]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vimeo.py
2 from __future__
import unicode_literals
9 from .common
import InfoExtractor
10 from ..compat
import (
36 class VimeoBaseInfoExtractor(InfoExtractor
):
37 _NETRC_MACHINE
= 'vimeo'
38 _LOGIN_REQUIRED
= False
39 _LOGIN_URL
= 'https://vimeo.com/log_in'
42 username
, password
= self
._get
_login
_info
()
44 if self
._LOGIN
_REQUIRED
:
45 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
47 webpage
= self
._download
_webpage
(
48 self
._LOGIN
_URL
, None, 'Downloading login page')
49 token
, vuid
= self
._extract
_xsrft
_and
_vuid
(webpage
)
57 self
._set
_vimeo
_cookie
('vuid', vuid
)
59 self
._download
_webpage
(
60 self
._LOGIN
_URL
, None, 'Logging in',
61 data
=urlencode_postdata(data
), headers
={
62 'Content-Type': 'application/x-www-form-urlencoded',
63 'Referer': self
._LOGIN
_URL
,
65 except ExtractorError
as e
:
66 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 418:
68 'Unable to log in: bad username or password',
70 raise ExtractorError('Unable to log in')
72 def _verify_video_password(self
, url
, video_id
, webpage
):
73 password
= self
._downloader
.params
.get('videopassword')
75 raise ExtractorError('This video is protected by a password, use the --video-password option', expected
=True)
76 token
, vuid
= self
._extract
_xsrft
_and
_vuid
(webpage
)
77 data
= urlencode_postdata({
81 if url
.startswith('http://'):
82 # vimeo only supports https now, but the user can give an http url
83 url
= url
.replace('http://', 'https://')
84 password_request
= sanitized_Request(url
+ '/password', data
)
85 password_request
.add_header('Content-Type', 'application/x-www-form-urlencoded')
86 password_request
.add_header('Referer', url
)
87 self
._set
_vimeo
_cookie
('vuid', vuid
)
88 return self
._download
_webpage
(
89 password_request
, video_id
,
90 'Verifying the password', 'Wrong password')
92 def _extract_xsrft_and_vuid(self
, webpage
):
93 xsrft
= self
._search
_regex
(
94 r
'(?:(?P<q1>["\'])xsrft(?P
=q1
)\s
*:|xsrft\s
*[=:])\s
*(?P
<q
>["\'])(?P<xsrft>.+?)(?P=q)',
95 webpage, 'login token', group='xsrft')
96 vuid = self._search_regex(
97 r'["\']vuid
["\']\s*:\s*(["\'])(?P
<vuid
>.+?
)\
1',
98 webpage, 'vuid
', group='vuid
')
101 def _set_vimeo_cookie(self, name, value):
102 self._set_cookie('vimeo
.com
', name, value)
104 def _vimeo_sort_formats(self, formats):
105 # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
106 # at the same time without actual units specified. This lead to wrong sorting.
107 self._sort_formats(formats, field_preference=('preference
', 'height
', 'width
', 'fps
', 'tbr
', 'format_id
'))
109 def _parse_config(self, config, video_id):
110 video_data = config['video
']
111 video_title = video_data['title
']
112 live_event = video_data.get('live_event
') or {}
113 is_live = live_event.get('status
') == 'started
'
116 config_files = video_data.get('files
') or config['request
'].get('files
', {})
117 for f in config_files.get('progressive
', []):
118 video_url = f.get('url
')
123 'format_id
': 'http
-%s' % f.get('quality
'),
124 'width
': int_or_none(f.get('width
')),
125 'height
': int_or_none(f.get('height
')),
126 'fps
': int_or_none(f.get('fps
')),
127 'tbr
': int_or_none(f.get('bitrate
')),
130 # TODO: fix handling of 308 status code returned for live archive manifest requests
131 for files_type in ('hls
', 'dash
'):
132 for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns
', {}).items():
133 manifest_url = cdn_data.get('url
')
136 format_id = '%s-%s' % (files_type, cdn_name)
137 if files_type == 'hls
':
138 formats.extend(self._extract_m3u8_formats(
139 manifest_url, video_id, 'mp4
',
140 'm3u8
' if is_live else 'm3u8_native
', m3u8_id=format_id,
141 note='Downloading
%s m3u8 information
' % cdn_name,
143 elif files_type == 'dash
':
144 mpd_pattern = r'/%s/(?
