2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
31 class RaiBaseIE(InfoExtractor
):
32 _UUID_RE
= r
'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
33 _GEO_COUNTRIES
= ['IT']
36 def _extract_relinker_info(self
, relinker_url
, video_id
):
37 if not re
.match(r
'https?://', relinker_url
):
38 return {'formats': [{'url': relinker_url}
]}
45 for platform
in ('mon', 'flash', 'native'):
46 relinker
= self
._download
_xml
(
47 relinker_url
, video_id
,
48 note
='Downloading XML metadata for platform %s' % platform
,
49 transform_source
=fix_xml_ampersands
,
50 query
={'output': 45, 'pl': platform}
,
51 headers
=self
.geo_verification_headers())
54 geoprotection
= xpath_text(
55 relinker
, './geoprotection', default
=None) == 'Y'
59 relinker
, './is_live', default
=None) == 'Y'
61 duration
= parse_duration(xpath_text(
62 relinker
, './duration', default
=None))
64 url_elem
= find_xpath_attr(relinker
, './url', 'type', 'content')
68 media_url
= url_elem
.text
70 # This does not imply geo restriction (e.g.
71 # http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html)
72 if '/video_no_available.mp4' in media_url
:
75 ext
= determine_ext(media_url
)
76 if (ext
== 'm3u8' and platform
!= 'mon') or (ext
== 'f4m' and platform
!= 'flash'):
79 if ext
== 'm3u8' or 'format=m3u8' in media_url
or platform
== 'mon':
80 formats
.extend(self
._extract
_m
3u8_formats
(
81 media_url
, video_id
, 'mp4', 'm3u8_native',
82 m3u8_id
='hls', fatal
=False))
83 elif ext
== 'f4m' or platform
== 'flash':
84 manifest_url
= update_url_query(
85 media_url
.replace('manifest#live_hds.f4m', 'manifest.f4m'),
86 {'hdcore': '3.7.0', 'plugin': 'aasp-3.7.0.39.44'}
)
87 formats
.extend(self
._extract
_f
4m
_formats
(
88 manifest_url
, video_id
, f4m_id
='hds', fatal
=False))
90 bitrate
= int_or_none(xpath_text(relinker
, 'bitrate'))
93 'tbr': bitrate
if bitrate
> 0 else None,
94 'format_id': 'http-%d' % bitrate
if bitrate
> 0 else 'http',
97 if not formats
and geoprotection
is True:
98 self
.raise_geo_restricted(countries
=self
._GEO
_COUNTRIES
, metadata_available
=True)
100 formats
.extend(self
._create
_http
_urls
(relinker_url
, formats
))
102 return dict((k
, v
) for k
, v
in {
104 'duration': duration
,
106 }.items() if v
is not None)
108 def _create_http_urls(self
, relinker_url
, fmts
):
109 _RELINKER_REG
= r
'https?://(?P<host>[^/]+?)/(?:i/)?(?P<extra>[^/]+?)/(?P<path>.+?)/(?P<id>\d+)(?:_(?P<quality>[\d\,]+))?(?:\.mp4|/playlist\.m3u8).+?'
