2 from __future__
import unicode_literals
10 from .common
import InfoExtractor
11 from ..compat
import (
41 class VimeoBaseInfoExtractor(InfoExtractor
):
42 _NETRC_MACHINE
= 'vimeo'
43 _LOGIN_REQUIRED
= False
44 _LOGIN_URL
= 'https://vimeo.com/log_in'
47 username
, password
= self
._get
_login
_info
()
49 if self
._LOGIN
_REQUIRED
:
50 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
52 webpage
= self
._download
_webpage
(
53 self
._LOGIN
_URL
, None, 'Downloading login page')
54 token
, vuid
= self
._extract
_xsrft
_and
_vuid
(webpage
)
62 self
._set
_vimeo
_cookie
('vuid', vuid
)
64 self
._download
_webpage
(
65 self
._LOGIN
_URL
, None, 'Logging in',
66 data
=urlencode_postdata(data
), headers
={
67 'Content-Type': 'application/x-www-form-urlencoded',
68 'Referer': self
._LOGIN
_URL
,
70 except ExtractorError
as e
:
71 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 418:
73 'Unable to log in: bad username or password',
75 raise ExtractorError('Unable to log in')
77 def _verify_video_password(self
, url
, video_id
, webpage
):
78 password
= self
._downloader
.params
.get('videopassword')
80 raise ExtractorError('This video is protected by a password, use the --video-password option', expected
=True)
81 token
, vuid
= self
._extract
_xsrft
_and
_vuid
(webpage
)
82 data
= urlencode_postdata({
86 if url
.startswith('http://'):
87 # vimeo only supports https now, but the user can give an http url
88 url
= url
.replace('http://', 'https://')
89 password_request
= sanitized_Request(url
+ '/password', data
)
90 password_request
.add_header('Content-Type', 'application/x-www-form-urlencoded')
91 password_request
.add_header('Referer', url
)
92 self
._set
_vimeo
_cookie
('vuid', vuid
)
93 return self
._download
_webpage
(
94 password_request
, video_id
,
95 'Verifying the password', 'Wrong password')
97 def _extract_xsrft_and_vuid(self
, webpage
):
98 xsrft
= self
._search
_regex
(
99 r
'(?:(?P<q1>["\'])xsrft(?P
=q1
)\s
*:|xsrft\s
*[=:])\s
*(?P
<q
>["\'])(?P<xsrft>.+?)(?P=q)',
100 webpage, 'login token', group='xsrft')
101 vuid = self._search_regex(
102 r'["\']vuid
["\']\s*:\s*(["\'])(?P
<vuid
>.+?
)\
1',
103 webpage, 'vuid
', group='vuid
')
106 def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
107 vimeo_config = self._search_regex(
108 r'vimeo\
.config\s
*=\s
*(?
:({.+?}
)|_extend\
([^
,]+,\s
+({.+?}
)\
));',
109 webpage, 'vimeo config
', *args, **compat_kwargs(kwargs))
111 return self._parse_json(vimeo_config, video_id)
113 def _set_vimeo_cookie(self, name, value):
114 self._set_cookie('vimeo
.com
', name, value)
116 def _vimeo_sort_formats(self, formats):
117 # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
118 # at the same time without actual units specified. This lead to wrong sorting.
