2 from __future__
import unicode_literals
8 from .common
import InfoExtractor
33 class VimeoBaseInfoExtractor(InfoExtractor
):
34 _NETRC_MACHINE
= 'vimeo'
35 _LOGIN_REQUIRED
= False
36 _LOGIN_URL
= 'https://vimeo.com/log_in'
39 (username
, password
) = self
._get
_login
_info
()
41 if self
._LOGIN
_REQUIRED
:
42 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
45 webpage
= self
._download
_webpage
(self
._LOGIN
_URL
, None, False)
46 token
, vuid
= self
._extract
_xsrft
_and
_vuid
(webpage
)
47 data
= urlencode_postdata({
54 login_request
= sanitized_Request(self
._LOGIN
_URL
, data
)
55 login_request
.add_header('Content-Type', 'application/x-www-form-urlencoded')
56 login_request
.add_header('Referer', self
._LOGIN
_URL
)
57 self
._set
_vimeo
_cookie
('vuid', vuid
)
58 self
._download
_webpage
(login_request
, None, False, 'Wrong login info')
60 def _verify_video_password(self
, url
, video_id
, webpage
):
61 password
= self
._downloader
.params
.get('videopassword')
63 raise ExtractorError('This video is protected by a password, use the --video-password option', expected
=True)
64 token
, vuid
= self
._extract
_xsrft
_and
_vuid
(webpage
)
65 data
= urlencode_postdata({
69 if url
.startswith('http://'):
70 # vimeo only supports https now, but the user can give an http url
71 url
= url
.replace('http://', 'https://')
72 password_request
= sanitized_Request(url
+ '/password', data
)
73 password_request
.add_header('Content-Type', 'application/x-www-form-urlencoded')
74 password_request
.add_header('Referer', url
)
75 self
._set
_vimeo
_cookie
('vuid', vuid
)
76 return self
._download
_webpage
(
77 password_request
, video_id
,
78 'Verifying the password', 'Wrong password')
80 def _extract_xsrft_and_vuid(self
, webpage
):
81 xsrft
= self
._search
_regex
(
82 r
'(?:(?P<q1>["\'])xsrft(?P
=q1
)\s
*:|xsrft\s
*[=:])\s
*(?P
<q
>["\'])(?P<xsrft>.+?)(?P=q)',
83 webpage, 'login token', group='xsrft')
84 vuid = self._search_regex(
85 r'["\']vuid
["\']\s*:\s*(["\'])(?P
<vuid
>.+?
)\
1',
86 webpage, 'vuid
', group='vuid
')
89 def _set_vimeo_cookie(self, name, value):
90 self._set_cookie('vimeo
.com
', name, value)
92 def _vimeo_sort_formats(self, formats):
93 # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
94 # at the same time without actual units specified. This lead to wrong sorting.
95 self._sort_formats(formats, field_preference=('preference
', 'height
', 'width
', 'fps
', 'format_id
'))
97 def _parse_config(self, config, video_id):
99 video_title = config['video
']['title
']
101 # Extract uploader, uploader_url and uploader_id
102 video_uploader = config['video
'].get('owner
', {}).get('name
')
103 video_uploader_url = config['video
'].get('owner
', {}).get('url
')
104 video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
106 # Extract video thumbnail
107 video_thumbnail = config['video
'].get('thumbnail
')
108 if video_thumbnail is None:
109 video_thumbs = config['video
'].get('thumbs
')
110 if video_thumbs and isinstance(video_thumbs, dict):
111 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
113 # Extract video duration
114 video_duration = int_or_none(config['video
'].get('duration
'))
117 config_files = config['video
'].get('files
') or config['request
'].get('files
', {})
118 for f in config_files.get('progressive
', []):
119 video_url = f.get('url
')
124 'format_id
': 'http
-%s' % f.get('quality
'),
125 'width
': int_or_none(f.get('width
')),
126 'height
': int_or_none(f.get('height
')),
127 'fps
': int_or_none(f.get('fps
')),
128 'tbr
': int_or_none(f.get('bitrate
')),
130 m3u8_url = config_files.get('hls
', {}).get('url
')
132 formats.extend(self._extract_m3u8_formats(
133 m3u8_url, video_id, 'mp4
', 'm3u8_native
', m3u8_id='hls
', fatal=False))
136 text_tracks = config['request
'].get('text_tracks
')
138 for tt in text_tracks:
139 subtitles[tt['lang
']] = [{
141 'url
': 'https
://vimeo
.com
' + tt['url
'],
145 'title
': video_title,
146 'uploader
': video_uploader,
147 'uploader_id
': video_uploader_id,
148 'uploader_url
': video_uploader_url,
149 'thumbnail
': video_thumbnail,
150 'duration
': video_duration,
152 'subtitles
': subtitles,
156 class VimeoIE(VimeoBaseInfoExtractor):
157 """Information extractor for vimeo.com."""
