]> jfr.im git - yt-dlp.git/blame_incremental - yt_dlp/extractor/vimeo.py
fix motherless
[yt-dlp.git] / yt_dlp / extractor / vimeo.py
... / ...
CommitLineData
1import base64
2import functools
3import itertools
4import re
5import urllib.parse
6
7from .common import InfoExtractor
8from ..networking import HEADRequest, Request
9from ..networking.exceptions import HTTPError
10from ..utils import (
11 ExtractorError,
12 OnDemandPagedList,
13 clean_html,
14 determine_ext,
15 get_element_by_class,
16 int_or_none,
17 js_to_json,
18 merge_dicts,
19 parse_filesize,
20 parse_iso8601,
21 parse_qs,
22 smuggle_url,
23 str_or_none,
24 traverse_obj,
25 try_get,
26 unified_timestamp,
27 unsmuggle_url,
28 urlencode_postdata,
29 urlhandle_detect_ext,
30 urljoin,
31)
32
33
34class VimeoBaseInfoExtractor(InfoExtractor):
35 _NETRC_MACHINE = 'vimeo'
36 _LOGIN_REQUIRED = False
37 _LOGIN_URL = 'https://vimeo.com/log_in'
38
39 @staticmethod
40 def _smuggle_referrer(url, referrer_url):
41 return smuggle_url(url, {'referer': referrer_url})
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()
47 if 'referer' in data:
48 headers['Referer'] = data['referer']
49 return url, data, headers
50
51 def _perform_login(self, username, password):
52 viewer = self._download_json('https://vimeo.com/_next/viewer', None, 'Downloading login token')
53 data = {
54 'action': 'login',
55 'email': username,
56 'password': password,
57 'service': 'vimeo',
58 'token': viewer['xsrft'],
59 }
60 self._set_vimeo_cookie('vuid', viewer['vuid'])
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:
69 if isinstance(e.cause, HTTPError) and e.cause.status == 418:
70 raise ExtractorError(
71 'Unable to log in: bad username or password',
72 expected=True)
73 raise ExtractorError('Unable to log in')
74
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
79 def _get_video_password(self):
80 password = self.get_param('videopassword')
81 if password is None:
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):
88 if url.startswith('http://'):
89 # vimeo only supports https now, but the user can give an http url
90 url = url.replace('http://', 'https://')
91 self._set_vimeo_cookie('vuid', vuid)
92 return self._download_webpage(
93 url + '/password', video_id, 'Verifying the password',
94 'Wrong password', data=urlencode_postdata({
95 'password': password,
96 'token': token,
97 }), headers={
98 'Content-Type': 'application/x-www-form-urlencoded',
99 'Referer': url,
100 })
101
102 def _extract_xsrft_and_vuid(self, webpage):
103 xsrft = self._search_regex(
104 r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
105 webpage, 'login token', group='xsrft')
106 vuid = self._search_regex(
107 r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
108 webpage, 'vuid', group='vuid')
109 return xsrft, vuid
110
111 def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
112 vimeo_config = self._search_regex(
113 r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
114 webpage, 'vimeo config', *args, **kwargs)
115 if vimeo_config:
116 return self._parse_json(vimeo_config, video_id)
117
118 def _set_vimeo_cookie(self, name, value):
119 self._set_cookie('vimeo.com', name, value)
120
121 def _parse_config(self, config, video_id):
122 video_data = config['video']
123 video_title = video_data.get('title')
124 live_event = video_data.get('live_event') or {}
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'
132 request = config.get('request') or {}
133
134 formats = []
135 subtitles = {}
136
137 config_files = video_data.get('files') or request.get('files') or {}
138 for f in (config_files.get('progressive') or []):
139 video_url = f.get('url')
140 if not video_url:
141 continue
142 formats.append({
143 'url': video_url,
144 'format_id': 'http-{}'.format(f.get('quality')),
145 'source_preference': 10,
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 })
151
152 # TODO: fix handling of 308 status code returned for live archive manifest requests
153 sep_pattern = r'/sep/video/'
154 for files_type in ('hls', 'dash'):
155 for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
156 manifest_url = cdn_data.get('url')
157 if not manifest_url:
158 continue
159 format_id = f'{files_type}-{cdn_name}'
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, f'/{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':
169 fmts, subs = self._extract_m3u8_formats_and_subtitles(
170 m_url, video_id, 'mp4', live=is_live, m3u8_id=f_id,
171 note=f'Downloading {cdn_name} m3u8 information',
172 fatal=False)
173 formats.extend(fmts)
174 self._merge_subtitles(subs, target=subtitles)
175 elif files_type == 'dash':
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
180 fmts, subs = self._extract_mpd_formats_and_subtitles(
181 m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
182 f'Downloading {cdn_name} MPD information',
183 fatal=False)
184 formats.extend(fmts)
185 self._merge_subtitles(subs, target=subtitles)
186
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,
193 'quality': 10,
194 })
195
196 for tt in (request.get('text_tracks') or []):
197 subtitles.setdefault(tt['lang'], []).append({
198 'ext': 'vtt',
199 'url': urljoin('https://vimeo.com', tt['url']),
