]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/vimeo.py
[utils] Better traceback for `ExtractorError`
[yt-dlp.git] / yt_dlp / extractor / vimeo.py
CommitLineData
dcdb292f 1# coding: utf-8
9148eb00
PH
2from __future__ import unicode_literals
3
79fec976 4import base64
eb9c9c74 5import functools
b3d14cbf 6import re
caeefc29 7import itertools
b3d14cbf
PH
8
9from .common import InfoExtractor
8c25f81b 10from ..compat import (
eb9c9c74 11 compat_kwargs,
1060425c 12 compat_HTTPError,
6a55bb66 13 compat_str,
9c44d242 14 compat_urlparse,
8c25f81b
PH
15)
16from ..utils import (
681ac7c9 17 clean_html,
d5f071af 18 determine_ext,
b3d14cbf 19 ExtractorError,
58ab5cbc 20 get_element_by_class,
9cb070f9 21 HEADRequest,
ca01d178 22 js_to_json,
9c44d242 23 int_or_none,
ae1c585c 24 merge_dicts,
eb9c9c74 25 OnDemandPagedList,
ca01d178 26 parse_filesize,
cce889b9 27 parse_iso8601,
4dfbf869 28 parse_qs,
67dda517 29 sanitized_Request,
30965ac6 30 smuggle_url,
681ac7c9 31 str_or_none,
c15cd296 32 try_get,
c15cd296 33 unified_timestamp,
9d4660ca 34 unsmuggle_url,
a980bc43 35 urlencode_postdata,
1c45ff55 36 urljoin,
b407e173 37 unescapeHTML,
9cb070f9 38 urlhandle_detect_ext,
b3d14cbf
PH
39)
40
bbafbe20 41
efb7e119
JMF
42class VimeoBaseInfoExtractor(InfoExtractor):
43 _NETRC_MACHINE = 'vimeo'
44 _LOGIN_REQUIRED = False
f6c3664d 45 _LOGIN_URL = 'https://vimeo.com/log_in'
efb7e119
JMF
46
47 def _login(self):
68217024 48 username, password = self._get_login_info()
efb7e119
JMF
49 if username is None:
50 if self._LOGIN_REQUIRED:
4f3e9430 51 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
efb7e119 52 return
26ad6bcd
S
53 webpage = self._download_webpage(
54 self._LOGIN_URL, None, 'Downloading login page')
7c845629 55 token, vuid = self._extract_xsrft_and_vuid(webpage)
26ad6bcd 56 data = {
f6c3664d 57 'action': 'login',
efb7e119
JMF
58 'email': username,
59 'password': password,
efb7e119
JMF
60 'service': 'vimeo',
61 'token': token,
26ad6bcd 62 }
9eab37dc 63 self._set_vimeo_cookie('vuid', vuid)
26ad6bcd
S
64 try:
65 self._download_webpage(
66 self._LOGIN_URL, None, 'Logging in',
67 data=urlencode_postdata(data), headers={
68 'Content-Type': 'application/x-www-form-urlencoded',
69 'Referer': self._LOGIN_URL,
70 })
71 except ExtractorError as e:
72 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
73 raise ExtractorError(
74 'Unable to log in: bad username or password',
75 expected=True)
76 raise ExtractorError('Unable to log in')
efb7e119 77
cce889b9 78 def _get_video_password(self):
a06916d9 79 password = self.get_param('videopassword')
c1ff6e1a 80 if password is None:
cce889b9 81 raise ExtractorError(
82 'This video is protected by a password, use the --video-password option',
83 expected=True)
84 return password
85
86 def _verify_video_password(self, url, video_id, password, token, vuid):
c1ff6e1a
YCH
87 if url.startswith('http://'):
88 # vimeo only supports https now, but the user can give an http url
89 url = url.replace('http://', 'https://')
c1ff6e1a
YCH
90 self._set_vimeo_cookie('vuid', vuid)
91 return self._download_webpage(
cce889b9 92 url + '/password', video_id, 'Verifying the password',
93 'Wrong password', data=urlencode_postdata({
94 'password': password,
95 'token': token,
96 }), headers={
97 'Content-Type': 'application/x-www-form-urlencoded',
98 'Referer': url,
99 })
c1ff6e1a 100
7c845629
S
101 def _extract_xsrft_and_vuid(self, webpage):
102 xsrft = self._search_regex(
b826035d 103 r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
f6c3664d 104 webpage, 'login token', group='xsrft')
7c845629
S
105 vuid = self._search_regex(
106 r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
107 webpage, 'vuid', group='vuid')
108 return xsrft, vuid
f6c3664d 109
eb9c9c74
RA
110 def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
111 vimeo_config = self._search_regex(
112 r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
113 webpage, 'vimeo config', *args, **compat_kwargs(kwargs))
114 if vimeo_config:
115 return self._parse_json(vimeo_config, video_id)
116
9eab37dc
S
117 def _set_vimeo_cookie(self, name, value):
118 self._set_cookie('vimeo.com', name, value)
119
531a7496 120 def _vimeo_sort_formats(self, formats):
bc104778 121 # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
122 # at the same time without actual units specified.
