]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vimeo.py
Initiate new release.
[youtubedl] / youtube_dl / extractor / vimeo.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import base64
5 import functools
6 import json
7 import re
8 import itertools
9
10 from .common import InfoExtractor
11 from ..compat import (
12 compat_kwargs,
13 compat_HTTPError,
14 compat_str,
15 compat_urlparse,
16 )
17 from ..utils import (
18 clean_html,
19 determine_ext,
20 dict_get,
21 ExtractorError,
22 js_to_json,
23 int_or_none,
24 merge_dicts,
25 OnDemandPagedList,
26 parse_filesize,
27 RegexNotFoundError,
28 sanitized_Request,
29 smuggle_url,
30 std_headers,
31 str_or_none,
32 try_get,
33 unified_timestamp,
34 unsmuggle_url,
35 urlencode_postdata,
36 urljoin,
37 unescapeHTML,
38 )
39
40
41 class VimeoBaseInfoExtractor(InfoExtractor):
42 _NETRC_MACHINE = 'vimeo'
43 _LOGIN_REQUIRED = False
44 _LOGIN_URL = 'https://vimeo.com/log_in'
45
46 def _login(self):
47 username, password = self._get_login_info()
48 if username is None:
49 if self._LOGIN_REQUIRED:
50 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
51 return
52 webpage = self._download_webpage(
53 self._LOGIN_URL, None, 'Downloading login page')
54 token, vuid = self._extract_xsrft_and_vuid(webpage)
55 data = {
56 'action': 'login',
57 'email': username,
58 'password': password,
59 'service': 'vimeo',
60 'token': token,
61 }
62 self._set_vimeo_cookie('vuid', vuid)
63 try:
64 self._download_webpage(
65 self._LOGIN_URL, None, 'Logging in',
66 data=urlencode_postdata(data), headers={
67 'Content-Type': 'application/x-www-form-urlencoded',
68 'Referer': self._LOGIN_URL,
69 })
70 except ExtractorError as e:
71 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
72 raise ExtractorError(
73 'Unable to log in: bad username or password',
74 expected=True)
75 raise ExtractorError('Unable to log in')
76
77 def _verify_video_password(self, url, video_id, webpage):
78 password = self._downloader.params.get('videopassword')
79 if password is None:
80 raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
81 token, vuid = self._extract_xsrft_and_vuid(webpage)
82 data = urlencode_postdata({
83 'password': password,
84 'token': token,
85 })
86 if url.startswith('http://'):
87 # vimeo only supports https now, but the user can give an http url
88 url = url.replace('http://', 'https://')
89 password_request = sanitized_Request(url + '/password', data)
90 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
91 password_request.add_header('Referer', url)
92 self._set_vimeo_cookie('vuid', vuid)
93 return self._download_webpage(
94 password_request, video_id,
95 'Verifying the password', 'Wrong password')
96
97 def _extract_xsrft_and_vuid(self, webpage):
98 xsrft = self._search_regex(
99 r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
100 webpage, 'login token', group='xsrft')
101 vuid = self._search_regex(
102 r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
103 webpage, 'vuid', group='vuid')
104 return xsrft, vuid
105
106 def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
107 vimeo_config = self._search_regex(
108 r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
109 webpage, 'vimeo config', *args, **compat_kwargs(kwargs))
110 if vimeo_config:
111 return self._parse_json(vimeo_config, video_id)
112
113 def _set_vimeo_cookie(self, name, value):
114 self._set_cookie('vimeo.com', name, value)
115
116 def _vimeo_sort_formats(self, formats):
117 # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
118 # at the same time without actual units specified. This lead to wrong sorting.