119 self._sort_formats(formats, field_preference=('preference
', 'height
', 'width
', 'fps
', 'tbr
', 'format_id
'))
121 def _parse_config(self, config, video_id):
122 video_data = config['video
']
123 video_title = video_data['title
']
124 live_event = video_data.get('live_event
') or {}
125 is_live = live_event.get('status
') == 'started
'
128 config_files = video_data.get('files
') or config['request
'].get('files
', {})
129 for f in config_files.get('progressive
', []):
130 video_url = f.get('url
')
135 'format_id
': 'http
-%s' % f.get('quality
'),
136 'width
': int_or_none(f.get('width
')),
137 'height
': int_or_none(f.get('height
')),
138 'fps
': int_or_none(f.get('fps
')),
139 'tbr
': int_or_none(f.get('bitrate
')),
142 # TODO: fix handling of 308 status code returned for live archive manifest requests
143 sep_pattern = r'/sep
/video
/'
144 for files_type in ('hls
', 'dash
'):
145 for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items():
146 manifest_url = cdn_data.get('url
')
149 format_id = '%s-%s' % (files_type, cdn_name)
150 sep_manifest_urls = []
151 if re.search(sep_pattern, manifest_url):
152 for suffix, repl in (('', 'video
'), ('_sep
', 'sep
/video
')):
153 sep_manifest_urls.append((format_id + suffix, re.sub(
154 sep_pattern, '/%s/' % repl, manifest_url)))
156 sep_manifest_urls = [(format_id, manifest_url)]
157 for f_id, m_url in sep_manifest_urls:
158 if files_type == 'hls
':
159 formats.extend(self._extract_m3u8_formats(
160 m_url, video_id, 'mp4
',
161 'm3u8
' if is_live else 'm3u8_native
', m3u8_id=f_id,
162 note='Downloading
%s m3u8 information
' % cdn_name,
164 elif files_type == 'dash
':
165 if 'json
=1' in m_url:
166 real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url
')
169 mpd_formats = self._extract_mpd_formats(
170 m_url.replace('/master
.json
', '/master
.mpd
'), video_id, f_id,
171 'Downloading
%s MPD information
' % cdn_name,
173 formats.extend(mpd_formats)
175 live_archive = live_event.get('archive
') or {}
176 live_archive_source_url = live_archive.get('source_url
')
177 if live_archive_source_url and live_archive.get('status
') == 'done
':
179 'format_id
': 'live
-archive
-source
',
180 'url
': live_archive_source_url,
184 # Reduntant code! This is already done in common.py
186 # if f.get('vcodec
') == 'none
':
187 # f['preference
'] = -50
188 # elif f.get('acodec
') == 'none
':
189 # f['preference
'] = -40
192 text_tracks = config['request
'].get('text_tracks
')
194 for tt in text_tracks:
195 subtitles[tt['lang
']] = [{
197 'url
': urljoin('https
://vimeo
.com
', tt['url
']),
202 for key, thumb in video_data.get('thumbs
', {}).items():
205 'width
': int_or_none(key),
208 thumbnail = video_data.get('thumbnail
')
214 owner = video_data.get('owner
') or {}
215 video_uploader_url = owner.get('url
')
218 'id': str_or_none(video_data.get('id')) or video_id,
219 'title
': self._live_title(video_title) if is_live else video_title,
220 'uploader
': owner.get('name
'),
221 'uploader_id
': video_uploader_url.split('/')[-1] if video_uploader_url else None,
222 'uploader_url
': video_uploader_url,
223 'thumbnails
': thumbnails,
224 'duration
': int_or_none(video_data.get('duration
')),
226 'subtitles
': subtitles,
230 def _extract_original_format(self, url, video_id):
231 download_data = self._download_json(
232 url, video_id, fatal=False,
233 query={'action': 'load_download_config'},
234 headers={'X-Requested-With': 'XMLHttpRequest'})
236 source_file = download_data.get('source_file
')
237 if isinstance(source_file, dict):
238 download_url = source_file.get('download_url
')
239 if download_url and not source_file.get('is_cold
') and not source_file.get('is_defrosting
'):
240 source_name = source_file.get('public_name
', 'Original
')
241 if self._is_valid_url(download_url, video_id, '%s video
' % source_name):
243 source_file, lambda x: x['extension
'],
244 compat_str) or determine_ext(
245 download_url, None) or 'mp4
').lower()
249 'width
': int_or_none(source_file.get('width
')),
250 'height
': int_or_none(source_file.get('height
')),
251 'filesize
': parse_filesize(source_file.get('size
')),
252 'format_id
': source_name,
257 class VimeoIE(VimeoBaseInfoExtractor):
258 """Information extractor for vimeo.com."""