110 _MP4_TMPL
= '%s&overrideUserAgentRule=mp4-%s'
122 '5000': [1920, 1080],
123 '10000': [1920, 1080],
127 resp
= self
._request
_webpage
(
128 HEADRequest(url
), None, headers
={'User-Agent': 'Rai'}
,
129 fatal
=False, errnote
=False, note
=False)
135 return False if resp
.url
== url
else resp
.url
138 def get_format_info(tbr
):
140 br
= int_or_none(tbr
)
141 if len(fmts
) == 1 and not br
:
142 br
= fmts
[0].get('tbr')
144 tbr
= compat_str(math
.floor(br
/ 100) * 100)
148 # try extracting info from available m3u8 formats
152 br_limit
= math
.floor(br
/ 100)
153 if br_limit
- 1 <= math
.floor(f
['tbr'] / 100) <= br_limit
+ 1:
154 format_copy
= f
.copy()
156 'width': format_copy
.get('width'),
157 'height': format_copy
.get('height'),
158 'tbr': format_copy
.get('tbr'),
159 'vcodec': format_copy
.get('vcodec'),
160 'acodec': format_copy
.get('acodec'),
161 'fps': format_copy
.get('fps'),
162 'format_id': 'https-%s' % tbr
,
163 } if format_copy
else {
164 'width': _QUALITY
[tbr
][0],
165 'height': _QUALITY
[tbr
][1],
166 'format_id': 'https-%s' % tbr
,
170 loc
= test_url(_MP4_TMPL
% (relinker_url
, '*'))
171 if not isinstance(loc
, compat_str
):
176 test_url(relinker_url
) or '')
180 available_qualities
= mobj
.group('quality').split(',') if mobj
.group('quality') else ['*']
181 available_qualities
= [i
for i
in available_qualities
if i
]
184 for q
in available_qualities
:
186 'url': _MP4_TMPL
% (relinker_url
, q
),
190 fmt
.update(get_format_info(q
))
195 def _extract_subtitles(url
, video_data
):
199 subtitles_array
= video_data
.get('subtitlesArray') or []
200 for k
in ('subtitles', 'subtitlesUrl'):
201 subtitles_array
.append({'url': video_data.get(k)}
)
202 for subtitle
in subtitles_array
:
203 sub_url
= subtitle
.get('url')
204 if sub_url
and isinstance(sub_url
, compat_str
):
205 sub_lang
= subtitle
.get('language') or 'it'
206 sub_url
= urljoin(url
, sub_url
)
207 sub_ext
= determine_ext(sub_url
, SRT_EXT
)
208 subtitles
.setdefault(sub_lang
, []).append({
212 if STL_EXT
== sub_ext
:
213 subtitles
[sub_lang
].append({
215 'url': sub_url
[:-len(STL_EXT
)] + SRT_EXT
,
220 class RaiPlayIE(RaiBaseIE
):
221 _VALID_URL
= r
'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s))\.(?:html|json)' % RaiBaseIE
._UUID
_RE
223 'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
224 'md5': '8970abf8caf8aef4696e7b1f2adfc696',
226 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
228 'title': 'Report del 07/04/2014',
229 'alt_title': 'St 2013/14 - Espresso nel caffè - 07/04/2014',
230 'description': 'md5:d730c168a58f4bb35600fc2f881ec04e',
231 'thumbnail': r
're:^https?://.*\.jpg$',
232 'uploader': 'Rai Gulp',
241 'skip_download': True,
244 # 1080p direct mp4 url
245 'url': 'https://www.raiplay.it/video/2021/03/Leonardo-S1E1-b5703b02-82ee-475a-85b6-c9e4a8adf642.html',
246 'md5': '2e501e8651d72f05ffe8f5d286ad560b',
248 'id': 'b5703b02-82ee-475a-85b6-c9e4a8adf642',
250 'title': 'Leonardo - S1E1',
251 'alt_title': 'St 1 Ep 1 - Episodio 1',
252 'description': 'md5:f5360cd267d2de146e4e3879a5a47d31',
253 'thumbnail': r
're:^https?://.*\.jpg$',
256 'series': 'Leonardo',
257 'season': 'Season 1',
260 'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
261 'only_matching': True,
263 # subtitles at 'subtitlesArray' key (see #27698)
264 'url': 'https://www.raiplay.it/video/2020/12/Report---04-01-2021-2e90f1de-8eee-4de4-ac0e-78d21db5b600.html',
265 'only_matching': True,
268 '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',
269 'only_matching': True,
272 def _real_extract(self
, url
):
273 base
, video_id
= re
.match(self
._VALID
_URL
, url
).groups()
275 media
= self
._download
_json
(
276 base
+ '.json', video_id
, 'Downloading video JSON')
278 if not self
.get_param('allow_unplayable_formats'):
281 (lambda x
: x
['rights_management']['rights']['drm'],
282 lambda x
: x
['program_info']['rights_management']['rights']['drm']),
284 raise ExtractorError('This video is DRM protected.', expected
=True)
286 title
= media
['name']
287 video
= media
['video']
289 relinker_info
= self
._extract
_relinker
_info
(video
['content_url'], video_id
)
290 self
._sort
_formats
(relinker_info
['formats'])
293 for _
, value