200 })
201
202 thumbnails = []
203 if not is_live:
204 for key, thumb in (video_data.get('thumbs') or {}).items():
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
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
229 return {
230 'id': str_or_none(video_data.get('id')) or video_id,
231 'title': video_title,
232 'uploader': owner.get('name'),
233 'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
234 'uploader_url': video_uploader_url,
235 'thumbnails': thumbnails,
236 'duration': duration,
237 'chapters': chapters or None,
238 'formats': formats,
239 'subtitles': subtitles,
240 'live_status': live_status,
241 'release_timestamp': traverse_obj(live_event, ('ingest', 'scheduled_start_time', {parse_iso8601})),
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'),
245 }
246
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
251 download_data = self._download_json(
252 url, video_id, fatal=False, query=query,
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, f'{source_name} video'):
260 ext = (try_get(
261 source_file, lambda x: x['extension'],
262 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 }
273
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
278 headers = {'Authorization': 'jwt {}'.format(jwt_response['jwt']), 'Accept': 'application/json'}
279 original_response = self._download_json(
280 f'https://api.vimeo.com/videos/{video_id}', video_id,
281 headers=headers, fatal=False, expected_status=(403, 404)) or {}
282 for download_data in original_response.get('download') or []:
283 download_url = download_data.get('link')
284 if not download_url or download_data.get('quality') != 'source':
285 continue
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)
291 return {
292 'url': download_url,
293 'ext': ext or 'unknown_video',
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
302
303class VimeoIE(VimeoBaseInfoExtractor):
304 """Information extractor for vimeo.com."""
305
306 # _VALID_URL matches Vimeo URLs
307 _VALID_URL = r'''(?x)
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 '''
335 IE_NAME = 'vimeo'
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 ]
344 _TESTS = [
345 {
346 'url': 'http://vimeo.com/56015672#at=0',
347 'md5': '8879b6cc097e987f02484baf890129e5',
348 'info_dict': {
349 'id': '56015672',
350 'ext': 'mp4',
351 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
352 'description': 'md5:2d3305bad981a06ff79f027f19865021',
353 'timestamp': 1355990239,
354 'upload_date': '20121220',
355 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
356 'uploader_id': 'user7108434',
357 'uploader': 'Filippo Valsorda',
358 'duration': 10,
359 'license': 'by-sa',
360 },
361 'params': {
362 'format': 'best[protocol=https]',
363 },
364 'skip': 'No longer available',
365 },
366 {
367 'url': 'http://player.vimeo.com/video/54469442',
368 'md5': '619b811a4417aa4abe78dc653becf511',
369 'note': 'Videos that embed the url in the player page',
370 'info_dict': {
371 'id': '54469442',
372 'ext': 'mp4',
373 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
374 'uploader': 'Business of Software',
375 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
376 'uploader_id': 'businessofsoftware',
377 'duration': 3610,
378 'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d_1280',
379 },
380 'params': {
381 'format': 'best[protocol=https]',
382 },
383 },
384 {
385 'url': 'http://vimeo.com/68375962',
386 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
387 'note': 'Video protected with password',
388 'info_dict': {
389 'id': '68375962',
390 'ext': 'mp4',
391 'title': 'youtube-dl password protected test video',
392 'timestamp': 1371200155,
393 'upload_date': '20130614',
394 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
395 'uploader_id': 'user18948128',
396 'uploader': 'Jaime Marquínez Ferrándiz',
397 'duration': 10,
398 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
399 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
400 'view_count': int,
401 'comment_count': int,
402 'like_count': int,
403 },
404 'params': {
405 'format': 'best[protocol=https]',
406 'videopassword': 'youtube-dl',
407 },
408 },
409 {
410 'url': 'http://vimeo.com/channels/keypeele/75629013',
411 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
412 'info_dict': {
413 'id': '75629013',
414 'ext': 'mp4',
415 'title': 'Key & Peele: Terrorist Interrogation',
416 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
417 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
418 'uploader_id': 'atencio',
419 'uploader': 'Peter Atencio',
420 'channel_id': 'keypeele',
421 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
422 'timestamp': 1380339469,
423 'upload_date': '20130928',
424 'duration': 187,
425 'thumbnail': 'https://i.vimeocdn.com/video/450239872-a05512d9b1e55d707a7c04365c10980f327b06d966351bc403a5d5d65c95e572-d_1280',
426 'view_count': int,
427 'comment_count': int,
428 'like_count': int,
429 },
430 'params': {'format': 'http-1080p'},
431 },
432 {
433 'url': 'http://vimeo.com/76979871',
434 'note': 'Video with subtitles',
435 'info_dict': {
436 'id': '76979871',
437 'ext': 'mov',
438 'title': 'The New Vimeo Player (You Know, For Videos)',
