]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vimeo.py
New upstream version 2018.04.25
[youtubedl] / youtube_dl / extractor / vimeo.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import json
5 import re
6 import itertools
7
8 from .common import InfoExtractor
9 from ..compat import (
10 compat_HTTPError,
11 compat_str,
12 compat_urlparse,
13 )
14 from ..utils import (
15 determine_ext,
16 ExtractorError,
17 InAdvancePagedList,
18 int_or_none,
19 NO_DEFAULT,
20 RegexNotFoundError,
21 sanitized_Request,
22 smuggle_url,
23 std_headers,
24 try_get,
25 unified_timestamp,
26 unsmuggle_url,
27 urlencode_postdata,
28 unescapeHTML,
29 parse_filesize,
30 )
31
32
33 class VimeoBaseInfoExtractor(InfoExtractor):
34 _NETRC_MACHINE = 'vimeo'
35 _LOGIN_REQUIRED = False
36 _LOGIN_URL = 'https://vimeo.com/log_in'
37
38 def _login(self):
39 (username, password) = self._get_login_info()
40 if username is None:
41 if self._LOGIN_REQUIRED:
42 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
43 return
44 webpage = self._download_webpage(
45 self._LOGIN_URL, None, 'Downloading login page')
46 token, vuid = self._extract_xsrft_and_vuid(webpage)
47 data = {
48 'action': 'login',
49 'email': username,
50 'password': password,
51 'service': 'vimeo',
52 'token': token,
53 }
54 self._set_vimeo_cookie('vuid', vuid)
55 try:
56 self._download_webpage(
57 self._LOGIN_URL, None, 'Logging in',
58 data=urlencode_postdata(data), headers={
59 'Content-Type': 'application/x-www-form-urlencoded',
60 'Referer': self._LOGIN_URL,
61 })
62 except ExtractorError as e:
63 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
64 raise ExtractorError(
65 'Unable to log in: bad username or password',
66 expected=True)
67 raise ExtractorError('Unable to log in')
68
69 def _verify_video_password(self, url, video_id, webpage):
70 password = self._downloader.params.get('videopassword')
71 if password is None:
72 raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
73 token, vuid = self._extract_xsrft_and_vuid(webpage)
74 data = urlencode_postdata({
75 'password': password,
76 'token': token,
77 })
78 if url.startswith('http://'):
79 # vimeo only supports https now, but the user can give an http url
80 url = url.replace('http://', 'https://')
81 password_request = sanitized_Request(url + '/password', data)
82 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
83 password_request.add_header('Referer', url)
84 self._set_vimeo_cookie('vuid', vuid)
85 return self._download_webpage(
86 password_request, video_id,
87 'Verifying the password', 'Wrong password')
88
89 def _extract_xsrft_and_vuid(self, webpage):
90 xsrft = self._search_regex(
91 r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
92 webpage, 'login token', group='xsrft')
93 vuid = self._search_regex(
94 r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
95 webpage, 'vuid', group='vuid')
96 return xsrft, vuid
97
98 def _set_vimeo_cookie(self, name, value):
99 self._set_cookie('vimeo.com', name, value)
100
101 def _vimeo_sort_formats(self, formats):
102 # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
103 # at the same time without actual units specified. This lead to wrong sorting.