:sep
/)?video
/' % video_id
145 mpd_manifest_urls = []
146 if re.search(mpd_pattern, manifest_url):
147 for suffix, repl in (('', 'video
'), ('_sep
', 'sep
/video
')):
148 mpd_manifest_urls.append((format_id + suffix, re.sub(
149 mpd_pattern, '/%s/%s/' % (video_id, repl), manifest_url)))
151 mpd_manifest_urls = [(format_id, manifest_url)]
152 for f_id, m_url in mpd_manifest_urls:
153 if 'json
=1' in m_url:
154 real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url
')
157 mpd_formats = self._extract_mpd_formats(
158 m_url.replace('/master
.json
', '/master
.mpd
'), video_id, f_id,
159 'Downloading
%s MPD information
' % cdn_name,
161 for f in mpd_formats:
162 if f.get('vcodec
') == 'none
':
163 f['preference
'] = -50
164 elif f.get('acodec
') == 'none
':
165 f['preference
'] = -40
166 formats.extend(mpd_formats)
168 live_archive = live_event.get('archive
') or {}
169 live_archive_source_url = live_archive.get('source_url
')
170 if live_archive_source_url and live_archive.get('status
') == 'done
':
172 'format_id
': 'live
-archive
-source
',
173 'url
': live_archive_source_url,
178 text_tracks = config['request
'].get('text_tracks
')
180 for tt in text_tracks:
181 subtitles[tt['lang
']] = [{
183 'url
': 'https
://vimeo
.com
' + tt['url
'],
188 for key, thumb in video_data.get('thumbs
', {}).items():
191 'width
': int_or_none(key),
194 thumbnail = video_data.get('thumbnail
')
200 owner = video_data.get('owner
') or {}
201 video_uploader_url = owner.get('url
')
204 'title
': self._live_title(video_title) if is_live else video_title,
205 'uploader
': owner.get('name
'),
206 'uploader_id
': video_uploader_url.split('/')[-1] if video_uploader_url else None,
207 'uploader_url
': video_uploader_url,
208 'thumbnails
': thumbnails,
209 'duration
': int_or_none(video_data.get('duration
')),
211 'subtitles
': subtitles,
215 def _extract_original_format(self, url, video_id):
216 download_data = self._download_json(
217 url, video_id, fatal=False,
218 query={'action
': 'load_download_config
'},
219 headers={'X
-Requested
-With
': 'XMLHttpRequest
'})
221 source_file = download_data.get('source_file
')
222 if isinstance(source_file, dict):
223 download_url = source_file.get('download_url
')
224 if download_url and not source_file.get('is_cold
') and not source_file.get('is_defrosting
'):
225 source_name = source_file.get('public_name
', 'Original
')
226 if self._is_valid_url(download_url, video_id, '%s video
' % source_name):
228 source_file, lambda x: x['extension
'],
229 compat_str) or determine_ext(
230 download_url, None) or 'mp4
').lower()
234 'width
': int_or_none(source_file.get('width
')),
235 'height
': int_or_none(source_file.get('height
')),
236 'filesize
': parse_filesize(source_file.get('size
')),
237 'format_id
': source_name,
242 class VimeoIE(VimeoBaseInfoExtractor):
243 """Information extractor for vimeo.com."""
245 # _VALID_URL matches Vimeo URLs
246 _VALID_URL = r'''(?x)
255 vimeo(?P<pro>pro)?\.com/
256 (?!(?:channels|album)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
261 moogaloop\.swf)\?clip_id=
266 /?(?:[?&].*)?(?:[#].*)?$
271 'url
': 'http
://vimeo
.com
/56015672#at=0',
272 'md5': '8879b6cc097e987f02484baf890129e5',
276 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
277 'description': 'md5:509a9ad5c9bf97c60faee9203aca4479',
278 'timestamp': 1355990239,
279 'upload_date': '20121220',
280 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/user7108434',
281 'uploader_id': 'user7108434',
282 'uploader': 'Filippo Valsorda',
288 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
289 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
290 'note': 'Vimeo Pro video (#1197)',
294 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
295 'uploader_id': 'openstreetmapus',
296 'uploader': 'OpenStreetMap US',
297 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
298 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
303 'url': 'http://player.vimeo.com/video/54469442',
304 'md5': '619b811a4417aa4abe78dc653becf511',
305 'note': 'Videos that embed the url in the player page',
309 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
310 'uploader': 'The BLN & Business of Software',
311 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
312 'uploader_id': 'theblnbusinessofsoftware',
318 'url': 'http://vimeo.com/68375962',
319 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
320 'note': 'Video protected with password',
324 'title': 'youtube-dl password protected test video',