119 self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'tbr', 'format_id'))
120
121 def _parse_config(self, config, video_id):
122 video_data = config['video']
123 video_title = video_data['title']
124 live_event = video_data.get('live_event') or {}
125 is_live = live_event.get('status') == 'started'
126
127 formats = []
128 config_files = video_data.get('files') or config['request'].get('files', {})
129 for f in config_files.get('progressive', []):
130 video_url = f.get('url')
131 if not video_url:
132 continue
133 formats.append({
134 'url': video_url,
135 'format_id': 'http-%s' % f.get('quality'),
136 'width': int_or_none(f.get('width')),
137 'height': int_or_none(f.get('height')),
138 'fps': int_or_none(f.get('fps')),
139 'tbr': int_or_none(f.get('bitrate')),
140 })
141
142 # TODO: fix handling of 308 status code returned for live archive manifest requests
143 sep_pattern = r'/sep/video/'
144 for files_type in ('hls', 'dash'):
145 for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items():
146 manifest_url = cdn_data.get('url')
147 if not manifest_url:
148 continue
149 format_id = '%s-%s' % (files_type, cdn_name)
150 sep_manifest_urls = []
151 if re.search(sep_pattern, manifest_url):
152 for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
153 sep_manifest_urls.append((format_id + suffix, re.sub(
154 sep_pattern, '/%s/' % repl, manifest_url)))
155 else:
156 sep_manifest_urls = [(format_id, manifest_url)]
157 for f_id, m_url in sep_manifest_urls:
158 if files_type == 'hls':
159 formats.extend(self._extract_m3u8_formats(
160 m_url, video_id, 'mp4',
161 'm3u8' if is_live else 'm3u8_native', m3u8_id=f_id,
162 note='Downloading %s m3u8 information' % cdn_name,
163 fatal=False))
164 elif files_type == 'dash':
165 if 'json=1' in m_url:
166 real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
167 if real_m_url:
168 m_url = real_m_url
169 mpd_formats = self._extract_mpd_formats(
170 m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
171 'Downloading %s MPD information' % cdn_name,
172 fatal=False)
173 formats.extend(mpd_formats)
174
175 live_archive = live_event.get('archive') or {}
176 live_archive_source_url = live_archive.get('source_url')
177 if live_archive_source_url and live_archive.get('status') == 'done':
178 formats.append({
179 'format_id': 'live-archive-source',
180 'url': live_archive_source_url,
181 'preference': 1,
182 })
183
184 for f in formats:
185 if f.get('vcodec') == 'none':
186 f['preference'] = -50
187 elif f.get('acodec') == 'none':
188 f['preference'] = -40
189
190 subtitles = {}
191 text_tracks = config['request'].get('text_tracks')
192 if text_tracks:
193 for tt in text_tracks:
194 subtitles[tt['lang']] = [{
195 'ext': 'vtt',
196 'url': urljoin('https://vimeo.com', tt['url']),
197 }]
198
199 thumbnails = []
200 if not is_live:
201 for key, thumb in video_data.get('thumbs', {}).items():
202 thumbnails.append({
203 'id': key,
204 'width': int_or_none(key),
205 'url': thumb,
206 })
207 thumbnail = video_data.get('thumbnail')
208 if thumbnail:
209 thumbnails.append({
210 'url': thumbnail,
211 })
212
213 owner = video_data.get('owner') or {}
214 video_uploader_url = owner.get('url')
215
216 return {
217 'id': str_or_none(video_data.get('id')) or video_id,
218 'title': self._live_title(video_title) if is_live else video_title,
219 'uploader': owner.get('name'),
220 'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
221 'uploader_url': video_uploader_url,
222 'thumbnails': thumbnails,
223 'duration': int_or_none(video_data.get('duration')),
224 'formats': formats,
225 'subtitles': subtitles,
226 'is_live': is_live,
227 }
228
229 def _extract_original_format(self, url, video_id):
230 download_data = self._download_json(
231 url, video_id, fatal=False,
232 query={'action': 'load_download_config'},
233 headers={'X-Requested-With': 'XMLHttpRequest'})
234 if download_data:
235 source_file = download_data.get('source_file')
236 if isinstance(source_file, dict):
237 download_url = source_file.get('download_url')
238 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
239 source_name = source_file.get('public_name', 'Original')
240 if self._is_valid_url(download_url, video_id, '%s video' % source_name):
241 ext = (try_get(
242 source_file, lambda x: x['extension'],
243 compat_str) or determine_ext(
244 download_url, None) or 'mp4').lower()
245 return {
246 'url': download_url,
247 'ext': ext,
248 'width': int_or_none(source_file.get('width')),
249 'height': int_or_none(source_file.get('height')),
250 'filesize': parse_filesize(source_file.get('size')),
251 'format_id': source_name,
252 'preference': 1,
253 }
254
255
256 class VimeoIE(VimeoBaseInfoExtractor):
257 """Information extractor for vimeo.com."""
258
259 # _VALID_URL matches Vimeo URLs
260 _VALID_URL = r'''(?x)
261 https?://
262 (?:
263 (?:
264 www|
265 player
266 )
267 \.
268 )?
269 vimeo(?:pro)?\.com/
270 (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
271 (?:.*?/)?
272 (?:
273 (?:
274 play_redirect_hls|
275 moogaloop\.swf)\?clip_id=
276 )?
277 (?:videos?/)?
278 (?P<id>[0-9]+)
279 (?:/[\da-f]+)?
