]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/vimeo.py
[misc] Add `hatch`, `ruff`, `pre-commit` and improve dev docs (#7409)
[yt-dlp.git] / yt_dlp / extractor / vimeo.py
CommitLineData
79fec976 1import base64
eb9c9c74 2import functools
caeefc29 3import itertools
e897bd82 4import re
b3d14cbf
PH
5
6from .common import InfoExtractor
3d2623a8 7from ..compat import compat_str, compat_urlparse
8from ..networking import HEADRequest, Request
9from ..networking.exceptions import HTTPError
8c25f81b 10from ..utils import (
e897bd82
SS
11 ExtractorError,
12 OnDemandPagedList,
681ac7c9 13 clean_html,
d5f071af 14 determine_ext,
58ab5cbc 15 get_element_by_class,
9c44d242 16 int_or_none,
e897bd82 17 js_to_json,
ae1c585c 18 merge_dicts,
ca01d178 19 parse_filesize,
cce889b9 20 parse_iso8601,
4dfbf869 21 parse_qs,
30965ac6 22 smuggle_url,
681ac7c9 23 str_or_none,
f0426e9c 24 traverse_obj,
c15cd296 25 try_get,
c15cd296 26 unified_timestamp,
9d4660ca 27 unsmuggle_url,
a980bc43 28 urlencode_postdata,
9cb070f9 29 urlhandle_detect_ext,
e897bd82 30 urljoin,
b3d14cbf
PH
31)
32
bbafbe20 33
efb7e119
JMF
34class VimeoBaseInfoExtractor(InfoExtractor):
35 _NETRC_MACHINE = 'vimeo'
36 _LOGIN_REQUIRED = False
f6c3664d 37 _LOGIN_URL = 'https://vimeo.com/log_in'
efb7e119 38
aedaa455 39 @staticmethod
40 def _smuggle_referrer(url, referrer_url):
f04b5bed 41 return smuggle_url(url, {'referer': referrer_url})
aedaa455 42
43 def _unsmuggle_headers(self, url):
44 """@returns (url, smuggled_data, headers)"""
45 url, data = unsmuggle_url(url, {})
46 headers = self.get_param('http_headers').copy()
f04b5bed 47 if 'referer' in data:
48 headers['Referer'] = data['referer']
aedaa455 49 return url, data, headers
50
52efa4b3 51 def _perform_login(self, username, password):
2e8de097 52 viewer = self._download_json('https://vimeo.com/_next/viewer', None, 'Downloading login token')
26ad6bcd 53 data = {
f6c3664d 54 'action': 'login',
efb7e119
JMF
55 'email': username,
56 'password': password,
efb7e119 57 'service': 'vimeo',
2e8de097 58 'token': viewer['xsrft'],
26ad6bcd 59 }
2e8de097 60 self._set_vimeo_cookie('vuid', viewer['vuid'])
26ad6bcd
S
61 try:
62 self._download_webpage(
63 self._LOGIN_URL, None, 'Logging in',
64 data=urlencode_postdata(data), headers={
65 'Content-Type': 'application/x-www-form-urlencoded',
66 'Referer': self._LOGIN_URL,
67 })
68 except ExtractorError as e:
3d2623a8 69 if isinstance(e.cause, HTTPError) and e.cause.status == 418:
26ad6bcd
S
70 raise ExtractorError(
71 'Unable to log in: bad username or password',
72 expected=True)
73 raise ExtractorError('Unable to log in')
efb7e119 74
52efa4b3 75 def _real_initialize(self):
76 if self._LOGIN_REQUIRED and not self._get_cookies('https://vimeo.com').get('vuid'):
77 self._raise_login_required()
78
cce889b9 79 def _get_video_password(self):
a06916d9 80 password = self.get_param('videopassword')
c1ff6e1a 81 if password is None:
cce889b9 82 raise ExtractorError(
83 'This video is protected by a password, use the --video-password option',
84 expected=True)
85 return password
86
87 def _verify_video_password(self, url, video_id, password, token, vuid):
c1ff6e1a
YCH
88 if url.startswith('http://'):
89 # vimeo only supports https now, but the user can give an http url
90 url = url.replace('http://', 'https://')
c1ff6e1a
YCH
91 self._set_vimeo_cookie('vuid', vuid)
92 return self._download_webpage(
cce889b9 93 url + '/password', video_id, 'Verifying the password',
94 'Wrong password', data=urlencode_postdata({
95 'password': password,
96 'token': token,
97 }), headers={
98 'Content-Type': 'application/x-www-form-urlencoded',
99 'Referer': url,
100 })
c1ff6e1a 101
7c845629
S
102 def _extract_xsrft_and_vuid(self, webpage):
103 xsrft = self._search_regex(
b826035d 104 r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
f6c3664d 105 webpage, 'login token', group='xsrft')
7c845629
S
106 vuid = self._search_regex(
107 r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
108 webpage, 'vuid', group='vuid')
109 return xsrft, vuid
f6c3664d 110
eb9c9c74
RA
111 def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
112 vimeo_config = self._search_regex(
113 r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
f9934b96 114 webpage, 'vimeo config', *args, **kwargs)
eb9c9c74
RA
115 if vimeo_config:
116 return self._parse_json(vimeo_config, video_id)
117
9eab37dc
S
118 def _set_vimeo_cookie(self, name, value):
119 self._set_cookie('vimeo.com', name, value)
120
531a7496 121 def _parse_config(self, config, video_id):
d8c507c9 122 video_data = config['video']
24146491 123 video_title = video_data.get('title')
85b6335d 124 live_event = video_data.get('live_event') or {}
f0426e9c
M
125 live_status = {
126 'pending': 'is_upcoming',
127 'active': 'is_upcoming',
128 'started': 'is_live',
129 'ended': 'post_live',
130 }.get(live_event.get('status'))
131 is_live = live_status == 'is_live'
58ab5cbc 132 request = config.get('request') or {}
531a7496
YCH
133
134 formats = []
3f047fc4
F
135 subtitles = {}
136
58ab5cbc 137 config_files = video_data.get('files') or request.get('files') or {}
138 for f in (config_files.get('progressive') or []):
531a7496
YCH
139 video_url = f.get('url')
140 if not video_url:
141 continue
142 formats.append({
143 'url': video_url,
144 'format_id': 'http-%s' % f.get('quality'),
bc104778 145 'source_preference': 10,
531a7496
YCH
146 'width': int_or_none(f.get('width')),
147 'height': int_or_none(f.get('height')),
148 'fps': int_or_none(f.get('fps')),
149 'tbr': int_or_none(f.get('bitrate')),
150 })
d8c507c9 151
85b6335d 152 # TODO: fix handling of 308 status code returned for live archive manifest requests
52c50a10 153 sep_pattern = r'/sep/video/'
d8c507c9 154 for files_type in ('hls', 'dash'):
58ab5cbc 155 for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
d8c507c9
RA
156 manifest_url = cdn_data.get('url')
157 if not manifest_url:
158 continue
159 format_id = '%s-%s' % (files_type, cdn_name)
52c50a10
RA
160 sep_manifest_urls = []
161 if re.search(sep_pattern, manifest_url):
162 for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
163 sep_manifest_urls.append((format_id + suffix, re.sub(
164 sep_pattern, '/%s/' % repl, manifest_url)))
165 else:
166 sep_manifest_urls = [(format_id, manifest_url)]
167 for f_id, m_url in sep_manifest_urls:
168 if files_type == 'hls':
3f047fc4 169 fmts, subs = self._extract_m3u8_formats_and_subtitles(
a5c0c202 170 m_url, video_id, 'mp4', live=is_live, m3u8_id=f_id,
52c50a10 171 note='Downloading %s m3u8 information' % cdn_name,
3f047fc4
F
172 fatal=False)
173 formats.extend(fmts)
174 self._merge_subtitles(subs, target=subtitles)
52c50a10 175 elif files_type == 'dash':
c25720ef
RA
176 if 'json=1' in m_url:
177 real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
178 if real_m_url:
179 m_url = real_m_url
3f047fc4 180 fmts, subs = self._extract_mpd_formats_and_subtitles(
ae9a173b
RA
181 m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
182 'Downloading %s MPD information' % cdn_name,
e834f044 183 fatal=False)
3f047fc4
F
184 formats.extend(fmts)
185 self._merge_subtitles(subs, target=subtitles)
531a7496 186
85b6335d
RA
187 live_archive = live_event.get('archive') or {}
188 live_archive_source_url = live_archive.get('source_url')
189 if live_archive_source_url and live_archive.get('status') == 'done':
190 formats.append({
191 'format_id': 'live-archive-source',
192 'url': live_archive_source_url,
f983b875 193 'quality': 10,
85b6335d
RA
194 })
195
58ab5cbc 196 for tt in (request.get('text_tracks') or []):
3f047fc4 197 subtitles.setdefault(tt['lang'], []).append({
58ab5cbc 198 'ext': 'vtt',
199 'url': urljoin('https://vimeo.com', tt['url']),
3f047fc4 200 })
531a7496 201
c25720ef
RA
202 thumbnails = []
203 if not is_live:
58ab5cbc 204 for key, thumb in (video_data.get('thumbs') or {}).items():
c25720ef
RA
205 thumbnails.append({
206 'id': key,
207 'width': int_or_none(key),
208 'url': thumb,
209 })
210 thumbnail = video_data.get('thumbnail')
211 if thumbnail:
212 thumbnails.append({
213 'url': thumbnail,
214 })
215
216 owner = video_data.get('owner') or {}
217 video_uploader_url = owner.get('url')
218
818faa3a 219 duration = int_or_none(video_data.get('duration'))
220 chapter_data = try_get(config, lambda x: x['embed']['chapters']) or []
221 chapters = [{
222 'title': current_chapter.get('title'),
223 'start_time': current_chapter.get('timecode'),
224 'end_time': next_chapter.get('timecode'),
225 } for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])]
226 if chapters and chapters[0]['start_time']: # Chapters may not start from 0
227 chapters[:0] = [{'title': '<Untitled>', 'start_time': 0, 'end_time': chapters[0]['start_time']}]
228
531a7496 229 return {
681ac7c9 230 'id': str_or_none(video_data.get('id')) or video_id,
39ca3b5c 231 'title': video_title,
c25720ef
RA
232 'uploader': owner.get('name'),
233 'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
531a7496 234 'uploader_url': video_uploader_url,
c25720ef 235 'thumbnails': thumbnails,
818faa3a 236 'duration': duration,
237 'chapters': chapters or None,
531a7496
YCH
238 'formats': formats,
239 'subtitles': subtitles,
f0426e9c
M
240 'live_status': live_status,
241 'release_timestamp': traverse_obj(live_event, ('ingest', 'scheduled_start_time', {parse_iso8601})),
9f14daf2 242 # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
243 # at the same time without actual units specified.
244 '_format_sort_fields': ('quality', 'res', 'fps', 'hdr:12', 'source'),
531a7496
YCH
245 }
246
bc2ca1bb 247 def _extract_original_format(self, url, video_id, unlisted_hash=None):
248 query = {'action': 'load_download_config'}
249 if unlisted_hash:
250 query['unlisted_hash'] = unlisted_hash
27655037 251 download_data = self._download_json(
bc2ca1bb 252 url, video_id, fatal=False, query=query,
9cb070f9 253 headers={'X-Requested-With': 'XMLHttpRequest'},
254 expected_status=(403, 404)) or {}
255 source_file = download_data.get('source_file')
256 download_url = try_get(source_file, lambda x: x['download_url'])
257 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
258 source_name = source_file.get('public_name', 'Original')
259 if self._is_valid_url(download_url, video_id, '%s video' % source_name):
260 ext = (try_get(
261 source_file, lambda x: x['extension'],
262 compat_str) or determine_ext(
263 download_url, None) or 'mp4').lower()
264 return {
265 'url': download_url,
266 'ext': ext,
267 'width': int_or_none(source_file.get('width')),
268 'height': int_or_none(source_file.get('height')),
269 'filesize': parse_filesize(source_file.get('size')),
270 'format_id': source_name,
271 'quality': 1,
272 }
27655037 273
605cad0b
A
274 jwt_response = self._download_json(
275 'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
276 if not jwt_response.get('jwt'):
277 return
8e765755 278 headers = {'Authorization': 'jwt %s' % jwt_response['jwt'], 'Accept': 'application/json'}
605cad0b
A
279 original_response = self._download_json(
280 f'https://api.vimeo.com/videos/{video_id}', video_id,
9cb070f9 281 headers=headers, fatal=False, expected_status=(403, 404)) or {}
282 for download_data in original_response.get('download') or []:
605cad0b
A
283 download_url = download_data.get('link')
284 if not download_url or download_data.get('quality') != 'source':
285 continue
9cb070f9 286 ext = determine_ext(parse_qs(download_url).get('filename', [''])[0].lower(), default_ext=None)
287 if not ext:
288 urlh = self._request_webpage(
289 HEADRequest(download_url), video_id, fatal=False, note='Determining source extension')
290 ext = urlh and urlhandle_detect_ext(urlh)
605cad0b
A
291 return {
292 'url': download_url,
9cb070f9 293 'ext': ext or 'unknown_video',
605cad0b
A
294 'format_id': download_data.get('public_name', 'Original'),
295 'width': int_or_none(download_data.get('width')),
296 'height': int_or_none(download_data.get('height')),
297 'fps': int_or_none(download_data.get('fps')),
298 'filesize': int_or_none(download_data.get('size')),
299 'quality': 1,
300 }
301
efb7e119 302
65469a7f 303class VimeoIE(VimeoBaseInfoExtractor):
b3d14cbf
PH
304 """Information extractor for vimeo.com."""
305
306 # _VALID_URL matches Vimeo URLs
bbafbe20 307 _VALID_URL = r'''(?x)
45b2ee6f 308 https?://
309 (?:
310 (?:
311 www|
312 player
313 )
314 \.
315 )?
316 vimeo\.com/
317 (?:
318 (?P<u>user)|
319 (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
320 (?:.*?/)??
321 (?P<q>
322 (?:
323 play_redirect_hls|
324 moogaloop\.swf)\?clip_id=
325 )?
326 (?:videos?/)?
327 )
328 (?P<id>[0-9]+)
329 (?(u)
330 /(?!videos|likes)[^/?#]+/?|
331 (?(q)|/(?P<unlisted_hash>[\da-f]{10}))?