123 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source'))
531a7496
YCH
124
125 def _parse_config(self, config, video_id):
d8c507c9 126 video_data = config['video']
d8c507c9 127 video_title = video_data['title']
85b6335d
RA
128 live_event = video_data.get('live_event') or {}
129 is_live = live_event.get('status') == 'started'
58ab5cbc 130 request = config.get('request') or {}
531a7496
YCH
131
132 formats = []
3f047fc4
F
133 subtitles = {}
134
58ab5cbc 135 config_files = video_data.get('files') or request.get('files') or {}
136 for f in (config_files.get('progressive') or []):
531a7496
YCH
137 video_url = f.get('url')
138 if not video_url:
139 continue
140 formats.append({
141 'url': video_url,
142 'format_id': 'http-%s' % f.get('quality'),
bc104778 143 'source_preference': 10,
531a7496
YCH
144 'width': int_or_none(f.get('width')),
145 'height': int_or_none(f.get('height')),
146 'fps': int_or_none(f.get('fps')),
147 'tbr': int_or_none(f.get('bitrate')),
148 })
d8c507c9 149
85b6335d 150 # TODO: fix handling of 308 status code returned for live archive manifest requests
52c50a10 151 sep_pattern = r'/sep/video/'
d8c507c9 152 for files_type in ('hls', 'dash'):
58ab5cbc 153 for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
d8c507c9
RA
154 manifest_url = cdn_data.get('url')
155 if not manifest_url:
156 continue
157 format_id = '%s-%s' % (files_type, cdn_name)
52c50a10
RA
158 sep_manifest_urls = []
159 if re.search(sep_pattern, manifest_url):
160 for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
161 sep_manifest_urls.append((format_id + suffix, re.sub(
162 sep_pattern, '/%s/' % repl, manifest_url)))
163 else:
164 sep_manifest_urls = [(format_id, manifest_url)]
165 for f_id, m_url in sep_manifest_urls:
166 if files_type == 'hls':
3f047fc4 167 fmts, subs = self._extract_m3u8_formats_and_subtitles(
a5c0c202 168 m_url, video_id, 'mp4', live=is_live, m3u8_id=f_id,
52c50a10 169 note='Downloading %s m3u8 information' % cdn_name,
3f047fc4
F
170 fatal=False)
171 formats.extend(fmts)
172 self._merge_subtitles(subs, target=subtitles)
52c50a10 173 elif files_type == 'dash':
c25720ef
RA
174 if 'json=1' in m_url:
175 real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
176 if real_m_url:
177 m_url = real_m_url
3f047fc4 178 fmts, subs = self._extract_mpd_formats_and_subtitles(
ae9a173b
RA
179 m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
180 'Downloading %s MPD information' % cdn_name,
e834f044 181 fatal=False)
3f047fc4
F
182 formats.extend(fmts)
183 self._merge_subtitles(subs, target=subtitles)
531a7496 184
85b6335d
RA
185 live_archive = live_event.get('archive') or {}
186 live_archive_source_url = live_archive.get('source_url')
187 if live_archive_source_url and live_archive.get('status') == 'done':
188 formats.append({
189 'format_id': 'live-archive-source',
190 'url': live_archive_source_url,
f983b875 191 'quality': 10,
85b6335d
RA
192 })
193
58ab5cbc 194 for tt in (request.get('text_tracks') or []):
3f047fc4 195 subtitles.setdefault(tt['lang'], []).append({
58ab5cbc 196 'ext': 'vtt',
197 'url': urljoin('https://vimeo.com', tt['url']),
3f047fc4 198 })
531a7496 199
c25720ef
RA
200 thumbnails = []
201 if not is_live:
58ab5cbc 202 for key, thumb in (video_data.get('thumbs') or {}).items():
c25720ef
RA
203 thumbnails.append({
204 'id': key,
205 'width': int_or_none(key),
206 'url': thumb,
207 })
208 thumbnail = video_data.get('thumbnail')
209 if thumbnail:
210 thumbnails.append({
211 'url': thumbnail,
212 })
213
214 owner = video_data.get('owner') or {}
215 video_uploader_url = owner.get('url')
216
818faa3a 217 duration = int_or_none(video_data.get('duration'))
218 chapter_data = try_get(config, lambda x: x['embed']['chapters']) or []
219 chapters = [{
220 'title': current_chapter.get('title'),
221 'start_time': current_chapter.get('timecode'),
222 'end_time': next_chapter.get('timecode'),
223 } for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])]
224 if chapters and chapters[0]['start_time']: # Chapters may not start from 0
225 chapters[:0] = [{'title': '<Untitled>', 'start_time': 0, 'end_time': chapters[0]['start_time']}]
226
531a7496 227 return {
681ac7c9 228 'id': str_or_none(video_data.get('id')) or video_id,
39ca3b5c 229 'title': video_title,
c25720ef
RA
230 'uploader': owner.get('name'),
231 'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
531a7496 232 'uploader_url': video_uploader_url,
c25720ef 233 'thumbnails': thumbnails,
818faa3a 234 'duration': duration,
235 'chapters': chapters or None,
531a7496
YCH
236 'formats': formats,
237 'subtitles': subtitles,
c25720ef 238 'is_live': is_live,
531a7496
YCH
239 }
240
bc2ca1bb 241 def _extract_original_format(self, url, video_id, unlisted_hash=None):
242 query = {'action': 'load_download_config'}
243 if unlisted_hash:
244 query['unlisted_hash'] = unlisted_hash
27655037 245 download_data = self._download_json(
bc2ca1bb 246 url, video_id, fatal=False, query=query,
9cb070f9 247 headers={'X-Requested-With': 'XMLHttpRequest'},
248 expected_status=(403, 404)) or {}
249 source_file = download_data.get('source_file')
250 download_url = try_get(source_file, lambda x: x['download_url'])
251 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
252 source_name = source_file.get('public_name', 'Original')
253 if self._is_valid_url(download_url, video_id, '%s video' % source_name):
254 ext = (try_get(
255 source_file, lambda x: x['extension'],
256 compat_str) or determine_ext(
257 download_url, None) or 'mp4').lower()
258 return {
259 'url': download_url,
260 'ext': ext,
261 'width': int_or_none(source_file.get('width')),
262 'height': int_or_none(source_file.get('height')),
263 'filesize': parse_filesize(source_file.get('size')),
264 'format_id': source_name,
265 'quality': 1,
266 }
27655037 267
605cad0b
A
268 jwt_response = self._download_json(
269 'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
270 if not jwt_response.get('jwt'):
271 return
272 headers = {'Authorization': 'jwt %s' % jwt_response['jwt']}
273 original_response = self._download_json(
274 f'https://api.vimeo.com/videos/{video_id}', video_id,
9cb070f9 275 headers=headers, fatal=False, expected_status=(403, 404)) or {}
276 for download_data in original_response.get('download') or []:
605cad0b
A
277 download_url = download_data.get('link')
278 if not download_url or download_data.get('quality') != 'source':
279 continue
9cb070f9 280 ext = determine_ext(parse_qs(download_url).get('filename', [''])[0].lower(), default_ext=None)
281 if not ext:
282 urlh = self._request_webpage(
283 HEADRequest(download_url), video_id, fatal=False, note='Determining source extension')
284 ext = urlh and urlhandle_detect_ext(urlh)
605cad0b
A
285 return {
286 'url': download_url,
9cb070f9 287 'ext': ext or 'unknown_video',
605cad0b
A
288 'format_id': download_data.get('public_name', 'Original'),
289 'width': int_or_none(download_data.get('width')),
290 'height': int_or_none(download_data.get('height')),
291 'fps': int_or_none(download_data.get('fps')),
292 'filesize': int_or_none(download_data.get('size')),
293 'quality': 1,
294 }
295
efb7e119 296
65469a7f 297class VimeoIE(VimeoBaseInfoExtractor):
b3d14cbf
PH
298 """Information extractor for vimeo.com."""
299
300 # _VALID_URL matches Vimeo URLs
bbafbe20 301 _VALID_URL = r'''(?x)
74278def
S
302 https?://
303 (?:
304 (?:
305 www|
681ac7c9 306 player
74278def
S
307 )
308 \.
309 )?
681ac7c9 310 vimeo(?:pro)?\.com/
eb9c9c74 311 (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
2a6f8475 312 (?:[^/]+/)*?
