]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vevo.py
1 from __future__
import unicode_literals
6 from .common
import InfoExtractor
19 class VevoBaseIE(InfoExtractor
):
20 def _extract_json(self
, webpage
, video_id
):
21 return self
._parse
_json
(
23 r
'window\.__INITIAL_STORE__\s*=\s*({.+?});\s*</script>',
24 webpage
, 'initial store'),
28 class VevoIE(VevoBaseIE
):
30 Accepts urls from vevo.com or in the format 'vevo:{id}'
31 (currently used by MTVIE and MySpaceIE)
34 (?:https?://(?:www\.)?vevo\.com/watch/(?!playlist|genre)(?:[^/]+/(?:[^/]+/)?)?|
35 https?://cache\.vevo\.com/m/html/embed\.html\?video=|
36 https?://videoplayer\.vevo\.com/embed/embedded\?videoId=|
37 https?://embed\.vevo\.com/.*?[?&]isrc=|
42 'url': 'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
43 'md5': '95ee28ee45e70130e3ab02b0f579ae23',
47 'title': 'Hurts - Somebody to Die For',
48 'timestamp': 1372057200,
49 'upload_date': '20130624',
51 'track': 'Somebody to Die For',
55 'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
57 'note': 'v3 SMIL format',
58 'url': 'http://www.vevo.com/watch/cassadee-pope/i-wish-i-could-break-your-heart/USUV71302923',
59 'md5': 'f6ab09b034f8c22969020b042e5ac7fc',
63 'title': 'Cassadee Pope - I Wish I Could Break Your Heart',
64 'timestamp': 1392796919,
65 'upload_date': '20140219',
66 'uploader': 'Cassadee Pope',
67 'track': 'I Wish I Could Break Your Heart',
68 'artist': 'Cassadee Pope',
71 'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
73 'note': 'Age-limited video',
74 'url': 'https://www.vevo.com/watch/justin-timberlake/tunnel-vision-explicit/USRV81300282',
78 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
80 'timestamp': 1372888800,
81 'upload_date': '20130703',
82 'uploader': 'Justin Timberlake',
83 'track': 'Tunnel Vision (Explicit)',
84 'artist': 'Justin Timberlake',
87 'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
89 'note': 'No video_info',
90 'url': 'http://www.vevo.com/watch/k-camp-1/Till-I-Die/USUV71503000',
91 'md5': '8b83cc492d72fc9cf74a02acee7dc1b0',
95 'title': 'K Camp ft. T.I. - Till I Die',
97 'timestamp': 1449468000,
98 'upload_date': '20151207',
100 'track': 'Till I Die',
104 'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
106 'note': 'Featured test',
107 'url': 'https://www.vevo.com/watch/lemaitre/Wait/USUV71402190',
108 'md5': 'd28675e5e8805035d949dc5cf161071d',
110 'id': 'USUV71402190',
112 'title': 'Lemaitre ft. LoLo - Wait',
114 'timestamp': 1413432000,
115 'upload_date': '20141016',
116 'uploader': 'Lemaitre',
118 'artist': 'Lemaitre',
119 'genre': 'Electronic',
121 'expected_warnings': ['Unable to download SMIL file', 'Unable to download info'],
123 'note': 'Only available via webpage',
124 'url': 'http://www.vevo.com/watch/GBUV71600656',
125 'md5': '67e79210613865b66a47c33baa5e37fe',
127 'id': 'GBUV71600656',
129 'title': 'ABC - Viva Love',
131 'timestamp': 1461830400,
132 'upload_date': '20160428',
134 'track': 'Viva Love',
138 'expected_warnings': ['Failed to download video versions info'],
140 # no genres available
141 'url': 'http://www.vevo.com/watch/INS171400764',
142 'only_matching': True,
144 # Another case available only via the webpage; using streams/streamsV3 formats
145 # Geo-restricted to Netherlands/Germany
