]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vimeo.py
New upstream version 2019.09.28
[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 determine_ext,
19 ExtractorError,
20 js_to_json,
21 int_or_none,
22 merge_dicts,
23 NO_DEFAULT,
24 OnDemandPagedList,
25 parse_filesize,
26 qualities,
27 RegexNotFoundError,
28 sanitized_Request,
29 smuggle_url,
30 std_headers,
31 try_get,
32 unified_timestamp,
33 unsmuggle_url,
34 urlencode_postdata,
35 unescapeHTML,
36 )
37
38
39 class VimeoBaseInfoExtractor(InfoExtractor):
40 _NETRC_MACHINE = 'vimeo'
41 _LOGIN_REQUIRED = False
42 _LOGIN_URL = 'https://vimeo.com/log_in'
43
44 def _login(self):
45 username, password = self._get_login_info()
46 if username is None:
47 if self._LOGIN_REQUIRED:
48 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
49 return
50 webpage = self._download_webpage(
51 self._LOGIN_URL, None, 'Downloading login page')
52 token, vuid = self._extract_xsrft_and_vuid(webpage)
53 data = {
54 'action': 'login',
55 'email': username,
56 'password': password,
57 'service': 'vimeo',
58 'token': token,
59 }
60 self._set_vimeo_cookie('vuid', 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, compat_HTTPError) and e.cause.code == 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 _verify_video_password(self, url, video_id, webpage):
76 password = self._downloader.params.get('videopassword')
77 if password is None:
78 raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
79 token, vuid = self._extract_xsrft_and_vuid(webpage)
80 data = urlencode_postdata({
81 'password': password,
82 'token': token,
83 })
84 if url.startswith('http://'):
85 # vimeo only supports https now, but the user can give an http url
86 url = url.replace('http://', 'https://')
87 password_request = sanitized_Request(url + '/password', data)
88 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
89 password_request.add_header('Referer', url)
90 self._set_vimeo_cookie('vuid', vuid)
91 return self._download_webpage(
92 password_request, video_id,
93 'Verifying the password', 'Wrong password')
94
95 def _extract_xsrft_and_vuid(self, webpage):
96 xsrft = self._search_regex(
97 r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
98 webpage, 'login token', group='xsrft')
99 vuid = self._search_regex(
100 r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
101 webpage, 'vuid', group='vuid')
102 return xsrft, vuid
103
104 def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
105 vimeo_config = self._search_regex(
106 r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
107 webpage, 'vimeo config', *args, **compat_kwargs(kwargs))
108 if vimeo_config:
109 return self._parse_json(vimeo_config, video_id)
110
111 def _set_vimeo_cookie(self, name, value):
112 self._set_cookie('vimeo.com', name, value)
113
114 def _vimeo_sort_formats(self, formats):
115 # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
116 # at the same time without actual units specified. This lead to wrong sorting.
117 self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'tbr', 'format_id'))
118
119 def _parse_config(self, config, video_id):
120 video_data = config['video']
121 video_title = video_data['title']
122 live_event = video_data.get('live_event') or {}
123 is_live = live_event.get('status') == 'started'
124
125 formats = []
126 config_files = video_data.get('files') or config['request'].get('files', {})
127 for f in config_files.get('progressive', []):
128 video_url = f.get('url')
129 if not video_url:
130 continue
131 formats.append({
132 'url': video_url,
133 'format_id': 'http-%s' % f.get('quality'),
134 'width': int_or_none(f.get('width')),
135 'height': int_or_none(f.get('height')),
136 'fps': int_or_none(f.get('fps')),
137 'tbr': int_or_none(f.get('bitrate')),
138 })
139
140 # TODO: fix handling of 308 status code returned for live archive manifest requests
141 for files_type in ('hls', 'dash'):
142 for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items():
143 manifest_url = cdn_data.get('url')
144 if not manifest_url:
145 continue
146 format_id = '%s-%s' % (files_type, cdn_name)
147 if files_type == 'hls':
148 formats.extend(self._extract_m3u8_formats(
149 manifest_url, video_id, 'mp4',
150 'm3u8' if is_live else 'm3u8_native', m3u8_id=format_id,
151 note='Downloading %s m3u8 information' % cdn_name,
152 fatal=False))
153 elif files_type == 'dash':
154 mpd_pattern = r'/%s/(?:sep/)?video/' % video_id
155 mpd_manifest_urls = []
156 if re.search(mpd_pattern, manifest_url):
157 for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
158 mpd_manifest_urls.append((format_id + suffix, re.sub(
159 mpd_pattern, '/%s/%s/' % (video_id, repl), manifest_url)))
160 else:
161 mpd_manifest_urls = [(format_id, manifest_url)]
162 for f_id, m_url in mpd_manifest_urls:
163 if 'json=1' in m_url:
164 real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
165 if real_m_url:
166 m_url = real_m_url
167 mpd_formats = self._extract_mpd_formats(
168 m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
169 'Downloading %s MPD information' % cdn_name,
170 fatal=False)
171 for f in mpd_formats:
172 if f.get('vcodec') == 'none':
173 f['preference'] = -50