280 /?(?:[?&].*)?(?:[#].*)?$
281 '''
282 IE_NAME = 'vimeo'
283 _TESTS = [
284 {
285 'url': 'http://vimeo.com/56015672#at=0',
286 'md5': '8879b6cc097e987f02484baf890129e5',
287 'info_dict': {
288 'id': '56015672',
289 'ext': 'mp4',
290 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
291 'description': 'md5:2d3305bad981a06ff79f027f19865021',
292 'timestamp': 1355990239,
293 'upload_date': '20121220',
294 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
295 'uploader_id': 'user7108434',
296 'uploader': 'Filippo Valsorda',
297 'duration': 10,
298 'license': 'by-sa',
299 },
300 'params': {
301 'format': 'best[protocol=https]',
302 },
303 },
304 {
305 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
306 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
307 'note': 'Vimeo Pro video (#1197)',
308 'info_dict': {
309 'id': '68093876',
310 'ext': 'mp4',
311 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
312 'uploader_id': 'openstreetmapus',
313 'uploader': 'OpenStreetMap US',
314 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
315 'description': 'md5:2c362968038d4499f4d79f88458590c1',
316 'duration': 1595,
317 'upload_date': '20130610',
318 'timestamp': 1370893156,
319 },
320 'params': {
321 'format': 'best[protocol=https]',
322 },
323 },
324 {
325 'url': 'http://player.vimeo.com/video/54469442',
326 'md5': '619b811a4417aa4abe78dc653becf511',
327 'note': 'Videos that embed the url in the player page',
328 'info_dict': {
329 'id': '54469442',
330 'ext': 'mp4',
331 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
332 'uploader': 'The BLN & Business of Software',
333 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
334 'uploader_id': 'theblnbusinessofsoftware',
335 'duration': 3610,
336 'description': None,
337 },
338 'params': {
339 'format': 'best[protocol=https]',
340 },
341 'expected_warnings': ['Unable to download JSON metadata'],
342 },
343 {
344 'url': 'http://vimeo.com/68375962',
345 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
346 'note': 'Video protected with password',
347 'info_dict': {
348 'id': '68375962',
349 'ext': 'mp4',
350 'title': 'youtube-dl password protected test video',
351 'timestamp': 1371200155,
352 'upload_date': '20130614',
353 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
354 'uploader_id': 'user18948128',
355 'uploader': 'Jaime Marquínez Ferrándiz',
356 'duration': 10,
357 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
358 },
359 'params': {
360 'format': 'best[protocol=https]',
361 'videopassword': 'youtube-dl',
362 },
363 },
364 {
365 'url': 'http://vimeo.com/channels/keypeele/75629013',
366 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
367 'info_dict': {
368 'id': '75629013',
369 'ext': 'mp4',
370 'title': 'Key & Peele: Terrorist Interrogation',
371 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
372 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
373 'uploader_id': 'atencio',
374 'uploader': 'Peter Atencio',
375 'channel_id': 'keypeele',
376 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
377 'timestamp': 1380339469,
378 'upload_date': '20130928',
379 'duration': 187,
380 },
381 'expected_warnings': ['Unable to download JSON metadata'],
382 },
383 {
384 'url': 'http://vimeo.com/76979871',
385 'note': 'Video with subtitles',
386 'info_dict': {
387 'id': '76979871',
388 'ext': 'mp4',
389 'title': 'The New Vimeo Player (You Know, For Videos)',
390 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
391 'timestamp': 1381846109,
392 'upload_date': '20131015',
393 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
394 'uploader_id': 'staff',
395 'uploader': 'Vimeo Staff',
396 'duration': 62,
397 }
398 },
399 {
400 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
401 'url': 'https://player.vimeo.com/video/98044508',
402 'note': 'The js code contains assignments to the same variable as the config',
403 'info_dict': {
404 'id': '98044508',
405 'ext': 'mp4',
406 'title': 'Pier Solar OUYA Official Trailer',
407 'uploader': 'Tulio Gonçalves',
408 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
409 'uploader_id': 'user28849593',
410 },
411 },
412 {
413 # contains original format
414 'url': 'https://vimeo.com/33951933',
415 'md5': '53c688fa95a55bf4b7293d37a89c5c53',
416 'info_dict': {
417 'id': '33951933',
418 'ext': 'mp4',
419 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
420 'uploader': 'The DMCI',
421 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
422 'uploader_id': 'dmci',
423 'timestamp': 1324343742,
424 'upload_date': '20111220',
425 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
426 },
427 },
428 {
429 # only available via https://vimeo.com/channels/tributes/6213729 and
430 # not via https://vimeo.com/6213729
431 'url': 'https://vimeo.com/channels/tributes/6213729',
432 'info_dict': {
433 'id': '6213729',
434 'ext': 'mp4',
435 'title': 'Vimeo Tribute: The Shining',
436 'uploader': 'Casey Donahue',
437 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
438 'uploader_id': 'caseydonahue',
439 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
440 'channel_id': 'tributes',
441 'timestamp': 1250886430,
442 'upload_date': '20090821',
443 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
444 },
445 'params': {
446 'skip_download': True,
447 },
448 'expected_warnings': ['Unable to download JSON metadata'],