159 # _VALID_URL matches Vimeo URLs
160 _VALID_URL = r'''(?x)
169 vimeo(?P<pro>pro)?\.com/
170 (?!(?:channels|album)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
175 moogaloop\.swf)\?clip_id=
180 /?(?:[?&].*)?(?:[#].*)?$
185 'url
': 'http
://vimeo
.com
/56015672#at=0',
186 'md5': '8879b6cc097e987f02484baf890129e5',
190 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
191 'description': 'md5:2d3305bad981a06ff79f027f19865021',
192 'upload_date': '20121220',
193 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user7108434',
194 'uploader_id': 'user7108434',
195 'uploader': 'Filippo Valsorda',
200 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
201 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
202 'note': 'Vimeo Pro video (#1197)',
206 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
207 'uploader_id': 'openstreetmapus',
208 'uploader': 'OpenStreetMap US',
209 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
210 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
215 'url': 'http://player.vimeo.com/video/54469442',
216 'md5': '619b811a4417aa4abe78dc653becf511',
217 'note': 'Videos that embed the url in the player page',
221 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
222 'uploader': 'The BLN & Business of Software',
223 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
224 'uploader_id': 'theblnbusinessofsoftware',
230 'url': 'http://vimeo.com/68375962',
231 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
232 'note': 'Video protected with password',
236 'title': 'youtube-dl password protected test video',
237 'upload_date': '20130614',
238 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user18948128',
239 'uploader_id': 'user18948128',
240 'uploader': 'Jaime Marquínez Ferrándiz',
242 'description': 'This is "youtube-dl password protected test video" by on Vimeo, the home for high quality videos and the people who love them.',
245 'videopassword': 'youtube-dl',
249 'url': 'http://vimeo.com/channels/keypeele/75629013',
250 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
254 'title': 'Key & Peele: Terrorist Interrogation',
255 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
256 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/atencio',
257 'uploader_id': 'atencio',
258 'uploader': 'Peter Atencio',
259 'upload_date': '20130927',
264 'url': 'http://vimeo.com/76979871',
265 'note': 'Video with subtitles',
269 'title': 'The New Vimeo Player (You Know, For Videos)',
270 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
271 'upload_date': '20131015',
272 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/staff',
273 'uploader_id': 'staff',
274 'uploader': 'Vimeo Staff',
279 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
280 'url': 'https://player.vimeo.com/video/98044508',
281 'note': 'The js code contains assignments to the same variable as the config',
285 'title': 'Pier Solar OUYA Official Trailer',
286 'uploader': 'Tulio Gonçalves',
287 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user28849593',
288 'uploader_id': 'user28849593',
292 # contains original format
293 'url': 'https://vimeo.com/33951933',
294 'md5': '2d9f5475e0537f013d0073e812ab89e6',
298 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
299 'uploader': 'The DMCI',
300 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/dmci',
301 'uploader_id': 'dmci',
302 'upload_date': '20111220',
303 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
307 # only available via https://vimeo.com/channels/tributes/6213729 and
308 # not via https://vimeo.com/6213729
309 'url': 'https://vimeo.com/channels/tributes/6213729',
313 'title': 'Vimeo Tribute: The Shining',
314 'uploader': 'Casey Donahue',
315 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/caseydonahue',
316 'uploader_id': 'caseydonahue',
317 'upload_date': '20090821',
318 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
321 'skip_download': True,
323 'expected_warnings': ['Unable to download JSON metadata'],
326 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
327 'only_matching': True,
330 'url': 'https://vimeo.com/109815029',
331 'note': 'Video not completely processed, "failed" seed status',
332 'only_matching': True,
335 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
336 'only_matching': True,
339 'url': 'https://vimeo.com/album/2632481/video/79010983',
340 'only_matching': True,
343 # source file returns 403: Forbidden
344 'url': 'https://vimeo.com/7809605',
345 'only_matching': True,
348 'url': 'https://vimeo.com/160743502/abd0e13fb4',
349 'only_matching': True,
354 def _smuggle_referrer(url
, referrer_url
):
355 return smuggle_url(url
, {'http_headers': {'Referer': referrer_url}
})
358 def _extract_urls(url
, webpage
):
360 # Look for embedded (iframe) Vimeo player
361 for mobj
in re
.finditer(
362 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//player\
.vimeo\
.com
/video
/.+?