in media
.get('images', {}).items():
296 'url': urljoin(url
, value
),
299 date_published
= media
.get('date_published')
300 time_published
= media
.get('time_published')
301 if date_published
and time_published
:
302 date_published
+= ' ' + time_published
304 subtitles
= self
._extract
_subtitles
(url
, video
)
306 program_info
= media
.get('program_info') or {}
307 season
= media
.get('season')
310 'id': remove_start(media
.get('id'), 'ContentItem-') or video_id
,
311 'display_id': video_id
,
312 'title': self
._live
_title
(title
) if relinker_info
.get(
313 'is_live') else title
,
314 'alt_title': strip_or_none(media
.get('subtitle')),
315 'description': media
.get('description'),
316 'uploader': strip_or_none(media
.get('channel')),
317 'creator': strip_or_none(media
.get('editor') or None),
318 'duration': parse_duration(video
.get('duration')),
319 'timestamp': unified_timestamp(date_published
),
320 'thumbnails': thumbnails
,
321 'series': program_info
.get('name'),
322 'season_number': int_or_none(season
),
323 'season': season
if (season
and not season
.isdigit()) else None,
324 'episode': media
.get('episode_title'),
325 'episode_number': int_or_none(media
.get('episode')),
326 'subtitles': subtitles
,
329 info
.update(relinker_info
)
333 class RaiPlayLiveIE(RaiPlayIE
):
334 _VALID_URL
= r
'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))'
336 'url': 'http://www.raiplay.it/dirette/rainews24',
338 'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c',
339 'display_id': 'rainews24',
341 'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
342 'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497',
343 'uploader': 'Rai News 24',
344 'creator': 'Rai News 24',
348 'skip_download': True,
353 class RaiPlayPlaylistIE(InfoExtractor
):
354 _VALID_URL
= r
'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))'
356 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/',
358 'id': 'nondirloalmiocapo',
359 'title': 'Non dirlo al mio capo',
360 'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b',
362 'playlist_mincount': 12,
365 def _real_extract(self
, url
):
366 base
, playlist_id
= re
.match(self
._VALID
_URL
, url
).groups()
368 program
= self
._download
_json
(
369 base
+ '.json', playlist_id
, 'Downloading program JSON')
372 for b
in (program
.get('blocks') or []):
373 for s
in (b
.get('sets') or []):
377 medias
= self
._download
_json
(
378 '%s/%s.json' % (base
, s_id
), s_id
,
379 'Downloading content set JSON', fatal
=False)
382 for m
in (medias
.get('items') or []):
383 path_id
= m
.get('path_id')
386 video_url
= urljoin(url
, path_id
)
387 entries
.append(self
.url_result(
388 video_url
, ie
=RaiPlayIE
.ie_key(),
389 video_id
=RaiPlayIE
._match
_id
(video_url
)))
391 return self
.playlist_result(
392 entries
, playlist_id
, program
.get('name'),
393 try_get(program
, lambda x
: x
['program_info']['description']))
396 class RaiIE(RaiBaseIE
):
397 _VALID_URL
= r
'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE
._UUID
_RE
399 # var uniquename = "ContentItem-..."
400 # data-id="ContentItem-..."
401 'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
403 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
405 'title': 'TG PRIMO TEMPO',
406 'thumbnail': r
're:^https?://.*\.jpg$',
408 'upload_date': '20140612',
410 'skip': 'This content is available only in Italy',
412 # with ContentItem in many metas
413 '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',
415 'id': '1632c009-c843-4836-bb65-80c33084a64b',
417 'title': 'Weekend al cinema, da Hollywood arriva il thriller di Tate Taylor "La ragazza del treno"',
418 'description': 'I film in uscita questa settimana.',
419 'thumbnail': r
're:^https?://.*\.png$',
421 'upload_date': '20161103',
424 # with ContentItem in og:url
425 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html',
426 'md5': '06345bd97c932f19ffb129973d07a020',
428 'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
430 'title': 'TG1 ore 20:00 del 03/11/2016',
431 'description': 'TG1 edizione integrale ore 20:00 del giorno 03/11/2016',
432 'thumbnail': r
're:^https?://.*\.jpg$',
434 'upload_date': '20161103',
437 # initEdizione('ContentItem-...'