260 # _VALID_URL matches Vimeo URLs
261 _VALID_URL = r'''(?x)
271 (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
276 moogaloop\.swf)\?clip_id=
281 /?(?:[?&].*)?(?:[#].*)?$
286 'url
': 'http
://vimeo
.com
/56015672#at=0',
287 'md5': '8879b6cc097e987f02484baf890129e5',
291 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
292 'description': 'md5:2d3305bad981a06ff79f027f19865021',
293 'timestamp': 1355990239,
294 'upload_date': '20121220',
295 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/user7108434',
296 'uploader_id': 'user7108434',
297 'uploader': 'Filippo Valsorda',
302 'format': 'best[protocol=https]',
306 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
307 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
308 'note': 'Vimeo Pro video (#1197)',
312 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
313 'uploader_id': 'openstreetmapus',
314 'uploader': 'OpenStreetMap US',
315 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
316 'description': 'md5:2c362968038d4499f4d79f88458590c1',
318 'upload_date': '20130610',
319 'timestamp': 1370893156,
322 'format': 'best[protocol=https]',
326 'url': 'http://player.vimeo.com/video/54469442',
327 'md5': '619b811a4417aa4abe78dc653becf511',
328 'note': 'Videos that embed the url in the player page',
332 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
333 'uploader': 'The BLN & Business of Software',
334 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
335 'uploader_id': 'theblnbusinessofsoftware',
340 'format': 'best[protocol=https]',
342 'expected_warnings': ['Unable to download JSON metadata'],
345 'url': 'http://vimeo.com/68375962',
346 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
347 'note': 'Video protected with password',
351 'title': 'youtube-dl password protected test video',
352 'timestamp': 1371200155,
353 'upload_date': '20130614',
354 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/user18948128',
355 'uploader_id': 'user18948128',
356 'uploader': 'Jaime Marquínez Ferrándiz',
358 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
361 'format': 'best[protocol=https]',
362 'videopassword': 'youtube-dl',
366 'url': 'http://vimeo.com/channels/keypeele/75629013',
367 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
371 'title': 'Key & Peele: Terrorist Interrogation',
372 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
373 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/atencio',
374 'uploader_id': 'atencio',
375 'uploader': 'Peter Atencio',
376 'channel_id': 'keypeele',
377 'channel_url': r
're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
378 'timestamp': 1380339469,
379 'upload_date': '20130928',
382 'expected_warnings': ['Unable to download JSON metadata'],
385 'url': 'http://vimeo.com/76979871',
386 'note': 'Video with subtitles',
390 'title': 'The New Vimeo Player (You Know, For Videos)',
391 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
392 'timestamp': 1381846109,
393 'upload_date': '20131015',
394 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/staff',
395 'uploader_id': 'staff',
396 'uploader': 'Vimeo Staff',
401 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
402 'url': 'https://player.vimeo.com/video/98044508',
403 'note': 'The js code contains assignments to the same variable as the config',
407 'title': 'Pier Solar OUYA Official Trailer',
408 'uploader': 'Tulio Gonçalves',
409 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/user28849593',
410 'uploader_id': 'user28849593',
414 # contains original format
415 'url': 'https://vimeo.com/33951933',
416 'md5': '53c688fa95a55bf4b7293d37a89c5c53',
420 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
421 'uploader': 'The DMCI',
422 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/dmci',
423 'uploader_id': 'dmci',
424 'timestamp': 1324343742,
425 'upload_date': '20111220',
426 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
430 # only available via https://vimeo.com/channels/tributes/6213729 and
431 # not via https://vimeo.com/6213729
432 'url': 'https://vimeo.com/channels/tributes/6213729',
436 'title': 'Vimeo Tribute: The Shining',
437 'uploader': 'Casey Donahue',
438 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/caseydonahue',
439 'uploader_id': 'caseydonahue',
440 'channel_url': r
're:https?://(?:www\.)?vimeo\.com/channels/tributes',
441 'channel_id': 'tributes',
442 'timestamp': 1250886430,
443 'upload_date': '20090821',
444 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
447 'skip_download': True,
449 'expected_warnings': ['Unable to download JSON metadata'],
452 # redirects to ondemand extractor and should be passed through it
453 # for successful extraction
454 'url': 'https://vimeo.com/73445910',
