3 from __future__
import unicode_literals
6 from .common
import InfoExtractor
21 from .dailymotion
import DailymotionIE
24 class FranceTVBaseInfoExtractor(InfoExtractor
):
25 def _make_url_result(self
, video_or_full_id
, catalog
=None):
26 full_id
= 'francetv:%s' % video_or_full_id
27 if '@' not in video_or_full_id
and catalog
:
28 full_id
+= '@%s' % catalog
29 return self
.url_result(
30 full_id
, ie
=FranceTVIE
.ie_key(),
31 video_id
=video_or_full_id
.split('@')[0])
34 class FranceTVIE(InfoExtractor
):
38 sivideo\.webservices\.francetelevisions\.fr/tools/getInfosOeuvre/v2/\?
39 .*?\bidDiffusion=[^&]+|
41 https?://videos\.francetv\.fr/video/|
44 (?P<id>[^@]+)(?:@(?P<catalog>.+))?
50 'url': 'https://sivideo.webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=162311093&callback=_jsonp_loader_callback_request_0',
51 'md5': 'c2248a8de38c4e65ea8fae7b5df2d84f',
55 'title': '13h15, le dimanche... - Les mystères de Jésus',
56 'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42',
57 'timestamp': 1502623500,
58 'upload_date': '20170813',
62 'url': 'https://sivideo.webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=NI_1004933&catalogue=Zouzous&callback=_jsonp_loader_callback_request_4',
63 'only_matching': True,
65 'url': 'http://videos.francetv.fr/video/NI_657393@Regions',
66 'only_matching': True,
68 'url': 'francetv:162311093',
69 'only_matching': True,
71 'url': 'francetv:NI_1004933@Zouzous',
72 'only_matching': True,
74 'url': 'francetv:NI_983319@Info-web',
75 'only_matching': True,
77 'url': 'francetv:NI_983319',
78 'only_matching': True,
80 'url': 'francetv:NI_657393@Regions',
81 'only_matching': True,
84 'url': 'francetv:SIM_France3',
85 'only_matching': True,
88 def _extract_video(self
, video_id
, catalogue
=None):
89 # Videos are identified by idDiffusion so catalogue part is optional.
90 # However when provided, some extra formats may be returned so we pass
92 info
= self
._download
_json
(
93 'https://sivideo.webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/',
94 video_id
, 'Downloading video JSON', query
={
95 'idDiffusion': video_id
,
96 'catalogue': catalogue
or '',
99 if info
.get('status') == 'NOK':
100 raise ExtractorError(
101 '%s returned error: %s' % (self
.IE_NAME
, info
['message']),
103 allowed_countries
= info
['videos'][0].get('geoblocage')
104 if allowed_countries
:
106 geo_info
= self
._download
_json
(
107 'http://geo.francetv.fr/ws/edgescape.json', video_id
,
108 'Downloading geo restriction info')
109 country
= geo_info
['reponse']['geo_info']['country_code']
110 if country
not in allowed_countries
:
111 raise ExtractorError(
112 'The video is not available from your location',
115 georestricted
= False
117 def sign(manifest_url
, manifest_id
):
118 for host
in ('hdfauthftv-a.akamaihd.net', 'hdfauth.francetv.fr'):
119 signed_url
= url_or_none(self
._download
_webpage
(
120 'https://%s/esi/TA' % host
, video_id
,
121 'Downloading signed %s manifest URL' % manifest_id
,
133 for video
in (info
.get('videos') or []):
134 if video
.get('statut') != 'ONLINE':
136 if not video
.get('url'):
141 for device_type
in ['desktop', 'mobile']:
142 fallback_info
= self
._download
_json
(
143 'https://player.webservices.francetelevisions.fr/v1/videos/%s' % video_id
,
144 video_id
, 'Downloading fallback %s video JSON' % device_type
, query
={
145 'device_type': device_type
,
149 if fallback_info
and fallback_info
.get('video'):
150 videos
.append(fallback_info
['video'])
155 video_url
= video
.get('url')
160 video
, lambda x
: x
['plages_ouverture'][0]['direct'], bool) is True
161 or video
.get('is_live') is True
162 or '/live.francetv.fr/' in video_url
)
163 format_id
= video
.get('format')
164 ext
= determine_ext(video_url
)
167 # See https://github.com/ytdl-org/youtube-dl/issues/3963
168 # m3u8 urls work fine
170 formats
.extend(self
._extract
_f
4m
_formats
(
171 sign(video_url
, format_id
) + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44',
172 video_id
, f4m_id
=format_id
, fatal
=False))
174 m3u8_fmts