174 elif f.get('acodec') == 'none':
175 f['preference'] = -40
176 formats.extend(mpd_formats)
177
178 live_archive = live_event.get('archive') or {}
179 live_archive_source_url = live_archive.get('source_url')
180 if live_archive_source_url and live_archive.get('status') == 'done':
181 formats.append({
182 'format_id': 'live-archive-source',
183 'url': live_archive_source_url,
184 'preference': 1,
185 })
186
187 subtitles = {}
188 text_tracks = config['request'].get('text_tracks')
189 if text_tracks:
190 for tt in text_tracks:
191 subtitles[tt['lang']] = [{
192 'ext': 'vtt',
193 'url': 'https://vimeo.com' + tt['url'],
194 }]
195
196 thumbnails = []
197 if not is_live:
198 for key, thumb in video_data.get('thumbs', {}).items():
199 thumbnails.append({
200 'id': key,
201 'width': int_or_none(key),
202 'url': thumb,
203 })
204 thumbnail = video_data.get('thumbnail')
205 if thumbnail:
206 thumbnails.append({
207 'url': thumbnail,
208 })
209
210 owner = video_data.get('owner') or {}
211 video_uploader_url = owner.get('url')
212
213 return {
214 'title': self._live_title(video_title) if is_live else video_title,
215 'uploader': owner.get('name'),
216 'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
217 'uploader_url': video_uploader_url,
218 'thumbnails': thumbnails,
219 'duration': int_or_none(video_data.get('duration')),
220 'formats': formats,
221 'subtitles': subtitles,
222 'is_live': is_live,
223 }
224
225 def _extract_original_format(self, url, video_id):
226 download_data = self._download_json(
227 url, video_id, fatal=False,
228 query={'action': 'load_download_config'},
229 headers={'X-Requested-With': 'XMLHttpRequest'})
230 if download_data:
231 source_file = download_data.get('source_file')
232 if isinstance(source_file, dict):
233 download_url = source_file.get('download_url')
234 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
235 source_name = source_file.get('public_name', 'Original')
236 if self._is_valid_url(download_url, video_id, '%s video' % source_name):
237 ext = (try_get(
238 source_file, lambda x: x['extension'],
239 compat_str) or determine_ext(
240 download_url, None) or 'mp4').lower()
241 return {
242 'url': download_url,
243 'ext': ext,
244 'width': int_or_none(source_file.get('width')),
245 'height': int_or_none(source_file.get('height')),
246 'filesize': parse_filesize(source_file.get('size')),
247 'format_id': source_name,
248 'preference': 1,
249 }
250
251
252 class VimeoIE(VimeoBaseInfoExtractor):
253 """Information extractor for vimeo.com."""
254
255 # _VALID_URL matches Vimeo URLs
256 _VALID_URL = r'''(?x)
257 https?://
258 (?:
259 (?:
260 www|
261 (?P<player>player)
262 )
263 \.
264 )?
265 vimeo(?P<pro>pro)?\.com/
266 (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
267 (?:.*?/)?
268 (?:
269 (?:
270 play_redirect_hls|
271 moogaloop\.swf)\?clip_id=
272 )?
273 (?:videos?/)?
274 (?P<id>[0-9]+)
275 (?:/[\da-f]+)?
276 /?(?:[?&].*)?(?:[#].*)?$
277 '''
278 IE_NAME = 'vimeo'
279 _TESTS = [
280 {
281 'url': 'http://vimeo.com/56015672#at=0',
282 'md5': '8879b6cc097e987f02484baf890129e5',
283 'info_dict': {
284 'id': '56015672',
285 'ext': 'mp4',
286 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
287 'description': 'md5:509a9ad5c9bf97c60faee9203aca4479',
288 'timestamp': 1355990239,
289 'upload_date': '20121220',
290 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
291 'uploader_id': 'user7108434',
292 'uploader': 'Filippo Valsorda',
293 'duration': 10,
294 'license': 'by-sa',
295 },
296 },
297 {
298 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
299 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
300 'note': 'Vimeo Pro video (#1197)',
301 'info_dict': {
302 'id': '68093876',
303 'ext': 'mp4',
304 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
305 'uploader_id': 'openstreetmapus',
306 'uploader': 'OpenStreetMap US',
307 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
308 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
309 'duration': 1595,
310 },
311 },
312 {
313 'url': 'http://player.vimeo.com/video/54469442',
314 'md5': '619b811a4417aa4abe78dc653becf511',
315 'note': 'Videos that embed the url in the player page',
316 'info_dict': {
317 'id': '54469442',
318 'ext': 'mp4',
319 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
320 'uploader': 'The BLN & Business of Software',
321 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
322 'uploader_id': 'theblnbusinessofsoftware',
323 'duration': 3610,
324 'description': None,
325 },
326 },
327 {
328 'url': 'http://vimeo.com/68375962',
329 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
330 'note': 'Video protected with password',
331 'info_dict': {
332 'id': '68375962',
333 'ext': 'mp4',
334 'title': 'youtube-dl password protected test video',
335 'timestamp': 1371200155,
336 'upload_date': '20130614',
337 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
338 'uploader_id': 'user18948128',
339 'uploader': 'Jaime Marquínez Ferrándiz',
340 'duration': 10,
341 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
342 },
343 'params': {
344 'videopassword': 'youtube-dl',
345 },
346 },
347 {
348 'url': 'http://vimeo.com/channels/keypeele/75629013',