458 'title': 'The Reluctant Revolutionary',
459 'uploader': '10Ft Films',
460 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
461 'uploader_id': 'tenfootfilms',
462 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
463 'upload_date': '20130830',
464 'timestamp': 1377853339,
467 'skip_download': True,
469 'expected_warnings': ['Unable to download JSON metadata'],
472 'url': 'http://player.vimeo.com/video/68375962',
473 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
477 'title': 'youtube-dl password protected test video',
478 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/user18948128',
479 'uploader_id': 'user18948128',
480 'uploader': 'Jaime Marquínez Ferrándiz',
484 'format': 'best[protocol=https]',
485 'videopassword': 'youtube-dl',
489 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
490 'only_matching': True,
493 'url': 'https://vimeo.com/109815029',
494 'note': 'Video not completely processed, "failed" seed status',
495 'only_matching': True,
498 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
499 'only_matching': True,
502 'url': 'https://vimeo.com/album/2632481/video/79010983',
503 'only_matching': True,
506 # source file returns 403: Forbidden
507 'url': 'https://vimeo.com/7809605',
508 'only_matching': True,
511 'url': 'https://vimeo.com/160743502/abd0e13fb4',
512 'only_matching': True,
514 # https://gettingthingsdone.com/workflowmap/
515 # vimeo embed with check-password page protected by Referer header
519 def _smuggle_referrer(url
, referrer_url
):
520 return smuggle_url(url
, {'http_headers': {'Referer': referrer_url}
})
523 def _extract_urls(url
, webpage
):
525 # Look for embedded (iframe) Vimeo player
526 for mobj
in re
.finditer(
527 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//player\
.vimeo\
.com
/video
/\d
+.*?
)\
1',
529 urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url
')), url))
531 # Look for embedded (swf embed) Vimeo player
532 r'<embed
[^
>]+?src
=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
533 # Look more for non-standard embedded Vimeo player
534 r'<video[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?vimeo\
.com
/[0-9]+)\
1',
536 for embed_re in PLAIN_EMBED_RE:
537 for mobj in re.finditer(embed_re, webpage):
538 urls.append(mobj.group('url
'))
542 def _extract_url(url, webpage):
543 urls = VimeoIE._extract_urls(url, webpage)
544 return urls[0] if urls else None
546 def _verify_player_video_password(self, url, video_id, headers):
547 password = self._downloader.params.get('videopassword
')
549 raise ExtractorError('This video
is protected by a password
, use the
--video
-password option
', expected=True)
550 data = urlencode_postdata({
551 'password
': base64.b64encode(password.encode()),
553 headers = merge_dicts(headers, {
554 'Content
-Type
': 'application
/x
-www
-form
-urlencoded
',
556 checked = self._download_json(
557 url + '/check
-password
', video_id,
558 'Verifying the password
', data=data, headers=headers)
560 raise ExtractorError('Wrong video password
', expected=True)
563 def _real_initialize(self):
566 def _real_extract(self, url):
567 url, data = unsmuggle_url(url, {})
568 headers = std_headers.copy()
569 if 'http_headers
' in data:
570 headers.update(data['http_headers
'])
571 if 'Referer
' not in headers:
572 headers['Referer
'] = url
574 channel_id = self._search_regex(
575 r'vimeo\
.com
/channels
/([^
/]+)', url, 'channel
id', default=None)
577 # Extract ID from URL
578 video_id = self._match_id(url)
580 is_pro = 'vimeopro
.com
/' in url
581 is_player = '://player
.vimeo
.com
/video
/' in url
583 # some videos require portfolio_id to be present in player url
584 # https://github.com/ytdl-org/youtube-dl/issues/20070
585 url = self._extract_url(url, self._download_webpage(url, video_id))
587 url = 'https
://vimeo
.com
/' + video_id
589 url = 'https
://player
.vimeo
.com
/video
/' + video_id
590 elif any(p in url for p in ('play_redirect_hls
', 'moogaloop
.swf
')):
591 url = 'https
://vimeo
.com
/' + video_id
594 # Retrieve video webpage to extract further information
595 webpage, urlh = self._download_webpage_handle(
596 url, video_id, headers=headers)
597 redirect_url = urlh.geturl()
598 except ExtractorError as ee:
599 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
600 errmsg = ee.cause.read()
601 if b'Because of its privacy settings
, this video cannot be played here
' in errmsg:
602 raise ExtractorError(
603 'Cannot download embed
-only video without embedding
'
604 'URL
. Please call youtube
-dlc
with the URL of the page
'
605 'that embeds this video
.',
609 # Now we begin extracting as much information as we can from what we
610 # retrieved. First we extract the information common to all extractors,
611 # and latter we extract those that are Vimeo specific.