, m3u8_subs
= self
._extract
_m
3u8_formats
_and
_subtitles
(
175 sign(video_url
, format_id
), video_id
, 'mp4',
176 entry_protocol
='m3u8_native', m3u8_id
=format_id
,
178 formats
.extend(m3u8_fmts
)
179 subtitles
= self
._merge
_subtitles
(subtitles
, m3u8_subs
)
181 formats
.extend(self
._extract
_mpd
_formats
(
182 sign(video_url
, format_id
), video_id
, mpd_id
=format_id
, fatal
=False))
183 elif video_url
.startswith('rtmp'):
186 'format_id': 'rtmp-%s' % format_id
,
190 if self
._is
_valid
_url
(video_url
, video_id
, format_id
):
193 'format_id': format_id
,
196 self
._sort
_formats
(formats
)
198 title
= info
['titre']
199 subtitle
= info
.get('sous_titre')
201 title
+= ' - %s' % subtitle
202 title
= title
.strip()
204 subtitles
.setdefault('fr', []).extend(
206 'url': subformat
['url'],
207 'ext': subformat
.get('format'),
208 } for subformat
in info
.get('subtitles', []) if subformat
.get('url')]
213 'title': self
._live
_title
(title
) if is_live
else title
,
214 'description': clean_html(info
.get('synopsis')),
215 'thumbnail': urljoin('https://sivideo.webservices.francetelevisions.fr', info
.get('image')),
216 'duration': int_or_none(info
.get('real_duration')) or parse_duration(info
.get('duree')),
217 'timestamp': int_or_none(try_get(info
, lambda x
: x
['diffusion']['timestamp'])),
220 'subtitles': subtitles
,
223 def _real_extract(self
, url
):
224 mobj
= self
._match
_valid
_url
(url
)
225 video_id
= mobj
.group('id')
226 catalog
= mobj
.group('catalog')
230 video_id
= qs
.get('idDiffusion', [None])[0]
231 catalog
= qs
.get('catalogue', [None])[0]
233 raise ExtractorError('Invalid URL', expected
=True)
235 return self
._extract
_video
(video_id
, catalog
)
238 class FranceTVSiteIE(FranceTVBaseInfoExtractor
):
239 _VALID_URL
= r
'https?://(?:(?:www\.)?france\.tv|mobile\.france\.tv)/(?:[^/]+/)*(?P<id>[^/]+)\.html'
242 'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
244 'id': 'ec217ecc-0733-48cf-ac06-af1347b849d1',
246 'title': '13h15, le dimanche... - Les mystères de Jésus',
247 'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42',
248 'timestamp': 1502623500,
249 'upload_date': '20170813',
252 'skip_download': True,
254 'add_ie': [FranceTVIE
.ie_key()],
257 'url': 'https://www.france.tv/france-3/des-chiffres-et-des-lettres/139063-emission-du-mardi-9-mai-2017.html',
258 'only_matching': True,
261 'url': 'https://www.france.tv/france-4/hero-corp/saison-1/134151-apres-le-calme.html',
262 'only_matching': True,
265 'url': 'https://www.france.tv/france-5/c-a-dire/saison-10/137013-c-a-dire.html',
266 'only_matching': True,
269 'url': 'https://www.france.tv/france-o/archipels/132249-mon-ancetre-l-esclave.html',
270 'only_matching': True,
273 'url': 'https://www.france.tv/france-2/direct.html',
274 'only_matching': True,
276 'url': 'https://www.france.tv/documentaires/histoire/136517-argentine-les-500-bebes-voles-de-la-dictature.html',
277 'only_matching': True,
279 'url': 'https://www.france.tv/jeux-et-divertissements/divertissements/133965-le-web-contre-attaque.html',
280 'only_matching': True,
282 'url': 'https://mobile.france.tv/france-5/c-dans-l-air/137347-emission-du-vendredi-12-mai-2017.html',
283 'only_matching': True,
285 'url': 'https://www.france.tv/142749-rouge-sang.html',
286 'only_matching': True,
289 'url': 'https://www.france.tv/france-3/direct.html',
290 'only_matching': True,
293 def _real_extract(self
, url
):
294 display_id
= self
._match
_id
(url
)
296 webpage
= self
._download
_webpage
(url
, display_id
)
299 video_id
= self
._search
_regex
(
300 r
'(?:data-main-video\s*=|videoId["\']?\s
*[:=])\s
*(["\'])(?P<id>(?:(?!\1).)+)\1',
301 webpage, 'video id', default=None, group='id')
304 video_id, catalogue = self._html_search_regex(
305 r'(?:href=|player\.setVideo\(\s*)"http
://videos?\
.francetv\
.fr
/video
/([^
@]+@[^
"]+)"',
306 webpage, 'video ID
').split('@')
308 return self._make_url_result(video_id, catalogue)
311 class FranceTVEmbedIE(FranceTVBaseInfoExtractor):
312 _VALID_URL = r'https?