349 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
350 'info_dict': {
351 'id': '75629013',
352 'ext': 'mp4',
353 'title': 'Key & Peele: Terrorist Interrogation',
354 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
355 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
356 'uploader_id': 'atencio',
357 'uploader': 'Peter Atencio',
358 'channel_id': 'keypeele',
359 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
360 'timestamp': 1380339469,
361 'upload_date': '20130928',
362 'duration': 187,
363 },
364 'expected_warnings': ['Unable to download JSON metadata'],
365 },
366 {
367 'url': 'http://vimeo.com/76979871',
368 'note': 'Video with subtitles',
369 'info_dict': {
370 'id': '76979871',
371 'ext': 'mp4',
372 'title': 'The New Vimeo Player (You Know, For Videos)',
373 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
374 'timestamp': 1381846109,
375 'upload_date': '20131015',
376 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
377 'uploader_id': 'staff',
378 'uploader': 'Vimeo Staff',
379 'duration': 62,
380 }
381 },
382 {
383 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
384 'url': 'https://player.vimeo.com/video/98044508',
385 'note': 'The js code contains assignments to the same variable as the config',
386 'info_dict': {
387 'id': '98044508',
388 'ext': 'mp4',
389 'title': 'Pier Solar OUYA Official Trailer',
390 'uploader': 'Tulio Gonçalves',
391 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
392 'uploader_id': 'user28849593',
393 },
394 },
395 {
396 # contains original format
397 'url': 'https://vimeo.com/33951933',
398 'md5': '53c688fa95a55bf4b7293d37a89c5c53',
399 'info_dict': {
400 'id': '33951933',
401 'ext': 'mp4',
402 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
403 'uploader': 'The DMCI',
404 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
405 'uploader_id': 'dmci',
406 'timestamp': 1324343742,
407 'upload_date': '20111220',
408 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
409 },
410 },
411 {
412 # only available via https://vimeo.com/channels/tributes/6213729 and
413 # not via https://vimeo.com/6213729
414 'url': 'https://vimeo.com/channels/tributes/6213729',
415 'info_dict': {
416 'id': '6213729',
417 'ext': 'mp4',
418 'title': 'Vimeo Tribute: The Shining',
419 'uploader': 'Casey Donahue',
420 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
421 'uploader_id': 'caseydonahue',
422 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
423 'channel_id': 'tributes',
424 'timestamp': 1250886430,
425 'upload_date': '20090821',
426 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
427 },
428 'params': {
429 'skip_download': True,
430 },
431 'expected_warnings': ['Unable to download JSON metadata'],
432 },
433 {
434 # redirects to ondemand extractor and should be passed through it
435 # for successful extraction
436 'url': 'https://vimeo.com/73445910',
437 'info_dict': {
438 'id': '73445910',
439 'ext': 'mp4',
440 'title': 'The Reluctant Revolutionary',
441 'uploader': '10Ft Films',
442 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
443 'uploader_id': 'tenfootfilms',
444 },
445 'params': {
446 'skip_download': True,
447 },
448 },
449 {
450 'url': 'http://player.vimeo.com/video/68375962',
451 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
452 'info_dict': {
453 'id': '68375962',
454 'ext': 'mp4',
455 'title': 'youtube-dl password protected test video',
456 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
457 'uploader_id': 'user18948128',
458 'uploader': 'Jaime Marquínez Ferrándiz',
459 'duration': 10,
460 },
461 'params': {
462 'videopassword': 'youtube-dl',
463 },
464 },
465 {
466 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
467 'only_matching': True,
468 },
469 {
470 'url': 'https://vimeo.com/109815029',
471 'note': 'Video not completely processed, "failed" seed status',
472 'only_matching': True,
473 },
474 {
475 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
476 'only_matching': True,
477 },
478 {
479 'url': 'https://vimeo.com/album/2632481/video/79010983',
480 'only_matching': True,
481 },
482 {
483 # source file returns 403: Forbidden
484 'url': 'https://vimeo.com/7809605',
485 'only_matching': True,
486 },
487 {
488 'url': 'https://vimeo.com/160743502/abd0e13fb4',
489 'only_matching': True,
490 }
491 # https://gettingthingsdone.com/workflowmap/
492 # vimeo embed with check-password page protected by Referer header
493 ]
494
495 @staticmethod
496 def _smuggle_referrer(url, referrer_url):
497 return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
498
499 @staticmethod
500 def _extract_urls(url, webpage):
501 urls = []
502 # Look for embedded (iframe) Vimeo player
503 for mobj in re.finditer(
504 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
505 webpage):
506 urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
507 PLAIN_EMBED_RE = (
508 # Look for embedded (swf embed) Vimeo player
509 r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
510 # Look more for non-standard embedded Vimeo player
511 r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
512 )
513 for embed_re in PLAIN_EMBED_RE:
514 for mobj in re.finditer(embed_re, webpage):