332 )
333 (?:(?(q)[&]|(?(u)|/?)[?]).*?)?(?:[#].*)?$
334 '''
9148eb00 335 IE_NAME = 'vimeo'
bfd973ec 336 _EMBED_REGEX = [
337 # iframe
338 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
339 # Embedded (swf embed) Vimeo player
340 r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
341 # Non-standard embedded Vimeo player
342 r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
343 ]
a91b954b
JMF
344 _TESTS = [
345 {
9148eb00 346 'url': 'http://vimeo.com/56015672#at=0',
9148eb00
PH
347 'md5': '8879b6cc097e987f02484baf890129e5',
348 'info_dict': {
ad5976b4
PH
349 'id': '56015672',
350 'ext': 'mp4',
b9c7b1e9 351 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
681ac7c9 352 'description': 'md5:2d3305bad981a06ff79f027f19865021',
c15cd296 353 'timestamp': 1355990239,
68f3b61f 354 'upload_date': '20121220',
ec85ded8 355 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
68f3b61f
S
356 'uploader_id': 'user7108434',
357 'uploader': 'Filippo Valsorda',
358 'duration': 10,
c38a67bc 359 'license': 'by-sa',
a91b954b 360 },
681ac7c9
RA
361 'params': {
362 'format': 'best[protocol=https]',
363 },
b9c7b1e9 364 'skip': 'No longer available'
a91b954b 365 },
aa32314d 366 {
9148eb00 367 'url': 'http://player.vimeo.com/video/54469442',
c0cd13fb 368 'md5': '619b811a4417aa4abe78dc653becf511',
9148eb00
PH
369 'note': 'Videos that embed the url in the player page',
370 'info_dict': {
4f3e9430
JMF
371 'id': '54469442',
372 'ext': 'mp4',
0e6ebc13 373 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
cce889b9 374 'uploader': 'Business of Software',
375 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
376 'uploader_id': 'businessofsoftware',
69c8fb9e 377 'duration': 3610,
b9c7b1e9 378 'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d_1280',
aa32314d 379 },
681ac7c9
RA
380 'params': {
381 'format': 'best[protocol=https]',
382 },
93b22c78
JMF
383 },
384 {
9148eb00 385 'url': 'http://vimeo.com/68375962',
9148eb00
PH
386 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
387 'note': 'Video protected with password',
388 'info_dict': {
4f3e9430
JMF
389 'id': '68375962',
390 'ext': 'mp4',
3867038a 391 'title': 'youtube-dl password protected test video',
c15cd296 392 'timestamp': 1371200155,
9148eb00 393 'upload_date': '20130614',
ec85ded8 394 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
9148eb00
PH
395 'uploader_id': 'user18948128',
396 'uploader': 'Jaime Marquínez Ferrándiz',
69c8fb9e 397 'duration': 10,
c0cd13fb
L
398 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
399 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
b9c7b1e9 400 'view_count': int,
401 'comment_count': int,
402 'like_count': int,
93b22c78 403 },
9148eb00 404 'params': {
681ac7c9 405 'format': 'best[protocol=https]',
3867038a 406 'videopassword': 'youtube-dl',
93b22c78
JMF
407 },
408 },
548f31d9
S
409 {
410 'url': 'http://vimeo.com/channels/keypeele/75629013',
411 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
548f31d9
S
412 'info_dict': {
413 'id': '75629013',
414 'ext': 'mp4',
415 'title': 'Key & Peele: Terrorist Interrogation',
c0cd13fb 416 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
ec85ded8 417 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
548f31d9
S
418 'uploader_id': 'atencio',
419 'uploader': 'Peter Atencio',
d03beddf
S
420 'channel_id': 'keypeele',
421 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
c15cd296
S
422 'timestamp': 1380339469,
423 'upload_date': '20130928',
548f31d9 424 'duration': 187,
b9c7b1e9 425 'thumbnail': 'https://i.vimeocdn.com/video/450239872-a05512d9b1e55d707a7c04365c10980f327b06d966351bc403a5d5d65c95e572-d_1280',
426 'view_count': int,
427 'comment_count': int,
428 'like_count': int,
548f31d9 429 },
9cb070f9 430 'params': {'format': 'http-1080p'},
548f31d9 431 },
1eac553e
S
432 {
433 'url': 'http://vimeo.com/76979871',
1eac553e
S
434 'note': 'Video with subtitles',
435 'info_dict': {
436 'id': '76979871',
b9c7b1e9 437 'ext': 'mov',
1eac553e
S
438 'title': 'The New Vimeo Player (You Know, For Videos)',
439 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
c15cd296 440 'timestamp': 1381846109,
1eac553e 441 'upload_date': '20131015',
ec85ded8 442 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
1eac553e
S
443 'uploader_id': 'staff',
444 'uploader': 'Vimeo Staff',
69c8fb9e 445 'duration': 62,
58ab5cbc 446 'subtitles': {
447 'de': [{'ext': 'vtt'}],
448 'en': [{'ext': 'vtt'}],
449 'es': [{'ext': 'vtt'}],
450 'fr': [{'ext': 'vtt'}],
451 },
9cb070f9 452 },
453 'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
1eac553e 454 },
4698f0d8
JMF
455 {
456 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
457 'url': 'https://player.vimeo.com/video/98044508',
458 'note': 'The js code contains assignments to the same variable as the config',
459 'info_dict': {
460 'id': '98044508',
461 'ext': 'mp4',
462 'title': 'Pier Solar OUYA Official Trailer',
463 'uploader': 'Tulio Gonçalves',
ec85ded8 464 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
4698f0d8 465 'uploader_id': 'user28849593',
b9c7b1e9 466 'duration': 118,
467 'thumbnail': 'https://i.vimeocdn.com/video/478636036-c18440305ef3df9decfb6bf207a61fe39d2d17fa462a96f6f2d93d30492b037d-d_1280',
4698f0d8
JMF
468 },
469 },
323f82a7 470 {
471 # contains original format
472 'url': 'https://vimeo.com/33951933',
365d136b 473 'md5': '53c688fa95a55bf4b7293d37a89c5c53',
323f82a7 474 'info_dict': {
475 'id': '33951933',
476 'ext': 'mp4',
477 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
478 'uploader': 'The DMCI',
ec85ded8 479 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
323f82a7 480 'uploader_id': 'dmci',
c15cd296 481 'timestamp': 1324343742,
323f82a7 482 'upload_date': '20111220',
483 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
b9c7b1e9 484 'duration': 60,
485 'comment_count': int,
486 'view_count': int,
487 'thumbnail': 'https://i.vimeocdn.com/video/231174622-dd07f015e9221ff529d451e1cc31c982b5d87bfafa48c4189b1da72824ee289a-d_1280',
488 'like_count': int,
323f82a7 489 },
490 },
605cad0b
A
491 {
492 'note': 'Contains original format not accessible in webpage',
493 'url': 'https://vimeo.com/393756517',
494 'md5': 'c464af248b592190a5ffbb5d33f382b0',
495 'info_dict': {
496 'id': '393756517',
497 'ext': 'mov',
498 'timestamp': 1582642091,
499 'uploader_id': 'frameworkla',
500 'title': 'Straight To Hell - Sabrina: Netflix',
501 'uploader': 'Framework Studio',
502 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
503 'upload_date': '20200225',
b9c7b1e9 504 'duration': 176,
505 'thumbnail': 'https://i.vimeocdn.com/video/859377297-836494a4ef775e9d4edbace83937d9ad34dc846c688c0c419c0e87f7ab06c4b3-d_1280',
506 'uploader_url': 'https://vimeo.com/frameworkla',
605cad0b 507 },
605cad0b 508 },
c143ddce
S
509 {
510 # only available via https://vimeo.com/channels/tributes/6213729 and
511 # not via https://vimeo.com/6213729
512 'url': 'https://vimeo.com/channels/tributes/6213729',
513 'info_dict': {
514 'id': '6213729',
d03beddf 515 'ext': 'mp4',
c143ddce
S
516 'title': 'Vimeo Tribute: The Shining',
517 'uploader': 'Casey Donahue',
ec85ded8 518 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
c143ddce 519 'uploader_id': 'caseydonahue',
d03beddf
S
520 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
521 'channel_id': 'tributes',
c15cd296 522 'timestamp': 1250886430,
c143ddce
S
523 'upload_date': '20090821',
524 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
b9c7b1e9 525 'duration': 321,
526 'comment_count': int,
527 'view_count': int,
528 'thumbnail': 'https://i.vimeocdn.com/video/22728298-bfc22146f930de7cf497821c7b0b9f168099201ecca39b00b6bd31fcedfca7a6-d_1280',
529 'like_count': int,