://embed\
.francetv\
.fr
/*\?.*?
\bue
=(?P
<id>[^
&]+)'
315 'url
': 'http
://embed
.francetv
.fr
/?ue
=7fd581a2ccf59d2fc5719c5c13cf6961
',
319 'title
': 'Le Pen Reims
',
320 'upload_date
': '20170505',
321 'timestamp
': 1493981780,
325 'skip_download
': True,
327 'add_ie
': [FranceTVIE.ie_key()],
330 def _real_extract(self, url):
331 video_id = self._match_id(url)
333 video = self._download_json(
334 'http
://api
-embed
.webservices
.francetelevisions
.fr
/key
/%s' % video_id,
337 return self._make_url_result(video['video_id
'], video.get('catalog
'))
340 class FranceTVInfoIE(FranceTVBaseInfoExtractor):
341 IE_NAME = 'francetvinfo
.fr
'
342 _VALID_URL = r'https?
://(?
:www|mobile|france3
-regions
)\
.francetvinfo\
.fr
/(?
:[^
/]+/)*(?P
<id>[^
/?
#&.]+)'
345 'url': 'https://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-jeudi-22-aout-2019_3561461.html',
347 'id': 'd12458ee-5062-48fe-bfdd-a30d6a01b793',
350 'upload_date': '20190822',
351 'timestamp': 1566510900,
352 'description': 'md5:72d167097237701d6e8452ff03b83c00',
358 'skip_download': True,
360 'add_ie': [FranceTVIE
.ie_key()],
362 'note': 'Only an image exists in initial webpage instead of the video',
363 'url': 'https://www.francetvinfo.fr/sante/maladie/coronavirus/covid-19-en-inde-une-situation-catastrophique-a-new-dehli_4381095.html',
365 'id': '7d204c9e-a2d3-11eb-9e4c-000d3a23d482',
367 'title': 'Covid-19 : une situation catastrophique à New Dehli',
370 'timestamp': 1619028518,
371 'upload_date': '20210421',
374 'skip_download': True,
376 'add_ie': [FranceTVIE
.ie_key()],
378 'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
379 'only_matching': True,
381 'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
382 'only_matching': True,
384 'url': 'http://france3-regions.francetvinfo.fr/bretagne/cotes-d-armor/thalassa-echappee-breizh-ce-venredi-dans-les-cotes-d-armor-954961.html',
385 'only_matching': True,
388 'url': 'http://www.francetvinfo.fr/politique/notre-dame-des-landes/video-sur-france-inter-cecile-duflot-denonce-le-regard-meprisant-de-patrick-cohen_1520091.html',
389 'md5': 'ee7f1828f25a648addc90cb2687b1f12',
393 'title': 'NDDL, référendum, Brexit : Cécile Duflot répond à Patrick Cohen',
394 'description': 'Au lendemain de la victoire du "oui" au référendum sur l\'aéroport de Notre-Dame-des-Landes, l\'ancienne ministre écologiste est l\'invitée de Patrick Cohen. Plus d\'info : https://www.franceinter.fr/emissions/le-7-9/le-7-9-27-juin-2016',
395 'timestamp': 1467011958,
396 'upload_date': '20160627',
397 'uploader': 'France Inter',
398 'uploader_id': 'x2q2ez',
400 'add_ie': ['Dailymotion'],
402 'url': 'http://france3-regions.francetvinfo.fr/limousin/emissions/jt-1213-limousin',
403 'only_matching': True,
405 # "<figure id=" pattern (#28792)
406 'url': 'https://www.francetvinfo.fr/culture/patrimoine/incendie-de-notre-dame-de-paris/notre-dame-de-paris-de-l-incendie-de-la-cathedrale-a-sa-reconstruction_4372291.html',
407 'only_matching': True,
410 def _real_extract(self
, url
):
411 display_id
= self
._match
_id
(url
)
413 webpage
= self
._download
_webpage
(url
, display_id
)
415 dailymotion_urls
= DailymotionIE
._extract
_urls
(webpage
)
417 return self
.playlist_result([
418 self
.url_result(dailymotion_url
, DailymotionIE
.ie_key())
419 for dailymotion_url
in dailymotion_urls
])
421 video_id
= self
._search
_regex
(
422 (r
'player\.load[^;]+src:\s*["\']([^
"\']+)',
423 r'id-video=([^@]+@[^"]+)',
424 r'<a
[^
>]+href
="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"',
425 r'(?:data-id|<figure[^<]+\bid)=["\']([\da
-f
]{8}
-[\da
-f
]{4}
-[\da
-f
]{4}
-[\da
-f
]{4}
-[\da
-f
]{12}
)'),
428 return self._make_url_result(video_id)
431 class FranceTVInfoSportIE(FranceTVBaseInfoExtractor):
432 IE_NAME = 'sport
.francetvinfo
.fr
'
433 _VALID_URL = r'https?