449 },
450 {
451 # redirects to ondemand extractor and should be passed through it
452 # for successful extraction
453 'url': 'https://vimeo.com/73445910',
454 'info_dict': {
455 'id': '73445910',
456 'ext': 'mp4',
457 'title': 'The Reluctant Revolutionary',
458 'uploader': '10Ft Films',
459 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
460 'uploader_id': 'tenfootfilms',
461 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
462 'upload_date': '20130830',
463 'timestamp': 1377853339,
464 },
465 'params': {
466 'skip_download': True,
467 },
468 'expected_warnings': ['Unable to download JSON metadata'],
469 },
470 {
471 'url': 'http://player.vimeo.com/video/68375962',
472 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
473 'info_dict': {
474 'id': '68375962',
475 'ext': 'mp4',
476 'title': 'youtube-dl password protected test video',
477 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
478 'uploader_id': 'user18948128',
479 'uploader': 'Jaime Marquínez Ferrándiz',
480 'duration': 10,
481 },
482 'params': {
483 'format': 'best[protocol=https]',
484 'videopassword': 'youtube-dl',
485 },
486 },
487 {
488 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
489 'only_matching': True,
490 },
491 {
492 'url': 'https://vimeo.com/109815029',
493 'note': 'Video not completely processed, "failed" seed status',
494 'only_matching': True,
495 },
496 {
497 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
498 'only_matching': True,
499 },
500 {
501 'url': 'https://vimeo.com/album/2632481/video/79010983',
502 'only_matching': True,
503 },
504 {
505 # source file returns 403: Forbidden
506 'url': 'https://vimeo.com/7809605',
507 'only_matching': True,
508 },
509 {
510 'url': 'https://vimeo.com/160743502/abd0e13fb4',
511 'only_matching': True,
512 }
513 # https://gettingthingsdone.com/workflowmap/
514 # vimeo embed with check-password page protected by Referer header
515 ]
516
517 @staticmethod
518 def _smuggle_referrer(url, referrer_url):
519 return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
520
521 @staticmethod
522 def _extract_urls(url, webpage):
523 urls = []
524 # Look for embedded (iframe) Vimeo player
525 for mobj in re.finditer(
526 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
527 webpage):
528 urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
529 PLAIN_EMBED_RE = (
530 # Look for embedded (swf embed) Vimeo player
531 r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
532 # Look more for non-standard embedded Vimeo player
533 r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
534 )
535 for embed_re in PLAIN_EMBED_RE:
536 for mobj in re.finditer(embed_re, webpage):
537 urls.append(mobj.group('url'))
538 return urls
539
540 @staticmethod
541 def _extract_url(url, webpage):
542 urls = VimeoIE._extract_urls(url, webpage)
543 return urls[0] if urls else None
544
545 def _verify_player_video_password(self, url, video_id, headers):
546 password = self._downloader.params.get('videopassword')
547 if password is None:
548 raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
549 data = urlencode_postdata({
550 'password': base64.b64encode(password.encode()),
551 })
552 headers = merge_dicts(headers, {
553 'Content-Type': 'application/x-www-form-urlencoded',
554 })
555 checked = self._download_json(
556 url + '/check-password', video_id,
557 'Verifying the password', data=data, headers=headers)
558 if checked is False:
559 raise ExtractorError('Wrong video password', expected=True)
560 return checked
561
562 def _real_initialize(self):
563 self._login()
564
565 def _real_extract(self, url):
566 url, data = unsmuggle_url(url, {})
567 headers = std_headers.copy()
568 if 'http_headers' in data:
569 headers.update(data['http_headers'])
570 if 'Referer' not in headers:
571 headers['Referer'] = url
572
573 channel_id = self._search_regex(
574 r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
575
576 # Extract ID from URL
577 video_id = self._match_id(url)
578 orig_url = url
579 is_pro = 'vimeopro.com/' in url
580 is_player = '://player.vimeo.com/video/' in url
581 if is_pro:
582 # some videos require portfolio_id to be present in player url
583 # https://github.com/ytdl-org/youtube-dl/issues/20070
584 url = self._extract_url(url, self._download_webpage(url, video_id))
585 if not url:
586 url = 'https://vimeo.com/' + video_id
587 elif is_player:
588 url = 'https://player.vimeo.com/video/' + video_id
589 elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
590 url = 'https://vimeo.com/' + video_id
591
592 try:
593 # Retrieve video webpage to extract further information
594 webpage, urlh = self._download_webpage_handle(
595 url, video_id, headers=headers)
596 redirect_url = urlh.geturl()
597 except ExtractorError as ee:
598 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
599 errmsg = ee.cause.read()
600 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
601 raise ExtractorError(
602 'Cannot download embed-only video without embedding '
603 'URL. Please call youtube-dl with the URL of the page '
604 'that embeds this video.',
605 expected=True)
606 raise
607
608 # Now we begin extracting as much information as we can from what we
609 # retrieved. First we extract the information common to all extractors,
610 # and latter we extract those that are Vimeo specific.