438 'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
440 'id': 'c2187016-8484-4e3a-8ac8-35e475b07303',
442 'title': r
're:TG1 ore \d{2}:\d{2} del \d{2}/\d{2}/\d{4}',
444 'upload_date': '20170401',
446 'skip': 'Changes daily',
448 # HLS live stream with ContentItem in og:url
449 'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',
451 'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9',
453 'title': 'La diretta di Rainews24',
456 'skip_download': True,
460 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html',
461 'only_matching': True,
463 'url': 'https://www.rainews.it/tgr/marche/notiziari/video/2019/02/ContentItem-6ba945a2-889c-4a80-bdeb-8489c70a8db9.html',
464 'only_matching': True,
467 def _extract_from_content_id(self
, content_id
, url
):
468 media
= self
._download
_json
(
469 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % content_id
,
470 content_id
, 'Downloading video JSON')
472 title
= media
['name'].strip()
474 media_type
= media
['type']
475 if 'Audio' in media_type
:
478 'format_id': media
.get('formatoAudio'),
479 'url': media
['audioUrl'],
480 'ext': media
.get('formatoAudio'),
483 elif 'Video' in media_type
:
484 relinker_info
= self
._extract
_relinker
_info
(media
['mediaUri'], content_id
)
486 raise ExtractorError('not a media file')
488 self
._sort
_formats
(relinker_info
['formats'])
491 for image_type
in ('image', 'image_medium', 'image_300'):
492 thumbnail_url
= media
.get(image_type
)
495 'url': compat_urlparse
.urljoin(url
, thumbnail_url
),
498 subtitles
= self
._extract
_subtitles
(url
, media
)
503 'description': strip_or_none(media
.get('desc')),
504 'thumbnails': thumbnails
,
505 'uploader': media
.get('author'),
506 'upload_date': unified_strdate(media
.get('date')),
507 'duration': parse_duration(media
.get('length')),
508 'subtitles': subtitles
,
511 info
.update(relinker_info
)
515 def _real_extract(self
, url
):
516 video_id
= self
._match
_id
(url
)
518 webpage
= self
._download
_webpage
(url
, video_id
)
520 content_item_id
= None
522 content_item_url
= self
._html
_search
_meta
(
523 ('og:url', 'og:video', 'og:video:secure_url', 'twitter:url',
524 'twitter:player', 'jsonlink'), webpage
, default
=None)
526 content_item_id
= self
._search
_regex
(
527 r
'ContentItem-(%s)' % self
._UUID
_RE
, content_item_url
,
528 'content item id', default
=None)
530 if not content_item_id
:
531 content_item_id
= self
._search
_regex
(
534 (?:initEdizione|drawMediaRaiTV)\(|
535 <(?:[^>]+\bdata-id|var\s+uniquename)=|
539 (?
:(?
!\
1).)*\bContentItem
-(?P
<id>%s)
541 webpage, 'content item id', default=None, group='id')
543 content_item_ids = set()
545 content_item_ids.add(content_item_id)
546 if video_id not in content_item_ids:
547 content_item_ids.add(video_id)
549 for content_item_id in content_item_ids:
551 return self._extract_from_content_id(content_item_id, url)
552 except GeoRestrictedError:
554 except ExtractorError:
557 relinker_url = self._proto_relative_url(self._search_regex(
566 //mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\?
567 (?:(?!\1).)*\bcont=(?:(?!\1).)+)\1
569 webpage, 'relinker URL', group='url'))
571 relinker_info = self._extract_relinker_info(
572 urljoin(url, relinker_url), video_id)
573 self._sort_formats(relinker_info['formats'])
575 title = self._search_regex(
576 r'var\s+videoTitolo\s*=\s*([\'"])(?P
<title
>[^
\'"]+)\1',
577 webpage, 'title', group='title',
578 default=None) or self._og_search_title(webpage)
585 info.update(relinker_info)