3 from __future__
import unicode_literals
7 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
,
132 for video
in info
['videos']:
133 if video
['statut'] != 'ONLINE':
135 video_url
= video
['url']
140 video
, lambda x
: x
['plages_ouverture'][0]['direct'],
141 bool) is True) or '/live.francetv.fr/' in video_url
142 format_id
= video
['format']
143 ext
= determine_ext(video_url
)
146 # See https://github.com/ytdl-org/youtube-dl/issues/3963
147 # m3u8 urls work fine
149 formats
.extend(self
._extract
_f
4m
_formats
(
150 sign(video_url
, format_id
) + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44',
151 video_id
, f4m_id
=format_id
, fatal
=False))
153 formats
.extend(self
._extract
_m
3u8_formats
(
154 sign(video_url
, format_id
), video_id
, 'mp4',
155 entry_protocol
='m3u8_native', m3u8_id
=format_id
,
157 elif video_url
.startswith('rtmp'):
160 'format_id': 'rtmp-%s' % format_id
,
164 if self
._is
_valid
_url
(video_url
, video_id
, format_id
):
167 'format_id': format_id
,
169 self
._sort
_formats
(formats
)
171 title
= info
['titre']
172 subtitle
= info
.get('sous_titre')
174 title
+= ' - %s' % subtitle
175 title
= title
.strip()
179 'url': subformat
['url'],
180 'ext': subformat
.get('format'),
181 } for subformat
in info
.get('subtitles', []) if subformat
.get('url')]
183 subtitles
['fr'] = subtitles_list
187 'title': self
._live
_title
(title
) if is_live
else title
,
188 'description': clean_html(info
['synopsis']),
189 'thumbnail': compat_urlparse
.urljoin('http://pluzz.francetv.fr', info
['image']),
190 'duration': int_or_none(info
.get('real_duration')) or parse_duration(info
['duree']),
191 'timestamp': int_or_none(info
['diffusion']['timestamp']),
194 'subtitles': subtitles
,
197 def _real_extract(self
, url
):
198 mobj
= re
.match(self
._VALID
_URL
, url
)
199 video_id
= mobj
.group('id')
200 catalog
= mobj
.group('catalog')
203 qs
= compat_urlparse
.parse_qs(compat_urlparse
.urlparse(url
).query
)
204 video_id
= qs
.get('idDiffusion', [None])[0]
205 catalog
= qs
.get('catalogue', [None])[0]
207 raise ExtractorError('Invalid URL', expected
=True)
209 return self
._extract
_video
(video_id
, catalog
)
212 class FranceTVSiteIE(FranceTVBaseInfoExtractor
):
213 _VALID_URL
= r
'https?://(?:(?:www\.)?france\.tv|mobile\.france\.tv)/(?:[^/]+/)*(?P<id>[^/]+)\.html'
216 'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
218 'id': 'ec217ecc-0733-48cf-ac06-af1347b849d1',
220 'title': '13h15, le dimanche... - Les mystères de Jésus',
221 'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42',
222 'timestamp': 1502623500,
223 'upload_date': '20170813',
226 'skip_download': True,
228 'add_ie': [FranceTVIE
.ie_key()],
231 'url': 'https://www.france.tv/france-3/des-chiffres-et-des-lettres/139063-emission-du-mardi-9-mai-2017.html',
232 'only_matching': True,
235 'url': 'https://www.france.tv/france-4/hero-corp/saison-1/134151-apres-le-calme.html',
236 'only_matching': True,
239 'url': 'https://www.france.tv/france-5/c-a-dire/saison-10/137013-c-a-dire.html',
240 'only_matching': True,
243 'url': 'https://www.france.tv/france-o/archipels/132249-mon-ancetre-l-esclave.html',
244 'only_matching': True,
247 'url': 'https://www.france.tv/france-2/direct.html',
248 'only_matching': True,
250 'url': 'https://www.france.tv/documentaires/histoire/136517-argentine-les-500-bebes-voles-de-la-dictature.html',
251 'only_matching': True,
253 'url': 'https://www.france.tv/jeux-et-divertissements/divertissements/133965-le-web-contre-attaque.html',
254 'only_matching': True,
256 'url': 'https://mobile.france.tv/france-5/c-dans-l-air/137347-emission-du-vendredi-12-mai-2017.html',
257 'only_matching': True,
259 'url': 'https://www.france.tv/142749-rouge-sang.html',
260 'only_matching': True,
263 'url': 'https://www.france.tv/france-3/direct.html',
264 'only_matching': True,
267 def _real_extract(self
, url
):
268 display_id
= self
._match
_id
(url
)
270 webpage
= self
._download
_webpage
(url
, display_id
)
273 video_id
= self
._search
_regex
(
274 r
'(?:data-main-video\s*=|videoId["\']?\s
*[:=])\s
*(["\'])(?P<id>(?:(?!\1).)+)\1',
275 webpage, 'video id', default=None, group='id')
278 video_id, catalogue = self._html_search_regex(
279 r'(?:href=|player\.setVideo\(\s*)"http
://videos?\
.francetv\
.fr
/video
/([^
@]+@[^
"]+)"',
280 webpage, 'video ID
').split('@')
282 return self._make_url_result(video_id, catalogue)
285 class FranceTVEmbedIE(FranceTVBaseInfoExtractor):
286 _VALID_URL = r'https?