://sport\
.francetvinfo\
.fr
/(?
:[^
/]+/)*(?P
<id>[^
/?
#&]+)'
435 'url': 'https://sport.francetvinfo.fr/les-jeux-olympiques/retour-sur-les-meilleurs-moments-de-pyeongchang-2018',
437 'id': '6e49080e-3f45-11e8-b459-000d3a2439ea',
439 'title': 'Retour sur les meilleurs moments de Pyeongchang 2018',
440 'timestamp': 1523639962,
441 'upload_date': '20180413',
444 'skip_download': True,
446 'add_ie': [FranceTVIE
.ie_key()],
449 def _real_extract(self
, url
):
450 display_id
= self
._match
_id
(url
)
451 webpage
= self
._download
_webpage
(url
, display_id
)
452 video_id
= self
._search
_regex
(r
'data-video="([^"]+)"', webpage
, 'video_id')
453 return self
._make
_url
_result
(video_id
, 'Sport-web')
456 class GenerationWhatIE(InfoExtractor
):
457 IE_NAME
= 'france2.fr:generation-what'
458 _VALID_URL
= r
'https?://generation-what\.francetv\.fr/[^/]+/video/(?P<id>[^/?#&]+)'
461 'url': 'http://generation-what.francetv.fr/portrait/video/present-arms',
465 'title': 'Generation What - Garde à vous - FRA',
466 'uploader': 'Generation What',
467 'uploader_id': 'UCHH9p1eetWCgt4kXBYCb3_w',
468 'upload_date': '20160411',
471 'skip_download': True,
473 'add_ie': ['Youtube'],
475 'url': 'http://generation-what.francetv.fr/europe/video/present-arms',
476 'only_matching': True,
479 def _real_extract(self
, url
):
480 display_id
= self
._match
_id
(url
)
482 webpage
= self
._download
_webpage
(url
, display_id
)
484 youtube_id
= self
._search
_regex
(
485 r
"window\.videoURL\s*=\s*'([0-9A-Za-z_-]{11})';",
486 webpage
, 'youtube id')
488 return self
.url_result(youtube_id
, ie
='Youtube', video_id
=youtube_id
)
491 class CultureboxIE(FranceTVBaseInfoExtractor
):
492 _VALID_URL
= r
'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?:[^/]+/)*(?P<id>[^/?#&]+)'
495 'url': 'https://culturebox.francetvinfo.fr/opera-classique/musique-classique/c-est-baroque/concerts/cantates-bwv-4-106-et-131-de-bach-par-raphael-pichon-57-268689',
499 'title': 'Cantates BWV 4, 106 et 131 de Bach par Raphaël Pichon 5/7',
500 'description': 'md5:19c44af004b88219f4daa50fa9a351d4',
501 'upload_date': '20180206',
502 'timestamp': 1517945220,
506 'skip_download': True,
508 'add_ie': [FranceTVIE
.ie_key()],
511 def _real_extract(self
, url
):
512 display_id
= self
._match
_id
(url
)
514 webpage
= self
._download
_webpage
(url
, display_id
)
516 if ">Ce live n'est plus disponible en replay<" in webpage
:
517 raise ExtractorError(
518 'Video %s is not available' % display_id
, expected
=True)
520 video_id
, catalogue
= self
._search
_regex
(
521 r
'["\'>]https?
://videos\
.francetv\
.fr
/video
/([^
@]+@.+?
)["\'<]',
522 webpage, 'video id').split('@')
524 return self._make_url_result(video_id, catalogue)
527 class FranceTVJeunesseIE(FranceTVBaseInfoExtractor):
528 _VALID_URL = r'(?P<url>https?://(?:www\.)?(?:zouzous|ludo)\.fr/heros/(?P<id>[^/?#&]+))'
531 'url': 'https://www.zouzous.fr/heros/simon',
537 'url': 'https://www.ludo.fr/heros/ninjago',
541 'playlist_count': 10,
543 'url': 'https://www.zouzous.fr/heros/simon?abc',
544 'only_matching': True,
547 def _real_extract(self, url):
548 mobj = self._match_valid_url(url)
549 playlist_id = mobj.group('id')
551 playlist = self._download_json(
552 '%s/%s' % (mobj.group('url'), 'playlist'), playlist_id)
554 if not playlist.get('count'):
555 raise ExtractorError(
556 '%s is not available' % playlist_id, expected=True)
559 for item in playlist['items']:
560 identity = item.get('identity')
561 if identity and isinstance(identity, compat_str):
562 entries.append(self._make_url_result(identity))
564 return self.playlist_result(entries, playlist_id)