325 'timestamp': 1371200155,
326 'upload_date': '20130614',
327 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/user18948128',
328 'uploader_id': 'user18948128',
329 'uploader': 'Jaime Marquínez Ferrándiz',
331 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
334 'videopassword': 'youtube-dl',
338 'url': 'http://vimeo.com/channels/keypeele/75629013',
339 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
343 'title': 'Key & Peele: Terrorist Interrogation',
344 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
345 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/atencio',
346 'uploader_id': 'atencio',
347 'uploader': 'Peter Atencio',
348 'channel_id': 'keypeele',
349 'channel_url': r
're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
350 'timestamp': 1380339469,
351 'upload_date': '20130928',
354 'expected_warnings': ['Unable to download JSON metadata'],
357 'url': 'http://vimeo.com/76979871',
358 'note': 'Video with subtitles',
362 'title': 'The New Vimeo Player (You Know, For Videos)',
363 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
364 'timestamp': 1381846109,
365 'upload_date': '20131015',
366 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/staff',
367 'uploader_id': 'staff',
368 'uploader': 'Vimeo Staff',
373 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
374 'url': 'https://player.vimeo.com/video/98044508',
375 'note': 'The js code contains assignments to the same variable as the config',
379 'title': 'Pier Solar OUYA Official Trailer',
380 'uploader': 'Tulio Gonçalves',
381 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/user28849593',
382 'uploader_id': 'user28849593',
386 # contains original format
387 'url': 'https://vimeo.com/33951933',
388 'md5': '53c688fa95a55bf4b7293d37a89c5c53',
392 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
393 'uploader': 'The DMCI',
394 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/dmci',
395 'uploader_id': 'dmci',
396 'timestamp': 1324343742,
397 'upload_date': '20111220',
398 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
402 # only available via https://vimeo.com/channels/tributes/6213729 and
403 # not via https://vimeo.com/6213729
404 'url': 'https://vimeo.com/channels/tributes/6213729',
408 'title': 'Vimeo Tribute: The Shining',
409 'uploader': 'Casey Donahue',
410 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/caseydonahue',
411 'uploader_id': 'caseydonahue',
412 'channel_url': r
're:https?://(?:www\.)?vimeo\.com/channels/tributes',
413 'channel_id': 'tributes',
414 'timestamp': 1250886430,
415 'upload_date': '20090821',
416 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
419 'skip_download': True,
421 'expected_warnings': ['Unable to download JSON metadata'],
424 # redirects to ondemand extractor and should be passed through it
425 # for successful extraction
426 'url': 'https://vimeo.com/73445910',
430 'title': 'The Reluctant Revolutionary',
431 'uploader': '10Ft Films',
432 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
433 'uploader_id': 'tenfootfilms',
436 'skip_download': True,
440 'url': 'http://player.vimeo.com/video/68375962',
441 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
445 'title': 'youtube-dl password protected test video',
446 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/user18948128',
447 'uploader_id': 'user18948128',
448 'uploader': 'Jaime Marquínez Ferrándiz',
452 'videopassword': 'youtube-dl',
456 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
457 'only_matching': True,
460 'url': 'https://vimeo.com/109815029',
461 'note': 'Video not completely processed, "failed" seed status',
462 'only_matching': True,
465 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
466 'only_matching': True,
469 'url': 'https://vimeo.com/album/2632481/video/79010983',
470 'only_matching': True,
473 # source file returns 403: Forbidden
474 'url': 'https://vimeo.com/7809605',
475 'only_matching': True,
478 'url': 'https://vimeo.com/160743502/abd0e13fb4',
479 'only_matching': True,
481 # https://gettingthingsdone.com/workflowmap/
482 # vimeo embed with check-password page protected by Referer header
486 def _smuggle_referrer(url
, referrer_url
):
487 return smuggle_url(url
, {'http_headers': {'Referer': referrer_url
}})
490 def _extract_urls(url
, webpage
):
492 # Look for embedded (iframe) Vimeo player
493 for mobj
in re
.finditer(
494 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//player\
.vimeo\
.com
/video
/\d
+.*?