612 self.report_extraction(video_id)
614 vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
616 seed_status = vimeo_config.get('seed_status
', {})
617 if seed_status.get('state
') == 'failed
':
618 raise ExtractorError(
619 '%s said
: %s' % (self.IE_NAME, seed_status['title
']),
624 video_description = None
626 # Extract the config JSON
629 config_url = self._html_search_regex(
630 r' data
-config
-url
="(.+?)"', webpage,
631 'config URL
', default=None)
633 # Sometimes new react-based page is served instead of old one that require
634 # different config URL extraction approach (see
635 # https://github.com/ytdl-org/youtube-dl/pull/7209)
636 page_config = self._parse_json(self._search_regex(
637 r'vimeo\
.(?
:clip|vod_title
)_page_config\s
*=\s
*({.+?}
);',
638 webpage, 'page config
'), video_id)
639 config_url = page_config['player
']['config_url
']
640 cc_license = page_config.get('cc_license
')
642 page_config, lambda x: x['clip
']['uploaded_on
'],
644 video_description = clean_html(dict_get(
645 page_config, ('description
', 'description_html_escaped
')))
646 config = self._download_json(config_url, video_id)
647 except RegexNotFoundError:
648 # For pro videos or player.vimeo.com urls
649 # We try to find out to which variable is assigned the config dic
650 m_variable_name = re.search(r'(\w
)\
.video\
.id', webpage)
651 if m_variable_name is not None:
652 config_re = [r'%s=({[^}
].+?
});' % re.escape(m_variable_name.group(1))]
654 config_re = [r' = {config:({.+?}
),assets
:', r'(?
:[abc
])=({.+?}
);']
655 config_re.append(r'\bvar\s
+r\s
*=\s
*({.+?}
)\s
*;')
656 config_re.append(r'\bconfig\s
*=\s
*({.+?}
)\s
*;')
657 config = self._search_regex(config_re, webpage, 'info section
',
659 config = json.loads(config)
660 except Exception as e:
661 if re.search('The creator of this video has
not given you permission to embed it on this domain
.', webpage):
662 raise ExtractorError('The author has restricted the access to this video
, try with the
"--referer" option
')
664 if re.search(r'<form
[^
>]+?
id="pw_form"', webpage) is not None:
665 if '_video_password_verified
' in data:
666 raise ExtractorError('video password verification failed
!')
667 self._verify_video_password(redirect_url, video_id, webpage)
668 return self._real_extract(
669 smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
671 raise ExtractorError('Unable to extract info section
',
674 if config.get('view
') == 4:
675 config = self._verify_player_video_password(redirect_url, video_id, headers)
677 vod = config.get('video
', {}).get('vod', {})
680 if '>You rented this title
.<' in webpage:
682 if config.get('user
', {}).get('purchased
'):
684 for purchase_option in vod.get('purchase_options
', []):
685 if purchase_option.get('purchased
'):
687 label = purchase_option.get('label_string
')
688 if label and (label.startswith('You rented this
') or label.endswith(' remaining
')):
692 if is_rented() and vod.get('is_trailer
'):
693 feature_id = vod.get('feature_id
')
694 if feature_id and not data.get('force_feature_id
', False):
695 return self.url_result(smuggle_url(
696 'https
://player
.vimeo
.com
/player
/%s' % feature_id,
697 {'force_feature_id': True}), 'Vimeo
')
699 # Extract video description
700 if not video_description:
701 video_description = self._html_search_regex(
702 r'(?s
)<div\s
+class="[^"]*description
[^
"]*"[^
>]*>(.*?