439 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
440 'timestamp': 1381846109,
441 'upload_date': '20131015',
442 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
443 'uploader_id': 'staff',
444 'uploader': 'Vimeo Staff',
445 'duration': 62,
446 'subtitles': {
447 'de': [{'ext': 'vtt'}],
448 'en': [{'ext': 'vtt'}],
449 'es': [{'ext': 'vtt'}],
450 'fr': [{'ext': 'vtt'}],
451 },
452 },
453 'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
454 },
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',
464 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
465 'uploader_id': 'user28849593',
466 'duration': 118,
467 'thumbnail': 'https://i.vimeocdn.com/video/478636036-c18440305ef3df9decfb6bf207a61fe39d2d17fa462a96f6f2d93d30492b037d-d_1280',
468 },
469 },
470 {
471 # contains original format
472 'url': 'https://vimeo.com/33951933',
473 'md5': '53c688fa95a55bf4b7293d37a89c5c53',
474 'info_dict': {
475 'id': '33951933',
476 'ext': 'mp4',
477 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
478 'uploader': 'The DMCI',
479 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
480 'uploader_id': 'dmci',
481 'timestamp': 1324343742,
482 'upload_date': '20111220',
483 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
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,
489 },
490 },
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',
504 'duration': 176,
505 'thumbnail': 'https://i.vimeocdn.com/video/859377297-836494a4ef775e9d4edbace83937d9ad34dc846c688c0c419c0e87f7ab06c4b3-d_1280',
506 'uploader_url': 'https://vimeo.com/frameworkla',
507 },
508 },
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',
515 'ext': 'mp4',
516 'title': 'Vimeo Tribute: The Shining',
517 'uploader': 'Casey Donahue',
518 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
519 'uploader_id': 'caseydonahue',
520 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
521 'channel_id': 'tributes',
522 'timestamp': 1250886430,
523 'upload_date': '20090821',
524 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
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,
530 },
531 'params': {
532 'skip_download': True,
533 },
534 },
535 {
536 # redirects to ondemand extractor and should be passed through it
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',
544 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
545 'uploader_id': 'tenfootfilms',
546 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
547 'upload_date': '20130830',
548 'timestamp': 1377853339,
549 },
550 'params': {
551 'skip_download': True,
552 },
553 'skip': 'this page is no longer available.',
554 },
555 {
556 'url': 'http://player.vimeo.com/video/68375962',
557 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
558 'info_dict': {
559 'id': '68375962',
560 'ext': 'mp4',
561 'title': 'youtube-dl password protected test video',
562 'timestamp': 1371200155,
563 'upload_date': '20130614',
564 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
565 'uploader_id': 'user18948128',
566 'uploader': 'Jaime Marquínez Ferrándiz',
567 'duration': 10,
568 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
569 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
570 'view_count': int,
571 'comment_count': int,
572 'like_count': int,
573 },
574 'params': {
575 'format': 'best[protocol=https]',
576 'videopassword': 'youtube-dl',
577 },
578 },
579 {
580 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
581 'only_matching': True,
582 },
583 {
584 'url': 'https://vimeo.com/109815029',
585 'note': 'Video not completely processed, "failed" seed status',
586 'only_matching': True,
587 },
588 {
589 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
590 'only_matching': True,
591 },
592 {
593 'url': 'https://vimeo.com/album/2632481/video/79010983',
594 'only_matching': True,
595 },
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',
602 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
603 'uploader': 'Philipp Hagemeister',
604 'uploader_id': 'user20132939',
605 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
606 'upload_date': '20150209',
607 'timestamp': 1423518307,
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,
614 },
615 'params': {
616 'format': 'best[protocol=https]',
617 'videopassword': 'youtube-dl',
618 },
619 },
620 {
621 # source file returns 403: Forbidden
622 'url': 'https://vimeo.com/7809605',
623 'only_matching': True,
624 },
625 {
626 'note': 'Direct URL with hash',
627 'url': 'https://vimeo.com/160743502/abd0e13fb4',
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',
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',
644 },
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 },
663 },
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',
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',
683 },
684 'params': {'skip_download': 'm3u8'},
685 },
686 {
687 # requires passing unlisted_hash(a52724358e) to load_download_config request
688 'url': 'https://vimeo.com/392479337/a52724358e',
689 'only_matching': True,
690 },
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',
697 'ext': 'mp4',
698 'timestamp': 1627621014,
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',