104 self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'tbr', 'format_id'))
105
106 def _parse_config(self, config, video_id):
107 video_data = config['video']
108 # Extract title
109 video_title = video_data['title']
110
111 # Extract uploader, uploader_url and uploader_id
112 video_uploader = video_data.get('owner', {}).get('name')
113 video_uploader_url = video_data.get('owner', {}).get('url')
114 video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
115
116 # Extract video thumbnail
117 video_thumbnail = video_data.get('thumbnail')
118 if video_thumbnail is None:
119 video_thumbs = video_data.get('thumbs')
120 if video_thumbs and isinstance(video_thumbs, dict):
121 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
122
123 # Extract video duration
124 video_duration = int_or_none(video_data.get('duration'))
125
126 formats = []
127 config_files = video_data.get('files') or config['request'].get('files', {})
128 for f in config_files.get('progressive', []):
129 video_url = f.get('url')
130 if not video_url:
131 continue
132 formats.append({
133 'url': video_url,
134 'format_id': 'http-%s' % f.get('quality'),
135 'width': int_or_none(f.get('width')),
136 'height': int_or_none(f.get('height')),
137 'fps': int_or_none(f.get('fps')),
138 'tbr': int_or_none(f.get('bitrate')),
139 })
140
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_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 mpd_formats = self._extract_mpd_formats(
164 m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
165 'Downloading %s MPD information' % cdn_name,
166 fatal=False)
167 for f in mpd_formats:
168 if f.get('vcodec') == 'none':
169 f['preference'] = -50
170 elif f.get('acodec') == 'none':
171 f['preference'] = -40
172 formats.extend(mpd_formats)
173
174 subtitles = {}
175 text_tracks = config['request'].get('text_tracks')
176 if text_tracks:
177 for tt in text_tracks:
178 subtitles[tt['lang']] = [{
179 'ext': 'vtt',
180 'url': 'https://vimeo.com' + tt['url'],
181 }]
182
183 return {
184 'title': video_title,
185 'uploader': video_uploader,
186 'uploader_id': video_uploader_id,
187 'uploader_url': video_uploader_url,
188 'thumbnail': video_thumbnail,
189 'duration': video_duration,
190 'formats': formats,
191 'subtitles': subtitles,
192 }
193
194
195 class VimeoIE(VimeoBaseInfoExtractor):
196 """Information extractor for vimeo.com."""
197
198 # _VALID_URL matches Vimeo URLs
199 _VALID_URL = r'''(?x)
200 https?://
201 (?:
202 (?:
203 www|
204 (?P<player>player)
205 )
206 \.
207 )?
208 vimeo(?P<pro>pro)?\.com/
209 (?!(?:channels|album)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
210 (?:.*?/)?
211 (?:
212 (?:
213 play_redirect_hls|
214 moogaloop\.swf)\?clip_id=
215 )?
216 (?:videos?/)?
217 (?P<id>[0-9]+)
218 (?:/[\da-f]+)?
219 /?(?:[?&].*)?(?:[#].*)?$
220 '''
221 IE_NAME = 'vimeo'
222 _TESTS = [
223 {
224 'url': 'http://vimeo.com/56015672#at=0',
225 'md5': '8879b6cc097e987f02484baf890129e5',
226 'info_dict': {
227 'id': '56015672',
228 'ext': 'mp4',
229 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
230 'description': 'md5:509a9ad5c9bf97c60faee9203aca4479',
231 'timestamp': 1355990239,
232 'upload_date': '20121220',
233 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
234 'uploader_id': 'user7108434',
235 'uploader': 'Filippo Valsorda',
236 'duration': 10,
237 'license': 'by-sa',
238 },
239 },
240 {
241 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
242 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
243 'note': 'Vimeo Pro video (#1197)',
244 'info_dict': {
245 'id': '68093876',
246 'ext': 'mp4',
247 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
248 'uploader_id': 'openstreetmapus',
249 'uploader': 'OpenStreetMap US',
250 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
251 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
252 'duration': 1595,
253 },
254 },
255 {
256 'url': 'http://player.vimeo.com/video/54469442',
257 'md5': '619b811a4417aa4abe78dc653becf511',
258 'note': 'Videos that embed the url in the player page',
259 'info_dict': {
260 'id': '54469442',
261 'ext': 'mp4',
262 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
263 'uploader': 'The BLN & Business of Software',
264 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
265 'uploader_id': 'theblnbusinessofsoftware',
266 'duration': 3610,
267 'description': None,
268 },
269 },
270 {
271 'url': 'http://vimeo.com/68375962',
272 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
273 'note': 'Video protected with password',
274 'info_dict': {
275 'id': '68375962',
276 'ext': 'mp4',
277 'title': 'youtube-dl password protected test video',
278 'timestamp': 1371200155,
279 'upload_date': '20130614',