)\
1', webpage):
363 urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url
')), url))
365 # Look for embedded (swf embed) Vimeo player
366 r'<embed
[^
>]+?src
=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
367 # Look more for non-standard embedded Vimeo player
368 r'<video[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?vimeo\
.com
/[0-9]+)\
1',
370 for embed_re in PLAIN_EMBED_RE:
371 for mobj in re.finditer(embed_re, webpage):
372 urls.append(mobj.group('url
'))
376 def _extract_url(url, webpage):
377 urls = VimeoIE._extract_urls(url, webpage)
378 return urls[0] if urls else None
380 def _verify_player_video_password(self, url, video_id):
381 password = self._downloader.params.get('videopassword
')
383 raise ExtractorError('This video
is protected by a password
, use the
--video
-password option
')
384 data = urlencode_postdata({'password': password})
385 pass_url = url + '/check
-password
'
386 password_request = sanitized_Request(pass_url, data)
387 password_request.add_header('Content
-Type
', 'application
/x
-www
-form
-urlencoded
')
388 password_request.add_header('Referer
', url)
389 return self._download_json(
390 password_request, video_id,
391 'Verifying the password
', 'Wrong password
')
393 def _real_initialize(self):
396 def _real_extract(self, url):
397 url, data = unsmuggle_url(url, {})
398 headers = std_headers.copy()
399 if 'http_headers
' in data:
400 headers.update(data['http_headers
'])
401 if 'Referer
' not in headers:
402 headers['Referer
'] = url
404 # Extract ID from URL
405 mobj = re.match(self._VALID_URL, url)
406 video_id = mobj.group('id')
408 if mobj.group('pro
') or mobj.group('player
'):
409 url = 'https
://player
.vimeo
.com
/video
/' + video_id
410 elif any(p in url for p in ('play_redirect_hls
', 'moogaloop
.swf
')):
411 url = 'https
://vimeo
.com
/' + video_id
413 # Retrieve video webpage to extract further information
414 request = sanitized_Request(url, headers=headers)
416 webpage = self._download_webpage(request, video_id)
417 except ExtractorError as ee:
418 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
419 errmsg = ee.cause.read()
420 if b'Because of its privacy settings
, this video cannot be played here
' in errmsg:
421 raise ExtractorError(
422 'Cannot download embed
-only video without embedding
'
423 'URL
. Please call youtube
-dl
with the URL of the page
'
424 'that embeds this video
.',
428 # Now we begin extracting as much information as we can from what we
429 # retrieved. First we extract the information common to all extractors,
430 # and latter we extract those that are Vimeo specific.
431 self.report_extraction(video_id)
433 vimeo_config = self._search_regex(
434 r'vimeo\
.config\s
*=\s
*(?
