2 from __future__
import unicode_literals
9 from .common
import InfoExtractor
10 from ..compat
import (
43 class VimeoBaseInfoExtractor(InfoExtractor
):
44 _NETRC_MACHINE
= 'vimeo'
45 _LOGIN_REQUIRED
= False
46 _LOGIN_URL
= 'https://vimeo.com/log_in'
49 username
, password
= self
._get
_login
_info
()
51 if self
._LOGIN
_REQUIRED
:
52 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
54 webpage
= self
._download
_webpage
(
55 self
._LOGIN
_URL
, None, 'Downloading login page')
56 token
, vuid
= self
._extract
_xsrft
_and
_vuid
(webpage
)
64 self
._set
_vimeo
_cookie
('vuid', vuid
)
66 self
._download
_webpage
(
67 self
._LOGIN
_URL
, None, 'Logging in',
68 data
=urlencode_postdata(data
), headers
={
69 'Content-Type': 'application/x-www-form-urlencoded',
70 'Referer': self
._LOGIN
_URL
,
72 except ExtractorError
as e
:
73 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 418:
75 'Unable to log in: bad username or password',
77 raise ExtractorError('Unable to log in')
79 def _get_video_password(self
):
80 password
= self
.get_param('videopassword')
83 'This video is protected by a password, use the --video-password option',
87 def _verify_video_password(self
, url
, video_id
, password
, token
, vuid
):
88 if url
.startswith('http://'):
89 # vimeo only supports https now, but the user can give an http url
90 url
= url
.replace('http://', 'https://')
91 self
._set
_vimeo
_cookie
('vuid', vuid
)
92 return self
._download
_webpage
(
93 url
+ '/password', video_id
, 'Verifying the password',
94 'Wrong password', data
=urlencode_postdata({
98 'Content-Type': 'application/x-www-form-urlencoded',
102 def _extract_xsrft_and_vuid(self
, webpage
):
103 xsrft
= self
._search
_regex
(
104 r
'(?:(?P<q1>["\'])xsrft(?P
=q1
)\s
*:|xsrft\s
*[=:])\s
*(?P
<q
>["\'])(?P<xsrft>.+?)(?P=q)',
105 webpage, 'login token', group='xsrft')
106 vuid = self._search_regex(
107 r'["\']vuid
["\']\s*:\s*(["\'])(?P
<vuid
>.+?
)\
1',
108 webpage, 'vuid
', group='vuid
')
111 def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
112 vimeo_config = self._search_regex(
113 r'vimeo\
.config\s
*=\s
*(?
:({.+?}
)|_extend\
([^
,]+,\s
+({.+?}
)\
));',
114 webpage, 'vimeo config
', *args, **compat_kwargs(kwargs))
116 return self._parse_json(vimeo_config, video_id)
118 def _set_vimeo_cookie(self, name, value):
119 self._set_cookie('vimeo
.com
', name, value)
121 def _vimeo_sort_formats(self, formats):
122 # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
123 # at the same time without actual units specified. This lead to wrong sorting.
124 # But since yt-dlp prefers 'res
,fps
' anyway, 'field_preference
' is not needed
125 self._sort_formats(formats)
127 def _parse_config(self, config, video_id):
128 video_data = config['video
']
129 video_title = video_data['title
']
130 live_event = video_data.get('live_event
') or {}
131 is_live = live_event.get('status
') == 'started
'
132 request = config.get('request
') or {}
135 config_files = video_data.get('files
') or request.get('files
') or {}
136 for f in (config_files.get('progressive
') or []):
137 video_url = f.get('url
')
142 'format_id
': 'http
-%s' % f.get('quality
'),
143 'width
': int_or_none(f.get('width
')),
144 'height
': int_or_none(f.get('height
')),
145 'fps
': int_or_none(f.get('fps
')),
146 'tbr
': int_or_none(f.get('bitrate
')),
149 # TODO: fix handling of 308 status code returned for live archive manifest requests
150 sep_pattern = r'/sep
/video
/'
151 for files_type in ('hls
', 'dash
'):
152 for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns
']) or {}).items():
153 manifest_url = cdn_data.get('url
')
156 format_id = '%s-%s' % (files_type, cdn_name)
157 sep_manifest_urls = []
158 if re.search(sep_pattern, manifest_url):
159 for suffix, repl in (('', 'video
'), ('_sep
', 'sep
/video
')):
160 sep_manifest_urls.append((format_id + suffix, re.sub(
161 sep_pattern, '/%s/' % repl, manifest_url)))
163 sep_manifest_urls = [(format_id, manifest_url)]
164 for f_id, m_url in sep_manifest_urls:
165 if files_type == 'hls
':
166 formats.extend(self._extract_m3u8_formats(