)\
1',
496 urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url
')), url))
498 # Look for embedded (swf embed) Vimeo player
499 r'<embed
[^
>]+?src
=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
500 # Look more for non-standard embedded Vimeo player
501 r'<video[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?vimeo\
.com
/[0-9]+)\
1',
503 for embed_re in PLAIN_EMBED_RE:
504 for mobj in re.finditer(embed_re, webpage):
505 urls.append(mobj.group('url
'))
509 def _extract_url(url, webpage):
510 urls = VimeoIE._extract_urls(url, webpage)
511 return urls[0] if urls else None
513 def _verify_player_video_password(self, url, video_id, headers):
514 password = self._downloader.params.get('videopassword
')
516 raise ExtractorError('This video
is protected by a password
, use the
--video
-password option
')
517 data = urlencode_postdata({
518 'password
': base64.b64encode(password.encode()),
520 headers = merge_dicts(headers, {
521 'Content
-Type
': 'application
/x
-www
-form
-urlencoded
',
523 checked = self._download_json(
524 url + '/check
-password
', video_id,
525 'Verifying the password
', data=data, headers=headers)
527 raise ExtractorError('Wrong video password
', expected=True)
530 def _real_initialize(self):
533 def _real_extract(self, url):
534 url, data = unsmuggle_url(url, {})
535 headers = std_headers.copy()
536 if 'http_headers
' in data:
537 headers.update(data['http_headers
'])
538 if 'Referer
' not in headers:
539 headers['Referer
'] = url
541 channel_id = self._search_regex(
542 r'vimeo\
.com
/channels
/([^
/]+)', url, 'channel
id', default=None)
544 # Extract ID from URL
545 mobj = re.match(self._VALID_URL, url)
546 video_id = mobj.group('id')
548 if mobj.group('pro
'):
549 # some videos require portfolio_id to be present in player url
550 # https://github.com/ytdl-org/youtube-dl/issues/20070
551 url = self._extract_url(url, self._download_webpage(url, video_id))
552 elif mobj.group('player
'):
553 url = 'https
://player
.vimeo
.com
/video
/' + video_id
554 elif any(p in url for p in ('play_redirect_hls
', 'moogaloop
.swf
')):
555 url = 'https
://vimeo
.com
/' + video_id
557 # Retrieve video webpage to extract further information
558 request = sanitized_Request(url, headers=headers)
560 webpage, urlh = self._download_webpage_handle(request, video_id)
561 redirect_url = compat_str(urlh.geturl())
562 # Some URLs redirect to ondemand can't be extracted
with
563 # this extractor right away thus should be passed through
564 # ondemand extractor (e.g. https://vimeo.com/73445910)
565 if VimeoOndemandIE
.suitable(redirect_url
):
566 return self
.url_result(redirect_url
, VimeoOndemandIE
.ie_key())
567 except ExtractorError
as ee
:
568 if isinstance(ee
.cause
, compat_HTTPError
) and ee
.cause
.code
== 403:
569 errmsg
= ee
.cause
.read()
570 if b
'Because of its privacy settings, this video cannot be played here' in errmsg
:
571 raise ExtractorError(
572 'Cannot download embed-only video without embedding '
573 'URL. Please call youtube-dl with the URL of the page '
574 'that embeds this video.',
578 # Now we begin extracting as much information as we can from what we
579 # retrieved. First we extract the information common to all extractors,
580 # and latter we extract those that are Vimeo specific.
581 self
.report_extraction(video_id
)
583 vimeo_config
= self
._search
_regex
(
584 r
'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage
,
585 'vimeo config', default
=None)
587 seed_status
= self
._parse
_json
(vimeo_config
, video_id
).get('seed_status', {})
588 if seed_status
.get('state') == 'failed':
589 raise ExtractorError(
590 '%s said: %s' % (self
.IE_NAME
, seed_status
['title']),
596 # Extract the config JSON
599 config_url
= self
._html
_search
_regex
(
600 r
' data-config-url="(.+?)"', webpage
,
601 'config URL', default
=None)
603 # Sometimes new react-based page is served instead of old one that require
604 # different config URL extraction approach (see
605 # https://github.com/ytdl-org/youtube-dl/pull/7209)
606 vimeo_clip_page_config
= self
._search
_regex
(
607 r
'vimeo\.clip_page_config\s*=\s*({.+?});', webpage
,
608 'vimeo clip page config')
609 page_config
= self
._parse
_json
(vimeo_clip_page_config
, video_id
)
610 config_url
= page_config
['player']['config_url']
611 cc_license
= page_config
.get('cc_license')
613 page_config
, lambda x
: x
['clip']['uploaded_on'],
615 config_json
= self
._download
_webpage
(config_url
, video_id
)
616 config
= json
.loads(config_json
)
617 except RegexNotFoundError
:
618 # For pro videos or player.vimeo.com urls
619 # We try to find out to which variable is assigned the config dic
620 m_variable_name
= re
.search(r
'(\w)\.video\.id', webpage
)
621 if m_variable_name
is not None:
622 config_re
= [r
'%s=({[^}].+?});' % re
.escape(m_variable_name
.group(1))]
624 config_re
= [r
' = {config:({.+?}),assets:', r
'(?:[abc])=({.+?});']
625 config_re
.append(r
'\bvar\s+r\s*=\s*({.+?})\s*;')
626 config_re
.append(r
'\bconfig\s*=\s*({.+?})\s*;')
627 config
= self
._search
_regex
(config_re
, webpage
, 'info section',
629 config
= json
.loads(config
)
630 except Exception as e
:
631 if re
.search('The creator of this video has not given you permission to embed it on this domain.', webpage
):
632 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
634 if re
.search(r
'<form[^>]+?id="pw_form"', webpage
) is not None:
635 if '_video_password_verified' in data
:
636 raise ExtractorError('video password verification failed!')