c143ddce
S
530 },
531 'params': {
532 'skip_download': True,
533 },
c143ddce 534 },
f16f8505 535 {
cccd70a2 536 # redirects to ondemand extractor and should be passed through it
f16f8505
S
537 # for successful extraction
538 'url': 'https://vimeo.com/73445910',
539 'info_dict': {
540 'id': '73445910',
541 'ext': 'mp4',
542 'title': 'The Reluctant Revolutionary',
543 'uploader': '10Ft Films',
ec85ded8 544 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
f16f8505 545 'uploader_id': 'tenfootfilms',
681ac7c9
RA
546 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
547 'upload_date': '20130830',
548 'timestamp': 1377853339,
f16f8505
S
549 },
550 'params': {
551 'skip_download': True,
552 },
cce889b9 553 'skip': 'this page is no longer available.',
f16f8505 554 },
79fec976
RA
555 {
556 'url': 'http://player.vimeo.com/video/68375962',
557 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
558 'info_dict': {
559 'id': '68375962',
560 'ext': 'mp4',
3867038a 561 'title': 'youtube-dl password protected test video',
b9c7b1e9 562 'timestamp': 1371200155,
563 'upload_date': '20130614',
79fec976
RA
564 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
565 'uploader_id': 'user18948128',
566 'uploader': 'Jaime Marquínez Ferrándiz',
567 'duration': 10,
c0cd13fb
L
568 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
569 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
b9c7b1e9 570 'view_count': int,
571 'comment_count': int,
572 'like_count': int,
79fec976
RA
573 },
574 'params': {
681ac7c9 575 'format': 'best[protocol=https]',
3867038a 576 'videopassword': 'youtube-dl',
79fec976
RA
577 },
578 },
c143ddce
S
579 {
580 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
581 'only_matching': True,
582 },
8bea039b
LL
583 {
584 'url': 'https://vimeo.com/109815029',
585 'note': 'Video not completely processed, "failed" seed status',
586 'only_matching': True,
587 },
6b7ceee1
S
588 {
589 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
590 'only_matching': True,
591 },
c8e3e097
S
592 {
593 'url': 'https://vimeo.com/album/2632481/video/79010983',
594 'only_matching': True,
595 },
1f52a09e 596 {
597 'url': 'https://vimeo.com/showcase/3253534/video/119195465',
598 'note': 'A video in a password protected album (showcase)',
599 'info_dict': {
600 'id': '119195465',
601 'ext': 'mp4',
b9c7b1e9 602 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
1f52a09e 603 'uploader': 'Philipp Hagemeister',
604 'uploader_id': 'user20132939',
605 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
606 'upload_date': '20150209',
607 'timestamp': 1423518307,
b9c7b1e9 608 'thumbnail': 'https://i.vimeocdn.com/video/default_1280',
609 'duration': 10,
610 'like_count': int,
611 'uploader_url': 'https://vimeo.com/user20132939',
612 'view_count': int,
613 'comment_count': int,
1f52a09e 614 },
615 'params': {
616 'format': 'best[protocol=https]',
617 'videopassword': 'youtube-dl',
618 },
619 },
16f1131a
S
620 {
621 # source file returns 403: Forbidden
622 'url': 'https://vimeo.com/7809605',
623 'only_matching': True,
624 },
241a318f 625 {
2a6f8475 626 'note': 'Direct URL with hash',
241a318f 627 'url': 'https://vimeo.com/160743502/abd0e13fb4',
2a6f8475 628 'info_dict': {
629 'id': '160743502',
630 'ext': 'mp4',
631 'uploader': 'Julian Tryba',
632 'uploader_id': 'aliniamedia',
633 'title': 'Harrisville New Hampshire',
634 'timestamp': 1459259666,
635 'upload_date': '20160329',
b9c7b1e9 636 'release_timestamp': 1459259666,
637 'license': 'by-nc',
638 'duration': 159,
639 'comment_count': int,
640 'thumbnail': 'https://i.vimeocdn.com/video/562802436-585eeb13b5020c6ac0f171a2234067938098f84737787df05ff0d767f6d54ee9-d_1280',
641 'like_count': int,
642 'uploader_url': 'https://vimeo.com/aliniamedia',
643 'release_date': '20160329',
2a6f8475 644 },
9cb070f9 645 'params': {'skip_download': True},
646 },
647 {
648 'url': 'https://vimeo.com/138909882',
649 'info_dict': {
650 'id': '138909882',
651 'ext': 'mp4',
652 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!',
653 'description': 'md5:5967e090768a831488f6e74b7821b3c1',
654 'uploader_id': 'fireworkchampions',
655 'uploader': 'Firework Champions',
656 'upload_date': '20150910',
657 'timestamp': 1441901895,
658 },
659 'params': {
660 'skip_download': True,
661 'format': 'Original',
662 },
bc2ca1bb 663 },
1ee34c76 664 {
665 'url': 'https://vimeo.com/channels/staffpicks/143603739',
666 'info_dict': {
667 'id': '143603739',
668 'ext': 'mp4',
669 'uploader': 'Karim Huu Do',
670 'timestamp': 1445846953,
671 'upload_date': '20151026',
672 'title': 'The Shoes - Submarine Feat. Blaine Harrison',
673 'uploader_id': 'karimhd',
674 'description': 'md5:8e2eea76de4504c2e8020a9bcfa1e843',
b9c7b1e9 675 'channel_id': 'staffpicks',
676 'duration': 336,
677 'comment_count': int,
678 'view_count': int,
679 'thumbnail': 'https://i.vimeocdn.com/video/541243181-b593db36a16db2f0096f655da3f5a4dc46b8766d77b0f440df937ecb0c418347-d_1280',
680 'like_count': int,
681 'uploader_url': 'https://vimeo.com/karimhd',
682 'channel_url': 'https://vimeo.com/channels/staffpicks',
1ee34c76 683 },
684 'params': {'skip_download': 'm3u8'},
685 },
bc2ca1bb 686 {
687 # requires passing unlisted_hash(a52724358e) to load_download_config request
688 'url': 'https://vimeo.com/392479337/a52724358e',
689 'only_matching': True,
9cb070f9 690 },
50e93e03 691 {
692 # similar, but all numeric: ID must be 581039021, not 9603038895
693 # issue #29690
694 'url': 'https://vimeo.com/581039021/9603038895',
695 'info_dict': {
696 'id': '581039021',
50e93e03 697 'ext': 'mp4',
698 'timestamp': 1627621014,
b9c7b1e9 699 'release_timestamp': 1627621014,
700 'duration': 976,
701 'comment_count': int,
702 'thumbnail': 'https://i.vimeocdn.com/video/1202249320-4ddb2c30398c0dc0ee059172d1bd5ea481ad12f0e0e3ad01d2266f56c744b015-d_1280',
703 'like_count': int,
704 'uploader_url': 'https://vimeo.com/txwestcapital',
705 'release_date': '20210730',
706 'uploader': 'Christopher Inks',
707 'title': 'Thursday, July 29, 2021 BMA Evening Video Update',
708 'uploader_id': 'txwestcapital',
709 'upload_date': '20210730',
50e93e03 710 },
711 'params': {
712 'skip_download': True,
713 },
45b2ee6f 714 },
715 {
716 # user playlist alias -> https://vimeo.com/258705797
717 'url': 'https://vimeo.com/user26785108/newspiritualguide',
718 'only_matching': True,
719 },
a1a46075
S
720 # https://gettingthingsdone.com/workflowmap/
721 # vimeo embed with check-password page protected by Referer header
a91b954b 722 ]
b3d14cbf 723
bfd973ec 724 @classmethod
725 def _extract_embed_urls(cls, url, webpage):
726 for embed_url in super()._extract_embed_urls(url, webpage):
727 yield cls._smuggle_referrer(embed_url, url)
b407e173 728
4080efeb 729 @classmethod
730 def _extract_url(cls, url, webpage):
731 return next(cls._extract_embed_urls(url, webpage), None)
732
a1a46075 733 def _verify_player_video_password(self, url, video_id, headers):
cce889b9 734 password = self._get_video_password()
79fec976
RA
735 data = urlencode_postdata({
736 'password': base64.b64encode(password.encode()),
737 })
a1a46075
S
738 headers = merge_dicts(headers, {
739 'Content-Type': 'application/x-www-form-urlencoded',
740 })
741 checked = self._download_json(
aedaa455 742 f'{compat_urlparse.urlsplit(url)._replace(query=None).geturl()}/check-password',
743 video_id, 'Verifying the password', data=data, headers=headers)
a1a46075
S
744 if checked is False:
745 raise ExtractorError('Wrong video password', expected=True)
746 return checked
0eecc6a4 747
58ab5cbc 748 def _extract_from_api(self, video_id, unlisted_hash=None):
749 token = self._download_json(
750 'https://vimeo.com/_rv/jwt', video_id, headers={