167 m_url, video_id, 'mp4
',
168 'm3u8
' if is_live else 'm3u8_native
', m3u8_id=f_id,
169 note='Downloading
%s m3u8 information
' % cdn_name,
171 elif files_type == 'dash
':
172 if 'json
=1' in m_url:
173 real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url
')
176 mpd_formats = self._extract_mpd_formats(
177 m_url.replace('/master
.json
', '/master
.mpd
'), video_id, f_id,
178 'Downloading
%s MPD information
' % cdn_name,
180 formats.extend(mpd_formats)
182 live_archive = live_event.get('archive
') or {}
183 live_archive_source_url = live_archive.get('source_url
')
184 if live_archive_source_url and live_archive.get('status
') == 'done
':
186 'format_id
': 'live
-archive
-source
',
187 'url
': live_archive_source_url,
192 for tt in (request.get('text_tracks
') or []):
193 subtitles[tt['lang
']] = [{
195 'url
': urljoin('https
://vimeo
.com
', tt['url
']),
200 for key, thumb in (video_data.get('thumbs
') or {}).items():
203 'width
': int_or_none(key),
206 thumbnail = video_data.get('thumbnail
')
212 owner = video_data.get('owner
') or {}
213 video_uploader_url = owner.get('url
')
216 'id': str_or_none(video_data.get('id')) or video_id,
217 'title
': self._live_title(video_title) if is_live else video_title,
218 'uploader
': owner.get('name
'),
219 'uploader_id
': video_uploader_url.split('/')[-1] if video_uploader_url else None,
220 'uploader_url
': video_uploader_url,
221 'thumbnails
': thumbnails,
222 'duration
': int_or_none(video_data.get('duration
')),
224 'subtitles
': subtitles,
228 def _extract_original_format(self, url, video_id, unlisted_hash=None):
229 query = {'action': 'load_download_config'}
231 query['unlisted_hash
'] = unlisted_hash
232 download_data = self._download_json(
233 url, video_id, fatal=False, query=query,
234 headers={'X-Requested-With': 'XMLHttpRequest'},
235 expected_status=(403, 404)) or {}
236 source_file = download_data.get('source_file
')
237 download_url = try_get(source_file, lambda x: x['download_url
'])
238 if download_url and not source_file.get('is_cold
') and not source_file.get('is_defrosting
'):
239 source_name = source_file.get('public_name
', 'Original
')
240 if self._is_valid_url(download_url, video_id, '%s video
' % source_name):
242 source_file, lambda x: x['extension
'],
243 compat_str) or determine_ext(
244 download_url, None) or 'mp4
').lower()
248 'width
': int_or_none(source_file.get('width
')),
249 'height
': int_or_none(source_file.get('height
')),
250 'filesize
': parse_filesize(source_file.get('size
')),
251 'format_id
': source_name,
255 jwt_response = self._download_json(
256 'https
://vimeo
.com
/_rv
/viewer
', video_id, note='Downloading jwt token
', fatal=False) or {}
257 if not jwt_response.get('jwt
'):
259 headers = {'Authorization': 'jwt %s' % jwt_response['jwt']}
260 original_response = self._download_json(
261 f'https
://api
.vimeo
.com
/videos
/{video_id}
', video_id,
262 headers=headers, fatal=False, expected_status=(403, 404)) or {}
263 for download_data in original_response.get('download
') or []:
264 download_url = download_data.get('link
')
265 if not download_url or download_data.get('quality
') != 'source
':
267 ext = determine_ext(parse_qs(download_url).get('filename
', [''])[0].lower(), default_ext=None)
269 urlh = self._request_webpage(
270 HEADRequest(download_url), video_id, fatal=False, note='Determining source extension
')
271 ext = urlh and urlhandle_detect_ext(urlh)
274 'ext
': ext or 'unknown_video
',
275 'format_id
': download_data.get('public_name
', 'Original
'),
276 'width
': int_or_none(download_data.get('width
')),
277 'height
': int_or_none(download_data.get('height
')),
278 'fps
': int_or_none(download_data.get('fps
')),
279 'filesize
': int_or_none(download_data.get('size
')),
284 class VimeoIE(VimeoBaseInfoExtractor):
285 """Information extractor for vimeo.com."""
287 # _VALID_URL matches Vimeo URLs
288 _VALID_URL = r'''(?x)
298 (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
303 moogaloop\.swf)\?clip_id=
307 (?:/(?P<unlisted_hash>[\da-f]{10}))?