611 self.report_extraction(video_id)
612
613 vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
614 if vimeo_config:
615 seed_status = vimeo_config.get('seed_status', {})
616 if seed_status.get('state') == 'failed':
617 raise ExtractorError(
618 '%s said: %s' % (self.IE_NAME, seed_status['title']),
619 expected=True)
620
621 cc_license = None
622 timestamp = None
623 video_description = None
624
625 # Extract the config JSON
626 try:
627 try:
628 config_url = self._html_search_regex(
629 r' data-config-url="(.+?)"', webpage,
630 'config URL', default=None)
631 if not config_url:
632 # Sometimes new react-based page is served instead of old one that require
633 # different config URL extraction approach (see
634 # https://github.com/ytdl-org/youtube-dl/pull/7209)
635 page_config = self._parse_json(self._search_regex(
636 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
637 webpage, 'page config'), video_id)
638 config_url = page_config['player']['config_url']
639 cc_license = page_config.get('cc_license')
640 timestamp = try_get(
641 page_config, lambda x: x['clip']['uploaded_on'],
642 compat_str)
643 video_description = clean_html(dict_get(
644 page_config, ('description', 'description_html_escaped')))
645 config = self._download_json(config_url, video_id)
646 except RegexNotFoundError:
647 # For pro videos or player.vimeo.com urls
648 # We try to find out to which variable is assigned the config dic
649 m_variable_name = re.search(r'(\w)\.video\.id', webpage)
650 if m_variable_name is not None:
651 config_re = [r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))]
652 else:
653 config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
654 config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;')
655 config_re.append(r'\bconfig\s*=\s*({.+?})\s*;')
656 config = self._search_regex(config_re, webpage, 'info section',
657 flags=re.DOTALL)
658 config = json.loads(config)
659 except Exception as e:
660 if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
661 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
662
663 if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
664 if '_video_password_verified' in data:
665 raise ExtractorError('video password verification failed!')
666 self._verify_video_password(redirect_url, video_id, webpage)
667 return self._real_extract(
668 smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
669 else:
670 raise ExtractorError('Unable to extract info section',
671 cause=e)
672 else:
673 if config.get('view') == 4:
674 config = self._verify_player_video_password(redirect_url, video_id, headers)
675
676 vod = config.get('video', {}).get('vod', {})
677
678 def is_rented():
679 if '>You rented this title.<' in webpage:
680 return True
681 if config.get('user', {}).get('purchased'):
682 return True
683 for purchase_option in vod.get('purchase_options', []):
684 if purchase_option.get('purchased'):
685 return True
686 label = purchase_option.get('label_string')
687 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
688 return True
689 return False
690
691 if is_rented() and vod.get('is_trailer'):
692 feature_id = vod.get('feature_id')
693 if feature_id and not data.get('force_feature_id', False):
694 return self.url_result(smuggle_url(
695 'https://player.vimeo.com/player/%s' % feature_id,
696 {'force_feature_id': True}), 'Vimeo')
697
698 # Extract video description
699 if not video_description:
700 video_description = self._html_search_regex(
701 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
702 webpage, 'description', default=None)
703 if not video_description:
704 video_description = self._html_search_meta(
705 'description', webpage, default=None)
706 if not video_description and is_pro:
707 orig_webpage = self._download_webpage(
708 orig_url, video_id,
709 note='Downloading webpage for description',
710 fatal=False)
711 if orig_webpage:
712 video_description = self._html_search_meta(
713 'description', orig_webpage, default=None)
714 if not video_description and not is_player:
715 self._downloader.report_warning('Cannot find video description')
716
717 # Extract upload date
718 if not timestamp:
719 timestamp = self._search_regex(
720 r'<time[^>]+datetime="([^"]+)"', webpage,
721 'timestamp', default=None)
722
723 try:
724 view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
725 like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