:({.+?}
)|_extend\
([^
,]+,\s
+({.+?}
)\
));', webpage,
435 'vimeo config
', default=None)
437 seed_status = self._parse_json(vimeo_config, video_id).get('seed_status
', {})
438 if seed_status.get('state
') == 'failed
':
439 raise ExtractorError(
440 '%s said
: %s' % (self.IE_NAME, seed_status['title
']),
443 # Extract the config JSON
446 config_url = self._html_search_regex(
447 r' data
-config
-url
="(.+?)"', webpage,
448 'config URL
', default=None)
450 # Sometimes new react-based page is served instead of old one that require
451 # different config URL extraction approach (see
452 # https://github.com/rg3/youtube-dl/pull/7209)
453 vimeo_clip_page_config = self._search_regex(
454 r'vimeo\
.clip_page_config\s
*=\s
*({.+?}
);', webpage,
455 'vimeo clip page config
')
456 config_url = self._parse_json(
457 vimeo_clip_page_config, video_id)['player
']['config_url
']
458 config_json = self._download_webpage(config_url, video_id)
459 config = json.loads(config_json)
460 except RegexNotFoundError:
461 # For pro videos or player.vimeo.com urls
462 # We try to find out to which variable is assigned the config dic
463 m_variable_name = re.search('(\w
)\
.video\
.id', webpage)
464 if m_variable_name is not None:
465 config_re = r'%s=({[^}
].+?
});' % re.escape(m_variable_name.group(1))
467 config_re = [r' = {config:({.+?}
),assets
:', r'(?
:[abc
])=({.+?}
);']
468 config = self._search_regex(config_re, webpage, 'info section
',
470 config = json.loads(config)
471 except Exception as e:
472 if re.search('The creator of this video has
not given you permission to embed it on this domain
.', webpage):
473 raise ExtractorError('The author has restricted the access to this video
, try with the
"--referer" option
')
475 if re.search(r'<form
[^
>]+?
id="pw_form"', webpage) is not None:
476 if '_video_password_verified
' in data:
477 raise ExtractorError('video password verification failed
!')
478 self._verify_video_password(url, video_id, webpage)
479 return self._real_extract(
480 smuggle_url(url, {'_video_password_verified': 'verified'}))
482 raise ExtractorError('Unable to extract info section
',
485 if config.get('view
') == 4:
486 config = self._verify_player_video_password(url, video_id)
489 if '>You rented this title
.<' in webpage:
491 if config.get('user
', {}).get('purchased
'):
494 config, lambda x: x['video
']['vod
']['purchase_options
'][0]['label_string
'], compat_str)
495 if label and label.startswith('You rented this
'):
500 feature_id = config.get('video
', {}).get('vod', {}).get('feature_id
')
501 if feature_id and not data.get('force_feature_id
', False):
502 return self.url_result(smuggle_url(
503 'https
://player
.vimeo
.com
/player
/%s' % feature_id,
504 {'force_feature_id': True}), 'Vimeo
')
506 # Extract video description
508 video_description = self._html_search_regex(
509 r'(?s
)<div\s
+class="[^"]*description
[^
"]*"[^
>]*>(.*?