280 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
281 'uploader_id': 'user18948128',
282 'uploader': 'Jaime Marquƭnez FerrƔndiz',
283 'duration': 10,
284 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
285 },
286 'params': {
287 'videopassword': 'youtube-dl',
288 },
289 },
290 {
291 'url': 'http://vimeo.com/channels/keypeele/75629013',
292 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
293 'info_dict': {
294 'id': '75629013',
295 'ext': 'mp4',
296 'title': 'Key & Peele: Terrorist Interrogation',
297 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
298 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
299 'uploader_id': 'atencio',
300 'uploader': 'Peter Atencio',
301 'timestamp': 1380339469,
302 'upload_date': '20130928',
303 'duration': 187,
304 },
305 },
306 {
307 'url': 'http://vimeo.com/76979871',
308 'note': 'Video with subtitles',
309 'info_dict': {
310 'id': '76979871',
311 'ext': 'mp4',
312 'title': 'The New Vimeo Player (You Know, For Videos)',
313 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
314 'timestamp': 1381846109,
315 'upload_date': '20131015',
316 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
317 'uploader_id': 'staff',
318 'uploader': 'Vimeo Staff',
319 'duration': 62,
320 }
321 },
322 {
323 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
324 'url': 'https://player.vimeo.com/video/98044508',
325 'note': 'The js code contains assignments to the same variable as the config',
326 'info_dict': {
327 'id': '98044508',
328 'ext': 'mp4',
329 'title': 'Pier Solar OUYA Official Trailer',
330 'uploader': 'Tulio GonƧalves',
331 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
332 'uploader_id': 'user28849593',
333 },
334 },
335 {
336 # contains original format
337 'url': 'https://vimeo.com/33951933',
338 'md5': '53c688fa95a55bf4b7293d37a89c5c53',
339 'info_dict': {
340 'id': '33951933',
341 'ext': 'mp4',
342 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
343 'uploader': 'The DMCI',
344 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
345 'uploader_id': 'dmci',
346 'timestamp': 1324343742,
347 'upload_date': '20111220',
348 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
349 },
350 },
351 {
352 # only available via https://vimeo.com/channels/tributes/6213729 and
353 # not via https://vimeo.com/6213729
354 'url': 'https://vimeo.com/channels/tributes/6213729',
355 'info_dict': {
356 'id': '6213729',
357 'ext': 'mov',
358 'title': 'Vimeo Tribute: The Shining',
359 'uploader': 'Casey Donahue',
360 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
361 'uploader_id': 'caseydonahue',
362 'timestamp': 1250886430,
363 'upload_date': '20090821',
364 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
365 },
366 'params': {
367 'skip_download': True,
368 },
369 'expected_warnings': ['Unable to download JSON metadata'],
370 },
371 {
372 # redirects to ondemand extractor and should be passed through it
373 # for successful extraction
374 'url': 'https://vimeo.com/73445910',
375 'info_dict': {
376 'id': '73445910',
377 'ext': 'mp4',
378 'title': 'The Reluctant Revolutionary',
379 'uploader': '10Ft Films',
380 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
381 'uploader_id': 'tenfootfilms',
382 },
383 'params': {
384 'skip_download': True,
385 },
386 },
387 {
388 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
389 'only_matching': True,
390 },
391 {
392 'url': 'https://vimeo.com/109815029',
393 'note': 'Video not completely processed, "failed" seed status',
394 'only_matching': True,
395 },
396 {
397 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
398 'only_matching': True,
399 },
400 {
401 'url': 'https://vimeo.com/album/2632481/video/79010983',
402 'only_matching': True,
403 },
404 {
405 # source file returns 403: Forbidden
406 'url': 'https://vimeo.com/7809605',
407 'only_matching': True,
408 },
409 {
410 'url': 'https://vimeo.com/160743502/abd0e13fb4',
411 'only_matching': True,
412 }
413 ]
414
415 @staticmethod
416 def _smuggle_referrer(url, referrer_url):
417 return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
418
419 @staticmethod
420 def _extract_urls(url, webpage):
421 urls = []
422 # Look for embedded (iframe) Vimeo player
423 for mobj in re.finditer(
424 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
425 webpage):
426 urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
427 PLAIN_EMBED_RE = (
428 # Look for embedded (swf embed) Vimeo player
429 r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
430 # Look more for non-standard embedded Vimeo player
431 r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
432 )
433 for embed_re in PLAIN_EMBED_RE:
434 for mobj in re.finditer(embed_re, webpage):