751 'X-Requested-With': 'XMLHttpRequest'
752 })['token']
753 api_url = 'https://api.vimeo.com/videos/' + video_id
754 if unlisted_hash:
755 api_url += ':' + unlisted_hash
756 video = self._download_json(
757 api_url, video_id, headers={
758 'Authorization': 'jwt ' + token,
8e765755 759 'Accept': 'application/json',
58ab5cbc 760 }, query={
761 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
762 })
763 info = self._parse_config(self._download_json(
764 video['config_url'], video_id), video_id)
58ab5cbc 765 get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
766 info.update({
767 'description': video.get('description'),
768 'license': video.get('license'),
769 'release_timestamp': get_timestamp('release'),
770 'timestamp': get_timestamp('created'),
771 'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
772 })
773 connections = try_get(
774 video, lambda x: x['metadata']['connections'], dict) or {}
775 for k in ('comment', 'like'):
776 info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
777 return info
778
1f52a09e 779 def _try_album_password(self, url):
780 album_id = self._search_regex(
781 r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
782 if not album_id:
783 return
784 viewer = self._download_json(
785 'https://vimeo.com/_rv/viewer', album_id, fatal=False)
786 if not viewer:
787 webpage = self._download_webpage(url, album_id)
788 viewer = self._parse_json(self._search_regex(
789 r'bootstrap_data\s*=\s*({.+?})</script>',
790 webpage, 'bootstrap data'), album_id)['viewer']
791 jwt = viewer['jwt']
792 album = self._download_json(
793 'https://api.vimeo.com/albums/' + album_id,
8e765755 794 album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
1f52a09e 795 query={'fields': 'description,name,privacy'})
796 if try_get(album, lambda x: x['privacy']['view']) == 'password':
a06916d9 797 password = self.get_param('videopassword')
1f52a09e 798 if not password:
799 raise ExtractorError(
800 'This album is protected by a password, use the --video-password option',
801 expected=True)
802 self._set_vimeo_cookie('vuid', viewer['vuid'])
803 try:
804 self._download_json(
805 'https://vimeo.com/showcase/%s/auth' % album_id,
806 album_id, 'Verifying the password', data=urlencode_postdata({
807 'password': password,
808 'token': viewer['xsrft'],
809 }), headers={
810 'X-Requested-With': 'XMLHttpRequest',
811 })
812 except ExtractorError as e:
3d2623a8 813 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
1f52a09e 814 raise ExtractorError('Wrong password', expected=True)
815 raise
816
a0088bdf 817 def _real_extract(self, url):
aedaa455 818 url, data, headers = self._unsmuggle_headers(url)
ba5d51b3
PH
819 if 'Referer' not in headers:
820 headers['Referer'] = url
9d4660ca 821
b3d14cbf 822 # Extract ID from URL
2a6f8475 823 mobj = self._match_valid_url(url).groupdict()
824 video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
cce889b9 825 if unlisted_hash:
58ab5cbc 826 return self._extract_from_api(video_id, unlisted_hash)
cce889b9 827
7ff2fafe 828 if any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
10831b5e 829 url = 'https://vimeo.com/' + video_id
b3d14cbf 830
1f52a09e 831 self._try_album_password(url)
1060425c 832 try:
681ac7c9
RA
833 # Retrieve video webpage to extract further information
834 webpage, urlh = self._download_webpage_handle(
835 url, video_id, headers=headers)
3d2623a8 836 redirect_url = urlh.url
1060425c 837 except ExtractorError as ee:
3d2623a8 838 if isinstance(ee.cause, HTTPError) and ee.cause.status == 403:
839 errmsg = ee.cause.response.read()
1060425c
PH
840 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
841 raise ExtractorError(
842 'Cannot download embed-only video without embedding '
7a5c1cfe 843 'URL. Please call yt-dlp with the URL of the page '
1060425c
PH
844 'that embeds this video.',
845 expected=True)
846 raise
b3d14cbf 847
58ab5cbc 848 if '://player.vimeo.com/video/' in url:
c0cd13fb
L
849 config = self._search_json(
850 r'\b(?:playerC|c)onfig\s*=', webpage, 'info section', video_id)
58ab5cbc 851 if config.get('view') == 4:
852 config = self._verify_player_video_password(
853 redirect_url, video_id, headers)
9f14daf2 854 return self._parse_config(config, video_id)
58ab5cbc 855
856 if re.search(r'<form[^>]+?id="pw_form"', webpage):
857 video_password = self._get_video_password()
858 token, vuid = self._extract_xsrft_and_vuid(webpage)
859 webpage = self._verify_video_password(
860 redirect_url, video_id, video_password, token, vuid)
b3d14cbf 861
eb9c9c74 862 vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
998e6cdb 863 if vimeo_config:
58ab5cbc 864 seed_status = vimeo_config.get('seed_status') or {}
998e6cdb
S
865 if seed_status.get('state') == 'failed':
866 raise ExtractorError(
b6aa99af 867 '%s said: %s' % (self.IE_NAME, seed_status['title']),
998e6cdb
S
868 expected=True)
869
c38a67bc 870 cc_license = None
c15cd296 871 timestamp = None
681ac7c9 872 video_description = None
58ab5cbc 873 info_dict = {}
1ee34c76 874 config_url = None
c38a67bc 875
58ab5cbc 876 channel_id = self._search_regex(
877 r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
878 if channel_id:
879 config_url = self._html_search_regex(
1ee34c76 880 r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
58ab5cbc 881 video_description = clean_html(get_element_by_class('description', webpage))
882 info_dict.update({
883 'channel_id': channel_id,
884 'channel_url': 'https://vimeo.com/channels/' + channel_id,
885 })
1ee34c76 886 if not config_url:
58ab5cbc 887 page_config = self._parse_json(self._search_regex(
888 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
889 webpage, 'page config', default='{}'), video_id, fatal=False)
890 if not page_config:
891 return self._extract_from_api(video_id)
892 config_url = page_config['player']['config_url']
893 cc_license = page_config.get('cc_license')
894 clip = page_config.get('clip') or {}
895 timestamp = clip.get('uploaded_on')
896 video_description = clean_html(
897 clip.get('description') or page_config.get('description_html_escaped'))
898 config = self._download_json(config_url, video_id)
bc2ca1bb 899 video = config.get('video') or {}
900 vod = video.get('vod') or {}
8b40c927 901
6a55bb66
S
902 def is_rented():
903 if '>You rented this title.<' in webpage:
904 return True
58ab5cbc 905 if try_get(config, lambda x: x['user']['purchased']):
6a55bb66 906 return True
58ab5cbc 907 for purchase_option in (vod.get('purchase_options') or []):
8b40c927
RA
908 if purchase_option.get('purchased'):
909 return True
910 label = purchase_option.get('label_string')
911 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
912 return True
6a55bb66
S
913 return False
914
8b40c927
RA
915 if is_rented() and vod.get('is_trailer'):
916 feature_id = vod.get('feature_id')
5dbe81a1
S
917 if feature_id and not data.get('force_feature_id', False):
918 return self.url_result(smuggle_url(
919 'https://player.vimeo.com/player/%s' % feature_id,
920 {'force_feature_id': True}), 'Vimeo')
921
681ac7c9
RA
922 if not video_description:
923 video_description = self._html_search_regex(
924 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
925 webpage, 'description', default=None)
58ea7ec8
PH
926 if not video_description:
927 video_description = self._html_search_meta(
58ab5cbc 928 ['description', 'og:description', 'twitter:description'],
929 webpage, default=None)
58ab5cbc 930 if not video_description:
6a39ee13 931 self.report_warning('Cannot find video description')
b3d14cbf 932
c15cd296
S
933 if not timestamp:
934 timestamp = self._search_regex(
935 r'<time[^>]+datetime="([^"]+)"', webpage,
936 'timestamp', default=None)
b3d14cbf 937