515 urls.append(mobj.group('url'))
516 return urls
517
518 @staticmethod
519 def _extract_url(url, webpage):
520 urls = VimeoIE._extract_urls(url, webpage)
521 return urls[0] if urls else None
522
523 def _verify_player_video_password(self, url, video_id, headers):
524 password = self._downloader.params.get('videopassword')
525 if password is None:
526 raise ExtractorError('This video is protected by a password, use the --video-password option')
527 data = urlencode_postdata({
528 'password': base64.b64encode(password.encode()),
529 })
530 headers = merge_dicts(headers, {
531 'Content-Type': 'application/x-www-form-urlencoded',
532 })
533 checked = self._download_json(
534 url + '/check-password', video_id,
535 'Verifying the password', data=data, headers=headers)
536 if checked is False:
537 raise ExtractorError('Wrong video password', expected=True)
538 return checked
539
540 def _real_initialize(self):
541 self._login()
542
543 def _real_extract(self, url):
544 url, data = unsmuggle_url(url, {})
545 headers = std_headers.copy()
546 if 'http_headers' in data:
547 headers.update(data['http_headers'])
548 if 'Referer' not in headers:
549 headers['Referer'] = url
550
551 channel_id = self._search_regex(
552 r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
553
554 # Extract ID from URL
555 mobj = re.match(self._VALID_URL, url)
556 video_id = mobj.group('id')
557 orig_url = url
558 if mobj.group('pro'):
559 # some videos require portfolio_id to be present in player url
560 # https://github.com/ytdl-org/youtube-dl/issues/20070
561 url = self._extract_url(url, self._download_webpage(url, video_id))
562 elif mobj.group('player'):
563 url = 'https://player.vimeo.com/video/' + video_id
564 elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
565 url = 'https://vimeo.com/' + video_id
566
567 # Retrieve video webpage to extract further information
568 request = sanitized_Request(url, headers=headers)
569 try:
570 webpage, urlh = self._download_webpage_handle(request, video_id)
571 redirect_url = compat_str(urlh.geturl())
572 # Some URLs redirect to ondemand can't be extracted with
573 # this extractor right away thus should be passed through
574 # ondemand extractor (e.g. https://vimeo.com/73445910)
575 if VimeoOndemandIE.suitable(redirect_url):
576 return self.url_result(redirect_url, VimeoOndemandIE.ie_key())
577 except ExtractorError as ee:
578 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
579 errmsg = ee.cause.read()
580 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
581 raise ExtractorError(
582 'Cannot download embed-only video without embedding '
583 'URL. Please call youtube-dl with the URL of the page '
584 'that embeds this video.',
585 expected=True)
586 raise
587
588 # Now we begin extracting as much information as we can from what we
589 # retrieved. First we extract the information common to all extractors,
590 # and latter we extract those that are Vimeo specific.
591 self.report_extraction(video_id)
592
593 vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
594 if vimeo_config:
595 seed_status = vimeo_config.get('seed_status', {})
596 if seed_status.get('state') == 'failed':
597 raise ExtractorError(
598 '%s said: %s' % (self.IE_NAME, seed_status['title']),
599 expected=True)
600
601 cc_license = None
602 timestamp = None
603
604 # Extract the config JSON
605 try:
606 try:
607 config_url = self._html_search_regex(
608 r' data-config-url="(.+?)"', webpage,
609 'config URL', default=None)
610 if not config_url:
611 # Sometimes new react-based page is served instead of old one that require
612 # different config URL extraction approach (see
613 # https://github.com/ytdl-org/youtube-dl/pull/7209)
614 vimeo_clip_page_config = self._search_regex(
615 r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
616 'vimeo clip page config')
617 page_config = self._parse_json(vimeo_clip_page_config, video_id)
618 config_url = page_config['player']['config_url']
619 cc_license = page_config.get('cc_license')
620 timestamp = try_get(
621 page_config, lambda x: x['clip']['uploaded_on'],
622 compat_str)
623 config_json = self._download_webpage(config_url, video_id)
624 config = json.loads(config_json)
625 except RegexNotFoundError:
626 # For pro videos or player.vimeo.com urls
627 # We try to find out to which variable is assigned the config dic
628 m_variable_name = re.search(r'(\w)\.video\.id', webpage)
629 if m_variable_name is not None:
630 config_re = [r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))]
631 else:
632 config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
633 config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;')
634 config_re.append(r'\bconfig\s*=\s*({.+?})\s*;')
635 config = self._search_regex(config_re, webpage, 'info section',
636 flags=re.DOTALL)
637 config = json.loads(config)
638 except Exception as e:
639 if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
640 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
641
642 if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
643 if '_video_password_verified' in data:
644 raise ExtractorError('video password verification failed!')