435 urls.append(mobj.group('url'))
436 return urls
437
438 @staticmethod
439 def _extract_url(url, webpage):
440 urls = VimeoIE._extract_urls(url, webpage)
441 return urls[0] if urls else None
442
443 def _verify_player_video_password(self, url, video_id):
444 password = self._downloader.params.get('videopassword')
445 if password is None:
446 raise ExtractorError('This video is protected by a password, use the --video-password option')
447 data = urlencode_postdata({'password': password})
448 pass_url = url + '/check-password'
449 password_request = sanitized_Request(pass_url, data)
450 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
451 password_request.add_header('Referer', url)
452 return self._download_json(
453 password_request, video_id,
454 'Verifying the password', 'Wrong password')
455
456 def _real_initialize(self):
457 self._login()
458
459 def _real_extract(self, url):
460 url, data = unsmuggle_url(url, {})
461 headers = std_headers.copy()
462 if 'http_headers' in data:
463 headers.update(data['http_headers'])
464 if 'Referer' not in headers:
465 headers['Referer'] = url
466
467 # Extract ID from URL
468 mobj = re.match(self._VALID_URL, url)
469 video_id = mobj.group('id')
470 orig_url = url
471 if mobj.group('pro') or mobj.group('player'):
472 url = 'https://player.vimeo.com/video/' + video_id
473 elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
474 url = 'https://vimeo.com/' + video_id
475
476 # Retrieve video webpage to extract further information
477 request = sanitized_Request(url, headers=headers)
478 try:
479 webpage, urlh = self._download_webpage_handle(request, video_id)
480 redirect_url = compat_str(urlh.geturl())
481 # Some URLs redirect to ondemand can't be extracted with
482 # this extractor right away thus should be passed through
483 # ondemand extractor (e.g. https://vimeo.com/73445910)
484 if VimeoOndemandIE.suitable(redirect_url):
485 return self.url_result(redirect_url, VimeoOndemandIE.ie_key())
486 except ExtractorError as ee:
487 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
488 errmsg = ee.cause.read()
489 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
490 raise ExtractorError(
491 'Cannot download embed-only video without embedding '
492 'URL. Please call youtube-dl with the URL of the page '
493 'that embeds this video.',
494 expected=True)
495 raise
496
497 # Now we begin extracting as much information as we can from what we
498 # retrieved. First we extract the information common to all extractors,
499 # and latter we extract those that are Vimeo specific.
500 self.report_extraction(video_id)
501
502 vimeo_config = self._search_regex(
503 r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
504 'vimeo config', default=None)
505 if vimeo_config:
506 seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
507 if seed_status.get('state') == 'failed':
508 raise ExtractorError(
509 '%s said: %s' % (self.IE_NAME, seed_status['title']),
510 expected=True)
511
512 cc_license = None
513 timestamp = None
514
515 # Extract the config JSON
516 try:
517 try:
518 config_url = self._html_search_regex(
519 r' data-config-url="(.+?)"', webpage,
520 'config URL', default=None)
521 if not config_url:
522 # Sometimes new react-based page is served instead of old one that require
523 # different config URL extraction approach (see
524 # https://github.com/rg3/youtube-dl/pull/7209)
525 vimeo_clip_page_config = self._search_regex(
526 r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
527 'vimeo clip page config')
528 page_config = self._parse_json(vimeo_clip_page_config, video_id)
529 config_url = page_config['player']['config_url']
530 cc_license = page_config.get('cc_license')
531 timestamp = try_get(
532 page_config, lambda x: x['clip']['uploaded_on'],
533 compat_str)
534 config_json = self._download_webpage(config_url, video_id)
535 config = json.loads(config_json)
536 except RegexNotFoundError:
537 # For pro videos or player.vimeo.com urls
538 # We try to find out to which variable is assigned the config dic
539 m_variable_name = re.search(r'(\w)\.video\.id', webpage)
540 if m_variable_name is not None:
541 config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
542 else:
543 config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
544 config = self._search_regex(config_re, webpage, 'info section',
545 flags=re.DOTALL)
546 config = json.loads(config)
547 except Exception as e:
548 if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
549 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
550
551 if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
552 if '_video_password_verified' in data:
553 raise ExtractorError('video password verification failed!')