710 },
711 'params': {
712 'skip_download': True,
713 },
714 },
715 {
716 # user playlist alias -> https://vimeo.com/258705797
717 'url': 'https://vimeo.com/user26785108/newspiritualguide',
718 'only_matching': True,
719 },
720 # https://gettingthingsdone.com/workflowmap/
721 # vimeo embed with check-password page protected by Referer header
722 ]
723
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)
728
729 @classmethod
730 def _extract_url(cls, url, webpage):
731 return next(cls._extract_embed_urls(url, webpage), None)
732
733 def _verify_player_video_password(self, url, video_id, headers):
734 password = self._get_video_password()
735 data = urlencode_postdata({
736 'password': base64.b64encode(password.encode()),
737 })
738 headers = merge_dicts(headers, {
739 'Content-Type': 'application/x-www-form-urlencoded',
740 })
741 checked = self._download_json(
742 f'{urllib.parse.urlsplit(url)._replace(query=None).geturl()}/check-password',
743 video_id, 'Verifying the password', data=data, headers=headers)
744 if checked is False:
745 raise ExtractorError('Wrong video password', expected=True)
746 return checked
747
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,
759 'Accept': 'application/json',
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)
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
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,
794 album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
795 query={'fields': 'description,name,privacy'})
796 if try_get(album, lambda x: x['privacy']['view']) == 'password':
797 password = self.get_param('videopassword')
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 f'https://vimeo.com/showcase/{album_id}/auth',
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:
813 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
814 raise ExtractorError('Wrong password', expected=True)
815 raise
816
817 def _real_extract(self, url):
818 url, data, headers = self._unsmuggle_headers(url)
819 if 'Referer' not in headers:
820 headers['Referer'] = url
821
822 # Extract ID from URL
823 mobj = self._match_valid_url(url).groupdict()
824 video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
825 if unlisted_hash:
826 return self._extract_from_api(video_id, unlisted_hash)
827
828 if any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
829 url = 'https://vimeo.com/' + video_id
830
831 self._try_album_password(url)
832 is_secure = urllib.parse.urlparse(url).scheme == 'https'
833 try:
834 # Retrieve video webpage to extract further information
835 webpage, urlh = self._download_webpage_handle(
836 url, video_id, headers=headers, impersonate=is_secure)
837 redirect_url = urlh.url
838 except ExtractorError as error:
839 if not isinstance(error.cause, HTTPError) or error.cause.status not in (403, 429):
840 raise
841 errmsg = error.cause.response.read()
842 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
843 raise ExtractorError(
844 'Cannot download embed-only video without embedding URL. Please call yt-dlp '
845 'with the URL of the page that embeds this video.', expected=True)
846 # 403 == vimeo.com TLS fingerprint or DC IP block; 429 == player.vimeo.com TLS FP block
847 status = error.cause.status
848 dcip_msg = 'If you are using a data center IP or VPN/proxy, your IP may be blocked'
849 if target := error.cause.response.extensions.get('impersonate'):
850 raise ExtractorError(
851 f'Got HTTP Error {status} when using impersonate target "{target}". {dcip_msg}')
852 elif not is_secure:
853 raise ExtractorError(f'Got HTTP Error {status}. {dcip_msg}', expected=True)
854 raise ExtractorError(
855 'This request has been blocked due to its TLS fingerprint. Install a '
856 'required impersonation dependency if possible, or else if you are okay with '
857 f'{self._downloader._format_err("compromising your security/cookies", "light red")}, '
858 f'try replacing "https:" with "http:" in the input URL. {dcip_msg}.', expected=True)
859
860 if '://player.vimeo.com/video/' in url:
861 config = self._search_json(
862 r'\b(?:playerC|c)onfig\s*=', webpage, 'info section', video_id)
863 if config.get('view') == 4:
864 config = self._verify_player_video_password(
865 redirect_url, video_id, headers)
866 return self._parse_config(config, video_id)
867
868 if re.search(r'<form[^>]+?id="pw_form"', webpage):
869 video_password = self._get_video_password()
870 token, vuid = self._extract_xsrft_and_vuid(webpage)
871 webpage = self._verify_video_password(
872 redirect_url, video_id, video_password, token, vuid)
873
874 vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
875 if vimeo_config:
876 seed_status = vimeo_config.get('seed_status') or {}
877 if seed_status.get('state') == 'failed':
878 raise ExtractorError(
879 '{} said: {}'.format(self.IE_NAME, seed_status['title']),
880 expected=True)
881
882 cc_license = None
883 timestamp = None
884 video_description = None
885 info_dict = {}
886 config_url = None
887
888 channel_id = self._search_regex(
889 r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
890 if channel_id:
891 config_url = self._html_search_regex(
892 r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