645 self._verify_video_password(redirect_url, video_id, webpage)
646 return self._real_extract(
647 smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
648 else:
649 raise ExtractorError('Unable to extract info section',
650 cause=e)
651 else:
652 if config.get('view') == 4:
653 config = self._verify_player_video_password(redirect_url, video_id, headers)
654
655 vod = config.get('video', {}).get('vod', {})
656
657 def is_rented():
658 if '>You rented this title.<' in webpage:
659 return True
660 if config.get('user', {}).get('purchased'):
661 return True
662 for purchase_option in vod.get('purchase_options', []):
663 if purchase_option.get('purchased'):
664 return True
665 label = purchase_option.get('label_string')
666 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
667 return True
668 return False
669
670 if is_rented() and vod.get('is_trailer'):
671 feature_id = vod.get('feature_id')
672 if feature_id and not data.get('force_feature_id', False):
673 return self.url_result(smuggle_url(
674 'https://player.vimeo.com/player/%s' % feature_id,
675 {'force_feature_id': True}), 'Vimeo')
676
677 # Extract video description
678
679 video_description = self._html_search_regex(
680 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
681 webpage, 'description', default=None)
682 if not video_description:
683 video_description = self._html_search_meta(
684 'description', webpage, default=None)
685 if not video_description and mobj.group('pro'):
686 orig_webpage = self._download_webpage(
687 orig_url, video_id,
688 note='Downloading webpage for description',
689 fatal=False)
690 if orig_webpage:
691 video_description = self._html_search_meta(
692 'description', orig_webpage, default=None)
693 if not video_description and not mobj.group('player'):
694 self._downloader.report_warning('Cannot find video description')
695
696 # Extract upload date
697 if not timestamp:
698 timestamp = self._search_regex(
699 r'<time[^>]+datetime="([^"]+)"', webpage,
700 'timestamp', default=None)
701
702 try:
703 view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
704 like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
705 comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
706 except RegexNotFoundError:
707 # This info is only available in vimeo.com/{id} urls
708 view_count = None
709 like_count = None
710 comment_count = None
711
712 formats = []
713
714 source_format = self._extract_original_format(
715 'https://vimeo.com/' + video_id, video_id)
716 if source_format:
717 formats.append(source_format)
718
719 info_dict_config = self._parse_config(config, video_id)
720 formats.extend(info_dict_config['formats'])
721 self._vimeo_sort_formats(formats)
722
723 json_ld = self._search_json_ld(webpage, video_id, default={})
724
725 if not cc_license:
726 cc_license = self._search_regex(
727 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
728 webpage, 'license', default=None, group='license')
729
730 channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
731
732 info_dict = {
733 'id': video_id,
734 'formats': formats,
735 'timestamp': unified_timestamp(timestamp),
736 'description': video_description,
737 'webpage_url': url,
738 'view_count': view_count,
739 'like_count': like_count,
740 'comment_count': comment_count,
741 'license': cc_license,
742 'channel_id': channel_id,
743 'channel_url': channel_url,
744 }
745
746 info_dict = merge_dicts(info_dict, info_dict_config, json_ld)
747
748 return info_dict
749
750
751 class VimeoOndemandIE(VimeoBaseInfoExtractor):
752 IE_NAME = 'vimeo:ondemand'
753 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)'
754 _TESTS = [{
755 # ondemand video not available via https://vimeo.com/id
756 'url': 'https://vimeo.com/ondemand/20704',
757 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
758 'info_dict': {
759 'id': '105442900',
760 'ext': 'mp4',
761 'title': 'המעבדה - במאי יותם פלדמן',
762 'uploader': 'גם סרטים',
763 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
764 'uploader_id': 'gumfilms',
765 },
766 'params': {
767 'format': 'best[protocol=https]',
768 },
769 }, {
770 # requires Referer to be passed along with og:video:url
771 'url': 'https://vimeo.com/ondemand/36938/126682985',
772 'info_dict': {
773 'id': '126682985',
774 'ext': 'mp4',
775 'title': 'Rävlock, rätt läte på rätt plats',
776 'uploader': 'Lindroth & Norin',
777 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user14430847',
778 'uploader_id': 'user14430847',
779 },
780 'params': {
781 'skip_download': True,
782 },
783 }, {
784 'url': 'https://vimeo.com/ondemand/nazmaalik',
785 'only_matching': True,
786 }, {
787 'url': 'https://vimeo.com/ondemand/141692381',
788 'only_matching': True,
789 }, {
790 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
791 'only_matching': True,
792 }]
793
794 def _real_extract(self, url):
795 video_id = self._match_id(url)
796 webpage = self._download_webpage(url, video_id)
797 return self.url_result(
798 # Some videos require Referer to be passed along with og:video:url
799 # similarly to generic vimeo embeds (e.g.