)</div
>',
703 webpage, 'description
', default=None)
704 if not video_description:
705 video_description = self._html_search_meta(
706 'description
', webpage, default=None)
707 if not video_description and is_pro:
708 orig_webpage = self._download_webpage(
710 note='Downloading webpage
for description
',
713 video_description = self._html_search_meta(
714 'description
', orig_webpage, default=None)
715 if not video_description and not is_player:
716 self._downloader.report_warning('Cannot find video description
')
718 # Extract upload date
720 timestamp = self._search_regex(
721 r'<time
[^
>]+datetime
="([^"]+)"', webpage,
722 'timestamp', default=None)
725 view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
726 like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
727 comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
728 except RegexNotFoundError:
729 # This info is only available in vimeo.com/{id} urls
736 source_format = self._extract_original_format(
737 'https://vimeo.com/' + video_id, video_id)
739 formats.append(source_format)
741 info_dict_config = self._parse_config(config, video_id)
742 formats.extend(info_dict_config['formats'])
743 self._vimeo_sort_formats(formats)
745 json_ld = self._search_json_ld(webpage, video_id, default={})
748 cc_license = self._search_regex(
749 r'<link[^>]+rel=["\']license
["\'][^>]+href=(["\'])(?P
<license
>(?
:(?
!\
1).)+)\
1',
750 webpage, 'license
', default=None, group='license
')
752 channel_url = 'https
://vimeo
.com
/channels
/%s' % channel_id if channel_id else None
756 'timestamp
': unified_timestamp(timestamp),
757 'description
': video_description,
759 'view_count
': view_count,
760 'like_count
': like_count,
761 'comment_count
': comment_count,
762 'license
': cc_license,
763 'channel_id
': channel_id,
764 'channel_url
': channel_url,
767 info_dict = merge_dicts(info_dict, info_dict_config, json_ld)
772 class VimeoOndemandIE(VimeoIE):
773 IE_NAME = 'vimeo
:ondemand
'
774 _VALID_URL = r'https?
://(?
:www\
.)?vimeo\
.com
/ondemand
/([^
/]+/)?
(?P
<id>[^
/?
#&]+)'
776 # ondemand video not available via https://vimeo.com/id
777 'url': 'https://vimeo.com/ondemand/20704',
778 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
782 'title': 'המעבדה - במאי יותם פלדמן',
783 'uploader': 'גם סרטים',
784 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/gumfilms',
785 'uploader_id': 'gumfilms',
786 'description': 'md5:4c027c965e439de4baab621e48b60791',
787 'upload_date': '20140906',
788 'timestamp': 1410032453,
791 'format': 'best[protocol=https]',
793 'expected_warnings': ['Unable to download JSON metadata'],
795 # requires Referer to be passed along with og:video:url
796 'url': 'https://vimeo.com/ondemand/36938/126682985',
800 'title': 'Rävlock, rätt läte på rätt plats',
801 'uploader': 'Lindroth & Norin',
802 'uploader_url': r
're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
803 'uploader_id': 'lindrothnorin',
804 'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
805 'upload_date': '20150502',
806 'timestamp': 1430586422,
809 'skip_download': True,
811 'expected_warnings': ['Unable to download JSON metadata'],
813 'url': 'https://vimeo.com/ondemand/nazmaalik',
814 'only_matching': True,
816 'url': 'https://vimeo.com/ondemand/141692381',
817 'only_matching': True,
819 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
820 'only_matching': True,
824 class VimeoChannelIE(VimeoBaseInfoExtractor
):
825 IE_NAME
= 'vimeo:channel'
826 _VALID_URL
= r
'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
827 _MORE_PAGES_INDICATOR
= r
'<a.+?rel="next"'
829 _TITLE_RE
= r
'<link rel="alternate"[^>]+?title="(.*?)"'
831 'url': 'https://vimeo.com/channels/tributes',
834 'title': 'Vimeo Tributes',
836 'playlist_mincount': 25,
838 _BASE_URL_TEMPL
= 'https://vimeo.com/channels/%s'
840 def _page_url(self
, base_url
, pagenum
):
841 return '%s/videos/page:%d/' % (base_url
, pagenum
)
843 def _extract_list_title(self
, webpage
):
844 return self
._TITLE
or self
._html
_search
_regex
(
845 self
._TITLE
_RE
, webpage
, 'list title', fatal
=False)
847 def _title_and_entries(self
, list_id
, base_url
):
848 for pagenum
in itertools
.count(1):
849 page_url
= self
._page
_url
(base_url
, pagenum
)
850 webpage
= self
._download
_webpage
(
852 'Downloading page %s' % pagenum
)
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 channel_id = self._match_id(url)
883 return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
886 class VimeoUserIE(VimeoChannelIE):
887 IE_NAME = 'vimeo
:user
'
888 _VALID_URL = r'https
://vimeo\
.com
/(?