58ab5cbc 938 view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None))
939 like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None))
940 comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None))
4e761794 941
a6387bfd 942 formats = []
27655037
RA
943
944 source_format = self._extract_original_format(
bc2ca1bb 945 'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
27655037
RA
946 if source_format:
947 formats.append(source_format)
1eac553e 948
ae1c585c
S
949 info_dict_config = self._parse_config(config, video_id)
950 formats.extend(info_dict_config['formats'])
9f14daf2 951 info_dict['_format_sort_fields'] = info_dict_config['_format_sort_fields']
c38a67bc 952
ae1c585c
S
953 json_ld = self._search_json_ld(webpage, video_id, default={})
954
c38a67bc
S
955 if not cc_license:
956 cc_license = self._search_regex(
957 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
958 webpage, 'license', default=None, group='license')
959
58ab5cbc 960 info_dict.update({
531a7496 961 'formats': formats,
c15cd296 962 'timestamp': unified_timestamp(timestamp),
b0268cb6 963 'description': video_description,
9103bbc5 964 'webpage_url': url,
4e761794
JMF
965 'view_count': view_count,
966 'like_count': like_count,
967 'comment_count': comment_count,
c38a67bc 968 'license': cc_license,
58ab5cbc 969 })
531a7496 970
58ab5cbc 971 return merge_dicts(info_dict, info_dict_config, json_ld)
caeefc29
JMF
972
973
6368e2e6 974class VimeoOndemandIE(VimeoIE): # XXX: Do not subclass from concrete IE
1e501364 975 IE_NAME = 'vimeo:ondemand'
58ab5cbc 976 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
74278def
S
977 _TESTS = [{
978 # ondemand video not available via https://vimeo.com/id
979 'url': 'https://vimeo.com/ondemand/20704',
980 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
981 'info_dict': {
982 'id': '105442900',
983 'ext': 'mp4',
984 'title': 'המעבדה - במאי יותם פלדמן',
985 'uploader': 'גם סרטים',
ec85ded8 986 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
74278def 987 'uploader_id': 'gumfilms',
b9c7b1e9 988 'description': 'md5:aeeba3dbd4d04b0fa98a4fdc9c639998',
681ac7c9
RA
989 'upload_date': '20140906',
990 'timestamp': 1410032453,
b9c7b1e9 991 'thumbnail': 'https://i.vimeocdn.com/video/488238335-d7bf151c364cff8d467f1b73784668fe60aae28a54573a35d53a1210ae283bd8-d_1280',
992 'comment_count': int,
993 'license': 'https://creativecommons.org/licenses/by-nc-nd/3.0/',
994 'duration': 53,
995 'view_count': int,
996 'like_count': int,
74278def 997 },
1fd0fc42
S
998 'params': {
999 'format': 'best[protocol=https]',
1000 },
681ac7c9 1001 'expected_warnings': ['Unable to download JSON metadata'],
d002e919
S
1002 }, {
1003 # requires Referer to be passed along with og:video:url
1004 'url': 'https://vimeo.com/ondemand/36938/126682985',
1005 'info_dict': {
681ac7c9 1006 'id': '126584684',
d002e919
S
1007 'ext': 'mp4',
1008 'title': 'Rävlock, rätt läte på rätt plats',
1009 'uploader': 'Lindroth & Norin',
681ac7c9
RA
1010 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
1011 'uploader_id': 'lindrothnorin',
1012 'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
1013 'upload_date': '20150502',
1014 'timestamp': 1430586422,
b9c7b1e9 1015 'duration': 121,
1016 'comment_count': int,
1017 'view_count': int,
1018 'thumbnail': 'https://i.vimeocdn.com/video/517077723-7066ae1d9a79d3eb361334fb5d58ec13c8f04b52f8dd5eadfbd6fb0bcf11f613-d_1280',
1019 'like_count': int,
d002e919
S
1020 },
1021 'params': {
1022 'skip_download': True,
1023 },
681ac7c9 1024 'expected_warnings': ['Unable to download JSON metadata'],
74278def
S
1025 }, {
1026 'url': 'https://vimeo.com/ondemand/nazmaalik',
1027 'only_matching': True,
1028 }, {
1029 'url': 'https://vimeo.com/ondemand/141692381',
1030 'only_matching': True,
1031 }, {
1032 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
1033 'only_matching': True,
1034 }]
1035
74278def 1036
f6c3664d 1037class VimeoChannelIE(VimeoBaseInfoExtractor):
9148eb00 1038 IE_NAME = 'vimeo:channel'
3946864c 1039 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
caeefc29 1040 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
84458766 1041 _TITLE = None
55a10eab 1042 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
2929b3e7 1043 _TESTS = [{
3946864c 1044 'url': 'https://vimeo.com/channels/tributes',
2929b3e7 1045 'info_dict': {
a3fa5da4 1046 'id': 'tributes',
2929b3e7
PH
1047 'title': 'Vimeo Tributes',
1048 },
b9c7b1e9 1049 'playlist_mincount': 22,
2929b3e7 1050 }]
681ac7c9 1051 _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
caeefc29 1052
5cc14c2f
JMF
1053 def _page_url(self, base_url, pagenum):
1054 return '%s/videos/page:%d/' % (base_url, pagenum)
1055
fb30ec22 1056 def _extract_list_title(self, webpage):
2605043d
S
1057 return self._TITLE or self._html_search_regex(
1058 self._TITLE_RE, webpage, 'list title', fatal=False)
fb30ec22 1059
2c94198e 1060 def _title_and_entries(self, list_id, base_url):
caeefc29 1061 for pagenum in itertools.count(1):
bf8f082a 1062 page_url = self._page_url(base_url, pagenum)
55a10eab 1063 webpage = self._download_webpage(
bf8f082a 1064 page_url, list_id,
9148eb00 1065 'Downloading page %s' % pagenum)
bf8f082a
PH
1066
1067 if pagenum == 1:
2c94198e
S
1068 yield self._extract_list_title(webpage)
1069
c8e3e097
S
1070 # Try extracting href first since not all videos are available via
1071 # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
1072 clips = re.findall(
04a3d4d2 1073 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
c8e3e097 1074 if clips:
04a3d4d2 1075 for video_id, video_url, video_title in clips:
c8e3e097
S
1076 yield self.url_result(
1077 compat_urlparse.urljoin(base_url, video_url),
04a3d4d2 1078 VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
c8e3e097
S
1079 # More relaxed fallback
1080 else:
1081 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
1082 yield self.url_result(
1083 'https://vimeo.com/%s' % video_id,
1084 VimeoIE.ie_key(), video_id=video_id)
bf8f082a 1085
caeefc29
JMF
1086 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1087 break
1088
2c94198e
S
1089 def _extract_videos(self, list_id, base_url):
1090 title_and_entries = self._title_and_entries(list_id, base_url)
1091 list_title = next(title_and_entries)
1092 return self.playlist_result(title_and_entries, list_id, list_title)
55a10eab
JMF
1093
1094 def _real_extract(self, url):
681ac7c9
RA
1095 channel_id = self._match_id(url)
1096 return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
55a10eab
JMF
1097
1098
6368e2e6 1099class VimeoUserIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
9148eb00 1100 IE_NAME = 'vimeo:user'
1d64a595 1101 _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos)?/?(?:$|[?#])'
55a10eab 1102 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
2929b3e7 1103 _TESTS = [{
3946864c 1104 'url': 'https://vimeo.com/nkistudio/videos',
2929b3e7
PH
1105 'info_dict': {
1106 'title': 'Nki',
a3fa5da4 1107 'id': 'nkistudio',
2929b3e7
PH
1108 },
1109 'playlist_mincount': 66,
1d64a595 1110 }, {
1111 'url': 'https://vimeo.com/nkistudio/',
1112 'only_matching': True,
2929b3e7 1113 }]
681ac7c9 1114 _BASE_URL_TEMPL = 'https://vimeo.com/%s'
5cc14c2f
JMF
1115
1116
51c7f40c 1117class VimeoAlbumIE(VimeoBaseInfoExtractor):
9148eb00 1118 IE_NAME = 'vimeo:album'
eb9c9c74 1119 _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
5cc14c2f 1120 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
2929b3e7 1121 _TESTS = [{
d1508cd6 1122 'url': 'https://vimeo.com/album/2632481',
2929b3e7 1123 'info_dict': {
a3fa5da4 1124 'id': '2632481',
2929b3e7
PH
1125 'title': 'Staff Favorites: November 2013',
1126 },
1127 'playlist_mincount': 13,
bf8f082a
PH