893 video_description = clean_html(get_element_by_class('description', webpage))
894 info_dict.update({
895 'channel_id': channel_id,
896 'channel_url': 'https://vimeo.com/channels/' + channel_id,
897 })
898 if not config_url:
899 page_config = self._parse_json(self._search_regex(
900 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
901 webpage, 'page config', default='{}'), video_id, fatal=False)
902 if not page_config:
903 return self._extract_from_api(video_id)
904 config_url = page_config['player']['config_url']
905 cc_license = page_config.get('cc_license')
906 clip = page_config.get('clip') or {}
907 timestamp = clip.get('uploaded_on')
908 video_description = clean_html(
909 clip.get('description') or page_config.get('description_html_escaped'))
910 config = self._download_json(config_url, video_id)
911 video = config.get('video') or {}
912 vod = video.get('vod') or {}
913
914 def is_rented():
915 if '>You rented this title.<' in webpage:
916 return True
917 if try_get(config, lambda x: x['user']['purchased']):
918 return True
919 for purchase_option in (vod.get('purchase_options') or []):
920 if purchase_option.get('purchased'):
921 return True
922 label = purchase_option.get('label_string')
923 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
924 return True
925 return False
926
927 if is_rented() and vod.get('is_trailer'):
928 feature_id = vod.get('feature_id')
929 if feature_id and not data.get('force_feature_id', False):
930 return self.url_result(smuggle_url(
931 f'https://player.vimeo.com/player/{feature_id}',
932 {'force_feature_id': True}), 'Vimeo')
933
934 if not video_description:
935 video_description = self._html_search_regex(
936 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
937 webpage, 'description', default=None)
938 if not video_description:
939 video_description = self._html_search_meta(
940 ['description', 'og:description', 'twitter:description'],
941 webpage, default=None)
942 if not video_description:
943 self.report_warning('Cannot find video description')
944
945 if not timestamp:
946 timestamp = self._search_regex(
947 r'<time[^>]+datetime="([^"]+)"', webpage,
948 'timestamp', default=None)
949
950 view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None))
951 like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None))
952 comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None))
953
954 formats = []
955
956 source_format = self._extract_original_format(
957 'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
958 if source_format:
959 formats.append(source_format)
960
961 info_dict_config = self._parse_config(config, video_id)
962 formats.extend(info_dict_config['formats'])
963 info_dict['_format_sort_fields'] = info_dict_config['_format_sort_fields']
964
965 json_ld = self._search_json_ld(webpage, video_id, default={})
966
967 if not cc_license:
968 cc_license = self._search_regex(
969 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
970 webpage, 'license', default=None, group='license')
971
972 info_dict.update({
973 'formats': formats,
974 'timestamp': unified_timestamp(timestamp),
975 'description': video_description,
976 'webpage_url': url,
977 'view_count': view_count,
978 'like_count': like_count,
979 'comment_count': comment_count,
980 'license': cc_license,
981 })
982
983 return merge_dicts(info_dict, info_dict_config, json_ld)
984
985
986class VimeoOndemandIE(VimeoIE): # XXX: Do not subclass from concrete IE
987 IE_NAME = 'vimeo:ondemand'
988 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
989 _TESTS = [{
990 # ondemand video not available via https://vimeo.com/id
991 'url': 'https://vimeo.com/ondemand/20704',
992 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
993 'info_dict': {
994 'id': '105442900',
995 'ext': 'mp4',
996 'title': 'המעבדה - במאי יותם פלדמן',
997 'uploader': 'גם סרטים',
998 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
999 'uploader_id': 'gumfilms',
1000 'description': 'md5:aeeba3dbd4d04b0fa98a4fdc9c639998',
1001 'upload_date': '20140906',
1002 'timestamp': 1410032453,
1003 'thumbnail': 'https://i.vimeocdn.com/video/488238335-d7bf151c364cff8d467f1b73784668fe60aae28a54573a35d53a1210ae283bd8-d_1280',
1004 'comment_count': int,
1005 'license': 'https://creativecommons.org/licenses/by-nc-nd/3.0/',
1006 'duration': 53,
1007 'view_count': int,
1008 'like_count': int,
1009 },
1010 'params': {
1011 'format': 'best[protocol=https]',
1012 },
1013 'expected_warnings': ['Unable to download JSON metadata'],
1014 }, {
1015 # requires Referer to be passed along with og:video:url
1016 'url': 'https://vimeo.com/ondemand/36938/126682985',
1017 'info_dict': {
1018 'id': '126584684',
1019 'ext': 'mp4',
1020 'title': 'Rävlock, rätt läte på rätt plats',
1021 'uploader': 'Lindroth & Norin',
1022 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
1023 'uploader_id': 'lindrothnorin',
1024 'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
1025 'upload_date': '20150502',
1026 'timestamp': 1430586422,
1027 'duration': 121,
1028 'comment_count': int,
1029 'view_count': int,
1030 'thumbnail': 'https://i.vimeocdn.com/video/517077723-7066ae1d9a79d3eb361334fb5d58ec13c8f04b52f8dd5eadfbd6fb0bcf11f613-d_1280',