!(?
:[0-9]+|watchlater
)(?
:$|
[?
#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
889 _TITLE_RE
= r
'<a[^>]+?class="user">([^<>]+?)</a>'
891 'url': 'https://vimeo.com/nkistudio/videos',
896 'playlist_mincount': 66,
898 _BASE_URL_TEMPL
= 'https://vimeo.com/%s'
901 class VimeoAlbumIE(VimeoBaseInfoExtractor
):
902 IE_NAME
= 'vimeo:album'
903 _VALID_URL
= r
'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
904 _TITLE_RE
= r
'<header id="page_header">\n\s*<h1>(.*?)</h1>'
906 'url': 'https://vimeo.com/album/2632481',
909 'title': 'Staff Favorites: November 2013',
911 'playlist_mincount': 13,
913 'note': 'Password-protected album',
914 'url': 'https://vimeo.com/album/3253534',
921 'videopassword': 'youtube-dl',
926 def _fetch_page(self
, album_id
, authorization
, hashed_pass
, page
):
929 'fields': 'link,uri',
931 'per_page': self
._PAGE
_SIZE
,
934 query
['_hashed_pass'] = hashed_pass
935 videos
= self
._download
_json
(
936 'https://api.vimeo.com/albums/%s/videos' % album_id
,
937 album_id
, 'Downloading page %d' % api_page
, query
=query
, headers
={
938 'Authorization': 'jwt ' + authorization
,
941 link
= video
.get('link')
944 uri
= video
.get('uri')
945 video_id
= self
._search
_regex
(r
'/videos/(\d+)', uri
, 'video_id', default
=None) if uri
else None
946 yield self
.url_result(link
, VimeoIE
.ie_key(), video_id
)
948 def _real_extract(self
, url
):
949 album_id
= self
._match
_id
(url
)
950 viewer
= self
._download
_json
(
951 'https://vimeo.com/_rv/viewer', album_id
, fatal
=False)
953 webpage
= self
._download
_webpage
(url
, album_id
)
954 viewer
= self
._parse
_json
(self
._search
_regex
(
955 r
'bootstrap_data\s*=\s*({.+?})</script>',
956 webpage
, 'bootstrap data'), album_id
)['viewer']
958 album
= self
._download
_json
(
959 'https://api.vimeo.com/albums/' + album_id
,
960 album_id
, headers
={'Authorization': 'jwt ' + jwt}
,
961 query
={'fields': 'description,name,privacy'}
)
963 if try_get(album
, lambda x
: x
['privacy']['view']) == 'password':
964 password
= self
._downloader
.params
.get('videopassword')
966 raise ExtractorError(
967 'This album is protected by a password, use the --video-password option',
969 self
._set
_vimeo
_cookie
('vuid', viewer
['vuid'])
971 hashed_pass
= self
._download
_json
(
972 'https://vimeo.com/showcase/%s/auth' % album_id
,
973 album_id
, 'Verifying the password', data
=urlencode_postdata({
974 'password': password
,
975 'token': viewer
['xsrft'],
977 'X-Requested-With': 'XMLHttpRequest',
979 except ExtractorError
as e
:
980 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 401:
981 raise ExtractorError('Wrong password', expected
=True)
983 entries
= OnDemandPagedList(functools
.partial(
984 self
._fetch
_page
, album_id
, jwt
, hashed_pass
), self
._PAGE
_SIZE
)
985 return self
.playlist_result(
986 entries
, album_id
, album
.get('name'), album
.get('description'))
989 class VimeoGroupsIE(VimeoChannelIE
):
990 IE_NAME
= 'vimeo:group'
991 _VALID_URL
= r
'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
993 'url': 'https://vimeo.com/groups/kattykay',
996 'title': 'Katty Kay',
998 'playlist_mincount': 27,
1000 _BASE_URL_TEMPL
= 'https://vimeo.com/groups/%s'
1003 class VimeoReviewIE(VimeoBaseInfoExtractor
):
1004 IE_NAME
= 'vimeo:review'
1005 IE_DESC
= 'Review pages on vimeo'
1006 _VALID_URL
= r
'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1008 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1009 'md5': 'c507a72f780cacc12b2248bb4006d253',
1013 'title': "DICK HARDWICK 'Comedian'",
1014 'uploader': 'Richard Hardwick',
1015 'uploader_id': 'user21297594',