://embed\
.francetv\
.fr
/*\?.*?
\bue
=(?P
<id>[^
&]+)'
289 'url
': 'http
://embed
.francetv
.fr
/?ue
=7fd581a2ccf59d2fc5719c5c13cf6961
',
293 'title
': 'Le Pen Reims
',
294 'upload_date
': '20170505',
295 'timestamp
': 1493981780,
299 'skip_download
': True,
301 'add_ie
': [FranceTVIE.ie_key()],
304 def _real_extract(self, url):
305 video_id = self._match_id(url)
307 video = self._download_json(
308 'http
://api
-embed
.webservices
.francetelevisions
.fr
/key
/%s' % video_id,
311 return self._make_url_result(video['video_id
'], video.get('catalog
'))
314 class FranceTVInfoIE(FranceTVBaseInfoExtractor):
315 IE_NAME = 'francetvinfo
.fr
'
316 _VALID_URL = r'https?
://(?
:www|mobile|france3
-regions
)\
.francetvinfo\
.fr
/(?
:[^
/]+/)*(?P
<id>[^
/?
#&.]+)'
319 'url': 'https://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-jeudi-22-aout-2019_3561461.html',
321 'id': 'd12458ee-5062-48fe-bfdd-a30d6a01b793',
324 'upload_date': '20190822',
325 'timestamp': 1566510900,
326 'description': 'md5:72d167097237701d6e8452ff03b83c00',
332 'skip_download': True,
334 'add_ie': [FranceTVIE
.ie_key()],
336 'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
337 'only_matching': True,
339 'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
340 'only_matching': True,
342 'url': 'http://france3-regions.francetvinfo.fr/bretagne/cotes-d-armor/thalassa-echappee-breizh-ce-venredi-dans-les-cotes-d-armor-954961.html',
343 'only_matching': True,
346 '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',
347 'md5': 'ee7f1828f25a648addc90cb2687b1f12',
351 'title': 'NDDL, référendum, Brexit : Cécile Duflot répond à Patrick Cohen',
352 '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',
353 'timestamp': 1467011958,
354 'upload_date': '20160627',
355 'uploader': 'France Inter',
356 'uploader_id': 'x2q2ez',
358 'add_ie': ['Dailymotion'],
360 'url': 'http://france3-regions.francetvinfo.fr/limousin/emissions/jt-1213-limousin',
361 'only_matching': True,
364 def _real_extract(self
, url
):
365 display_id
= self
._match
_id
(url
)
367 webpage
= self
._download
_webpage
(url
, display_id
)
369 dailymotion_urls
= DailymotionIE
._extract
_urls
(webpage
)
371 return self
.playlist_result([
372 self
.url_result(dailymotion_url
, DailymotionIE
.ie_key())
373 for dailymotion_url
in dailymotion_urls
])
375 video_id
= self
._search
_regex
(
376 (r
'player\.load[^;]+src:\s*["\']([^
"\']+)',
377 r'id-video=([^@]+@[^"]+)',
378 r'<a
[^
>]+href
="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"',
379 r'data-id="([^
"]+)"'),
382 return self._make_url_result(video_id)
385 class FranceTVInfoSportIE(FranceTVBaseInfoExtractor):
386 IE_NAME = 'sport
.francetvinfo
.fr
'
387 _VALID_URL = r'https?
://sport\
.francetvinfo\
.fr
/(?