1031 'like_count': int,
1032 },
1033 'params': {
1034 'skip_download': True,
1035 },
1036 'expected_warnings': ['Unable to download JSON metadata'],
1037 }, {
1038 'url': 'https://vimeo.com/ondemand/nazmaalik',
1039 'only_matching': True,
1040 }, {
1041 'url': 'https://vimeo.com/ondemand/141692381',
1042 'only_matching': True,
1043 }, {
1044 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
1045 'only_matching': True,
1046 }]
1047
1048
1049class VimeoChannelIE(VimeoBaseInfoExtractor):
1050 IE_NAME = 'vimeo:channel'
1051 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
1052 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
1053 _TITLE = None
1054 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
1055 _TESTS = [{
1056 'url': 'https://vimeo.com/channels/tributes',
1057 'info_dict': {
1058 'id': 'tributes',
1059 'title': 'Vimeo Tributes',
1060 },
1061 'playlist_mincount': 22,
1062 }]
1063 _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
1064
1065 def _page_url(self, base_url, pagenum):
1066 return f'{base_url}/videos/page:{pagenum}/'
1067
1068 def _extract_list_title(self, webpage):
1069 return self._TITLE or self._html_search_regex(
1070 self._TITLE_RE, webpage, 'list title', fatal=False)
1071
1072 def _title_and_entries(self, list_id, base_url):
1073 for pagenum in itertools.count(1):
1074 page_url = self._page_url(base_url, pagenum)
1075 webpage = self._download_webpage(
1076 page_url, list_id,
1077 f'Downloading page {pagenum}')
1078
1079 if pagenum == 1:
1080 yield self._extract_list_title(webpage)
1081
1082 # Try extracting href first since not all videos are available via
1083 # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
1084 clips = re.findall(
1085 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
1086 if clips:
1087 for video_id, video_url, video_title in clips:
1088 yield self.url_result(
1089 urllib.parse.urljoin(base_url, video_url),
1090 VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
1091 # More relaxed fallback
1092 else:
1093 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
1094 yield self.url_result(
1095 f'https://vimeo.com/{video_id}',
1096 VimeoIE.ie_key(), video_id=video_id)
1097
1098 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1099 break
1100
1101 def _extract_videos(self, list_id, base_url):
1102 title_and_entries = self._title_and_entries(list_id, base_url)
1103 list_title = next(title_and_entries)
1104 return self.playlist_result(title_and_entries, list_id, list_title)
1105
1106 def _real_extract(self, url):
1107 channel_id = self._match_id(url)
1108 return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
1109
1110
1111class VimeoUserIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
1112 IE_NAME = 'vimeo:user'
1113 _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos)?/?(?:$|[?#])'
1114 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
1115 _TESTS = [{
1116 'url': 'https://vimeo.com/nkistudio/videos',
1117 'info_dict': {
1118 'title': 'Nki',
1119 'id': 'nkistudio',
1120 },
1121 'playlist_mincount': 66,
1122 }, {
1123 'url': 'https://vimeo.com/nkistudio/',
1124 'only_matching': True,
1125 }]
1126 _BASE_URL_TEMPL = 'https://vimeo.com/%s'
1127
1128
1129class VimeoAlbumIE(VimeoBaseInfoExtractor):
1130 IE_NAME = 'vimeo:album'
1131 _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
1132 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
1133 _TESTS = [{
1134 'url': 'https://vimeo.com/album/2632481',
1135 'info_dict': {
1136 'id': '2632481',
1137 'title': 'Staff Favorites: November 2013',
1138 },
1139 'playlist_mincount': 13,
1140 }, {
1141 'note': 'Password-protected album',
1142 'url': 'https://vimeo.com/album/3253534',
1143 'info_dict': {
1144 'title': 'test',
1145 'id': '3253534',
1146 },
1147 'playlist_count': 1,
1148 'params': {
1149 'videopassword': 'youtube-dl',
1150 },
1151 }]
1152 _PAGE_SIZE = 100
1153
1154 def _fetch_page(self, album_id, authorization, hashed_pass, page):
1155 api_page = page + 1
1156 query = {
1157 'fields': 'link,uri',
1158 'page': api_page,
1159 'per_page': self._PAGE_SIZE,
1160 }
1161 if hashed_pass:
1162 query['_hashed_pass'] = hashed_pass
1163 try:
1164 videos = self._download_json(
1165 f'https://api.vimeo.com/albums/{album_id}/videos',
1166 album_id, f'Downloading page {api_page}', query=query, headers={
1167 'Authorization': 'jwt ' + authorization,
1168 'Accept': 'application/json',
1169 })['data']
1170 except ExtractorError as e:
1171 if isinstance(e.cause, HTTPError) and e.cause.status == 400:
1172 return
1173 raise
1174 for video in videos:
1175 link = video.get('link')
1176 if not link:
1177 continue
1178 uri = video.get('uri')
1179 video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
1180 yield self.url_result(link, VimeoIE.ie_key(), video_id)
1181
1182 def _real_extract(self, url):
1183 album_id = self._match_id(url)
1184 viewer = self._download_json(
1185 'https://vimeo.com/_rv/viewer', album_id, fatal=False)
1186 if not viewer:
1187 webpage = self._download_webpage(url, album_id)
1188 viewer = self._parse_json(self._search_regex(
1189 r'bootstrap_data\s*=\s*({.+?})</script>',
1190 webpage, 'bootstrap data'), album_id)['viewer']