)</div
>',
510 webpage, 'description
', default=None)
511 if not video_description:
512 video_description = self._html_search_meta(
513 'description
', webpage, default=None)
514 if not video_description and mobj.group('pro
'):
515 orig_webpage = self._download_webpage(
517 note='Downloading webpage
for description
',
520 video_description = self._html_search_meta(
521 'description
', orig_webpage, default=None)
522 if not video_description and not mobj.group('player
'):
523 self._downloader.report_warning('Cannot find video description
')
525 # Extract upload date
526 video_upload_date = None
527 mobj = re.search(r'<time
[^
>]+datetime
="([^"]+)"', webpage)
529 video_upload_date = unified_strdate(mobj.group(1))
532 view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
533 like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
534 comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
535 except RegexNotFoundError:
536 # This info is only available in vimeo.com/{id} urls
542 download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={
543 'X-Requested-With': 'XMLHttpRequest'})
544 download_data = self._download_json(download_request, video_id, fatal=False)
546 source_file = download_data.get('source_file')
547 if isinstance(source_file, dict):
548 download_url = source_file.get('download_url')
549 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
550 source_name = source_file.get('public_name', 'Original')
551 if self._is_valid_url(download_url, video_id, '%s video' % source_name):
552 ext = source_file.get('extension', determine_ext(download_url)).lower()
556 'width': int_or_none(source_file.get('width')),
557 'height': int_or_none(source_file.get('height')),
558 'filesize': parse_filesize(source_file.get('size')),
559 'format_id': source_name,
563 info_dict = self._parse_config(config, video_id)
564 formats.extend(info_dict['formats'])
565 self._vimeo_sort_formats(formats)
569 'upload_date': video_upload_date,
570 'description': video_description,
572 'view_count': view_count,
573 'like_count': like_count,
574 'comment_count': comment_count,
580 class VimeoOndemandIE(VimeoBaseInfoExtractor):
581 IE_NAME = 'vimeo:ondemand'
582 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)'
584 # ondemand video not available via https://vimeo.com/id
585 'url': 'https://vimeo.com/ondemand/20704',
586 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
590 'title': 'המעבדה - במאי יותם פלדמן',
591 'uploader': 'גם סרטים',
592 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/gumfilms',
593 'uploader_id': 'gumfilms',
596 # requires Referer to be passed along with og:video:url
597 'url': 'https://vimeo.com/ondemand/36938/126682985',
601 'title': 'Rävlock, rätt läte på rätt plats',
602 'uploader': 'Lindroth & Norin',
603 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user14430847',
604 'uploader_id': 'user14430847',
607 'skip_download': True,
610 'url': 'https://vimeo.com/ondemand/nazmaalik',
611 'only_matching': True,
613 'url': 'https://vimeo.com/ondemand/141692381',
614 'only_matching': True,
616 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
617 'only_matching': True,
620 def _real_extract(self, url):
621 video_id = self._match_id(url)
622 webpage = self._download_webpage(url, video_id)
623 return self.url_result(
624 # Some videos require Referer to be passed along with og:video:url
625 # similarly to generic vimeo embeds (e.g.
626 # https://vimeo.com/ondemand/36938/126682985).
627 VimeoIE._smuggle_referrer(self._og_search_video_url(webpage), url),
631 class VimeoChannelIE(VimeoBaseInfoExtractor):
632 IE_NAME = 'vimeo:channel'
633 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
634 _MORE_PAGES_INDICATOR = r'<a.+?rel="next
"'
636 _TITLE_RE = r'<link rel="alternate
"[^>]+?title="(.*?
)"'
638 'url': 'https://vimeo.com/channels/tributes',
641 'title': 'Vimeo Tributes',
643 'playlist_mincount': 25,
646 def _page_url(self, base_url, pagenum):
647 return '%s/videos/page:%d/' % (base_url, pagenum)
649 def _extract_list_title(self, webpage):
650 return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
652 def _login_list_password(self, page_url, list_id, webpage):
653 login_form = self._search_regex(