308 /?(?:[?&].*)?(?:[#].*)?$
313 'url
': 'http
://vimeo
.com
/56015672#at=0',
314 'md5': '8879b6cc097e987f02484baf890129e5',
318 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
319 'description': 'md5:2d3305bad981a06ff79f027f19865021',
320 'timestamp': 1355990239,
321 'upload_date': '20121220',
322 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/user7108434',
323 'uploader_id': 'user7108434',
324 'uploader': 'Filippo Valsorda',
329 'format': 'best[protocol=https]',
333 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
334 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
335 'note': 'Vimeo Pro video (#1197)',
339 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
340 'uploader_id': 'openstreetmapus',
341 'uploader': 'OpenStreetMap US',
342 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
343 'description': 'md5:2c362968038d4499f4d79f88458590c1',
345 'upload_date': '20130610',
346 'timestamp': 1370893156,
350 'format': 'best[protocol=https]',
354 'url': 'http://player.vimeo.com/video/54469442',
355 'md5': '619b811a4417aa4abe78dc653becf511',
356 'note': 'Videos that embed the url in the player page',
360 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
361 'uploader': 'Business of Software',
362 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
363 'uploader_id': 'businessofsoftware',
368 'format': 'best[protocol=https]',
372 'url': 'http://vimeo.com/68375962',
373 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
374 'note': 'Video protected with password',
378 'title': 'youtube-dl password protected test video',
379 'timestamp': 1371200155,
380 'upload_date': '20130614',
381 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/user18948128',
382 'uploader_id': 'user18948128',
383 'uploader': 'Jaime Marquínez Ferrándiz',
385 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
388 'format': 'best[protocol=https]',
389 'videopassword': 'youtube-dl',
393 'url': 'http://vimeo.com/channels/keypeele/75629013',
394 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
398 'title': 'Key & Peele: Terrorist Interrogation',
399 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
400 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/atencio',
401 'uploader_id': 'atencio',
402 'uploader': 'Peter Atencio',
403 'channel_id': 'keypeele',
404 'channel_url': r
're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
405 'timestamp': 1380339469,
406 'upload_date': '20130928',
409 'params': {'format': 'http-1080p'}
,
412 'url': 'http://vimeo.com/76979871',
413 'note': 'Video with subtitles',
417 'title': 'The New Vimeo Player (You Know, For Videos)',
418 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
419 'timestamp': 1381846109,
420 'upload_date': '20131015',
421 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/staff',
422 'uploader_id': 'staff',
423 'uploader': 'Vimeo Staff',
426 'de': [{'ext': 'vtt'}
],
427 'en': [{'ext': 'vtt'}
],
428 'es': [{'ext': 'vtt'}
],
429 'fr': [{'ext': 'vtt'}
],
432 'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
435 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
436 'url': 'https://player.vimeo.com/video/98044508',
437 'note': 'The js code contains assignments to the same variable as the config',
441 'title': 'Pier Solar OUYA Official Trailer',
442 'uploader': 'Tulio Gonçalves',
443 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/user28849593',
444 'uploader_id': 'user28849593',
448 # contains original format
449 'url': 'https://vimeo.com/33951933',
450 'md5': '53c688fa95a55bf4b7293d37a89c5c53',
454 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
455 'uploader': 'The DMCI',
456 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/dmci',
457 'uploader_id': 'dmci',
458 'timestamp': 1324343742,
459 'upload_date': '20111220',
460 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
464 'note': 'Contains original format not accessible in webpage',
465 'url': 'https://vimeo.com/393756517',
466 'md5': 'c464af248b592190a5ffbb5d33f382b0',
470 'timestamp': 1582642091,
471 'uploader_id': 'frameworkla',
472 'title': 'Straight To Hell - Sabrina: Netflix',
473 'uploader': 'Framework Studio',
474 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
475 'upload_date': '20200225',
479 # only available via https://vimeo.com/channels/tributes/6213729 and
480 # not via https://vimeo.com/6213729
481 'url': 'https://vimeo.com/channels/tributes/6213729',
485 'title': 'Vimeo Tribute: The Shining',
486 'uploader': 'Casey Donahue',
487 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/caseydonahue',
488 'uploader_id': 'caseydonahue',
489 'channel_url': r
're:https?://(?:www\.)?vimeo\.com/channels/tributes',
490 'channel_id': 'tributes',
491 'timestamp': 1250886430,
492 'upload_date': '20090821',
493 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
496 'skip_download': True,
500 # redirects to ondemand extractor and should be passed through it
501 # for successful extraction
502 'url': 'https://vimeo.com/73445910',
506 'title': 'The Reluctant Revolutionary',
507 'uploader': '10Ft Films',
508 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
509 'uploader_id': 'tenfootfilms',
510 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
511 'upload_date': '20130830',
512 'timestamp': 1377853339,
515 'skip_download': True,
517 'skip': 'this page is no longer available.',
520 'url': 'http://player.vimeo.com/video/68375962',