800 # https://vimeo.com/ondemand/36938/126682985).
801 VimeoIE._smuggle_referrer(self._og_search_video_url(webpage), url),
802 VimeoIE.ie_key())
803
804
805 class VimeoChannelIE(VimeoBaseInfoExtractor):
806 IE_NAME = 'vimeo:channel'
807 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
808 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
809 _TITLE = None
810 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
811 _TESTS = [{
812 'url': 'https://vimeo.com/channels/tributes',
813 'info_dict': {
814 'id': 'tributes',
815 'title': 'Vimeo Tributes',
816 },
817 'playlist_mincount': 25,
818 }]
819
820 def _page_url(self, base_url, pagenum):
821 return '%s/videos/page:%d/' % (base_url, pagenum)
822
823 def _extract_list_title(self, webpage):
824 return self._TITLE or self._html_search_regex(
825 self._TITLE_RE, webpage, 'list title', fatal=False)
826
827 def _login_list_password(self, page_url, list_id, webpage):
828 login_form = self._search_regex(
829 r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
830 webpage, 'login form', default=None)
831 if not login_form:
832 return webpage
833
834 password = self._downloader.params.get('videopassword')
835 if password is None:
836 raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
837 fields = self._hidden_inputs(login_form)
838 token, vuid = self._extract_xsrft_and_vuid(webpage)
839 fields['token'] = token
840 fields['password'] = password
841 post = urlencode_postdata(fields)
842 password_path = self._search_regex(
843 r'action="([^"]+)"', login_form, 'password URL')
844 password_url = compat_urlparse.urljoin(page_url, password_path)
845 password_request = sanitized_Request(password_url, post)
846 password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
847 self._set_vimeo_cookie('vuid', vuid)
848 self._set_vimeo_cookie('xsrft', token)
849
850 return self._download_webpage(
851 password_request, list_id,
852 'Verifying the password', 'Wrong password')
853
854 def _title_and_entries(self, list_id, base_url):
855 for pagenum in itertools.count(1):
856 page_url = self._page_url(base_url, pagenum)
857 webpage = self._download_webpage(
858 page_url, list_id,
859 'Downloading page %s' % pagenum)
860
861 if pagenum == 1:
862 webpage = self._login_list_password(page_url, list_id, webpage)
863 yield self._extract_list_title(webpage)
864
865 # Try extracting href first since not all videos are available via
866 # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
867 clips = re.findall(
868 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
869 if clips:
870 for video_id, video_url, video_title in clips:
871 yield self.url_result(
872 compat_urlparse.urljoin(base_url, video_url),
873 VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
874 # More relaxed fallback
875 else:
876 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
877 yield self.url_result(
878 'https://vimeo.com/%s' % video_id,
879 VimeoIE.ie_key(), video_id=video_id)
880
881 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
882 break
883
884 def _extract_videos(self, list_id, base_url):
885 title_and_entries = self._title_and_entries(list_id, base_url)
886 list_title = next(title_and_entries)
887 return self.playlist_result(title_and_entries, list_id, list_title)
888
889 def _real_extract(self, url):
890 mobj = re.match(self._VALID_URL, url)
891 channel_id = mobj.group('id')
892 return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
893
894
895 class VimeoUserIE(VimeoChannelIE):
896 IE_NAME = 'vimeo:user'
897 _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
898 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
899 _TESTS = [{
900 'url': 'https://vimeo.com/nkistudio/videos',
901 'info_dict': {
902 'title': 'Nki',
903 'id': 'nkistudio',
904 },
905 'playlist_mincount': 66,
906 }]
907
908 def _real_extract(self, url):
909 mobj = re.match(self._VALID_URL, url)
910 name = mobj.group('name')
911 return self._extract_videos(name, 'https://vimeo.com/%s' % name)
912
913
914 class VimeoAlbumIE(VimeoChannelIE):
915 IE_NAME = 'vimeo:album'
916 _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
917 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
918 _TESTS = [{
919 'url': 'https://vimeo.com/album/2632481',
920 'info_dict': {
921 'id': '2632481',
922 'title': 'Staff Favorites: November 2013',
923 },
924 'playlist_mincount': 13,
925 }, {
926 'note': 'Password-protected album',
927 'url': 'https://vimeo.com/album/3253534',
928 'info_dict': {
929 'title': 'test',
930 'id': '3253534',
931 },
932 'playlist_count': 1,
933 'params': {
934 'videopassword': 'youtube-dl',
935 }
936 }]
937 _PAGE_SIZE = 100
938
939 def _fetch_page(self, album_id, authorizaion, hashed_pass, page):
940 api_page = page + 1
941 query = {
942 'fields': 'link',
943 'page': api_page,
944 'per_page': self._PAGE_SIZE,
945 }
946 if hashed_pass:
947 query['_hashed_pass'] = hashed_pass
948 videos = self._download_json(