74278def
S
313 (?:
314 (?:
315 play_redirect_hls|
316 moogaloop\.swf)\?clip_id=
317 )?
318 (?:videos?/)?
319 (?P<id>[0-9]+)
cce889b9 320 (?:/(?P<unlisted_hash>[\da-f]{10}))?
74278def
S
321 /?(?:[?&].*)?(?:[#].*)?$
322 '''
9148eb00 323 IE_NAME = 'vimeo'
a91b954b
JMF
324 _TESTS = [
325 {
9148eb00 326 'url': 'http://vimeo.com/56015672#at=0',
9148eb00
PH
327 'md5': '8879b6cc097e987f02484baf890129e5',
328 'info_dict': {
ad5976b4
PH
329 'id': '56015672',
330 'ext': 'mp4',
3867038a 331 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
681ac7c9 332 'description': 'md5:2d3305bad981a06ff79f027f19865021',
c15cd296 333 'timestamp': 1355990239,
68f3b61f 334 'upload_date': '20121220',
ec85ded8 335 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
68f3b61f
S
336 'uploader_id': 'user7108434',
337 'uploader': 'Filippo Valsorda',
338 'duration': 10,
c38a67bc 339 'license': 'by-sa',
a91b954b 340 },
681ac7c9
RA
341 'params': {
342 'format': 'best[protocol=https]',
343 },
a91b954b
JMF
344 },
345 {
9148eb00 346 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
9148eb00
PH
347 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
348 'note': 'Vimeo Pro video (#1197)',
349 'info_dict': {
4f3e9430
JMF
350 'id': '68093876',
351 'ext': 'mp4',
ec85ded8 352 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
9148eb00
PH
353 'uploader_id': 'openstreetmapus',
354 'uploader': 'OpenStreetMap US',
355 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
681ac7c9 356 'description': 'md5:2c362968038d4499f4d79f88458590c1',
69c8fb9e 357 'duration': 1595,
681ac7c9
RA
358 'upload_date': '20130610',
359 'timestamp': 1370893156,
58ab5cbc 360 'license': 'by',
681ac7c9
RA
361 },
362 'params': {
363 'format': 'best[protocol=https]',
a91b954b
JMF
364 },
365 },
aa32314d 366 {
9148eb00 367 'url': 'http://player.vimeo.com/video/54469442',
9148eb00
PH
368 'md5': '619b811a4417aa4abe78dc653becf511',
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,
58ea7ec8 378 'description': None,
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,
365d136b 398 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
93b22c78 399 },
9148eb00 400 'params': {
681ac7c9 401 'format': 'best[protocol=https]',
3867038a 402 'videopassword': 'youtube-dl',
93b22c78
JMF
403 },
404 },
548f31d9
S
405 {
406 'url': 'http://vimeo.com/channels/keypeele/75629013',
407 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
548f31d9
S
408 'info_dict': {
409 'id': '75629013',
410 'ext': 'mp4',
411 'title': 'Key & Peele: Terrorist Interrogation',
412 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
ec85ded8 413 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
548f31d9
S
414 'uploader_id': 'atencio',
415 'uploader': 'Peter Atencio',
d03beddf
S
416 'channel_id': 'keypeele',
417 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
c15cd296
S
418 'timestamp': 1380339469,
419 'upload_date': '20130928',
548f31d9
S
420 'duration': 187,
421 },
9cb070f9 422 'params': {'format': 'http-1080p'},
548f31d9 423 },
1eac553e
S
424 {
425 'url': 'http://vimeo.com/76979871',
1eac553e
S
426 'note': 'Video with subtitles',
427 'info_dict': {
428 'id': '76979871',
429 'ext': 'mp4',
430 'title': 'The New Vimeo Player (You Know, For Videos)',
431 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
c15cd296 432 'timestamp': 1381846109,
1eac553e 433 'upload_date': '20131015',
ec85ded8 434 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
1eac553e
S
435 'uploader_id': 'staff',
436 'uploader': 'Vimeo Staff',
69c8fb9e 437 'duration': 62,
58ab5cbc 438 'subtitles': {
439 'de': [{'ext': 'vtt'}],
440 'en': [{'ext': 'vtt'}],
441 'es': [{'ext': 'vtt'}],
442 'fr': [{'ext': 'vtt'}],
443 },
9cb070f9 444 },
445 'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
1eac553e 446 },
4698f0d8
JMF
447 {
448 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
449 'url': 'https://player.vimeo.com/video/98044508',
450 'note': 'The js code contains assignments to the same variable as the config',
451 'info_dict': {
452 'id': '98044508',
453 'ext': 'mp4',
454 'title': 'Pier Solar OUYA Official Trailer',
455 'uploader': 'Tulio Gonçalves',
ec85ded8 456 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
4698f0d8
JMF
457 'uploader_id': 'user28849593',
458 },
459 },
323f82a7 460 {
461 # contains original format
462 'url': 'https://vimeo.com/33951933',
365d136b 463 'md5': '53c688fa95a55bf4b7293d37a89c5c53',
323f82a7 464 'info_dict': {
465 'id': '33951933',
466 'ext': 'mp4',
467 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
468 'uploader': 'The DMCI',
ec85ded8 469 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
323f82a7 470 'uploader_id': 'dmci',
c15cd296 471 'timestamp': 1324343742,
323f82a7 472 'upload_date': '20111220',
473 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
474 },
475 },
605cad0b
A
476 {
477 'note': 'Contains original format not accessible in webpage',
478 'url': 'https://vimeo.com/393756517',
479 'md5': 'c464af248b592190a5ffbb5d33f382b0',
480 'info_dict': {
481 'id': '393756517',
482 'ext': 'mov',
483 'timestamp': 1582642091,
484 'uploader_id': 'frameworkla',
485 'title': 'Straight To Hell - Sabrina: Netflix',
486 'uploader': 'Framework Studio',
487 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
488 'upload_date': '20200225',
489 },
605cad0b 490 },
c143ddce
S
491 {
492 # only available via https://vimeo.com/channels/tributes/6213729 and
493 # not via https://vimeo.com/6213729
494 'url': 'https://vimeo.com/channels/tributes/6213729',
495 'info_dict': {
496 'id': '6213729',
d03beddf 497 'ext': 'mp4',
c143ddce
S
498 'title': 'Vimeo Tribute: The Shining',
499 'uploader': 'Casey Donahue',
ec85ded8 500 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
c143ddce 501 'uploader_id': 'caseydonahue',
d03beddf
S
502 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
503 'channel_id': 'tributes',
c15cd296 504 'timestamp': 1250886430,
c143ddce
S
505 'upload_date': '20090821',
506 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
507 },
508 'params': {
509 'skip_download': True,
510 },
c143ddce 511 },
f16f8505 512 {
cccd70a2 513 # redirects to ondemand extractor and should be passed through it
f16f8505
S