1191 jwt = viewer['jwt']
1192 album = self._download_json(
1193 'https://api.vimeo.com/albums/' + album_id,
1194 album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
1195 query={'fields': 'description,name,privacy'})
1196 hashed_pass = None
1197 if try_get(album, lambda x: x['privacy']['view']) == 'password':
1198 password = self.get_param('videopassword')
1199 if not password:
1200 raise ExtractorError(
1201 'This album is protected by a password, use the --video-password option',
1202 expected=True)
1203 self._set_vimeo_cookie('vuid', viewer['vuid'])
1204 try:
1205 hashed_pass = self._download_json(
1206 f'https://vimeo.com/showcase/{album_id}/auth',
1207 album_id, 'Verifying the password', data=urlencode_postdata({
1208 'password': password,
1209 'token': viewer['xsrft'],
1210 }), headers={
1211 'X-Requested-With': 'XMLHttpRequest',
1212 })['hashed_pass']
1213 except ExtractorError as e:
1214 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
1215 raise ExtractorError('Wrong password', expected=True)
1216 raise
1217 entries = OnDemandPagedList(functools.partial(
1218 self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
1219 return self.playlist_result(
1220 entries, album_id, album.get('name'), album.get('description'))
1221
1222
1223class VimeoGroupsIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
1224 IE_NAME = 'vimeo:group'
1225 _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
1226 _TESTS = [{
1227 'url': 'https://vimeo.com/groups/meetup',
1228 'info_dict': {
1229 'id': 'meetup',
1230 'title': 'Vimeo Meetup!',
1231 },
1232 'playlist_mincount': 27,
1233 }]
1234 _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
1235
1236
1237class VimeoReviewIE(VimeoBaseInfoExtractor):
1238 IE_NAME = 'vimeo:review'
1239 IE_DESC = 'Review pages on vimeo'
1240 _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1241 _TESTS = [{
1242 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1243 'md5': 'c507a72f780cacc12b2248bb4006d253',
1244 'info_dict': {
1245 'id': '75524534',
1246 'ext': 'mp4',
1247 'title': "DICK HARDWICK 'Comedian'",
1248 'uploader': 'Richard Hardwick',
1249 'uploader_id': 'user21297594',
1250 'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1251 'duration': 304,
1252 'thumbnail': 'https://i.vimeocdn.com/video/450115033-43303819d9ebe24c2630352e18b7056d25197d09b3ae901abdac4c4f1d68de71-d_1280',
1253 'uploader_url': 'https://vimeo.com/user21297594',
1254 },
1255 }, {
1256 'note': 'video player needs Referer',
1257 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1258 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1259 'info_dict': {
1260 'id': '91613211',
1261 'ext': 'mp4',
1262 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1263 'uploader': 'DevWeek Events',
1264 'duration': 2773,
1265 'thumbnail': r're:^https?://.*\.jpg$',
1266 'uploader_id': 'user22258446',
1267 },
1268 'skip': 'video gone',
1269 }, {
1270 'note': 'Password protected',
1271 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1272 'info_dict': {
1273 'id': '138823582',
1274 'ext': 'mp4',
1275 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1276 'uploader': 'TMB',
1277 'uploader_id': 'user37284429',
1278 },
1279 'params': {
1280 'videopassword': 'holygrail',
1281 },
1282 'skip': 'video gone',
1283 }]
1284
1285 def _real_extract(self, url):
1286 page_url, video_id = self._match_valid_url(url).groups()
1287 data = self._download_json(
1288 page_url.replace('/review/', '/review/data/'), video_id)
1289 if data.get('isLocked') is True:
1290 video_password = self._get_video_password()
1291 viewer = self._download_json(
1292 'https://vimeo.com/_rv/viewer', video_id)
1293 webpage = self._verify_video_password(
1294 'https://vimeo.com/' + video_id, video_id,
1295 video_password, viewer['xsrft'], viewer['vuid'])
1296 clip_page_config = self._parse_json(self._search_regex(
1297 r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
1298 webpage, 'clip page config'), video_id)
1299 config_url = clip_page_config['player']['config_url']
1300 clip_data = clip_page_config.get('clip') or {}
1301 else:
1302 clip_data = data['clipData']
1303 config_url = clip_data['configUrl']
1304 config = self._download_json(config_url, video_id)
1305 info_dict = self._parse_config(config, video_id)
1306 source_format = self._extract_original_format(
1307 page_url + '/action', video_id)
1308 if source_format:
1309 info_dict['formats'].append(source_format)
1310 info_dict['description'] = clean_html(clip_data.get('description'))
1311 return info_dict
1312
1313
1314class VimeoWatchLaterIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
1315 IE_NAME = 'vimeo:watchlater'
1316 IE_DESC = 'Vimeo watch later list, ":vimeowatchlater" keyword (requires authentication)'
1317 _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1318 _TITLE = 'Watch Later'
1319 _LOGIN_REQUIRED = True
1320 _TESTS = [{
1321 'url': 'https://vimeo.com/watchlater',
1322 'only_matching': True,
1323 }]
1324
1325 def _page_url(self, base_url, pagenum):
1326 url = f'{base_url}/page:{pagenum}/'
1327 request = Request(url)
1328 # Set the header to get a partial html page with the ids,
1329 # the normal page doesn't contain them.