1128 }, {
1129 'note': 'Password-protected album',
1130 'url': 'https://vimeo.com/album/3253534',
1131 'info_dict': {
1132 'title': 'test',
1133 'id': '3253534',
1134 },
1135 'playlist_count': 1,
1136 'params': {
3867038a 1137 'videopassword': 'youtube-dl',
bf8f082a 1138 }
2929b3e7 1139 }]
eb9c9c74
RA
1140 _PAGE_SIZE = 100
1141
a0566bbf 1142 def _fetch_page(self, album_id, authorization, hashed_pass, page):
eb9c9c74
RA
1143 api_page = page + 1
1144 query = {
974311b5 1145 'fields': 'link,uri',
eb9c9c74
RA
1146 'page': api_page,
1147 'per_page': self._PAGE_SIZE,
1148 }
1149 if hashed_pass:
1150 query['_hashed_pass'] = hashed_pass
421a4595 1151 try:
1152 videos = self._download_json(
1153 'https://api.vimeo.com/albums/%s/videos' % album_id,
1154 album_id, 'Downloading page %d' % api_page, query=query, headers={
1155 'Authorization': 'jwt ' + authorization,
8e765755 1156 'Accept': 'application/json',
421a4595 1157 })['data']
1158 except ExtractorError as e:
3d2623a8 1159 if isinstance(e.cause, HTTPError) and e.cause.status == 400:
421a4595 1160 return
8e765755 1161 raise
eb9c9c74
RA
1162 for video in videos:
1163 link = video.get('link')
1164 if not link:
1165 continue
974311b5
RA
1166 uri = video.get('uri')
1167 video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
1168 yield self.url_result(link, VimeoIE.ie_key(), video_id)
5cc14c2f
JMF
1169
1170 def _real_extract(self, url):
bf8f082a 1171 album_id = self._match_id(url)
8bdd16b4 1172 viewer = self._download_json(
1173 'https://vimeo.com/_rv/viewer', album_id, fatal=False)
1174 if not viewer:
1175 webpage = self._download_webpage(url, album_id)
1176 viewer = self._parse_json(self._search_regex(
1177 r'bootstrap_data\s*=\s*({.+?})</script>',
1178 webpage, 'bootstrap data'), album_id)['viewer']
51c7f40c
RA
1179 jwt = viewer['jwt']
1180 album = self._download_json(
1181 'https://api.vimeo.com/albums/' + album_id,
8e765755 1182 album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
51c7f40c
RA
1183 query={'fields': 'description,name,privacy'})
1184 hashed_pass = None
1185 if try_get(album, lambda x: x['privacy']['view']) == 'password':
a06916d9 1186 password = self.get_param('videopassword')
51c7f40c
RA
1187 if not password:
1188 raise ExtractorError(
1189 'This album is protected by a password, use the --video-password option',
1190 expected=True)
1191 self._set_vimeo_cookie('vuid', viewer['vuid'])
1192 try:
1193 hashed_pass = self._download_json(
1194 'https://vimeo.com/showcase/%s/auth' % album_id,
1195 album_id, 'Verifying the password', data=urlencode_postdata({
1196 'password': password,
1197 'token': viewer['xsrft'],
1198 }), headers={
1199 'X-Requested-With': 'XMLHttpRequest',
1200 })['hashed_pass']
1201 except ExtractorError as e:
3d2623a8 1202 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
51c7f40c
RA
1203 raise ExtractorError('Wrong password', expected=True)
1204 raise
eb9c9c74 1205 entries = OnDemandPagedList(functools.partial(
51c7f40c
RA
1206 self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
1207 return self.playlist_result(
1208 entries, album_id, album.get('name'), album.get('description'))
fb30ec22
JMF
1209
1210
6368e2e6 1211class VimeoGroupsIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
9148eb00 1212 IE_NAME = 'vimeo:group'
681ac7c9 1213 _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
2929b3e7 1214 _TESTS = [{
9cb070f9 1215 'url': 'https://vimeo.com/groups/meetup',
2929b3e7 1216 'info_dict': {
9cb070f9 1217 'id': 'meetup',
1218 'title': 'Vimeo Meetup!',
2929b3e7 1219 },
681ac7c9 1220 'playlist_mincount': 27,
2929b3e7 1221 }]
681ac7c9 1222 _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
fcea44c6
PH
1223
1224
531a7496 1225class VimeoReviewIE(VimeoBaseInfoExtractor):
9148eb00
PH
1226 IE_NAME = 'vimeo:review'
1227 IE_DESC = 'Review pages on vimeo'
27655037 1228 _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
d36d3f42 1229 _TESTS = [{
fcea44c6 1230 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
fcea44c6
PH
1231 'md5': 'c507a72f780cacc12b2248bb4006d253',
1232 'info_dict': {
fc09240e
PH
1233 'id': '75524534',
1234 'ext': 'mp4',
fcea44c6
PH
1235 'title': "DICK HARDWICK 'Comedian'",
1236 'uploader': 'Richard Hardwick',
531a7496 1237 'uploader_id': 'user21297594',
681ac7c9 1238 'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
b9c7b1e9 1239 'duration': 304,
1240 'thumbnail': 'https://i.vimeocdn.com/video/450115033-43303819d9ebe24c2630352e18b7056d25197d09b3ae901abdac4c4f1d68de71-d_1280',
1241 'uploader_url': 'https://vimeo.com/user21297594',
681ac7c9 1242 },
d36d3f42
PH
1243 }, {
1244 'note': 'video player needs Referer',
3946864c 1245 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
d36d3f42
PH
1246 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1247 'info_dict': {
1248 'id': '91613211',
1249 'ext': 'mp4',
9dec9930 1250 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
d36d3f42
PH
1251 'uploader': 'DevWeek Events',
1252 'duration': 2773,
ec85ded8 1253 'thumbnail': r're:^https?://.*\.jpg$',
531a7496 1254 'uploader_id': 'user22258446',
681ac7c9
RA
1255 },
1256 'skip': 'video gone',
c1ff6e1a
YCH
1257 }, {
1258 'note': 'Password protected',
1259 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1260 'info_dict': {
1261 'id': '138823582',
1262 'ext': 'mp4',
1263 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1264 'uploader': 'TMB',
1265 'uploader_id': 'user37284429',
1266 },
1267 'params': {
1268 'videopassword': 'holygrail',
1269 },
a093cfc7 1270 'skip': 'video gone',
d36d3f42 1271 }]
fcea44c6
PH
1272
1273 def _real_extract(self, url):
5ad28e7f 1274 page_url, video_id = self._match_valid_url(url).groups()
cce889b9 1275 data = self._download_json(
1276 page_url.replace('/review/', '/review/data/'), video_id)
1277 if data.get('isLocked') is True:
1278 video_password = self._get_video_password()
1279 viewer = self._download_json(
1280 'https://vimeo.com/_rv/viewer', video_id)
1281 webpage = self._verify_video_password(
1282 'https://vimeo.com/' + video_id, video_id,
1283 video_password, viewer['xsrft'], viewer['vuid'])
1284 clip_page_config = self._parse_json(self._search_regex(
1285 r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
1286 webpage, 'clip page config'), video_id)
1287 config_url = clip_page_config['player']['config_url']
1288 clip_data = clip_page_config.get('clip') or {}
1289 else:
1290 clip_data = data['clipData']
1291 config_url = clip_data['configUrl']
c1ff6e1a 1292 config = self._download_json(config_url, video_id)
531a7496 1293 info_dict = self._parse_config(config, video_id)
681ac7c9
RA
1294 source_format = self._extract_original_format(
1295 page_url + '/action', video_id)
27655037
RA
1296 if source_format:
1297 info_dict['formats'].append(source_format)
681ac7c9 1298 info_dict['description'] = clean_html(clip_data.get('description'))
531a7496 1299 return info_dict
efb7e119
JMF
1300
1301
6368e2e6 1302class VimeoWatchLaterIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
efb7e119 1303 IE_NAME = 'vimeo:watchlater'
8dcce6a8 1304 IE_DESC = 'Vimeo watch later list, ":vimeowatchlater" keyword (requires authentication)'
84458766
S
1305 _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1306 _TITLE = 'Watch Later'
efb7e119 1307 _LOGIN_REQUIRED = True
2929b3e7 1308 _TESTS = [{
84458766 1309 'url': 'https://vimeo.com/watchlater',
2929b3e7
PH
1310 'only_matching': True,
1311 }]
efb7e119 1312
efb7e119
JMF
1313 def _page_url(self, base_url, pagenum):
1314 url = '%s/page:%d/' % (base_url, pagenum)
3d2623a8 1315 request = Request(url)
efb7e119
JMF
1316 # Set the header to get a partial html page with the ids,
1317 # the normal page doesn't contain them.