514 # for successful extraction
515 'url': 'https://vimeo.com/73445910',
516 'info_dict': {
517 'id': '73445910',
518 'ext': 'mp4',
519 'title': 'The Reluctant Revolutionary',
520 'uploader': '10Ft Films',
ec85ded8 521 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
f16f8505 522 'uploader_id': 'tenfootfilms',
681ac7c9
RA
523 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
524 'upload_date': '20130830',
525 'timestamp': 1377853339,
f16f8505
S
526 },
527 'params': {
528 'skip_download': True,
529 },
cce889b9 530 'skip': 'this page is no longer available.',
f16f8505 531 },
79fec976
RA
532 {
533 'url': 'http://player.vimeo.com/video/68375962',
534 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
535 'info_dict': {
536 'id': '68375962',
537 'ext': 'mp4',
3867038a 538 'title': 'youtube-dl password protected test video',
79fec976
RA
539 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
540 'uploader_id': 'user18948128',
541 'uploader': 'Jaime Marquínez Ferrándiz',
542 'duration': 10,
543 },
544 'params': {
681ac7c9 545 'format': 'best[protocol=https]',
3867038a 546 'videopassword': 'youtube-dl',
79fec976
RA
547 },
548 },
c143ddce
S
549 {
550 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
551 'only_matching': True,
552 },
8bea039b
LL
553 {
554 'url': 'https://vimeo.com/109815029',
555 'note': 'Video not completely processed, "failed" seed status',
556 'only_matching': True,
557 },
6b7ceee1
S
558 {
559 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
560 'only_matching': True,
561 },
c8e3e097
S
562 {
563 'url': 'https://vimeo.com/album/2632481/video/79010983',
564 'only_matching': True,
565 },
1f52a09e 566 {
567 'url': 'https://vimeo.com/showcase/3253534/video/119195465',
568 'note': 'A video in a password protected album (showcase)',
569 'info_dict': {
570 'id': '119195465',
571 'ext': 'mp4',
572 'title': 'youtube-dl test video \'ä"BaW_jenozKc',
573 'uploader': 'Philipp Hagemeister',
574 'uploader_id': 'user20132939',
575 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
576 'upload_date': '20150209',
577 'timestamp': 1423518307,
578 },
579 'params': {
580 'format': 'best[protocol=https]',
581 'videopassword': 'youtube-dl',
582 },
583 },
16f1131a
S
584 {
585 # source file returns 403: Forbidden
586 'url': 'https://vimeo.com/7809605',
587 'only_matching': True,
588 },
241a318f 589 {
2a6f8475 590 'note': 'Direct URL with hash',
241a318f 591 'url': 'https://vimeo.com/160743502/abd0e13fb4',
2a6f8475 592 'info_dict': {
593 'id': '160743502',
594 'ext': 'mp4',
595 'uploader': 'Julian Tryba',
596 'uploader_id': 'aliniamedia',
597 'title': 'Harrisville New Hampshire',
598 'timestamp': 1459259666,
599 'upload_date': '20160329',
600 },
9cb070f9 601 'params': {'skip_download': True},
602 },
603 {
604 'url': 'https://vimeo.com/138909882',
605 'info_dict': {
606 'id': '138909882',
607 'ext': 'mp4',
608 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!',
609 'description': 'md5:5967e090768a831488f6e74b7821b3c1',
610 'uploader_id': 'fireworkchampions',
611 'uploader': 'Firework Champions',
612 'upload_date': '20150910',
613 'timestamp': 1441901895,
614 },
615 'params': {
616 'skip_download': True,
617 'format': 'Original',
618 },
bc2ca1bb 619 },
1ee34c76 620 {
621 'url': 'https://vimeo.com/channels/staffpicks/143603739',
622 'info_dict': {
623 'id': '143603739',
624 'ext': 'mp4',
625 'uploader': 'Karim Huu Do',
626 'timestamp': 1445846953,
627 'upload_date': '20151026',
628 'title': 'The Shoes - Submarine Feat. Blaine Harrison',
629 'uploader_id': 'karimhd',
630 'description': 'md5:8e2eea76de4504c2e8020a9bcfa1e843',
631 },
632 'params': {'skip_download': 'm3u8'},
633 },
bc2ca1bb 634 {
635 # requires passing unlisted_hash(a52724358e) to load_download_config request
636 'url': 'https://vimeo.com/392479337/a52724358e',
637 'only_matching': True,
9cb070f9 638 },
50e93e03 639 {
640 # similar, but all numeric: ID must be 581039021, not 9603038895
641 # issue #29690
642 'url': 'https://vimeo.com/581039021/9603038895',
643 'info_dict': {
644 'id': '581039021',
645 # these have to be provided but we don't care
646 'ext': 'mp4',
647 'timestamp': 1627621014,
648 'title': 're:.+',
649 'uploader_id': 're:.+',
650 'uploader': 're:.+',
651 'upload_date': r're:\d+',
652 },
653 'params': {
654 'skip_download': True,
655 },
656 }
a1a46075
S
657 # https://gettingthingsdone.com/workflowmap/
658 # vimeo embed with check-password page protected by Referer header
a91b954b 659 ]
b3d14cbf 660
d002e919
S
661 @staticmethod
662 def _smuggle_referrer(url, referrer_url):
663 return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
664
b407e173 665 @staticmethod
09b9c45e
S
666 def _extract_urls(url, webpage):
667 urls = []
b407e173 668 # Look for embedded (iframe) Vimeo player
09b9c45e 669 for mobj in re.finditer(
7c1f4193 670 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
f475e881 671 webpage):
09b9c45e
S
672 urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
673 PLAIN_EMBED_RE = (
674 # Look for embedded (swf embed) Vimeo player
675 r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
676 # Look more for non-standard embedded Vimeo player
677 r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
678 )
679 for embed_re in PLAIN_EMBED_RE:
680 for mobj in re.finditer(embed_re, webpage):
681 urls.append(mobj.group('url'))
682 return urls
683
684 @staticmethod
685 def _extract_url(url, webpage):
686 urls = VimeoIE._extract_urls(url, webpage)
687 return urls[0] if urls else None
b407e173 688
a1a46075 689 def _verify_player_video_password(self, url, video_id, headers):
cce889b9 690 password = self._get_video_password()
79fec976
RA
691 data = urlencode_postdata({
692 'password': base64.b64encode(password.encode()),
693 })
a1a46075
S
694 headers = merge_dicts(headers, {
695 'Content-Type': 'application/x-www-form-urlencoded',
696 })
697 checked = self._download_json(
698 url + '/check-password', video_id,
699 'Verifying the password', data=data, headers=headers)
700 if checked is False:
701 raise ExtractorError('Wrong video password', expected=True)
702 return checked
0eecc6a4 703
fc79158d
JMF
704 def _real_initialize(self):
705 self._login()
706