:[^
/]+/)*(?P
<id>[^
/?
#&]+)'
389 'url': 'https://sport.francetvinfo.fr/les-jeux-olympiques/retour-sur-les-meilleurs-moments-de-pyeongchang-2018',
391 'id': '6e49080e-3f45-11e8-b459-000d3a2439ea',
393 'title': 'Retour sur les meilleurs moments de Pyeongchang 2018',
394 'timestamp': 1523639962,
395 'upload_date': '20180413',
398 'skip_download': True,
400 'add_ie': [FranceTVIE
.ie_key()],
403 def _real_extract(self
, url
):
404 display_id
= self
._match
_id
(url
)
405 webpage
= self
._download
_webpage
(url
, display_id
)
406 video_id
= self
._search
_regex
(r
'data-video="([^"]+)"', webpage
, 'video_id')
407 return self
._make
_url
_result
(video_id
, 'Sport-web')
410 class GenerationWhatIE(InfoExtractor
):
411 IE_NAME
= 'france2.fr:generation-what'
412 _VALID_URL
= r
'https?://generation-what\.francetv\.fr/[^/]+/video/(?P<id>[^/?#&]+)'
415 'url': 'http://generation-what.francetv.fr/portrait/video/present-arms',
419 'title': 'Generation What - Garde à vous - FRA',
420 'uploader': 'Generation What',
421 'uploader_id': 'UCHH9p1eetWCgt4kXBYCb3_w',
422 'upload_date': '20160411',
425 'skip_download': True,
427 'add_ie': ['Youtube'],
429 'url': 'http://generation-what.francetv.fr/europe/video/present-arms',
430 'only_matching': True,
433 def _real_extract(self
, url
):
434 display_id
= self
._match
_id
(url
)
436 webpage
= self
._download
_webpage
(url
, display_id
)
438 youtube_id
= self
._search
_regex
(
439 r
"window\.videoURL\s*=\s*'([0-9A-Za-z_-]{11})';",
440 webpage
, 'youtube id')
442 return self
.url_result(youtube_id
, ie
='Youtube', video_id
=youtube_id
)
445 class CultureboxIE(FranceTVBaseInfoExtractor
):
446 _VALID_URL
= r
'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?:[^/]+/)*(?P<id>[^/?#&]+)'
449 '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',
453 'title': 'Cantates BWV 4, 106 et 131 de Bach par Raphaël Pichon 5/7',
454 'description': 'md5:19c44af004b88219f4daa50fa9a351d4',
455 'upload_date': '20180206',
456 'timestamp': 1517945220,
460 'skip_download': True,
462 'add_ie': [FranceTVIE
.ie_key()],
465 def _real_extract(self
, url
):
466 display_id
= self
._match
_id
(url
)
468 webpage
= self
._download
_webpage
(url
, display_id
)
470 if ">Ce live n'est plus disponible en replay<" in webpage
:
471 raise ExtractorError(
472 'Video %s is not available' % display_id
, expected
=True)
474 video_id
, catalogue
= self
._search
_regex
(
475 r
'["\'>]https?
://videos\
.francetv\
.fr
/video
/([^
@]+@.+?
)["\'<]',
476 webpage, 'video id').split('@')
478 return self._make_url_result(video_id, catalogue)
481 class FranceTVJeunesseIE(FranceTVBaseInfoExtractor):
482 _VALID_URL = r'(?P<url>https?://(?:www\.)?(?:zouzous|ludo)\.fr/heros/(?P<id>[^/?#&]+))'
485 'url': 'https://www.zouzous.fr/heros/simon',
491 'url': 'https://www.ludo.fr/heros/ninjago',
495 'playlist_count': 10,
497 'url': 'https://www.zouzous.fr/heros/simon?abc',
498 'only_matching': True,
501 def _real_extract(self, url):
502 mobj = re.match(self._VALID_URL, url)
503 playlist_id = mobj.group('id')
505 playlist = self._download_json(
506 '%s/%s' % (mobj.group('url'), 'playlist'), playlist_id)
508 if not playlist.get('count'):
509 raise ExtractorError(
510 '%s is not available' % playlist_id, expected=True)
513 for item in playlist['items']:
514 identity = item.get('identity')
515 if identity and isinstance(identity, compat_str):
516 entries.append(self._make_url_result(identity))
518 return self.playlist_result(entries, playlist_id)