637 self
._verify
_video
_password
(redirect_url
, video_id
, webpage
)
638 return self
._real
_extract
(
639 smuggle_url(redirect_url
, {'_video_password_verified': 'verified'}))
641 raise ExtractorError('Unable to extract info section',
644 if config
.get('view') == 4:
645 config
= self
._verify
_player
_video
_password
(redirect_url
, video_id
, headers
)
647 vod
= config
.get('video', {}).get('vod', {})
650 if '>You rented this title.<' in webpage
:
652 if config
.get('user', {}).get('purchased'):
654 for purchase_option
in vod
.get('purchase_options', []):
655 if purchase_option
.get('purchased'):
657 label
= purchase_option
.get('label_string')
658 if label
and (label
.startswith('You rented this') or label
.endswith(' remaining')):
662 if is_rented() and vod
.get('is_trailer'):
663 feature_id
= vod
.get('feature_id')
664 if feature_id
and not data
.get('force_feature_id', False):
665 return self
.url_result(smuggle_url(
666 'https://player.vimeo.com/player/%s' % feature_id
,
667 {'force_feature_id': True}), 'Vimeo')
669 # Extract video description
671 video_description
= self
._html
_search
_regex
(
672 r
'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
673 webpage
, 'description', default
=None)
674 if not video_description
:
675 video_description
= self
._html
_search
_meta
(
676 'description', webpage
, default
=None)
677 if not video_description
and mobj
.group('pro'):
678 orig_webpage
= self
._download
_webpage
(
680 note
='Downloading webpage for description',
683 video_description
= self
._html
_search
_meta
(
684 'description', orig_webpage
, default
=None)
685 if not video_description
and not mobj
.group('player'):
686 self
._downloader
.report_warning('Cannot find video description')
688 # Extract upload date
690 timestamp
= self
._search
_regex
(
691 r
'<time[^>]+datetime="([^"]+)"', webpage
,
692 'timestamp', default
=None)
695 view_count
= int(self
._search
_regex
(r
'UserPlays:(\d+)', webpage
, 'view count'))
696 like_count
= int(self
._search
_regex
(r
'UserLikes:(\d+)', webpage
, 'like count'))
697 comment_count
= int(self
._search
_regex
(r
'UserComments:(\d+)', webpage
, 'comment count'))
698 except RegexNotFoundError
:
699 # This info is only available in vimeo.com/{id} urls
706 source_format
= self
._extract
_original
_format
(
707 'https://vimeo.com/' + video_id
, video_id
)
709 formats
.append(source_format
)
711 info_dict_config
= self
._parse
_config
(config
, video_id
)
712 formats
.extend(info_dict_config
['formats'])
713 self
._vimeo
_sort
_formats
(formats
)
715 json_ld
= self
._search
_json
_ld
(webpage
, video_id
, default
={})
718 cc_license
= self
._search
_regex
(
719 r
'<link[^>]+rel=["\']license
["\'][^>]+href=(["\'])(?P
<license
>(?
:(?
!\
1).)+)\
1',
720 webpage, 'license
', default=None, group='license
')
722 channel_url = 'https
://vimeo
.com
/channels
/%s' % channel_id if channel_id else None
727 'timestamp
': unified_timestamp(timestamp),
728 'description
': video_description,
730 'view_count
': view_count,
731 'like_count
': like_count,
732 'comment_count
': comment_count,
733 'license
': cc_license,
734 'channel_id
': channel_id,
735 'channel_url
': channel_url,
738 info_dict = merge_dicts(info_dict, info_dict_config, json_ld)
743 class VimeoOndemandIE(VimeoBaseInfoExtractor):
744 IE_NAME = 'vimeo
:ondemand
'
745 _VALID_URL = r'https?
://(?
:www\
.)?vimeo\
.com
/ondemand
/(?P
<id>[^
/?
#&]+)'
747 # ondemand video not available via https://vimeo.com/id
748 'url': 'https://vimeo.com/ondemand/20704',
749 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
753 'title': 'המעבדה - במאי יותם פלדמן',
754 'uploader': 'גם סרטים',
755 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/gumfilms',
756 'uploader_id': 'gumfilms',
759 'format': 'best[protocol=https]',
762 # requires Referer to be passed along with og:video:url
763 'url': 'https://vimeo.com/ondemand/36938/126682985',
767 'title': 'Rävlock, rätt läte på rätt plats',
768 'uploader': 'Lindroth & Norin',
769 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/user14430847',
770 'uploader_id': 'user14430847',
773 'skip_download': True,
776 'url': 'https://vimeo.com/ondemand/nazmaalik',
777 'only_matching': True,
779 'url': 'https://vimeo.com/ondemand/141692381',
780 'only_matching': True,
782 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
783 'only_matching': True,
786 def _real_extract(self
, url
):
787 video_id
= self
._match
_id
(url
)
788 webpage
= self
._download
_webpage
(url
, video_id
)
789 return self
.url_result(
790 # Some videos require Referer to be passed along with og:video:url
791 # similarly to generic vimeo embeds (e.g.