1016 'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1018 'expected_warnings': ['Unable to download JSON metadata'],
1020 'note': 'video player needs Referer',
1021 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1022 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1026 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1027 'uploader': 'DevWeek Events',
1029 'thumbnail': r
're:^https?://.*\.jpg$',
1030 'uploader_id': 'user22258446',
1032 'skip': 'video gone',
1034 'note': 'Password protected',
1035 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1039 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1041 'uploader_id': 'user37284429',
1044 'videopassword': 'holygrail',
1046 'skip': 'video gone',
1049 def _real_initialize(self
):
1052 def _real_extract(self
, url
):
1053 page_url
, video_id
= re
.match(self
._VALID
_URL
, url
).groups()
1054 clip_data
= self
._download
_json
(
1055 page_url
.replace('/review/', '/review/data/'),
1056 video_id
)['clipData']
1057 config_url
= clip_data
['configUrl']
1058 config
= self
._download
_json
(config_url
, video_id
)
1059 info_dict
= self
._parse
_config
(config
, video_id
)
1060 source_format
= self
._extract
_original
_format
(
1061 page_url
+ '/action', video_id
)
1063 info_dict
['formats'].append(source_format
)
1064 self
._vimeo
_sort
_formats
(info_dict
['formats'])
1065 info_dict
['description'] = clean_html(clip_data
.get('description'))
1069 class VimeoWatchLaterIE(VimeoChannelIE
):
1070 IE_NAME
= 'vimeo:watchlater'
1071 IE_DESC
= 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
1072 _VALID_URL
= r
'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1073 _TITLE
= 'Watch Later'
1074 _LOGIN_REQUIRED
= True
1076 'url': 'https://vimeo.com/watchlater',
1077 'only_matching': True,
1080 def _real_initialize(self
):
1083 def _page_url(self
, base_url
, pagenum
):
1084 url
= '%s/page:%d/' % (base_url
, pagenum
)
1085 request
= sanitized_Request(url
)
1086 # Set the header to get a partial html page with the ids,
1087 # the normal page doesn't contain them.
1088 request
.add_header('X-Requested-With', 'XMLHttpRequest')
1091 def _real_extract(self
, url
):
1092 return self
._extract
_videos
('watchlater', 'https://vimeo.com/watchlater')
1095 class VimeoLikesIE(VimeoChannelIE
):
1096 _VALID_URL
= r
'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1097 IE_NAME
= 'vimeo:likes'
1098 IE_DESC
= 'Vimeo user likes'
1100 'url': 'https://vimeo.com/user755559/likes/',
1101 'playlist_mincount': 293,
1104 'title': 'urza’s Likes',
1107 'url': 'https://vimeo.com/stormlapse/likes',
1108 'only_matching': True,
1111 def _page_url(self
, base_url
, pagenum
):
1112 return '%s/page:%d/' % (base_url
, pagenum
)
1114 def _real_extract(self
, url
):
1115 user_id
= self
._match
_id
(url
)
1116 return self
._extract
_videos
(user_id
, 'https://vimeo.com/%s/likes' % user_id
)
1119 class VHXEmbedIE(VimeoBaseInfoExtractor
):
1120 IE_NAME
= 'vhx:embed'
1121 _VALID_URL
= r
'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1124 def _extract_url(webpage
):
1126 r
'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage
)
1127 return unescapeHTML(mobj
.group(1)) if mobj
else None
1129 def _real_extract(self
, url
):
1130 video_id
= self
._match
_id
(url
)
1131 webpage
= self
._download
_webpage
(url
, video_id
)
1132 config_url
= self
._parse
_json
(self
._search
_regex
(
1133 r
'window\.OTTData\s*=\s*({.+})', webpage
,
1134 'ott data'), video_id
, js_to_json
)['config_url']
1135 config
= self
._download
_json
(config_url
, video_id
)
1136 info
= self
._parse
_config
(config
, video_id
)
1137 info
['id'] = video_id
1138 self
._vimeo
_sort
_formats
(info
['formats'])