521 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
525 'title': 'youtube-dl password protected test video',
526 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/user18948128',
527 'uploader_id': 'user18948128',
528 'uploader': 'Jaime Marquínez Ferrándiz',
532 'format': 'best[protocol=https]',
533 'videopassword': 'youtube-dl',
537 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
538 'only_matching': True,
541 'url': 'https://vimeo.com/109815029',
542 'note': 'Video not completely processed, "failed" seed status',
543 'only_matching': True,
546 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
547 'only_matching': True,
550 'url': 'https://vimeo.com/album/2632481/video/79010983',
551 'only_matching': True,
554 'url': 'https://vimeo.com/showcase/3253534/video/119195465',
555 'note': 'A video in a password protected album (showcase)',
559 'title': 'youtube-dl test video \'ä"BaW_jenozKc',
560 'uploader': 'Philipp Hagemeister',
561 'uploader_id': 'user20132939',
562 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
563 'upload_date': '20150209',
564 'timestamp': 1423518307,
567 'format': 'best[protocol=https]',
568 'videopassword': 'youtube-dl',
572 # source file returns 403: Forbidden
573 'url': 'https://vimeo.com/7809605',
574 'only_matching': True,
577 'note': 'Direct URL with hash',
578 'url': 'https://vimeo.com/160743502/abd0e13fb4',
582 'uploader': 'Julian Tryba',
583 'uploader_id': 'aliniamedia',
584 'title': 'Harrisville New Hampshire',
585 'timestamp': 1459259666,
586 'upload_date': '20160329',
588 'params': {'skip_download': True}
,
591 'url': 'https://vimeo.com/138909882',
595 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!',
596 'description': 'md5:5967e090768a831488f6e74b7821b3c1',
597 'uploader_id': 'fireworkchampions',
598 'uploader': 'Firework Champions',
599 'upload_date': '20150910',
600 'timestamp': 1441901895,
603 'skip_download': True,
604 'format': 'Original',
608 'url': 'https://vimeo.com/channels/staffpicks/143603739',
612 'uploader': 'Karim Huu Do',
613 'timestamp': 1445846953,
614 'upload_date': '20151026',
615 'title': 'The Shoes - Submarine Feat. Blaine Harrison',
616 'uploader_id': 'karimhd',
617 'description': 'md5:8e2eea76de4504c2e8020a9bcfa1e843',
619 'params': {'skip_download': 'm3u8'}
,
622 # requires passing unlisted_hash(a52724358e) to load_download_config request
623 'url': 'https://vimeo.com/392479337/a52724358e',
624 'only_matching': True,
626 # https://gettingthingsdone.com/workflowmap/
627 # vimeo embed with check-password page protected by Referer header
631 def _smuggle_referrer(url
, referrer_url
):
632 return smuggle_url(url
, {'http_headers': {'Referer': referrer_url}
})
635 def _extract_urls(url
, webpage
):
637 # Look for embedded (iframe) Vimeo player
638 for mobj
in re
.finditer(
639 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//player\
.vimeo\
.com
/video
/\d
+.*?
)\
1',
641 urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url
')), url))
643 # Look for embedded (swf embed) Vimeo player
644 r'<embed
[^
>]+?src
=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
645 # Look more for non-standard embedded Vimeo player
646 r'<video[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?vimeo\
.com
/[0-9]+)\
1',
648 for embed_re in PLAIN_EMBED_RE:
649 for mobj in re.finditer(embed_re, webpage):
650 urls.append(mobj.group('url
'))
654 def _extract_url(url, webpage):
655 urls = VimeoIE._extract_urls(url, webpage)
656 return urls[0] if urls else None
658 def _verify_player_video_password(self, url, video_id, headers):
659 password = self._get_video_password()
660 data = urlencode_postdata({
661 'password
': base64.b64encode(password.encode()),
663 headers = merge_dicts(headers, {
664 'Content
-Type
': 'application
/x
-www
-form
-urlencoded
',
666 checked = self._download_json(
667 url + '/check
-password
', video_id,
668 'Verifying the password
', data=data, headers=headers)
670 raise ExtractorError('Wrong video password
', expected=True)
673 def _real_initialize(self):
676 def _extract_from_api(self, video_id, unlisted_hash=None):
677 token = self._download_json(
678 'https
://vimeo
.com
/_rv
/jwt
', video_id, headers={
679 'X
-Requested
-With
': 'XMLHttpRequest
'
681 api_url = 'https
://api
.vimeo
.com
/videos
/' + video_id
683 api_url += ':' + unlisted_hash
684 video = self._download_json(
685 api_url, video_id, headers={
686 'Authorization
': 'jwt
' + token,
688 'fields
': 'config_url
,created_time
,description
,license
,metadata
.connections
.comments
.total
,metadata
.connections
.likes
.total
,release_time
,stats
.plays
',
690 info = self._parse_config(self._download_json(
691 video['config_url
'], video_id), video_id)
692 self._vimeo_sort_formats(info['formats
'])
693 get_timestamp = lambda x: parse_iso8601(video.get(x + '_time
'))
695 'description
': video.get('description
'),
696 'license
': video.get('license
'),
697 'release_timestamp
': get_timestamp('release
'),
698 'timestamp
': get_timestamp('created
'),
699 'view_count
': int_or_none(try_get(video, lambda x: x['stats
']['plays
'])),
701 connections = try_get(
702 video, lambda x: x['metadata
']['connections
'], dict) or {}
703 for k in ('comment
', 'like
'):
704 info[k + '_count
'] = int_or_none(try_get(connections, lambda x: x[k + 's
']['total
']))
707 def _try_album_password(self, url):
708 album_id = self._search_regex(
709 r'vimeo\
.com
/(?