726 comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
727 except RegexNotFoundError:
728 # This info is only available in vimeo.com/{id} urls
729 view_count = None
730 like_count = None
731 comment_count = None
732
733 formats = []
734
735 source_format = self._extract_original_format(
736 'https://vimeo.com/' + video_id, video_id)
737 if source_format:
738 formats.append(source_format)
739
740 info_dict_config = self._parse_config(config, video_id)
741 formats.extend(info_dict_config['formats'])
742 self._vimeo_sort_formats(formats)
743
744 json_ld = self._search_json_ld(webpage, video_id, default={})
745
746 if not cc_license:
747 cc_license = self._search_regex(
748 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
749 webpage, 'license', default=None, group='license')
750
751 channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
752
753 info_dict = {
754 'formats': formats,
755 'timestamp': unified_timestamp(timestamp),
756 'description': video_description,
757 'webpage_url': url,
758 'view_count': view_count,
759 'like_count': like_count,
760 'comment_count': comment_count,
761 'license': cc_license,
762 'channel_id': channel_id,
763 'channel_url': channel_url,
764 }
765
766 info_dict = merge_dicts(info_dict, info_dict_config, json_ld)
767
768 return info_dict
769
770
771 class VimeoOndemandIE(VimeoIE):
772 IE_NAME = 'vimeo:ondemand'
773 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/([^/]+/)?(?P<id>[^/?#&]+)'
774 _TESTS = [{
775 # ondemand video not available via https://vimeo.com/id
776 'url': 'https://vimeo.com/ondemand/20704',
777 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
778 'info_dict': {
779 'id': '105442900',
780 'ext': 'mp4',
781 'title': 'המעבדה - במאי יותם פלדמן',
782 'uploader': 'גם סרטים',
783 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
784 'uploader_id': 'gumfilms',
785 'description': 'md5:4c027c965e439de4baab621e48b60791',
786 'upload_date': '20140906',
787 'timestamp': 1410032453,
788 },
789 'params': {
790 'format': 'best[protocol=https]',
791 },
792 'expected_warnings': ['Unable to download JSON metadata'],
793 }, {
794 # requires Referer to be passed along with og:video:url
795 'url': 'https://vimeo.com/ondemand/36938/126682985',
796 'info_dict': {
797 'id': '126584684',
798 'ext': 'mp4',
799 'title': 'Rävlock, rätt läte på rätt plats',
800 'uploader': 'Lindroth & Norin',
801 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
802 'uploader_id': 'lindrothnorin',
803 'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
804 'upload_date': '20150502',
805 'timestamp': 1430586422,
806 },
807 'params': {
808 'skip_download': True,
809 },
810 'expected_warnings': ['Unable to download JSON metadata'],
811 }, {
812 'url': 'https://vimeo.com/ondemand/nazmaalik',
813 'only_matching': True,
814 }, {
815 'url': 'https://vimeo.com/ondemand/141692381',
816 'only_matching': True,
817 }, {
818 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
819 'only_matching': True,
820 }]
821
822
823 class VimeoChannelIE(VimeoBaseInfoExtractor):
824 IE_NAME = 'vimeo:channel'
825 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
826 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
827 _TITLE = None
828 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
829 _TESTS = [{
830 'url': 'https://vimeo.com/channels/tributes',
831 'info_dict': {
832 'id': 'tributes',
833 'title': 'Vimeo Tributes',
834 },
835 'playlist_mincount': 25,
836 }]
837 _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
838
839 def _page_url(self, base_url, pagenum):
840 return '%s/videos/page:%d/' % (base_url, pagenum)
841
842 def _extract_list_title(self, webpage):
843 return self._TITLE or self._html_search_regex(
844 self._TITLE_RE, webpage, 'list title', fatal=False)
845
846 def _title_and_entries(self, list_id, base_url):
847 for pagenum in itertools.count(1):
848 page_url = self._page_url(base_url, pagenum)
849 webpage = self._download_webpage(
850 page_url, list_id,
851 'Downloading page %s' % pagenum)
852
853 if pagenum == 1:
854 yield self._extract_list_title(webpage)
855
856 # Try extracting href first since not all videos are available via
857 # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
858 clips = re.findall(
859 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
860 if clips:
861 for video_id, video_url, video_title in clips:
862 yield self.url_result(
863 compat_urlparse.urljoin(base_url, video_url),
864 VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
865 # More relaxed fallback
866 else:
867 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
868 yield self.url_result(
869 'https://vimeo.com/%s' % video_id,
870 VimeoIE.ie_key(), video_id=video_id)
871
872 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
873 break
874
875 def _extract_videos(self, list_id, base_url):
876 title_and_entries = self._title_and_entries(list_id, base_url)
877 list_title = next(title_and_entries)
878 return self.playlist_result(title_and_entries, list_id, list_title)
879
880 def _real_extract(self, url):
881 channel_id = self._match_id(url)
882 return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
883
884
885 class VimeoUserIE(VimeoChannelIE):
886 IE_NAME = 'vimeo:user'
887 _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
888 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
889 _TESTS = [{
890 'url': 'https://vimeo.com/nkistudio/videos',
891 'info_dict': {
892 'title': 'Nki',
893 'id': 'nkistudio',
894 },
895 'playlist_mincount': 66,
896 }]
897 _BASE_URL_TEMPL = 'https://vimeo.com/%s'
898
899
900 class VimeoAlbumIE(VimeoBaseInfoExtractor):
901 IE_NAME = 'vimeo:album'
902 _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
903 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
904 _TESTS = [{
905 'url': 'https://vimeo.com/album/2632481',
906 'info_dict': {
907 'id': '2632481',
908 'title': 'Staff Favorites: November 2013',
909 },
910 'playlist_mincount': 13,
911 }, {
912 'note': 'Password-protected album',
913 'url': 'https://vimeo.com/album/3253534',
914 'info_dict': {
915 'title': 'test',
916 'id': '3253534',
917 },
918 'playlist_count': 1,
919 'params': {
920 'videopassword': 'youtube-dl',
921 }
922 }]
923 _PAGE_SIZE = 100
924
925 def _fetch_page(self, album_id, authorizaion, hashed_pass, page):
926 api_page = page + 1
927 query = {
928 'fields': 'link,uri',
929 'page': api_page,
930 'per_page': self._PAGE_SIZE,
931 }
932 if hashed_pass:
933 query['_hashed_pass'] = hashed_pass
934 videos = self._download_json(
935 'https://api.vimeo.com/albums/%s/videos' % album_id,
936 album_id, 'Downloading page %d' % api_page, query=query, headers={
937 'Authorization': 'jwt ' + authorizaion,
938 })['data']
939 for video in videos:
940 link = video.get('link')
941 if not link:
942 continue
943 uri = video.get('uri')
944 video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
945 yield self.url_result(link, VimeoIE.ie_key(), video_id)
946
947 def _real_extract(self, url):
948 album_id = self._match_id(url)
949 webpage = self._download_webpage(url, album_id)
950 viewer = self._parse_json(self._search_regex(
951 r'bootstrap_data\s*=\s*({.+?})</script>',
952 webpage, 'bootstrap data'), album_id)['viewer']
953 jwt = viewer['jwt']
954 album = self._download_json(
955 'https://api.vimeo.com/albums/' + album_id,
956 album_id, headers={'Authorization': 'jwt ' + jwt},
957 query={'fields': 'description,name,privacy'})
958 hashed_pass = None
959 if try_get(album, lambda x: x['privacy']['view']) == 'password':
960 password = self._downloader.params.get('videopassword')
961 if not password:
962 raise ExtractorError(
963 'This album is protected by a password, use the --video-password option',
964 expected=True)
965 self._set_vimeo_cookie('vuid', viewer['vuid'])
966 try:
967 hashed_pass = self._download_json(
968 'https://vimeo.com/showcase/%s/auth' % album_id,
969 album_id, 'Verifying the password', data=urlencode_postdata({
970 'password': password,
971 'token': viewer['xsrft'],
972 }), headers={
973 'X-Requested-With': 'XMLHttpRequest',
974 })['hashed_pass']
975 except ExtractorError as e:
976 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
977 raise ExtractorError('Wrong password', expected=True)
978 raise
979 entries = OnDemandPagedList(functools.partial(
980 self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
981 return self.playlist_result(
982 entries, album_id, album.get('name'), album.get('description'))
983
984
985 class VimeoGroupsIE(VimeoChannelIE):
986 IE_NAME = 'vimeo:group'
987 _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
988 _TESTS = [{
989 'url': 'https://vimeo.com/groups/kattykay',
990 'info_dict': {
991 'id': 'kattykay',
992 'title': 'Katty Kay',
993 },
994 'playlist_mincount': 27,
995 }]