792 # https://vimeo.com/ondemand/36938/126682985).
793 VimeoIE
._smuggle
_referrer
(self
._og
_search
_video
_url
(webpage
), url
),
797 class VimeoChannelIE(VimeoBaseInfoExtractor
):
798 IE_NAME
= 'vimeo:channel'
799 _VALID_URL
= r
'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
800 _MORE_PAGES_INDICATOR
= r
'<a.+?rel="next"'
802 _TITLE_RE
= r
'<link rel="alternate"[^>]+?title="(.*?)"'
804 'url': 'https://vimeo.com/channels/tributes',
807 'title': 'Vimeo Tributes',
809 'playlist_mincount': 25,
812 def _page_url(self
, base_url
, pagenum
):
813 return '%s/videos/page:%d/' % (base_url
, pagenum
)
815 def _extract_list_title(self
, webpage
):
816 return self
._TITLE
or self
._html
_search
_regex
(
817 self
._TITLE
_RE
, webpage
, 'list title', fatal
=False)
819 def _login_list_password(self
, page_url
, list_id
, webpage
):
820 login_form
= self
._search
_regex
(
821 r
'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
822 webpage
, 'login form', default
=None)
826 password
= self
._downloader
.params
.get('videopassword')
828 raise ExtractorError('This album is protected by a password, use the --video-password option', expected
=True)
829 fields
= self
._hidden
_inputs
(login_form
)
830 token
, vuid
= self
._extract
_xsrft
_and
_vuid
(webpage
)
831 fields
['token'] = token
832 fields
['password'] = password
833 post
= urlencode_postdata(fields
)
834 password_path
= self
._search
_regex
(
835 r
'action="([^"]+)"', login_form
, 'password URL')
836 password_url
= compat_urlparse
.urljoin(page_url
, password_path
)
837 password_request
= sanitized_Request(password_url
, post
)
838 password_request
.add_header('Content-type', 'application/x-www-form-urlencoded')
839 self
._set
_vimeo
_cookie
('vuid', vuid
)
840 self
._set
_vimeo
_cookie
('xsrft', token
)
842 return self
._download
_webpage
(
843 password_request
, list_id
,
844 'Verifying the password', 'Wrong password')
846 def _title_and_entries(self
, list_id
, base_url
):
847 for pagenum
in itertools
.count(1):
848 page_url
= self
._page
_url
(base_url
, pagenum
)
849 webpage
= self
._download
_webpage
(
851 'Downloading page %s' % pagenum
)
854 webpage
= self
._login
_list
_password
(page_url
, list_id
, webpage
)
855 yield self
._extract
_list
_title
(webpage
)
857 # Try extracting href first since not all videos are available via
858 # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
860 r
'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage
)
862 for video_id
, video_url
, video_title
in clips
:
863 yield self
.url_result(
864 compat_urlparse
.urljoin(base_url
, video_url
),
865 VimeoIE
.ie_key(), video_id
=video_id
, video_title
=video_title
)
866 # More relaxed fallback
868 for video_id
in re
.findall(r
'id=["\']clip_(\d
+)', webpage):
869 yield self.url_result(
870 'https
://vimeo
.com
/%s' % video_id,
871 VimeoIE.ie_key(), video_id=video_id)
873 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
876 def _extract_videos(self, list_id, base_url):
877 title_and_entries = self._title_and_entries(list_id, base_url)
878 list_title = next(title_and_entries)
879 return self.playlist_result(title_and_entries, list_id, list_title)
881 def _real_extract(self, url):
882 mobj = re.match(self._VALID_URL, url)
883 channel_id = mobj.group('id')
884 return self._extract_videos(channel_id, 'https
://vimeo
.com
/channels
/%s' % channel_id)
887 class VimeoUserIE(VimeoChannelIE):
888 IE_NAME = 'vimeo
:user
'
889 _VALID_URL = r'https
://vimeo\
.com
/(?
!(?
:[0-9]+|watchlater
)(?
:$|
[?