58ab5cbc 707 def _extract_from_api(self, video_id, unlisted_hash=None):
708 token = self._download_json(
709 'https://vimeo.com/_rv/jwt', video_id, headers={
710 'X-Requested-With': 'XMLHttpRequest'
711 })['token']
712 api_url = 'https://api.vimeo.com/videos/' + video_id
713 if unlisted_hash:
714 api_url += ':' + unlisted_hash
715 video = self._download_json(
716 api_url, video_id, headers={
717 'Authorization': 'jwt ' + token,
718 }, query={
719 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
720 })
721 info = self._parse_config(self._download_json(
722 video['config_url'], video_id), video_id)
723 self._vimeo_sort_formats(info['formats'])
724 get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
725 info.update({
726 'description': video.get('description'),
727 'license': video.get('license'),
728 'release_timestamp': get_timestamp('release'),
729 'timestamp': get_timestamp('created'),
730 'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
731 })
732 connections = try_get(
733 video, lambda x: x['metadata']['connections'], dict) or {}
734 for k in ('comment', 'like'):
735 info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
736 return info
737
1f52a09e 738 def _try_album_password(self, url):
739 album_id = self._search_regex(
740 r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
741 if not album_id:
742 return
743 viewer = self._download_json(
744 'https://vimeo.com/_rv/viewer', album_id, fatal=False)
745 if not viewer:
746 webpage = self._download_webpage(url, album_id)
747 viewer = self._parse_json(self._search_regex(
748 r'bootstrap_data\s*=\s*({.+?})</script>',
749 webpage, 'bootstrap data'), album_id)['viewer']
750 jwt = viewer['jwt']
751 album = self._download_json(
752 'https://api.vimeo.com/albums/' + album_id,
753 album_id, headers={'Authorization': 'jwt ' + jwt},
754 query={'fields': 'description,name,privacy'})
755 if try_get(album, lambda x: x['privacy']['view']) == 'password':
a06916d9 756 password = self.get_param('videopassword')
1f52a09e 757 if not password:
758 raise ExtractorError(
759 'This album is protected by a password, use the --video-password option',
760 expected=True)
761 self._set_vimeo_cookie('vuid', viewer['vuid'])
762 try:
763 self._download_json(
764 'https://vimeo.com/showcase/%s/auth' % album_id,
765 album_id, 'Verifying the password', data=urlencode_postdata({
766 'password': password,
767 'token': viewer['xsrft'],
768 }), headers={
769 'X-Requested-With': 'XMLHttpRequest',
770 })
771 except ExtractorError as e:
772 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
773 raise ExtractorError('Wrong password', expected=True)
774 raise
775
a0088bdf 776 def _real_extract(self, url):
5dbe81a1 777 url, data = unsmuggle_url(url, {})
8b7539d2 778 headers = self.get_param('http_headers').copy()
5dbe81a1 779 if 'http_headers' in data:
5dbe81a1 780 headers.update(data['http_headers'])
ba5d51b3
PH
781 if 'Referer' not in headers:
782 headers['Referer'] = url
9d4660ca 783
b3d14cbf 784 # Extract ID from URL
2a6f8475 785 mobj = self._match_valid_url(url).groupdict()
786 video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
cce889b9 787 if unlisted_hash:
58ab5cbc 788 return self._extract_from_api(video_id, unlisted_hash)
cce889b9 789
58ea7ec8 790 orig_url = url
681ac7c9 791 is_pro = 'vimeopro.com/' in url
681ac7c9 792 if is_pro:
06242d44 793 # some videos require portfolio_id to be present in player url
067aa17e 794 # https://github.com/ytdl-org/youtube-dl/issues/20070
06242d44 795 url = self._extract_url(url, self._download_webpage(url, video_id))
681ac7c9
RA
796 if not url:
797 url = 'https://vimeo.com/' + video_id
40b6495d 798 elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
10831b5e 799 url = 'https://vimeo.com/' + video_id
b3d14cbf 800
1f52a09e 801 self._try_album_password(url)
1060425c 802 try:
681ac7c9
RA
803 # Retrieve video webpage to extract further information
804 webpage, urlh = self._download_webpage_handle(
805 url, video_id, headers=headers)
7947a1f7 806 redirect_url = urlh.geturl()
1060425c
PH
807 except ExtractorError as ee:
808 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
809 errmsg = ee.cause.read()
810 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
811 raise ExtractorError(
812 'Cannot download embed-only video without embedding '
7a5c1cfe 813 'URL. Please call yt-dlp with the URL of the page '
1060425c
PH
814 'that embeds this video.',
815 expected=True)
816 raise
b3d14cbf 817
58ab5cbc 818 if '://player.vimeo.com/video/' in url:
819 config = self._parse_json(self._search_regex(
820 r'\bconfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
821 if config.get('view') == 4:
822 config = self._verify_player_video_password(
823 redirect_url, video_id, headers)
824 info = self._parse_config(config, video_id)
825 self._vimeo_sort_formats(info['formats'])
826 return info
827
828 if re.search(r'<form[^>]+?id="pw_form"', webpage):
829 video_password = self._get_video_password()
830 token, vuid = self._extract_xsrft_and_vuid(webpage)
831 webpage = self._verify_video_password(
832 redirect_url, video_id, video_password, token, vuid)
b3d14cbf 833
eb9c9c74 834 vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
998e6cdb 835 if vimeo_config:
58ab5cbc 836 seed_status = vimeo_config.get('seed_status') or {}
998e6cdb
S
837 if seed_status.get('state') == 'failed':
838 raise ExtractorError(
b6aa99af 839 '%s said: %s' % (self.IE_NAME, seed_status['title']),
998e6cdb
S
840 expected=True)
841
c38a67bc 842 cc_license = None
c15cd296 843 timestamp = None
681ac7c9 844 video_description = None
58ab5cbc 845 info_dict = {}
1ee34c76 846 config_url = None
c38a67bc 847
58ab5cbc 848 channel_id = self._search_regex(
849 r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
850 if channel_id:
851 config_url = self._html_search_regex(
1ee34c76 852 r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
58ab5cbc 853 video_description = clean_html(get_element_by_class('description', webpage))
854 info_dict.update({
855 'channel_id': channel_id,
856 'channel_url': 'https://vimeo.com/channels/' + channel_id,
857 })
1ee34c76 858 if not config_url:
58ab5cbc 859 page_config = self._parse_json(self._search_regex(
