19ffb129973d07a020',
437 'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
439 'title': 'TG1 ore 20:00 del 03/11/2016',
440 'description': 'TG1 edizione integrale ore 20:00 del giorno 03/11/2016',
441 'thumbnail': r
're:^https?://.*\.jpg$',
443 'upload_date': '20161103',
446 # initEdizione('ContentItem-...'
447 'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
449 'id': 'c2187016-8484-4e3a-8ac8-35e475b07303',
451 'title': r
're:TG1 ore \d{2}:\d{2} del \d{2}/\d{2}/\d{4}',
453 'upload_date': '20170401',
455 'skip': 'Changes daily',
457 # HLS live stream with ContentItem in og:url
458 'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',
460 'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9',
462 'title': 'La diretta di Rainews24',
465 'skip_download': True,
469 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html',
470 'only_matching': True,
472 'url': 'https://www.rainews.it/tgr/marche/notiziari/video/2019/02/ContentItem-6ba945a2-889c-4a80-bdeb-8489c70a8db9.html',
473 'only_matching': True,
476 def _extract_from_content_id(self
, content_id
, url
):
477 media
= self
._download
_json
(
478 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % content_id
,
479 content_id
, 'Downloading video JSON')
481 title
= media
['name'].strip()
483 media_type
= media
['type']
484 if 'Audio' in media_type
:
487 'format_id': media
.get('formatoAudio'),
488 'url': media
['audioUrl'],
489 'ext': media
.get('formatoAudio'),
492 elif 'Video' in media_type
:
493 relinker_info
= self
._extract
_relinker
_info
(media
['mediaUri'], content_id
)
495 raise ExtractorError('not a media file')
497 self
._sort
_formats
(relinker_info
['formats'])
500 for image_type
in ('image', 'image_medium', 'image_300'):
501 thumbnail_url
= media
.get(image_type
)
504 'url': compat_urlparse
.urljoin(url
, thumbnail_url
),
507 subtitles
= self
._extract
_subtitles
(url
, media
)
512 'description': strip_or_none(media
.get('desc')),
513 'thumbnails': thumbnails
,
514 'uploader': media
.get('author'),
515 'upload_date': unified_strdate(media
.get('date')),
516 'duration': parse_duration(media
.get('length')),
517 'subtitles': subtitles
,
520 info
.update(relinker_info
)
524 def _real_extract(self
, url
):
525 video_id
= self
._match
_id
(url
)
527 webpage
= self
._download
_webpage
(url
, video_id
)
529 content_item_id
= None
531 content_item_url
= self
._html
_search
_meta
(
532 ('og:url', 'og:video', 'og:video:secure_url', 'twitter:url',
533 'twitter:player', 'jsonlink'), webpage
, default
=None)
535 content_item_id
= self
._search
_regex
(
536 r
'ContentItem-(%s)' % self
._UUID
_RE
, content_item_url
,
537 'content item id', default
=None)
539 if not content_item_id
:
540 content_item_id
= self
._search
_regex
(
543 (?:initEdizione|drawMediaRaiTV)\(|
544 <(?:[^>]+\bdata-id|var\s+uniquename)=|
548 (?
:(?
!\
1).)*\bContentItem
-(?P
<id>%s)
550 webpage, 'content item id', default=None, group='id')
552 content_item_ids = set()
554 content_item_ids.add(content_item_id)
555 if video_id not in content_item_ids:
556 content_item_ids.add(video_id)
558 for content_item_id in content_item_ids:
560 return self._extract_from_content_id(content_item_id, url)
561 except GeoRestrictedError:
563 except ExtractorError:
566 relinker_url = self._proto_relative_url(self._search_regex(
575 //mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\?
576 (?:(?!\1).)*\bcont=(?:(?!\1).)+)\1
578 webpage, 'relinker URL', group='url'))
580 relinker_info = self._extract_relinker_info(
581 urljoin(url, relinker_url), video_id)
582 self._sort_formats(relinker_info['formats'])
584 title = self._search_regex(
585 r'var\s+videoTitolo\s*=\s*([\'"])(?P
<title
>[^
\'"]+)\1',
586 webpage, 'title', group='title',
587 default=None) or self._og_search_title(webpage)
594 info.update(relinker_info)
599 class RaiPlayRadioBaseIE(InfoExtractor):
600 _BASE = 'https://www.raiplayradio.it'
602 def get_playlist_iter(self, url, uid):
603 webpage = self._download_webpage(url, uid)
604 for attrs in parse_list(webpage):
605 title = attrs['data-title'].strip()
606 audio_url = urljoin(url, attrs['data-mediapolis'])
609 'id': attrs['data-uniquename'].lstrip('ContentItem-'),
614 if 'data-image' in attrs:
615 entry['thumbnail'] = urljoin(url, attrs['data-image'])
619 class RaiPlayRadioIE(RaiPlayRadioBaseIE):
620 _VALID_URL = r'%s/audio/.+?-(?P<id>%s)\.html' % (
621 RaiPlayRadioBaseIE._BASE, RaiBaseIE._UUID_RE)
623 'url': 'https://www.raiplayradio.it/audio/2019/07/RADIO3---LEZIONI-DI-MUSICA-36b099ff-4123-4443-9bf9-38e43ef5e025.html',
625 'id': '36b099ff-4123-4443-9bf9-38e43ef5e025',
627 'title': 'Dal "Chiaro di luna
" al "Clair de lune
", prima parte con Giovanni Bietti',
628 'thumbnail': r're:^https?://.*\.jpg$',
633 def _real_extract(self, url):
634 audio_id = self._match_id(url)
635 list_url = url.replace('.html', '-list.html')
636 return next(entry for entry in self.get_playlist_iter(list_url, audio_id) if entry['id'] == audio_id)
639 class RaiPlayRadioPlaylistIE(RaiPlayRadioBaseIE):
640 _VALID_URL = r'%s/playlist/.+?-(?P<id>%s)\.html' % (
641 RaiPlayRadioBaseIE._BASE, RaiBaseIE._UUID_RE)
643 'url': 'https://www.raiplayradio.it/playlist/2017/12/Alice-nel-paese-delle-meraviglie-72371d3c-d998-49f3-8860-d168cfdf4966.html',
645 'id': '72371d3c-d998-49f3-8860-d168cfdf4966',
646 'title': "Alice nel paese delle meraviglie
",
647 'description': "di Lewis Carrol letto da Aldo Busi
",
649 'playlist_count': 11,
652 def _real_extract(self, url):
653 playlist_id = self._match_id(url)
654 playlist_webpage = self._download_webpage(url, playlist_id)
655 playlist_title = unescapeHTML(self._html_search_regex(
656 r'data-playlist-title="(.+?
)"', playlist_webpage, 'title'))
657 playlist_creator = self._html_search_meta(
658 'nomeProgramma', playlist_webpage)
659 playlist_description = get_element_by_class(
660 'textDescriptionProgramma', playlist_webpage)
662 player_href = self._html_search_regex(
663 r'data-player-href="(.+?
)"', playlist_webpage, 'href')
664 list_url = urljoin(url, player_href)
666 entries = list(self.get_playlist_iter(list_url, playlist_id))
667 for index, entry in enumerate(entries, start=1):
669 'track': entry['title'],
670 'track_number': index,
671 'artist': playlist_creator,
672 'album': playlist_title
675 return self.playlist_result(
676 entries, playlist_id, playlist_title, playlist_description,
677 creator=playlist_creator)