#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
890 _TITLE_RE
= r
'<a[^>]+?class="user">([^<>]+?)</a>'
892 'url': 'https://vimeo.com/nkistudio/videos',
897 'playlist_mincount': 66,
900 def _real_extract(self
, url
):
901 mobj
= re
.match(self
._VALID
_URL
, url
)
902 name
= mobj
.group('name')
903 return self
._extract
_videos
(name
, 'https://vimeo.com/%s' % name
)
906 class VimeoAlbumIE(VimeoChannelIE
):
907 IE_NAME
= 'vimeo:album'
908 _VALID_URL
= r
'https://vimeo\.com/album/(?P<id>\d+)(?:$|[?#]|/(?!video))'
909 _TITLE_RE
= r
'<header id="page_header">\n\s*<h1>(.*?)</h1>'
911 'url': 'https://vimeo.com/album/2632481',
914 'title': 'Staff Favorites: November 2013',
916 'playlist_mincount': 13,
918 'note': 'Password-protected album',
919 'url': 'https://vimeo.com/album/3253534',
926 'videopassword': 'youtube-dl',
929 'url': 'https://vimeo.com/album/2632481/sort:plays/format:thumbnail',
930 'only_matching': True,
932 # TODO: respect page number
933 'url': 'https://vimeo.com/album/2632481/page:2/sort:plays/format:thumbnail',
934 'only_matching': True,
937 def _page_url(self
, base_url
, pagenum
):
938 return '%s/page:%d/' % (base_url
, pagenum
)
940 def _real_extract(self
, url
):
941 album_id
= self
._match
_id
(url
)
942 return self
._extract
_videos
(album_id
, 'https://vimeo.com/album/%s' % album_id
)
945 class VimeoGroupsIE(VimeoAlbumIE
):
946 IE_NAME
= 'vimeo:group'
947 _VALID_URL
= r
'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
949 'url': 'https://vimeo.com/groups/rolexawards',
952 'title': 'Rolex Awards for Enterprise',
954 'playlist_mincount': 73,
957 def _extract_list_title(self
, webpage
):
958 return self
._og
_search
_title
(webpage
, fatal
=False)
960 def _real_extract(self
, url
):
961 mobj
= re
.match(self
._VALID
_URL
, url
)
962 name
= mobj
.group('name')
963 return self
._extract
_videos
(name
, 'https://vimeo.com/groups/%s' % name
)
966 class VimeoReviewIE(VimeoBaseInfoExtractor
):
967 IE_NAME
= 'vimeo:review'
968 IE_DESC
= 'Review pages on vimeo'
969 _VALID_URL
= r
'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
971 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
972 'md5': 'c507a72f780cacc12b2248bb4006d253',
976 'title': "DICK HARDWICK 'Comedian'",
977 'uploader': 'Richard Hardwick',
978 'uploader_id': 'user21297594',
981 'note': 'video player needs Referer',
982 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
983 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
987 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
988 'uploader': 'DevWeek Events',
990 'thumbnail': r
're:^https?://.*\.jpg$',
991 'uploader_id': 'user22258446',
994 'note': 'Password protected',
995 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
999 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1001 'uploader_id': 'user37284429',
1004 'videopassword': 'holygrail',
1006 'skip': 'video gone',
1009 def _real_initialize(self
):
1012 def _get_config_url(self
, webpage_url
, video_id
, video_password_verified
=False):
1013 webpage
= self
._download
_webpage
(webpage_url
, video_id
)
1014 config_url
= self
._html
_search
_regex
(
1015 r
'data-config-url=(["\'])(?P
<url
>(?
:(?
!\
1).)+)\
1', webpage,
1016 'config URL
', default=None, group='url
')
1018 data = self._parse_json(self._search_regex(
1019 r'window\s
*=\s
*_extend\
(window
,\s
*({.+?
})\
);', webpage, 'data
',
1020 default=NO_DEFAULT if video_password_verified else '{}'), video_id)
1021 config = data.get('vimeo_esi
', {}).get('config
', {})
1022 config_url = config.get('configUrl
') or try_get(config, lambda x: x['clipData
']['configUrl
'])
1023 if config_url is None:
1024 self._verify_video_password(webpage_url, video_id, webpage)
1025 config_url = self._get_config_url(
1026 webpage_url, video_id, video_password_verified=True)
1029 def _real_extract(self, url):
1030 page_url, video_id = re.match(self._VALID_URL, url).groups()
1031 config_url = self._get_config_url(url, video_id)
1032 config = self._download_json(config_url, video_id)
1033 info_dict = self._parse_config(config, video_id)
1034 source_format = self._extract_original_format(page_url, video_id)
1036 info_dict['formats
'].append(source_format)
1037 self._vimeo_sort_formats(info_dict['formats
'])
1038 info_dict['id'] = video_id
1042 class VimeoWatchLaterIE(VimeoChannelIE):
1043 IE_NAME = 'vimeo
:watchlater
'
1044 IE_DESC = 'Vimeo watch later
list, "vimeowatchlater" keyword (requires authentication
)'
1045 _VALID_URL = r'https
://vimeo\
.com
/(?