860 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
861 webpage, 'page config', default='{}'), video_id, fatal=False)
862 if not page_config:
863 return self._extract_from_api(video_id)
864 config_url = page_config['player']['config_url']
865 cc_license = page_config.get('cc_license')
866 clip = page_config.get('clip') or {}
867 timestamp = clip.get('uploaded_on')
868 video_description = clean_html(
869 clip.get('description') or page_config.get('description_html_escaped'))
870 config = self._download_json(config_url, video_id)
bc2ca1bb 871 video = config.get('video') or {}
872 vod = video.get('vod') or {}
8b40c927 873
6a55bb66
S
874 def is_rented():
875 if '>You rented this title.<' in webpage:
876 return True
58ab5cbc 877 if try_get(config, lambda x: x['user']['purchased']):
6a55bb66 878 return True
58ab5cbc 879 for purchase_option in (vod.get('purchase_options') or []):
8b40c927
RA
880 if purchase_option.get('purchased'):
881 return True
882 label = purchase_option.get('label_string')
883 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
884 return True
6a55bb66
S
885 return False
886
8b40c927
RA
887 if is_rented() and vod.get('is_trailer'):
888 feature_id = vod.get('feature_id')
5dbe81a1
S
889 if feature_id and not data.get('force_feature_id', False):
890 return self.url_result(smuggle_url(
891 'https://player.vimeo.com/player/%s' % feature_id,
892 {'force_feature_id': True}), 'Vimeo')
893
681ac7c9
RA
894 if not video_description:
895 video_description = self._html_search_regex(
896 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
897 webpage, 'description', default=None)
58ea7ec8
PH
898 if not video_description:
899 video_description = self._html_search_meta(
58ab5cbc 900 ['description', 'og:description', 'twitter:description'],
901 webpage, default=None)
681ac7c9 902 if not video_description and is_pro:
58ea7ec8
PH
903 orig_webpage = self._download_webpage(
904 orig_url, video_id,
905 note='Downloading webpage for description',
906 fatal=False)
907 if orig_webpage:
908 video_description = self._html_search_meta(
909 'description', orig_webpage, default=None)
58ab5cbc 910 if not video_description:
6a39ee13 911 self.report_warning('Cannot find video description')
b3d14cbf 912
c15cd296
S
913 if not timestamp:
914 timestamp = self._search_regex(
915 r'<time[^>]+datetime="([^"]+)"', webpage,
916 'timestamp', default=None)
b3d14cbf 917
58ab5cbc 918 view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None))
919 like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None))
920 comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None))
4e761794 921
a6387bfd 922 formats = []
27655037
RA
923
924 source_format = self._extract_original_format(
bc2ca1bb 925 'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
27655037
RA
926 if source_format:
927 formats.append(source_format)
1eac553e 928
ae1c585c
S
929 info_dict_config = self._parse_config(config, video_id)
930 formats.extend(info_dict_config['formats'])
531a7496 931 self._vimeo_sort_formats(formats)
c38a67bc 932
ae1c585c
S
933 json_ld = self._search_json_ld(webpage, video_id, default={})
934
c38a67bc
S
935 if not cc_license:
936 cc_license = self._search_regex(
937 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
938 webpage, 'license', default=None, group='license')
939
58ab5cbc 940 info_dict.update({
531a7496 941 'formats': formats,
c15cd296 942 'timestamp': unified_timestamp(timestamp),
b0268cb6 943 'description': video_description,
9103bbc5 944 'webpage_url': url,
4e761794
JMF
945 'view_count': view_count,
946 'like_count': like_count,
947 'comment_count': comment_count,
c38a67bc 948 'license': cc_license,
58ab5cbc 949 })
531a7496 950
58ab5cbc 951 return merge_dicts(info_dict, info_dict_config, json_ld)
caeefc29
JMF
952
953
681ac7c9 954class VimeoOndemandIE(VimeoIE):
1e501364 955 IE_NAME = 'vimeo:ondemand'
58ab5cbc 956 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
74278def
S
957 _TESTS = [{
958 # ondemand video not available via https://vimeo.com/id
959 'url': 'https://vimeo.com/ondemand/20704',
960 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
961 'info_dict': {
962 'id': '105442900',
963 'ext': 'mp4',
964 'title': 'המעבדה - במאי יותם פלדמן',
965 'uploader': 'גם סרטים',
ec85ded8 966 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
74278def 967 'uploader_id': 'gumfilms',
681ac7c9
RA
968 'description': 'md5:4c027c965e439de4baab621e48b60791',
969 'upload_date': '20140906',
970 'timestamp': 1410032453,
74278def 971 },
1fd0fc42
S
972 'params': {
973 'format': 'best[protocol=https]',
974 },
681ac7c9 975 'expected_warnings': ['Unable to download JSON metadata'],
d002e919
S
976 }, {
977 # requires Referer to be passed along with og:video:url
978 'url': 'https://vimeo.com/ondemand/36938/126682985',
979 'info_dict': {
681ac7c9 980 'id': '126584684',
d002e919
S
981 'ext': 'mp4',
982 'title': 'Rävlock, rätt läte på rätt plats',
983 'uploader': 'Lindroth & Norin',
681ac7c9
RA
984 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
985 'uploader_id': 'lindrothnorin',
986 'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
987 'upload_date': '20150502',
988 'timestamp': 1430586422,
d002e919
S
989 },
990 'params': {
991 'skip_download': True,
992 },
681ac7c9 993 'expected_warnings': ['Unable to download JSON metadata'],
74278def
S
994 }, {
995 'url': 'https://vimeo.com/ondemand/nazmaalik',
996 'only_matching': True,
997 }, {
998 'url': 'https://vimeo.com/ondemand/141692381',
999 'only_matching': True,
1000 }, {
1001 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
1002 'only_matching': True,
1003 }]
1004
74278def 1005
f6c3664d 1006class VimeoChannelIE(VimeoBaseInfoExtractor):
9148eb00 1007 IE_NAME = 'vimeo:channel'
3946864c 1008 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
caeefc29 1009 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
84458766 1010 _TITLE = None
55a10eab 1011 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
2929b3e7 1012 _TESTS = [{
3946864c 1013 'url': 'https://vimeo.com/channels/tributes',
2929b3e7 1014 'info_dict': {
a3fa5da4 1015 'id': 'tributes',
2929b3e7
PH
1016 'title': 'Vimeo Tributes',
1017 },
1018 'playlist_mincount': 25,