146 'url': 'http://www.vevo.com/watch/boostee/pop-corn-clip-officiel/FR1A91600909',
147 'only_matching': True,
149 'url': 'https://embed.vevo.com/?isrc=USH5V1923499&partnerId=4d61b777-8023-4191-9ede-497ed6c24647&partnerAdCode=',
150 'only_matching': True,
153 0: 'youtube', # only in AuthenticateVideo videoVersions
160 def _initialize_api(self
, video_id
):
161 webpage
= self
._download
_webpage
(
162 'https://accounts.vevo.com/token', None,
163 note
='Retrieving oauth token',
164 errnote
='Unable to retrieve oauth token',
166 'client_id': 'SPupX1tvqFEopQ1YS6SS',
167 'grant_type': 'urn:vevo:params:oauth:grant-type:anonymous',
170 'Content-Type': 'application/json',
173 if re
.search(r
'(?i)THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION', webpage
):
174 self
.raise_geo_restricted(
175 '%s said: This page is currently unavailable in your region' % self
.IE_NAME
)
177 auth_info
= self
._parse
_json
(webpage
, video_id
)
178 self
._api
_url
_template
= self
.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info
['legacy_token']
180 def _call_api(self
, path
, *args
, **kwargs
):
182 data
= self
._download
_json
(self
._api
_url
_template
% path
, *args
, **kwargs
)
183 except ExtractorError
as e
:
184 if isinstance(e
.cause
, compat_HTTPError
):
185 errors
= self
._parse
_json
(e
.cause
.read().decode(), None)['errors']
186 error_message
= ', '.join([error
['message'] for error
in errors
])
187 raise ExtractorError('%s said: %s' % (self
.IE_NAME
, error_message
), expected
=True)
191 def _real_extract(self
, url
):
192 video_id
= self
._match
_id
(url
)
194 self
._initialize
_api
(video_id
)
196 video_info
= self
._call
_api
(
197 'video/%s' % video_id
, video_id
, 'Downloading api video info',
198 'Failed to download video info')
200 video_versions
= self
._call
_api
(
201 'video/%s/streams' % video_id
, video_id
,
202 'Downloading video versions info',
203 'Failed to download video versions info',
206 # Some videos are only available via webpage (e.g.
207 # https://github.com/ytdl-org/youtube-dl/issues/9366)
208 if not video_versions
:
209 webpage
= self
._download
_webpage
(url
, video_id
)
210 json_data
= self
._extract
_json
(webpage
, video_id
)
211 if 'streams' in json_data
.get('default', {}):
212 video_versions
= json_data
['default']['streams'][video_id
][0]
216 for key
, value
in json_data
['apollo']['data'].items()
217 if key
.startswith('%s.streams' % video_id
)]
221 featured_artist
= None
222 artists
= video_info
.get('artists')
223 for curr_artist
in artists
:
224 if curr_artist
.get('role') == 'Featured':
225 featured_artist
= curr_artist
['name']
227 artist
= uploader
= curr_artist
['name']
230 for video_version
in video_versions
:
231 version
= self
._VERSIONS
.get(video_version
.get('version'), 'generic')
232 version_url
= video_version
.get('url')
236 if '.ism' in version_url
:
238 elif '.mpd' in version_url
:
239 formats
.extend(self
._extract
_mpd
_formats
(
240 version_url
, video_id
, mpd_id
='dash-%s' % version
,
241 note
='Downloading %s MPD information' % version
,
242 errnote
='Failed to download %s MPD information' % version
,
244 elif '.m3u8' in version_url
:
245 formats
.extend(self
._extract
_m
3u8_formats
(
246 version_url
, video_id
, 'mp4', 'm3u8_native',
247 m3u8_id