:album|showcase
)/([^
/]+)', url, 'album
id', default=None)
712 viewer = self._download_json(
713 'https
://vimeo
.com
/_rv
/viewer
', album_id, fatal=False)
715 webpage = self._download_webpage(url, album_id)
716 viewer = self._parse_json(self._search_regex(
717 r'bootstrap_data\s
*=\s
*({.+?}
)</script
>',
718 webpage, 'bootstrap data
'), album_id)['viewer
']
720 album = self._download_json(
721 'https
://api
.vimeo
.com
/albums
/' + album_id,
722 album_id, headers={'Authorization': 'jwt ' + jwt},
723 query={'fields': 'description,name,privacy'})
724 if try_get(album, lambda x: x['privacy
']['view
']) == 'password
':
725 password = self.get_param('videopassword
')
727 raise ExtractorError(
728 'This album
is protected by a password
, use the
--video
-password option
',
730 self._set_vimeo_cookie('vuid
', viewer['vuid
'])
733 'https
://vimeo
.com
/showcase
/%s/auth
' % album_id,
734 album_id, 'Verifying the password
', data=urlencode_postdata({
735 'password
': password,
736 'token
': viewer['xsrft
'],
738 'X
-Requested
-With
': 'XMLHttpRequest
',
740 except ExtractorError as e:
741 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
742 raise ExtractorError('Wrong password
', expected=True)
745 def _real_extract(self, url):
746 url, data = unsmuggle_url(url, {})
747 headers = std_headers.copy()
748 if 'http_headers
' in data:
749 headers.update(data['http_headers
'])
750 if 'Referer
' not in headers:
751 headers['Referer
'] = url
753 # Extract ID from URL
754 mobj = self._match_valid_url(url).groupdict()
755 video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash
')
757 return self._extract_from_api(video_id, unlisted_hash)
760 is_pro = 'vimeopro
.com
/' in url
762 # some videos require portfolio_id to be present in player url
763 # https://github.com/ytdl-org/youtube-dl/issues/20070
764 url = self._extract_url(url, self._download_webpage(url, video_id))
766 url = 'https
://vimeo
.com
/' + video_id
767 elif any(p in url for p in ('play_redirect_hls
', 'moogaloop
.swf
')):
768 url = 'https
://vimeo
.com
/' + video_id
770 self._try_album_password(url)
772 # Retrieve video webpage to extract further information
773 webpage, urlh = self._download_webpage_handle(
774 url, video_id, headers=headers)
775 redirect_url = urlh.geturl()
776 except ExtractorError as ee:
777 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
778 errmsg = ee.cause.read()
779 if b'Because of its privacy settings
, this video cannot be played here
' in errmsg:
780 raise ExtractorError(
781 'Cannot download embed
-only video without embedding
'
782 'URL
. Please call yt
-dlp
with the URL of the page
'
783 'that embeds this video
.',
787 if '://player
.vimeo
.com
/video
/' in url:
788 config = self._parse_json(self._search_regex(
789 r'\bconfig\s
*=\s
*({.+?}
)\s
*;', webpage, 'info section
'), video_id)
790 if config.get('view
') == 4:
791 config = self._verify_player_video_password(
792 redirect_url, video_id, headers)
793 info = self._parse_config(config, video_id)
794 self._vimeo_sort_formats(info['formats
'])
797 if re.search(r'<form
[^
>]+?
id="pw_form"', webpage):
798 video_password = self._get_video_password()
799 token, vuid = self._extract_xsrft_and_vuid(webpage)
800 webpage = self._verify_video_password(
801 redirect_url, video_id, video_password, token, vuid)
803 vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
805 seed_status = vimeo_config.get('seed_status
') or {}
806 if seed_status.get('state
') == 'failed
':
807 raise ExtractorError(
808 '%s said
: %s' % (self.IE_NAME, seed_status['title
']),
813 video_description = None
817 channel_id = self._search_regex(
818 r'vimeo\
.com
/channels
/([^
/]+)', url, 'channel
id', default=None)
820 config_url = self._html_search_regex(
821 r'\bdata
-config
-url
="([^"]+)"', webpage, 'config URL', default=None)
822 video_description = clean_html(get_element_by_class('description', webpage))
824 'channel_id': channel_id,
825 'channel_url': 'https://vimeo.com/channels/' + channel_id,
828 page_config = self._parse_json(self._search_regex(
829 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
830 webpage, 'page config', default='{}'), video_id, fatal=False)
832 return self._extract_from_api(video_id)
833 config_url = page_config['player']['config_url']
834 cc_license = page_config.get('cc_license')
835 clip = page_config.get('clip') or {}
836 timestamp = clip.get('uploaded_on')
837 video_description = clean_html(
838 clip.get('description') or page_config.get('description_html_escaped'))
839 config = self._download_json(config_url, video_id)
840 video = config.get('video') or {}
841 vod = video.get('vod') or {}
844 if '>You rented this title.<' in webpage:
846 if try_get(config, lambda x: x['user']['purchased']):
848 for purchase_option in (vod.get('purchase_options') or []):
849 if purchase_option.get('purchased'):