1330 request.headers['X-Requested-With'] = 'XMLHttpRequest'
1331 return request
1332
1333 def _real_extract(self, url):
1334 return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1335
1336
1337class VimeoLikesIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
1338 _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1339 IE_NAME = 'vimeo:likes'
1340 IE_DESC = 'Vimeo user likes'
1341 _TESTS = [{
1342 'url': 'https://vimeo.com/user755559/likes/',
1343 'playlist_mincount': 293,
1344 'info_dict': {
1345 'id': 'user755559',
1346 'title': 'urza’s Likes',
1347 },
1348 }, {
1349 'url': 'https://vimeo.com/stormlapse/likes',
1350 'only_matching': True,
1351 }]
1352
1353 def _page_url(self, base_url, pagenum):
1354 return f'{base_url}/page:{pagenum}/'
1355
1356 def _real_extract(self, url):
1357 user_id = self._match_id(url)
1358 return self._extract_videos(user_id, f'https://vimeo.com/{user_id}/likes')
1359
1360
1361class VHXEmbedIE(VimeoBaseInfoExtractor):
1362 IE_NAME = 'vhx:embed'
1363 _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1364 _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://embed\.vhx\.tv/videos/\d+[^"]*)"']
1365
1366 @classmethod
1367 def _extract_embed_urls(cls, url, webpage):
1368 for embed_url in super()._extract_embed_urls(url, webpage):
1369 yield cls._smuggle_referrer(embed_url, url)
1370
1371 def _real_extract(self, url):
1372 video_id = self._match_id(url)
1373 url, _, headers = self._unsmuggle_headers(url)
1374 webpage = self._download_webpage(url, video_id, headers=headers)
1375 config_url = self._parse_json(self._search_regex(
1376 r'window\.OTTData\s*=\s*({.+})', webpage,
1377 'ott data'), video_id, js_to_json)['config_url']
1378 config = self._download_json(config_url, video_id)
1379 info = self._parse_config(config, video_id)
1380 info['id'] = video_id
1381 return info
1382
1383
1384class VimeoProIE(VimeoBaseInfoExtractor):
1385 IE_NAME = 'vimeo:pro'
1386 _VALID_URL = r'https?://(?:www\.)?vimeopro\.com/[^/?#]+/(?P<slug>[^/?#]+)(?:(?:/videos?/(?P<id>[0-9]+)))?'
1387 _TESTS = [{
1388 # Vimeo URL derived from video_id
1389 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
1390 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
1391 'note': 'Vimeo Pro video (#1197)',
1392 'info_dict': {
1393 'id': '68093876',
1394 'ext': 'mp4',
1395 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
1396 'uploader_id': 'openstreetmapus',
1397 'uploader': 'OpenStreetMap US',
1398 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
1399 'description': 'md5:2c362968038d4499f4d79f88458590c1',
1400 'duration': 1595,
1401 'upload_date': '20130610',
1402 'timestamp': 1370893156,
1403 'license': 'by',
1404 'thumbnail': 'https://i.vimeocdn.com/video/440260469-19b0d92fca3bd84066623b53f1eb8aaa3980c6c809e2d67b6b39ab7b4a77a344-d_960',
1405 'view_count': int,
1406 'comment_count': int,
1407 'like_count': int,
1408 'tags': 'count:1',
1409 },
1410 'params': {
1411 'format': 'best[protocol=https]',
1412 },
1413 }, {
1414 # password-protected VimeoPro page with Vimeo player embed
1415 'url': 'https://vimeopro.com/cadfem/simulation-conference-mechanische-systeme-in-perfektion',
1416 'info_dict': {
1417 'id': '764543723',
1418 'ext': 'mp4',
1419 'title': 'Mechanische Systeme in Perfektion: Realität erfassen, Innovation treiben',
1420 'thumbnail': 'https://i.vimeocdn.com/video/1543784598-a1a750494a485e601110136b9fe11e28c2131942452b3a5d30391cb3800ca8fd-d_1280',
1421 'description': 'md5:2a9d195cd1b0f6f79827107dc88c2420',
1422 'uploader': 'CADFEM',
1423 'uploader_id': 'cadfem',
1424 'uploader_url': 'https://vimeo.com/cadfem',
1425 'duration': 12505,
1426 'chapters': 'count:10',
1427 },
1428 'params': {
1429 'videopassword': 'Conference2022',
1430 'skip_download': True,
1431 },
1432 }]
1433
1434 def _real_extract(self, url):
1435 display_id, video_id = self._match_valid_url(url).group('slug', 'id')
1436 if video_id:
1437 display_id = video_id
1438 webpage = self._download_webpage(url, display_id)
1439
1440 password_form = self._search_regex(
1441 r'(?is)<form[^>]+?method=["\']post["\'][^>]*>(.+?password.+?)</form>',
1442 webpage, 'password form', default=None)
1443 if password_form:
1444 try:
1445 webpage = self._download_webpage(url, display_id, data=urlencode_postdata({
1446 'password': self._get_video_password(),
1447 **self._hidden_inputs(password_form),
1448 }), note='Logging in with video password')
1449 except ExtractorError as e:
1450 if isinstance(e.cause, HTTPError) and e.cause.status == 418:
1451 raise ExtractorError('Wrong video password', expected=True)
1452 raise
1453
1454 description = None
1455 # even if we have video_id, some videos require player URL with portfolio_id query param
1456 # https://github.com/ytdl-org/youtube-dl/issues/20070
1457 vimeo_url = VimeoIE._extract_url(url, webpage)
1458 if vimeo_url:
1459 description = self._html_search_meta('description', webpage, default=None)
1460 elif video_id:
1461 vimeo_url = f'https://vimeo.com/{video_id}'
1462 else:
1463 raise ExtractorError(
1464 'No Vimeo embed or video ID could be found in VimeoPro page', expected=True)
1465
1466 return self.url_result(vimeo_url, VimeoIE, video_id, url_transparent=True,
1467 description=description)