949 'https://api.vimeo.com/albums/%s/videos' % album_id,
950 album_id, 'Downloading page %d' % api_page, query=query, headers={
951 'Authorization': 'jwt ' + authorizaion,
952 })['data']
953 for video in videos:
954 link = video.get('link')
955 if not link:
956 continue
957 yield self.url_result(link, VimeoIE.ie_key(), VimeoIE._match_id(link))
958
959 def _real_extract(self, url):
960 album_id = self._match_id(url)
961 webpage = self._download_webpage(url, album_id)
962 webpage = self._login_list_password(url, album_id, webpage)
963 api_config = self._extract_vimeo_config(webpage, album_id)['api']
964 entries = OnDemandPagedList(functools.partial(
965 self._fetch_page, album_id, api_config['jwt'],
966 api_config.get('hashed_pass')), self._PAGE_SIZE)
967 return self.playlist_result(entries, album_id, self._html_search_regex(
968 r'<title>\s*(.+?)(?:\s+on Vimeo)?</title>', webpage, 'title', fatal=False))
969
970
971 class VimeoGroupsIE(VimeoAlbumIE):
972 IE_NAME = 'vimeo:group'
973 _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
974 _TESTS = [{
975 'url': 'https://vimeo.com/groups/rolexawards',
976 'info_dict': {
977 'id': 'rolexawards',
978 'title': 'Rolex Awards for Enterprise',
979 },
980 'playlist_mincount': 73,
981 }]
982
983 def _extract_list_title(self, webpage):
984 return self._og_search_title(webpage, fatal=False)
985
986 def _real_extract(self, url):
987 mobj = re.match(self._VALID_URL, url)
988 name = mobj.group('name')
989 return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
990
991
992 class VimeoReviewIE(VimeoBaseInfoExtractor):
993 IE_NAME = 'vimeo:review'
994 IE_DESC = 'Review pages on vimeo'
995 _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
996 _TESTS = [{
997 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
998 'md5': 'c507a72f780cacc12b2248bb4006d253',
999 'info_dict': {
1000 'id': '75524534',
1001 'ext': 'mp4',
1002 'title': "DICK HARDWICK 'Comedian'",
1003 'uploader': 'Richard Hardwick',
1004 'uploader_id': 'user21297594',
1005 }
1006 }, {
1007 'note': 'video player needs Referer',
1008 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1009 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1010 'info_dict': {
1011 'id': '91613211',
1012 'ext': 'mp4',
1013 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1014 'uploader': 'DevWeek Events',
1015 'duration': 2773,
1016 'thumbnail': r're:^https?://.*\.jpg$',
1017 'uploader_id': 'user22258446',
1018 }
1019 }, {
1020 'note': 'Password protected',
1021 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1022 'info_dict': {
1023 'id': '138823582',
1024 'ext': 'mp4',
1025 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1026 'uploader': 'TMB',
1027 'uploader_id': 'user37284429',
1028 },
1029 'params': {
1030 'videopassword': 'holygrail',
1031 },
1032 'skip': 'video gone',
1033 }]
1034
1035 def _real_initialize(self):
1036 self._login()
1037
1038 def _get_config_url(self, webpage_url, video_id, video_password_verified=False):
1039 webpage = self._download_webpage(webpage_url, video_id)
1040 config_url = self._html_search_regex(
1041 r'data-config-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
1042 'config URL', default=None, group='url')
1043 if not config_url:
1044 data = self._parse_json(self._search_regex(
1045 r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data',
1046 default=NO_DEFAULT if video_password_verified else '{}'), video_id)
1047 config = data.get('vimeo_esi', {}).get('config', {})
1048 config_url = config.get('configUrl') or try_get(config, lambda x: x['clipData']['configUrl'])
1049 if config_url is None:
1050 self._verify_video_password(webpage_url, video_id, webpage)
1051 config_url = self._get_config_url(
1052 webpage_url, video_id, video_password_verified=True)
1053 return config_url
1054
1055 def _real_extract(self, url):
1056 page_url, video_id = re.match(self._VALID_URL, url).groups()
1057 config_url = self._get_config_url(url, video_id)
1058 config = self._download_json(config_url, video_id)
1059 info_dict = self._parse_config(config, video_id)
1060 source_format = self._extract_original_format(page_url, video_id)
1061 if source_format:
1062 info_dict['formats'].append(source_format)
1063 self._vimeo_sort_formats(info_dict['formats'])
1064 info_dict['id'] = video_id
1065 return info_dict
1066
1067
1068 class VimeoWatchLaterIE(VimeoChannelIE):
1069 IE_NAME = 'vimeo:watchlater'
1070 IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
1071 _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1072 _TITLE = 'Watch Later'
1073 _LOGIN_REQUIRED = True
1074 _TESTS = [{
1075 'url': 'https://vimeo.com/watchlater',
1076 'only_matching': True,
1077 }]
1078
1079 def _real_initialize(self):
1080 self._login()
1081
1082 def _page_url(self, base_url, pagenum):
1083 url = '%s/page:%d/' % (base_url, pagenum)
1084 request = sanitized_Request(url)
1085 # Set the header to get a partial html page with the ids,
1086 # the normal page doesn't contain them.