:home
/)?watchlater|
:vimeowatchlater
'
1046 _TITLE = 'Watch Later
'
1047 _LOGIN_REQUIRED = True
1049 'url
': 'https
://vimeo
.com
/watchlater
',
1050 'only_matching
': True,
1053 def _real_initialize(self):
1056 def _page_url(self, base_url, pagenum):
1057 url = '%s/page
:%d/' % (base_url, pagenum)
1058 request = sanitized_Request(url)
1059 # Set the header to get a partial html page with the ids,
1060 # the normal page doesn't contain them
.
1061 request
.add_header('X-Requested-With', 'XMLHttpRequest')
1064 def _real_extract(self
, url
):
1065 return self
._extract
_videos
('watchlater', 'https://vimeo.com/watchlater')
1068 class VimeoLikesIE(VimeoChannelIE
):
1069 _VALID_URL
= r
'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1070 IE_NAME
= 'vimeo:likes'
1071 IE_DESC
= 'Vimeo user likes'
1073 'url': 'https://vimeo.com/user755559/likes/',
1074 'playlist_mincount': 293,
1077 'title': 'urza’s Likes',
1080 'url': 'https://vimeo.com/stormlapse/likes',
1081 'only_matching': True,
1084 def _page_url(self
, base_url
, pagenum
):
1085 return '%s/page:%d/' % (base_url
, pagenum
)
1087 def _real_extract(self
, url
):
1088 user_id
= self
._match
_id
(url
)
1089 return self
._extract
_videos
(user_id
, 'https://vimeo.com/%s/likes' % user_id
)
1092 class VHXEmbedIE(InfoExtractor
):
1093 IE_NAME
= 'vhx:embed'
1094 _VALID_URL
= r
'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1096 def _call_api(self
, video_id
, access_token
, path
='', query
=None):
1097 return self
._download
_json
(
1098 'https://api.vhx.tv/videos/' + video_id
+ path
, video_id
, headers
={
1099 'Authorization': 'Bearer ' + access_token
,
1102 def _real_extract(self
, url
):
1103 video_id
= self
._match
_id
(url
)
1104 webpage
= self
._download
_webpage
(url
, video_id
)
1105 credentials
= self
._parse
_json
(self
._search
_regex
(
1106 r
'(?s)credentials\s*:\s*({.+?}),', webpage
,
1107 'config'), video_id
, js_to_json
)
1108 access_token
= credentials
['access_token']
1111 for k
, v
in credentials
.items():
1112 if k
in ('authorization', 'authUserToken', 'ticket') and v
and v
!= 'undefined':
1113 if k
== 'authUserToken':
1114 query
['auth_user_token'] = v
1117 files
= self
._call
_api
(video_id
, access_token
, '/files', query
)
1121 href
= try_get(f
, lambda x
: x
['_links']['source']['href'])
1124 method
= f
.get('method')
1126 formats
.extend(self
._extract
_m
3u8_formats
(
1127 href
, video_id
, 'mp4', 'm3u8_native',
1128 m3u8_id
='hls', fatal
=False))
1129 elif method
== 'dash':
1130 formats
.extend(self
._extract
_mpd
_formats
(
1131 href
, video_id
, mpd_id
='dash', fatal
=False))
1134 'filesize': int_or_none(try_get(f
, lambda x
: x
['size']['bytes'])),
1135 'format_id': 'http',
1138 'vcodec': f
.get('codec'),
1140 quality
= f
.get('quality')
1143 'format_id': 'http-' + quality
,
1144 'height': int_or_none(self
._search
_regex
(r
'(\d+)p', quality
, 'height', default
=None)),
1147 self
._sort
_formats
(formats
)
1149 video_data
= self
._call
_api
(video_id
, access_token
)
1150 title
= video_data
.get('title') or video_data
['name']
1153 for subtitle
in try_get(video_data
, lambda x
: x
['tracks']['subtitles'], list) or []:
1154 lang
= subtitle
.get('srclang') or subtitle
.get('label')
1155 for _link
in subtitle
.get('_links', {}).values():
1156 href
= _link
.get('href')
1159 subtitles
.setdefault(lang
, []).append({
1163 q
= qualities(['small', 'medium', 'large', 'source'])
1165 for thumbnail_id
, thumbnail_url
in video_data
.get('thumbnail', {}).items():
1168 'url': thumbnail_url
,
1169 'preference': q(thumbnail_id
),
1175 'description': video_data
.get('description'),
1176 'duration': int_or_none(try_get(video_data
, lambda x
: x
['duration']['seconds'])),
1178 'subtitles': subtitles
,
1179 'thumbnails': thumbnails
,
1180 'timestamp': unified_timestamp(video_data
.get('created_at')),
1181 'view_count': int_or_none(video_data
.get('plays_count')),