1019 }]
681ac7c9 1020 _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
caeefc29 1021
5cc14c2f
JMF
1022 def _page_url(self, base_url, pagenum):
1023 return '%s/videos/page:%d/' % (base_url, pagenum)
1024
fb30ec22 1025 def _extract_list_title(self, webpage):
2605043d
S
1026 return self._TITLE or self._html_search_regex(
1027 self._TITLE_RE, webpage, 'list title', fatal=False)
fb30ec22 1028
2c94198e 1029 def _title_and_entries(self, list_id, base_url):
caeefc29 1030 for pagenum in itertools.count(1):
bf8f082a 1031 page_url = self._page_url(base_url, pagenum)
55a10eab 1032 webpage = self._download_webpage(
bf8f082a 1033 page_url, list_id,
9148eb00 1034 'Downloading page %s' % pagenum)
bf8f082a
PH
1035
1036 if pagenum == 1:
2c94198e
S
1037 yield self._extract_list_title(webpage)
1038
c8e3e097
S
1039 # Try extracting href first since not all videos are available via
1040 # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
1041 clips = re.findall(
04a3d4d2 1042 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
c8e3e097 1043 if clips:
04a3d4d2 1044 for video_id, video_url, video_title in clips:
c8e3e097
S
1045 yield self.url_result(
1046 compat_urlparse.urljoin(base_url, video_url),
04a3d4d2 1047 VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
c8e3e097
S
1048 # More relaxed fallback
1049 else:
1050 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
1051 yield self.url_result(
1052 'https://vimeo.com/%s' % video_id,
1053 VimeoIE.ie_key(), video_id=video_id)
bf8f082a 1054
caeefc29
JMF
1055 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1056 break
1057
2c94198e
S
1058 def _extract_videos(self, list_id, base_url):
1059 title_and_entries = self._title_and_entries(list_id, base_url)
1060 list_title = next(title_and_entries)
1061 return self.playlist_result(title_and_entries, list_id, list_title)
55a10eab
JMF
1062
1063 def _real_extract(self, url):
681ac7c9
RA
1064 channel_id = self._match_id(url)
1065 return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
55a10eab
JMF
1066
1067
1068class VimeoUserIE(VimeoChannelIE):
9148eb00 1069 IE_NAME = 'vimeo:user'
681ac7c9 1070 _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
55a10eab 1071 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
2929b3e7 1072 _TESTS = [{
3946864c 1073 'url': 'https://vimeo.com/nkistudio/videos',
2929b3e7
PH
1074 'info_dict': {
1075 'title': 'Nki',
a3fa5da4 1076 'id': 'nkistudio',
2929b3e7
PH
1077 },
1078 'playlist_mincount': 66,
1079 }]
681ac7c9 1080 _BASE_URL_TEMPL = 'https://vimeo.com/%s'
5cc14c2f
JMF
1081
1082
51c7f40c 1083class VimeoAlbumIE(VimeoBaseInfoExtractor):
9148eb00 1084 IE_NAME = 'vimeo:album'
eb9c9c74 1085 _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
5cc14c2f 1086 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
2929b3e7 1087 _TESTS = [{
d1508cd6 1088 'url': 'https://vimeo.com/album/2632481',
2929b3e7 1089 'info_dict': {
a3fa5da4 1090 'id': '2632481',
2929b3e7
PH
1091 'title': 'Staff Favorites: November 2013',
1092 },
1093 'playlist_mincount': 13,
bf8f082a
PH
1094 }, {
1095 'note': 'Password-protected album',
1096 'url': 'https://vimeo.com/album/3253534',
1097 'info_dict': {
1098 'title': 'test',
1099 'id': '3253534',
1100 },
1101 'playlist_count': 1,
1102 'params': {
3867038a 1103 'videopassword': 'youtube-dl',
bf8f082a 1104 }
2929b3e7 1105 }]
eb9c9c74
RA
1106 _PAGE_SIZE = 100
1107
a0566bbf 1108 def _fetch_page(self, album_id, authorization, hashed_pass, page):
eb9c9c74
RA
1109 api_page = page + 1
1110 query = {
974311b5 1111 'fields': 'link,uri',
eb9c9c74
RA
1112 'page': api_page,
1113 'per_page': self._PAGE_SIZE,
1114 }
1115 if hashed_pass:
1116 query['_hashed_pass'] = hashed_pass
421a4595 1117 try:
1118 videos = self._download_json(
1119 'https://api.vimeo.com/albums/%s/videos' % album_id,
1120 album_id, 'Downloading page %d' % api_page, query=query, headers={
1121 'Authorization': 'jwt ' + authorization,
1122 })['data']
1123 except ExtractorError as e:
1124 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
1125 return
eb9c9c74
RA
1126 for video in videos:
1127 link = video.get('link')
1128 if not link:
1129 continue
974311b5
RA
1130 uri = video.get('uri')
1131 video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
1132 yield self.url_result(link, VimeoIE.ie_key(), video_id)
5cc14c2f
JMF
1133
1134 def _real_extract(self, url):
bf8f082a 1135 album_id = self._match_id(url)
8bdd16b4 1136 viewer = self._download_json(
1137 'https://vimeo.com/_rv/viewer', album_id, fatal=False)
1138 if not viewer:
1139 webpage = self._download_webpage(url, album_id)
1140 viewer = self._parse_json(self._search_regex(
1141 r'bootstrap_data\s*=\s*({.+?})</script>',
1142 webpage, 'bootstrap data'), album_id)['viewer']
51c7f40c
RA
1143 jwt = viewer['jwt']
1144 album = self._download_json(
1145 'https://api.vimeo.com/albums/' + album_id,
1146 album_id, headers={'Authorization': 'jwt ' + jwt},
1147 query={'fields': 'description,name,privacy'})
1148 hashed_pass = None
1149 if try_get(album, lambda x: x['privacy']['view']) == 'password':
a06916d9 1150 password = self.get_param('videopassword')
51c7f40c
RA
1151 if not password:
1152 raise ExtractorError(
1153 'This album is protected by a password, use the --video-password option',
1154 expected=True)
1155 self._set_vimeo_cookie('vuid', viewer['vuid'])
1156 try:
1157 hashed_pass = self._download_json(
1158 'https://vimeo.com/showcase/%s/auth' % album_id,
1159 album_id, 'Verifying the password', data=urlencode_postdata({
1160 'password': password,
1161 'token': viewer['xsrft'],
1162 }), headers={
1163 'X-Requested-With': 'XMLHttpRequest',
1164 })['hashed_pass']
1165 except ExtractorError as e:
1166 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
1167 raise ExtractorError('Wrong password', expected=True)
1168 raise
eb9c9c74 1169 entries = OnDemandPagedList(functools.partial(
51c7f40c
RA
1170 self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
1171 return self.playlist_result(
1172 entries, album_id, album.get('name'), album.get('description'))
fb30ec22
JMF
1173
1174
681ac7c9 1175class VimeoGroupsIE(VimeoChannelIE):
9148eb00 1176 IE_NAME = 'vimeo:group'
681ac7c9 1177 _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