851 label = purchase_option.get('label_string')
852 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
856 if is_rented() and vod.get('is_trailer'):
857 feature_id = vod.get('feature_id')
858 if feature_id and not data.get('force_feature_id', False):
859 return self.url_result(smuggle_url(
860 'https://player.vimeo.com/player/%s' % feature_id,
861 {'force_feature_id': True}), 'Vimeo')
863 if not video_description:
864 video_description = self._html_search_regex(
865 r'(?s)<div\s+class="[^
"]*description[^"]*"[^>]*>(.*?)</div>',
866 webpage, 'description', default=None)
867 if not video_description:
868 video_description = self._html_search_meta(
869 ['description', 'og:description', 'twitter:description'],
870 webpage, default=None)
871 if not video_description and is_pro:
872 orig_webpage = self._download_webpage(
874 note='Downloading webpage for description',
877 video_description = self._html_search_meta(
878 'description', orig_webpage, default=None)
879 if not video_description:
880 self.report_warning('Cannot find video description')
883 timestamp = self._search_regex(
884 r'<time[^>]+datetime="([^
"]+)"', webpage,
885 'timestamp
', default=None)
887 view_count = int_or_none(self._search_regex(r'UserPlays
:(\d
+)', webpage, 'view count
', default=None))
888 like_count = int_or_none(self._search_regex(r'UserLikes
:(\d
+)', webpage, 'like count
', default=None))
889 comment_count = int_or_none(self._search_regex(r'UserComments
:(\d
+)', webpage, 'comment count
', default=None))
893 source_format = self._extract_original_format(
894 'https
://vimeo
.com
/' + video_id, video_id, video.get('unlisted_hash
'))
896 formats.append(source_format)
898 info_dict_config = self._parse_config(config, video_id)
899 formats.extend(info_dict_config['formats
'])
900 self._vimeo_sort_formats(formats)
902 json_ld = self._search_json_ld(webpage, video_id, default={})
905 cc_license = self._search_regex(
906 r'<link
[^
>]+rel
=["\']license["\'][^
>]+href
=(["\'])(?P<license>(?:(?!\1).)+)\1',
907 webpage, 'license', default=None, group='license')
911 'timestamp': unified_timestamp(timestamp),
912 'description': video_description,
914 'view_count': view_count,
915 'like_count': like_count,
916 'comment_count': comment_count,
917 'license': cc_license,
920 return merge_dicts(info_dict, info_dict_config, json_ld)
923 class VimeoOndemandIE(VimeoIE):
924 IE_NAME = 'vimeo:ondemand'
925 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
927 # ondemand video not available via https://vimeo.com/id
928 'url': 'https://vimeo.com/ondemand/20704',
929 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
933 'title': 'המעבדה - במאי יותם פלדמן',
934 'uploader': 'גם סרטים',
935 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
936 'uploader_id': 'gumfilms',
937 'description': 'md5:4c027c965e439de4baab621e48b60791',
938 'upload_date': '20140906',
939 'timestamp': 1410032453,
942 'format': 'best[protocol=https]',
944 'expected_warnings': ['Unable to download JSON metadata'],
946 # requires Referer to be passed along with og:video:url
947 'url': 'https://vimeo.com/ondemand/36938/126682985',
951 'title': 'Rävlock, rätt läte på rätt plats',
952 'uploader': 'Lindroth & Norin',
953 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
954 'uploader_id': 'lindrothnorin',
955 'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
956 'upload_date': '20150502',
957 'timestamp': 1430586422,
960 'skip_download': True,
962 'expected_warnings': ['Unable to download JSON metadata'],
964 'url': 'https://vimeo.com/ondemand/nazmaalik',
965 'only_matching': True,
967 'url': 'https://vimeo.com/ondemand/141692381',
968 'only_matching': True,
970 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
971 'only_matching': True,
975 class VimeoChannelIE(VimeoBaseInfoExtractor):
976 IE_NAME = 'vimeo:channel'
977 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
978 _MORE_PAGES_INDICATOR = r'<a.+?rel="next
"'
980 _TITLE_RE = r'<link rel="alternate
"[^>]+?title="(.*?
)"'
982 'url': 'https://vimeo.com/channels/tributes',
985 'title': 'Vimeo Tributes',
987 'playlist_mincount': 25,
989 _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
991 def _page_url(self, base_url, pagenum):
992 return '%s/videos/page:%d/' % (base_url, pagenum)
994 def _extract_list_title(self, webpage):
995 return self._TITLE or self._html_search_regex(
996 self._TITLE_RE, webpage, 'list title', fatal=False)
998 def _title_and_entries(self, list_id, base_url):
999 for pagenum in itertools.count(1):
1000 page_url = self._page_url(base_url, pagenum)
1001 webpage = self._download_webpage(
1003 'Downloading page %s' % pagenum)
1006 yield self._extract_list_title(webpage)
1008 # Try extracting href first since not all videos are available via
1009 # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
1011 r'id="clip_(\d
+)"[^>]*>\s*<a[^>]+href="(/(?
:[^
/]+/)*\
1)(?