654 r'(?s)<form[^>]+?id="pw_form
"(.*?)</form>',
655 webpage, 'login form', default=None)
659 password = self._downloader.params.get('videopassword')
661 raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
662 fields = self._hidden_inputs(login_form)
663 token, vuid = self._extract_xsrft_and_vuid(webpage)
664 fields['token'] = token
665 fields['password'] = password
666 post = urlencode_postdata(fields)
667 password_path = self._search_regex(
668 r'action="([^
"]+)"', login_form, 'password URL
')
669 password_url = compat_urlparse.urljoin(page_url, password_path)
670 password_request = sanitized_Request(password_url, post)
671 password_request.add_header('Content
-type', 'application
/x
-www
-form
-urlencoded
')
672 self._set_vimeo_cookie('vuid
', vuid)
673 self._set_vimeo_cookie('xsrft
', token)
675 return self._download_webpage(
676 password_request, list_id,
677 'Verifying the password
', 'Wrong password
')
679 def _title_and_entries(self, list_id, base_url):
680 for pagenum in itertools.count(1):
681 page_url = self._page_url(base_url, pagenum)
682 webpage = self._download_webpage(
684 'Downloading page
%s' % pagenum)
687 webpage = self._login_list_password(page_url, list_id, webpage)
688 yield self._extract_list_title(webpage)
690 # Try extracting href first since not all videos are available via
691 # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
693 r'id="clip_(\d+)"[^
>]*>\s
*<a
[^
>]+href
="(/(?:[^/]+/)*\1)', webpage)
695 for video_id, video_url in clips:
696 yield self.url_result(
697 compat_urlparse.urljoin(base_url, video_url),
698 VimeoIE.ie_key(), video_id=video_id)
699 # More relaxed fallback
701 for video_id in re.findall(r'id=["\']clip_(\d
+)', webpage):
702 yield self.url_result(
703 'https
://vimeo
.com
/%s' % video_id,
704 VimeoIE.ie_key(), video_id=video_id)
706 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
709 def _extract_videos(self, list_id, base_url):
710 title_and_entries = self._title_and_entries(list_id, base_url)
711 list_title = next(title_and_entries)
712 return self.playlist_result(title_and_entries, list_id, list_title)
714 def _real_extract(self, url):
715 mobj = re.match(self._VALID_URL, url)
716 channel_id = mobj.group('id')
717 return self._extract_videos(channel_id, 'https
://vimeo
.com
/channels
/%s' % channel_id)
720 class VimeoUserIE(VimeoChannelIE):
721 IE_NAME = 'vimeo
:user
'
722 _VALID_URL = r'https
://vimeo\
.com
/(?
!(?
:[0-9]+|watchlater
)(?
:$|
[?
#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
723 _TITLE_RE
= r
'<a[^>]+?class="user">([^<>]+?)</a>'
725 'url': 'https://vimeo.com/nkistudio/videos',
730 'playlist_mincount': 66,
733 def _real_extract(self
, url
):
734 mobj
= re
.match(self
._VALID
_URL
, url
)
735 name
= mobj
.group('name')
736 return self
._extract
_videos
(name
, 'https://vimeo.com/%s' % name
)
739 class VimeoAlbumIE(VimeoChannelIE
):
740 IE_NAME
= 'vimeo:album'
741 _VALID_URL
= r
'https://vimeo\.com/album/(?P<id>\d+)(?:$|[?#]|/(?!video))'
742 _TITLE_RE
= r
'<header id="page_header">\n\s*<h1>(.*?)</h1>'
744 'url': 'https://vimeo.com/album/2632481',
747 'title': 'Staff Favorites: November 2013',
749 'playlist_mincount': 13,
751 'note': 'Password-protected album',
752 'url': 'https://vimeo.com/album/3253534',
759 'videopassword': 'youtube-dl',
762 'url': 'https://vimeo.com/album/2632481/sort:plays/format:thumbnail',
763 'only_matching': True,
765 # TODO: respect page number
766 'url': 'https://vimeo.com/album/2632481/page:2/sort:plays/format:thumbnail',
767 'only_matching': True,
770 def _page_url(self
, base_url
, pagenum
):
771 return '%s/page:%d/' % (base_url
, pagenum
)
773 def _real_extract(self
, url
):
774 album_id
= self
._match
_id
(url
)
775 return self
._extract
_videos
(album_id
, 'https://vimeo.com/album/%s' % album_id
)
778 class VimeoGroupsIE(VimeoAlbumIE
):
779 IE_NAME
= 'vimeo:group'
780 _VALID_URL
= r
'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
782 'url': 'https://vimeo.com/groups/rolexawards',
785 'title': 'Rolex Awards for Enterprise',
787 'playlist_mincount': 73,
790 def _extract_list_title(self
, webpage
):
791 return self
._og
_search
_title
(webpage
)
793 def _real_extract(self
, url
):
794 mobj
= re
.match(self
._VALID