1087 request.add_header('X-Requested-With', 'XMLHttpRequest')
1088 return request
1089
1090 def _real_extract(self, url):
1091 return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1092
1093
1094 class VimeoLikesIE(VimeoChannelIE):
1095 _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1096 IE_NAME = 'vimeo:likes'
1097 IE_DESC = 'Vimeo user likes'
1098 _TESTS = [{
1099 'url': 'https://vimeo.com/user755559/likes/',
1100 'playlist_mincount': 293,
1101 'info_dict': {
1102 'id': 'user755559',
1103 'title': 'urza’s Likes',
1104 },
1105 }, {
1106 'url': 'https://vimeo.com/stormlapse/likes',
1107 'only_matching': True,
1108 }]
1109
1110 def _page_url(self, base_url, pagenum):
1111 return '%s/page:%d/' % (base_url, pagenum)
1112
1113 def _real_extract(self, url):
1114 user_id = self._match_id(url)
1115 return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
1116
1117
1118 class VHXEmbedIE(InfoExtractor):
1119 IE_NAME = 'vhx:embed'
1120 _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1121
1122 def _call_api(self, video_id, access_token, path='', query=None):
1123 return self._download_json(
1124 'https://api.vhx.tv/videos/' + video_id + path, video_id, headers={
1125 'Authorization': 'Bearer ' + access_token,
1126 }, query=query)
1127
1128 def _real_extract(self, url):
1129 video_id = self._match_id(url)
1130 webpage = self._download_webpage(url, video_id)
1131 credentials = self._parse_json(self._search_regex(
1132 r'(?s)credentials\s*:\s*({.+?}),', webpage,
1133 'config'), video_id, js_to_json)
1134 access_token = credentials['access_token']
1135
1136 query = {}
1137 for k, v in credentials.items():
1138 if k in ('authorization', 'authUserToken', 'ticket') and v and v != 'undefined':
1139 if k == 'authUserToken':
1140 query['auth_user_token'] = v
1141 else:
1142 query[k] = v
1143 files = self._call_api(video_id, access_token, '/files', query)
1144
1145 formats = []
1146 for f in files:
1147 href = try_get(f, lambda x: x['_links']['source']['href'])
1148 if not href:
1149 continue
1150 method = f.get('method')
1151 if method == 'hls':
1152 formats.extend(self._extract_m3u8_formats(
1153 href, video_id, 'mp4', 'm3u8_native',
1154 m3u8_id='hls', fatal=False))
1155 elif method == 'dash':
1156 formats.extend(self._extract_mpd_formats(
1157 href, video_id, mpd_id='dash', fatal=False))
1158 else:
1159 fmt = {
1160 'filesize': int_or_none(try_get(f, lambda x: x['size']['bytes'])),
1161 'format_id': 'http',
1162 'preference': 1,
1163 'url': href,
1164 'vcodec': f.get('codec'),
1165 }
1166 quality = f.get('quality')
1167 if quality:
1168 fmt.update({
1169 'format_id': 'http-' + quality,
1170 'height': int_or_none(self._search_regex(r'(\d+)p', quality, 'height', default=None)),
1171 })
1172 formats.append(fmt)
1173 self._sort_formats(formats)
1174
1175 video_data = self._call_api(video_id, access_token)
1176 title = video_data.get('title') or video_data['name']
1177
1178 subtitles = {}
1179 for subtitle in try_get(video_data, lambda x: x['tracks']['subtitles'], list) or []:
1180 lang = subtitle.get('srclang') or subtitle.get('label')
1181 for _link in subtitle.get('_links', {}).values():
1182 href = _link.get('href')
1183 if not href:
1184 continue
1185 subtitles.setdefault(lang, []).append({
1186 'url': href,
1187 })
1188
1189 q = qualities(['small', 'medium', 'large', 'source'])
1190 thumbnails = []
1191 for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items():
1192 thumbnails.append({
1193 'id': thumbnail_id,
1194 'url': thumbnail_url,
1195 'preference': q(thumbnail_id),
1196 })
1197
1198 return {
1199 'id': video_id,
1200 'title': title,
1201 'description': video_data.get('description'),
1202 'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])),
1203 'formats': formats,
1204 'subtitles': subtitles,
1205 'thumbnails': thumbnails,
1206 'timestamp': unified_timestamp(video_data.get('created_at')),
1207 'view_count': int_or_none(video_data.get('plays_count')),
1208 }