996 _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
997
998
999 class VimeoReviewIE(VimeoBaseInfoExtractor):
1000 IE_NAME = 'vimeo:review'
1001 IE_DESC = 'Review pages on vimeo'
1002 _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1003 _TESTS = [{
1004 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1005 'md5': 'c507a72f780cacc12b2248bb4006d253',
1006 'info_dict': {
1007 'id': '75524534',
1008 'ext': 'mp4',
1009 'title': "DICK HARDWICK 'Comedian'",
1010 'uploader': 'Richard Hardwick',
1011 'uploader_id': 'user21297594',
1012 'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1013 },
1014 'expected_warnings': ['Unable to download JSON metadata'],
1015 }, {
1016 'note': 'video player needs Referer',
1017 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1018 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1019 'info_dict': {
1020 'id': '91613211',
1021 'ext': 'mp4',
1022 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1023 'uploader': 'DevWeek Events',
1024 'duration': 2773,
1025 'thumbnail': r're:^https?://.*\.jpg$',
1026 'uploader_id': 'user22258446',
1027 },
1028 'skip': 'video gone',
1029 }, {
1030 'note': 'Password protected',
1031 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1032 'info_dict': {
1033 'id': '138823582',
1034 'ext': 'mp4',
1035 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1036 'uploader': 'TMB',
1037 'uploader_id': 'user37284429',
1038 },
1039 'params': {
1040 'videopassword': 'holygrail',
1041 },
1042 'skip': 'video gone',
1043 }]
1044
1045 def _real_initialize(self):
1046 self._login()
1047
1048 def _real_extract(self, url):
1049 page_url, video_id = re.match(self._VALID_URL, url).groups()
1050 clip_data = self._download_json(
1051 page_url.replace('/review/', '/review/data/'),
1052 video_id)['clipData']
1053 config_url = clip_data['configUrl']
1054 config = self._download_json(config_url, video_id)
1055 info_dict = self._parse_config(config, video_id)
1056 source_format = self._extract_original_format(
1057 page_url + '/action', video_id)
1058 if source_format:
1059 info_dict['formats'].append(source_format)
1060 self._vimeo_sort_formats(info_dict['formats'])
1061 info_dict['description'] = clean_html(clip_data.get('description'))
1062 return info_dict
1063
1064
1065 class VimeoWatchLaterIE(VimeoChannelIE):
1066 IE_NAME = 'vimeo:watchlater'
1067 IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
1068 _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1069 _TITLE = 'Watch Later'
1070 _LOGIN_REQUIRED = True
1071 _TESTS = [{
1072 'url': 'https://vimeo.com/watchlater',
1073 'only_matching': True,
1074 }]
1075
1076 def _real_initialize(self):
1077 self._login()
1078
1079 def _page_url(self, base_url, pagenum):
1080 url = '%s/page:%d/' % (base_url, pagenum)
1081 request = sanitized_Request(url)
1082 # Set the header to get a partial html page with the ids,
1083 # the normal page doesn't contain them.
1084 request.add_header('X-Requested-With', 'XMLHttpRequest')
1085 return request
1086
1087 def _real_extract(self, url):
1088 return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1089
1090
1091 class VimeoLikesIE(VimeoChannelIE):
1092 _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1093 IE_NAME = 'vimeo:likes'
1094 IE_DESC = 'Vimeo user likes'
1095 _TESTS = [{
1096 'url': 'https://vimeo.com/user755559/likes/',
1097 'playlist_mincount': 293,
1098 'info_dict': {
1099 'id': 'user755559',
1100 'title': 'urza’s Likes',
1101 },
1102 }, {
1103 'url': 'https://vimeo.com/stormlapse/likes',
1104 'only_matching': True,
1105 }]
1106
1107 def _page_url(self, base_url, pagenum):
1108 return '%s/page:%d/' % (base_url, pagenum)
1109
1110 def _real_extract(self, url):
1111 user_id = self._match_id(url)
1112 return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
1113
1114
1115 class VHXEmbedIE(VimeoBaseInfoExtractor):
1116 IE_NAME = 'vhx:embed'
1117 _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1118
1119 def _real_extract(self, url):
1120 video_id = self._match_id(url)
1121 webpage = self._download_webpage(url, video_id)
1122 config_url = self._parse_json(self._search_regex(
1123 r'window\.OTTData\s*=\s*({.+})', webpage,
1124 'ott data'), video_id, js_to_json)['config_url']
1125 config = self._download_json(config_url, video_id)
1126 info = self._parse_config(config, video_id)
1127 self._vimeo_sort_formats(info['formats'])
1128 return info