:[^
>]+\btitle
="([^"]+)")?', webpage)
1013 for video_id, video_url, video_title in clips:
1014 yield self.url_result(
1015 compat_urlparse.urljoin(base_url, video_url),
1016 VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
1017 # More relaxed fallback
1019 for video_id in re.findall(r'id=["\']clip_(\d
+)', webpage):
1020 yield self.url_result(
1021 'https
://vimeo
.com
/%s' % video_id,
1022 VimeoIE.ie_key(), video_id=video_id)
1024 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1027 def _extract_videos(self, list_id, base_url):
1028 title_and_entries = self._title_and_entries(list_id, base_url)
1029 list_title = next(title_and_entries)
1030 return self.playlist_result(title_and_entries, list_id, list_title)
1032 def _real_extract(self, url):
1033 channel_id = self._match_id(url)
1034 return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
1037 class VimeoUserIE(VimeoChannelIE):
1038 IE_NAME = 'vimeo
:user
'
1039 _VALID_URL = r'https
://vimeo\
.com
/(?
!(?
:[0-9]+|watchlater
)(?
:$|
[?
#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
1040 _TITLE_RE
= r
'<a[^>]+?class="user">([^<>]+?)</a>'
1042 'url': 'https://vimeo.com/nkistudio/videos',
1047 'playlist_mincount': 66,
1049 _BASE_URL_TEMPL
= 'https://vimeo.com/%s'
1052 class VimeoAlbumIE(VimeoBaseInfoExtractor
):
1053 IE_NAME
= 'vimeo:album'
1054 _VALID_URL
= r
'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
1055 _TITLE_RE
= r
'<header id="page_header">\n\s*<h1>(.*?)</h1>'
1057 'url': 'https://vimeo.com/album/2632481',
1060 'title': 'Staff Favorites: November 2013',
1062 'playlist_mincount': 13,
1064 'note': 'Password-protected album',
1065 'url': 'https://vimeo.com/album/3253534',
1070 'playlist_count': 1,
1072 'videopassword': 'youtube-dl',
1077 def _fetch_page(self
, album_id
, authorization
, hashed_pass
, page
):
1080 'fields': 'link,uri',
1082 'per_page': self
._PAGE
_SIZE
,
1085 query
['_hashed_pass'] = hashed_pass
1087 videos
= self
._download
_json
(
1088 'https://api.vimeo.com/albums/%s/videos' % album_id
,
1089 album_id
, 'Downloading page %d' % api_page
, query
=query
, headers
={
1090 'Authorization': 'jwt ' + authorization
,
1092 except ExtractorError
as e
:
1093 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 400:
1095 for video
in videos
:
1096 link
= video
.get('link')
1099 uri
= video
.get('uri')
1100 video_id
= self
._search
_regex
(r
'/videos/(\d+)', uri
, 'video_id', default
=None) if uri
else None
1101 yield self
.url_result(link
, VimeoIE
.ie_key(), video_id
)
1103 def _real_extract(self
, url
):
1104 album_id
= self
._match
_id
(url
)
1105 viewer
= self
._download
_json
(
1106 'https://vimeo.com/_rv/viewer', album_id
, fatal
=False)
1108 webpage
= self
._download
_webpage
(url
, album_id
)
1109 viewer
= self
._parse
_json
(self
._search
_regex
(
1110 r
'bootstrap_data\s*=\s*({.+?})</script>',
1111 webpage
, 'bootstrap data'), album_id
)['viewer']
1113 album
= self
._download
_json
(
1114 'https://api.vimeo.com/albums/' + album_id
,
1115 album_id
, headers
={'Authorization': 'jwt ' + jwt}
,
1116 query
={'fields': 'description,name,privacy'}
)
1118 if try_get(album
, lambda x
: x
['privacy']['view']) == 'password':
1119 password
= self
.get_param('videopassword')
1121 raise ExtractorError(
1122 'This album is protected by a password, use the --video-password option',
1124 self
._set
_vimeo
_cookie
('vuid', viewer
['vuid'])
1126 hashed_pass
= self
._download
_json
(
1127 'https://vimeo.com/showcase/%s/auth' % album_id
,
1128 album_id
, 'Verifying the password', data
=urlencode_postdata({
1129 'password': password
,
1130 'token': viewer
['xsrft'],
1132 'X-Requested-With': 'XMLHttpRequest',
1134 except ExtractorError
as e
:
1135 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 401:
1136 raise ExtractorError('Wrong password', expected
=True)
1138 entries
= OnDemandPagedList(functools
.partial(
1139 self
._fetch
_page
, album_id
, jwt
, hashed_pass
), self
._PAGE
_SIZE
)
1140 return self
.playlist_result(
1141 entries
, album_id
, album
.get('name'), album
.get('description'))
1144 class VimeoGroupsIE(VimeoChannelIE
):
1145 IE_NAME
= 'vimeo:group'
1146 _VALID_URL
= r
'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
1148 'url': 'https://vimeo.com/groups/meetup',
1151 'title': 'Vimeo Meetup!',
1153 'playlist_mincount': 27,
1155 _BASE_URL_TEMPL
= 'https://vimeo.com/groups/%s'
1158 class VimeoReviewIE(VimeoBaseInfoExtractor
):
1159 IE_NAME
= 'vimeo:review'
1160 IE_DESC
= 'Review pages on vimeo'
1161 _VALID_URL
= r