_URL
, url
)
795 name
= mobj
.group('name')
796 return self
._extract
_videos
(name
, 'https://vimeo.com/groups/%s' % name
)
799 class VimeoReviewIE(VimeoBaseInfoExtractor
):
800 IE_NAME
= 'vimeo:review'
801 IE_DESC
= 'Review pages on vimeo'
802 _VALID_URL
= r
'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
804 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
805 'md5': 'c507a72f780cacc12b2248bb4006d253',
809 'title': "DICK HARDWICK 'Comedian'",
810 'uploader': 'Richard Hardwick',
811 'uploader_id': 'user21297594',
814 'note': 'video player needs Referer',
815 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
816 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
820 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
821 'uploader': 'DevWeek Events',
823 'thumbnail': 're:^https?://.*\.jpg$',
824 'uploader_id': 'user22258446',
827 'note': 'Password protected',
828 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
832 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
834 'uploader_id': 'user37284429',
837 'videopassword': 'holygrail',
841 def _real_initialize(self
):
844 def _get_config_url(self
, webpage_url
, video_id
, video_password_verified
=False):
845 webpage
= self
._download
_webpage
(webpage_url
, video_id
)
846 config_url
= self
._html
_search
_regex
(
847 r
'data-config-url="([^"]+)"', webpage
, 'config URL',
848 default
=NO_DEFAULT
if video_password_verified
else None)
849 if config_url
is None:
850 self
._verify
_video
_password
(webpage_url
, video_id
, webpage
)
851 config_url
= self
._get
_config
_url
(
852 webpage_url
, video_id
, video_password_verified
=True)
855 def _real_extract(self
, url
):
856 video_id
= self
._match
_id
(url
)
857 config_url
= self
._get
_config
_url
(url
, video_id
)
858 config
= self
._download
_json
(config_url
, video_id
)
859 info_dict
= self
._parse
_config
(config
, video_id
)
860 self
._vimeo
_sort
_formats
(info_dict
['formats'])
861 info_dict
['id'] = video_id
865 class VimeoWatchLaterIE(VimeoChannelIE
):
866 IE_NAME
= 'vimeo:watchlater'
867 IE_DESC
= 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
868 _VALID_URL
= r
'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
869 _TITLE
= 'Watch Later'
870 _LOGIN_REQUIRED
= True
872 'url': 'https://vimeo.com/watchlater',
873 'only_matching': True,
876 def _real_initialize(self
):
879 def _page_url(self
, base_url
, pagenum
):
880 url
= '%s/page:%d/' % (base_url
, pagenum
)
881 request
= sanitized_Request(url
)
882 # Set the header to get a partial html page with the ids,
883 # the normal page doesn't contain them.
884 request
.add_header('X-Requested-With', 'XMLHttpRequest')
887 def _real_extract(self
, url
):
888 return self
._extract
_videos
('watchlater', 'https://vimeo.com/watchlater')
891 class VimeoLikesIE(InfoExtractor
):
892 _VALID_URL
= r
'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
893 IE_NAME
= 'vimeo:likes'
894 IE_DESC
= 'Vimeo user likes'
896 'url': 'https://vimeo.com/user755559/likes/',
897 'playlist_mincount': 293,
899 'id': 'user755559_likes',
900 'description': 'See all the videos urza likes',
901 'title': 'Videos urza likes',
905 def _real_extract(self
, url
):
906 user_id
= self
._match
_id
(url
)
907 webpage
= self
._download
_webpage
(url
, user_id
)
908 page_count
= self
._int
(
910 r
'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
911 .*?</a></li>\s*<li\s+class="pagination_next">
912 ''', webpage
, 'page count'),
913 'page count', fatal
=True)
915 title
= self
._html
_search
_regex
(
916 r
'(?s)<h1>(.+?)</h1>', webpage
, 'title', fatal
=False)
917 description
= self
._html
_search
_meta
('description', webpage
)
920 page_url
= 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
922 webpage
= self
._download
_webpage
(
924 note
='Downloading page %d/%d' % (idx
+ 1, page_count
))
925 video_list
= self
._search
_regex
(
926 r
'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
927 webpage
, 'video content')
929 r
'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list
)
933 'url': compat_urlparse
.urljoin(page_url
, path
),
936 pl
= InAdvancePagedList(_get_page
, page_count
, PAGE_SIZE
)
940 'id': 'user%s_likes' % user_id
,
942 'description': description
,