='hls-%s' % version
,
248 note
='Downloading %s m3u8 information' % version
,
249 errnote
='Failed to download %s m3u8 information' % version
,
252 m
= re
.search(r
'''(?xi)
253 _(?P<width>[0-9]+)x(?P<height>[0-9]+)
254 _(?P<vcodec>[a-z0-9]+)
256 _(?P<acodec>[a-z0-9]+)
258 \.(?P<ext>[a-z0-9]+)''', version_url
)
264 'format_id': 'http-%s-%s' % (version
, video_version
['quality']),
265 'vcodec': m
.group('vcodec'),
266 'acodec': m
.group('acodec'),
267 'vbr': int(m
.group('vbr')),
268 'abr': int(m
.group('abr')),
269 'ext': m
.group('ext'),
270 'width': int(m
.group('width')),
271 'height': int(m
.group('height')),
273 self
._sort
_formats
(formats
)
275 track
= video_info
['title']
277 artist
= '%s ft. %s' % (artist
, featured_artist
)
278 title
= '%s - %s' % (artist
, track
) if artist
else track
280 genres
= video_info
.get('genres')
282 genres
[0] if genres
and isinstance(genres
, list)
283 and isinstance(genres
[0], compat_str
) else None)
285 is_explicit
= video_info
.get('isExplicit')
286 if is_explicit
is True:
288 elif is_explicit
is False:
297 'thumbnail': video_info
.get('imageUrl') or video_info
.get('thumbnailUrl'),
298 'timestamp': parse_iso8601(video_info
.get('releaseDate')),
299 'uploader': uploader
,
300 'duration': int_or_none(video_info
.get('duration')),
301 'view_count': int_or_none(video_info
.get('views', {}).get('total')),
302 'age_limit': age_limit
,
309 class VevoPlaylistIE(VevoBaseIE
):
310 _VALID_URL
= r
'https?://(?:www\.)?vevo\.com/watch/(?P<kind>playlist|genre)/(?P<id>[^/?#&]+)'
313 'url': 'http://www.vevo.com/watch/playlist/dadbf4e7-b99f-4184-9670-6f0e547b6a29',
315 'id': 'dadbf4e7-b99f-4184-9670-6f0e547b6a29',
316 'title': 'Best-Of: Birdman',
318 'playlist_count': 10,
320 'url': 'http://www.vevo.com/watch/genre/rock',
325 'playlist_count': 20,
327 'url': 'http://www.vevo.com/watch/playlist/dadbf4e7-b99f-4184-9670-6f0e547b6a29?index=0',
328 'md5': '32dcdfddddf9ec6917fc88ca26d36282',
330 'id': 'USCMV1100073',
332 'title': 'Birdman - Y.U. MAD',
333 'timestamp': 1323417600,
334 'upload_date': '20111209',
335 'uploader': 'Birdman',
338 'genre': 'Rap/Hip-Hop',
340 'expected_warnings': ['Unable to download SMIL file'],
342 'url': 'http://www.vevo.com/watch/genre/rock?index=0',
343 'only_matching': True,
346 def _real_extract(self
, url
):
347 mobj
= re
.match(self
._VALID
_URL
, url
)
348 playlist_id
= mobj
.group('id')
349 playlist_kind
= mobj
.group('kind')
351 webpage
= self
._download
_webpage
(url
, playlist_id
)
353 qs
= compat_urlparse
.parse_qs(compat_urlparse
.urlparse(url
).query
)
354 index
= qs
.get('index', [None])[0]
357 video_id
= self
._search
_regex
(
358 r
'<meta[^>]+content=(["\'])vevo
://video
/(?P
<id>.+?
)\
1[^
>]*>',
359 webpage, 'video
id', default=None, group='id')
361 return self.url_result('vevo
:%s' % video_id, VevoIE.ie_key())
363 playlists = self._extract_json(webpage, playlist_id)['default
']['%ss' % playlist_kind]
365 playlist = (list(playlists.values())[0]
366 if playlist_kind == 'playlist
' else playlists[playlist_id])
369 self.url_result('vevo
:%s' % src, VevoIE.ie_key())
370 for src in playlist['isrcs
']]
372 return self.playlist_result(
373 entries, playlist.get('playlistId
') or playlist_id,
374 playlist.get('name
'), playlist.get('description
'))