3d2623a8 1318 request.headers['X-Requested-With'] = 'XMLHttpRequest'
efb7e119
JMF
1319 return request
1320
1321 def _real_extract(self, url):
84458766 1322 return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
d6e6a422
PH
1323
1324
6368e2e6 1325class VimeoLikesIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
361a965b 1326 _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
d6e6a422
PH
1327 IE_NAME = 'vimeo:likes'
1328 IE_DESC = 'Vimeo user likes'
361a965b 1329 _TESTS = [{
9c44d242
PH
1330 'url': 'https://vimeo.com/user755559/likes/',
1331 'playlist_mincount': 293,
611c1dd9 1332 'info_dict': {
091c9b43
S
1333 'id': 'user755559',
1334 'title': 'urza’s Likes',
d6e6a422 1335 },
361a965b
S
1336 }, {
1337 'url': 'https://vimeo.com/stormlapse/likes',
1338 'only_matching': True,
1339 }]
d6e6a422 1340
091c9b43
S
1341 def _page_url(self, base_url, pagenum):
1342 return '%s/page:%d/' % (base_url, pagenum)
1343
d6e6a422
PH
1344 def _real_extract(self, url):
1345 user_id = self._match_id(url)
091c9b43 1346 return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
ca01d178
RA
1347
1348
a1ee23e9 1349class VHXEmbedIE(VimeoBaseInfoExtractor):
ca01d178
RA
1350 IE_NAME = 'vhx:embed'
1351 _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
bfd973ec 1352 _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://embed\.vhx\.tv/videos/\d+[^"]*)"']
ca01d178 1353
bfd973ec 1354 @classmethod
1355 def _extract_embed_urls(cls, url, webpage):
1356 for embed_url in super()._extract_embed_urls(url, webpage):
1357 yield cls._smuggle_referrer(embed_url, url)
29f7c58a 1358
ca01d178
RA
1359 def _real_extract(self, url):
1360 video_id = self._match_id(url)
aedaa455 1361 url, _, headers = self._unsmuggle_headers(url)
1362 webpage = self._download_webpage(url, video_id, headers=headers)
a1ee23e9
RA
1363 config_url = self._parse_json(self._search_regex(
1364 r'window\.OTTData\s*=\s*({.+})', webpage,
1365 'ott data'), video_id, js_to_json)['config_url']
1366 config = self._download_json(config_url, video_id)
1367 info = self._parse_config(config, video_id)
29f7c58a 1368 info['id'] = video_id
a1ee23e9 1369 return info
7ff2fafe 1370
1371
1372class VimeoProIE(VimeoBaseInfoExtractor):
1373 IE_NAME = 'vimeo:pro'
1374 _VALID_URL = r'https?://(?:www\.)?vimeopro\.com/[^/?#]+/(?P<slug>[^/?#]+)(?:(?:/videos?/(?P<id>[0-9]+)))?'
1375 _TESTS = [{
1376 # Vimeo URL derived from video_id
1377 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
1378 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
1379 'note': 'Vimeo Pro video (#1197)',
1380 'info_dict': {
1381 'id': '68093876',
1382 'ext': 'mp4',
1383 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
1384 'uploader_id': 'openstreetmapus',
1385 'uploader': 'OpenStreetMap US',
1386 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
1387 'description': 'md5:2c362968038d4499f4d79f88458590c1',
1388 'duration': 1595,
1389 'upload_date': '20130610',
1390 'timestamp': 1370893156,
1391 'license': 'by',
1392 'thumbnail': 'https://i.vimeocdn.com/video/440260469-19b0d92fca3bd84066623b53f1eb8aaa3980c6c809e2d67b6b39ab7b4a77a344-d_960',
1393 'view_count': int,
1394 'comment_count': int,
1395 'like_count': int,
1396 'tags': 'count:1',
1397 },
1398 'params': {
1399 'format': 'best[protocol=https]',
1400 },
1401 }, {
1402 # password-protected VimeoPro page with Vimeo player embed
1403 'url': 'https://vimeopro.com/cadfem/simulation-conference-mechanische-systeme-in-perfektion',
1404 'info_dict': {
1405 'id': '764543723',
1406 'ext': 'mp4',
1407 'title': 'Mechanische Systeme in Perfektion: Realität erfassen, Innovation treiben',
1408 'thumbnail': 'https://i.vimeocdn.com/video/1543784598-a1a750494a485e601110136b9fe11e28c2131942452b3a5d30391cb3800ca8fd-d_1280',
1409 'description': 'md5:2a9d195cd1b0f6f79827107dc88c2420',
1410 'uploader': 'CADFEM',
1411 'uploader_id': 'cadfem',
1412 'uploader_url': 'https://vimeo.com/cadfem',
1413 'duration': 12505,
1414 'chapters': 'count:10',
1415 },
1416 'params': {
1417 'videopassword': 'Conference2022',
1418 'skip_download': True,
1419 },
1420 }]
1421
1422 def _real_extract(self, url):
1423 display_id, video_id = self._match_valid_url(url).group('slug', 'id')
1424 if video_id:
1425 display_id = video_id
1426 webpage = self._download_webpage(url, display_id)
1427
1428 password_form = self._search_regex(
1429 r'(?is)<form[^>]+?method=["\']post["\'][^>]*>(.+?password.+?)</form>',
1430 webpage, 'password form', default=None)
1431 if password_form:
1432 try:
1433 webpage = self._download_webpage(url, display_id, data=urlencode_postdata({
1434 'password': self._get_video_password(),
1435 **self._hidden_inputs(password_form),
1436 }), note='Logging in with video password')
1437 except ExtractorError as e:
3d2623a8 1438 if isinstance(e.cause, HTTPError) and e.cause.status == 418:
7ff2fafe 1439 raise ExtractorError('Wrong video password', expected=True)
1440 raise
1441
1442 description = None
1443 # even if we have video_id, some videos require player URL with portfolio_id query param
1444 # https://github.com/ytdl-org/youtube-dl/issues/20070
1445 vimeo_url = VimeoIE._extract_url(url, webpage)
1446 if vimeo_url:
1447 description = self._html_search_meta('description', webpage, default=None)
1448 elif video_id:
1449 vimeo_url = f'https://vimeo.com/{video_id}'
1450 else:
1451 raise ExtractorError(
1452 'No Vimeo embed or video ID could be found in VimeoPro page', expected=True)
1453
1454 return self.url_result(vimeo_url, VimeoIE, video_id, url_transparent=True,
1455 description=description)