2929b3e7 1178 _TESTS = [{
9cb070f9 1179 'url': 'https://vimeo.com/groups/meetup',
2929b3e7 1180 'info_dict': {
9cb070f9 1181 'id': 'meetup',
1182 'title': 'Vimeo Meetup!',
2929b3e7 1183 },
681ac7c9 1184 'playlist_mincount': 27,
2929b3e7 1185 }]
681ac7c9 1186 _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
fcea44c6
PH
1187
1188
531a7496 1189class VimeoReviewIE(VimeoBaseInfoExtractor):
9148eb00
PH
1190 IE_NAME = 'vimeo:review'
1191 IE_DESC = 'Review pages on vimeo'
27655037 1192 _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
d36d3f42 1193 _TESTS = [{
fcea44c6 1194 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
fcea44c6
PH
1195 'md5': 'c507a72f780cacc12b2248bb4006d253',
1196 'info_dict': {
fc09240e
PH
1197 'id': '75524534',
1198 'ext': 'mp4',
fcea44c6
PH
1199 'title': "DICK HARDWICK 'Comedian'",
1200 'uploader': 'Richard Hardwick',
531a7496 1201 'uploader_id': 'user21297594',
681ac7c9
RA
1202 'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1203 },
d36d3f42
PH
1204 }, {
1205 'note': 'video player needs Referer',
3946864c 1206 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
d36d3f42
PH
1207 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1208 'info_dict': {
1209 'id': '91613211',
1210 'ext': 'mp4',
9dec9930 1211 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
d36d3f42
PH
1212 'uploader': 'DevWeek Events',
1213 'duration': 2773,
ec85ded8 1214 'thumbnail': r're:^https?://.*\.jpg$',
531a7496 1215 'uploader_id': 'user22258446',
681ac7c9
RA
1216 },
1217 'skip': 'video gone',
c1ff6e1a
YCH
1218 }, {
1219 'note': 'Password protected',
1220 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1221 'info_dict': {
1222 'id': '138823582',
1223 'ext': 'mp4',
1224 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1225 'uploader': 'TMB',
1226 'uploader_id': 'user37284429',
1227 },
1228 'params': {
1229 'videopassword': 'holygrail',
1230 },
a093cfc7 1231 'skip': 'video gone',
d36d3f42 1232 }]
fcea44c6 1233
c1ff6e1a
YCH
1234 def _real_initialize(self):
1235 self._login()
1236
fcea44c6 1237 def _real_extract(self, url):
5ad28e7f 1238 page_url, video_id = self._match_valid_url(url).groups()
cce889b9 1239 data = self._download_json(
1240 page_url.replace('/review/', '/review/data/'), video_id)
1241 if data.get('isLocked') is True:
1242 video_password = self._get_video_password()
1243 viewer = self._download_json(
1244 'https://vimeo.com/_rv/viewer', video_id)
1245 webpage = self._verify_video_password(
1246 'https://vimeo.com/' + video_id, video_id,
1247 video_password, viewer['xsrft'], viewer['vuid'])
1248 clip_page_config = self._parse_json(self._search_regex(
1249 r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
1250 webpage, 'clip page config'), video_id)
1251 config_url = clip_page_config['player']['config_url']
1252 clip_data = clip_page_config.get('clip') or {}
1253 else:
1254 clip_data = data['clipData']
1255 config_url = clip_data['configUrl']
c1ff6e1a 1256 config = self._download_json(config_url, video_id)
531a7496 1257 info_dict = self._parse_config(config, video_id)
681ac7c9
RA
1258 source_format = self._extract_original_format(
1259 page_url + '/action', video_id)
27655037
RA
1260 if source_format:
1261 info_dict['formats'].append(source_format)
531a7496 1262 self._vimeo_sort_formats(info_dict['formats'])
681ac7c9 1263 info_dict['description'] = clean_html(clip_data.get('description'))
531a7496 1264 return info_dict
efb7e119
JMF
1265
1266
f6c3664d 1267class VimeoWatchLaterIE(VimeoChannelIE):
efb7e119
JMF
1268 IE_NAME = 'vimeo:watchlater'
1269 IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
84458766
S
1270 _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1271 _TITLE = 'Watch Later'
efb7e119 1272 _LOGIN_REQUIRED = True
2929b3e7 1273 _TESTS = [{
84458766 1274 'url': 'https://vimeo.com/watchlater',
2929b3e7
PH
1275 'only_matching': True,
1276 }]
efb7e119
JMF
1277
1278 def _real_initialize(self):
1279 self._login()
1280
1281 def _page_url(self, base_url, pagenum):
1282 url = '%s/page:%d/' % (base_url, pagenum)
67dda517 1283 request = sanitized_Request(url)
efb7e119
JMF
1284 # Set the header to get a partial html page with the ids,
1285 # the normal page doesn't contain them.
1286 request.add_header('X-Requested-With', 'XMLHttpRequest')
1287 return request
1288
1289 def _real_extract(self, url):
84458766 1290 return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
d6e6a422
PH
1291
1292
091c9b43 1293class VimeoLikesIE(VimeoChannelIE):
361a965b 1294 _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
d6e6a422
PH
1295 IE_NAME = 'vimeo:likes'
1296 IE_DESC = 'Vimeo user likes'
361a965b 1297 _TESTS = [{
9c44d242
PH
1298 'url': 'https://vimeo.com/user755559/likes/',
1299 'playlist_mincount': 293,
611c1dd9 1300 'info_dict': {
091c9b43
S
1301 'id': 'user755559',
1302 'title': 'urza’s Likes',
d6e6a422 1303 },
361a965b
S
1304 }, {
1305 'url': 'https://vimeo.com/stormlapse/likes',
1306 'only_matching': True,
1307 }]
d6e6a422 1308
091c9b43
S
1309 def _page_url(self, base_url, pagenum):
1310 return '%s/page:%d/' % (base_url, pagenum)
1311
d6e6a422
PH
1312 def _real_extract(self, url):
1313 user_id = self._match_id(url)
091c9b43 1314 return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
ca01d178
RA
1315
1316
a1ee23e9 1317class VHXEmbedIE(VimeoBaseInfoExtractor):
ca01d178
RA
1318 IE_NAME = 'vhx:embed'
1319 _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1320
29f7c58a 1321 @staticmethod
1322 def _extract_url(webpage):
1323 mobj = re.search(
1324 r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage)
1325 return unescapeHTML(mobj.group(1)) if mobj else None
1326
ca01d178
RA
1327 def _real_extract(self, url):
1328 video_id = self._match_id(url)
1329 webpage = self._download_webpage(url, video_id)
a1ee23e9
RA
1330 config_url = self._parse_json(self._search_regex(
1331 r'window\.OTTData\s*=\s*({.+})', webpage,
1332 'ott data'), video_id, js_to_json)['config_url']
1333 config = self._download_json(config_url, video_id)
1334 info = self._parse_config(config, video_id)
29f7c58a 1335 info['id'] = video_id
a1ee23e9
RA
1336 self._vimeo_sort_formats(info['formats'])
1337 return info