'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1163 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1164 'md5': 'c507a72f780cacc12b2248bb4006d253',
1168 'title': "DICK HARDWICK 'Comedian'",
1169 'uploader': 'Richard Hardwick',
1170 'uploader_id': 'user21297594',
1171 'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1174 'note': 'video player needs Referer',
1175 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1176 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1180 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1181 'uploader': 'DevWeek Events',
1183 'thumbnail': r
're:^https?://.*\.jpg$',
1184 'uploader_id': 'user22258446',
1186 'skip': 'video gone',
1188 'note': 'Password protected',
1189 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1193 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1195 'uploader_id': 'user37284429',
1198 'videopassword': 'holygrail',
1200 'skip': 'video gone',
1203 def _real_initialize(self
):
1206 def _real_extract(self
, url
):
1207 page_url
, video_id
= self
._match
_valid
_url
(url
).groups()
1208 data
= self
._download
_json
(
1209 page_url
.replace('/review/', '/review/data/'), video_id
)
1210 if data
.get('isLocked') is True:
1211 video_password
= self
._get
_video
_password
()
1212 viewer
= self
._download
_json
(
1213 'https://vimeo.com/_rv/viewer', video_id
)
1214 webpage
= self
._verify
_video
_password
(
1215 'https://vimeo.com/' + video_id
, video_id
,
1216 video_password
, viewer
['xsrft'], viewer
['vuid'])
1217 clip_page_config
= self
._parse
_json
(self
._search
_regex
(
1218 r
'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
1219 webpage
, 'clip page config'), video_id
)
1220 config_url
= clip_page_config
['player']['config_url']
1221 clip_data
= clip_page_config
.get('clip') or {}
1223 clip_data
= data
['clipData']
1224 config_url
= clip_data
['configUrl']
1225 config
= self
._download
_json
(config_url
, video_id
)
1226 info_dict
= self
._parse
_config
(config
, video_id
)
1227 source_format
= self
._extract
_original
_format
(
1228 page_url
+ '/action', video_id
)
1230 info_dict
['formats'].append(source_format
)
1231 self
._vimeo
_sort
_formats
(info_dict
['formats'])
1232 info_dict
['description'] = clean_html(clip_data
.get('description'))
1236 class VimeoWatchLaterIE(VimeoChannelIE
):
1237 IE_NAME
= 'vimeo:watchlater'
1238 IE_DESC
= 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
1239 _VALID_URL
= r
'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1240 _TITLE
= 'Watch Later'
1241 _LOGIN_REQUIRED
= True
1243 'url': 'https://vimeo.com/watchlater',
1244 'only_matching': True,
1247 def _real_initialize(self
):
1250 def _page_url(self
, base_url
, pagenum
):
1251 url
= '%s/page:%d/' % (base_url
, pagenum
)
1252 request
= sanitized_Request(url
)
1253 # Set the header to get a partial html page with the ids,
1254 # the normal page doesn't contain them.
1255 request
.add_header('X-Requested-With', 'XMLHttpRequest')
1258 def _real_extract(self
, url
):
1259 return self
._extract
_videos
('watchlater', 'https://vimeo.com/watchlater')
1262 class VimeoLikesIE(VimeoChannelIE
):
1263 _VALID_URL
= r
'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1264 IE_NAME
= 'vimeo:likes'
1265 IE_DESC
= 'Vimeo user likes'
1267 'url': 'https://vimeo.com/user755559/likes/',
1268 'playlist_mincount': 293,
1271 'title': 'urza’s Likes',
1274 'url': 'https://vimeo.com/stormlapse/likes',
1275 'only_matching': True,
1278 def _page_url(self
, base_url
, pagenum
):
1279 return '%s/page:%d/' % (base_url
, pagenum
)
1281 def _real_extract(self
, url
):
1282 user_id
= self
._match
_id
(url
)
1283 return self
._extract
_videos
(user_id
, 'https://vimeo.com/%s/likes' % user_id
)
1286 class VHXEmbedIE(VimeoBaseInfoExtractor
):
1287 IE_NAME
= 'vhx:embed'
1288 _VALID_URL
= r
'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1291 def _extract_url(webpage
):
1293 r
'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage
)
1294 return unescapeHTML(mobj
.group(1)) if mobj
else None
1296 def _real_extract(self
, url
):
1297 video_id
= self
._match
_id
(url
)
1298 webpage
= self
._download
_webpage
(url
, video_id
)
1299 config_url
= self
._parse
_json
(self
._search
_regex
(
1300 r
'window\.OTTData\s*=\s*({.+})', webpage
,
1301 'ott data'), video_id
, js_to_json
)['config_url']
1302 config
= self
._download
_json
(config_url
, video_id
)
1303 info
= self
._parse
_config
(config
, video_id
)
1304 info
['id'] = video_id
1305 self
._vimeo
_sort
_formats
(info
['formats'])