554 self._verify_video_password(redirect_url, video_id, webpage)
555 return self._real_extract(
556 smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
557 else:
558 raise ExtractorError('Unable to extract info section',
559 cause=e)
560 else:
561 if config.get('view') == 4:
562 config = self._verify_player_video_password(redirect_url, video_id)
563
564 def is_rented():
565 if '>You rented this title.<' in webpage:
566 return True
567 if config.get('user', {}).get('purchased'):
568 return True
569 label = try_get(
570 config, lambda x: x['video']['vod']['purchase_options'][0]['label_string'], compat_str)
571 if label and label.startswith('You rented this'):
572 return True
573 return False
574
575 if is_rented():
576 feature_id = config.get('video', {}).get('vod', {}).get('feature_id')
577 if feature_id and not data.get('force_feature_id', False):
578 return self.url_result(smuggle_url(
579 'https://player.vimeo.com/player/%s' % feature_id,
580 {'force_feature_id': True}), 'Vimeo')
581
582 # Extract video description
583
584 video_description = self._html_search_regex(
585 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
586 webpage, 'description', default=None)
587 if not video_description:
588 video_description = self._html_search_meta(
589 'description', webpage, default=None)
590 if not video_description and mobj.group('pro'):
591 orig_webpage = self._download_webpage(
592 orig_url, video_id,
593 note='Downloading webpage for description',
594 fatal=False)
595 if orig_webpage:
596 video_description = self._html_search_meta(
597 'description', orig_webpage, default=None)
598 if not video_description and not mobj.group('player'):
599 self._downloader.report_warning('Cannot find video description')
600
601 # Extract upload date
602 if not timestamp:
603 timestamp = self._search_regex(
604 r'<time[^>]+datetime="([^"]+)"', webpage,
605 'timestamp', default=None)
606
607 try:
608 view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
609 like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
610 comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
611 except RegexNotFoundError:
612 # This info is only available in vimeo.com/{id} urls
613 view_count = None
614 like_count = None
615 comment_count = None
616
617 formats = []
618 download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={
619 'X-Requested-With': 'XMLHttpRequest'})
620 download_data = self._download_json(download_request, video_id, fatal=False)
621 if download_data:
622 source_file = download_data.get('source_file')
623 if isinstance(source_file, dict):
624 download_url = source_file.get('download_url')
625 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
626 source_name = source_file.get('public_name', 'Original')
627 if self._is_valid_url(download_url, video_id, '%s video' % source_name):
628 ext = (try_get(
629 source_file, lambda x: x['extension'],
630 compat_str) or determine_ext(
631 download_url, None) or 'mp4').lower()
632 formats.append({
633 'url': download_url,
634 'ext': ext,
635 'width': int_or_none(source_file.get('width')),
636 'height': int_or_none(source_file.get('height')),
637 'filesize': parse_filesize(source_file.get('size')),
638 'format_id': source_name,
639 'preference': 1,
640 })
641
642 info_dict = self._parse_config(config, video_id)
643 formats.extend(info_dict['formats'])
644 self._vimeo_sort_formats(formats)
645
646 if not cc_license:
647 cc_license = self._search_regex(
648 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
649 webpage, 'license', default=None, group='license')
650
651 info_dict.update({
652 'id': video_id,
653 'formats': formats,
654 'timestamp': unified_timestamp(timestamp),
655 'description': video_description,
656 'webpage_url': url,
657 'view_count': view_count,
658 'like_count': like_count,
659 'comment_count': comment_count,
660 'license': cc_license,
661 })
662
663 return info_dict
664
665
666 class VimeoOndemandIE(VimeoBaseInfoExtractor):
667 IE_NAME = 'vimeo:ondemand'
668 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)'
669 _TESTS = [{
670 # ondemand video not available via https://vimeo.com/id
671 'url': 'https://vimeo.com/ondemand/20704',
672 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
673 'info_dict': {
674 'id': '105442900',
675 'ext': 'mp4',
676 'title': 'המעבדה - במאי יו×Ŗם פלדמן',
677 'uploader': 'גם ×”×Øטים',
678 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
679 'uploader_id': 'gumfilms',
680 },
681 'params': {
682 'format': 'best[protocol=https]',
683 },
684 }, {
685 # requires Referer to be passed along with og:video:url
686 'url': 'https://vimeo.com/ondemand/36938/126682985',
687 'info_dict': {
688 'id': '126682985',
689 'ext': 'mp4',
690 'title': 'RƤvlock, rƤtt lƤte pƄ rƤtt plats',
691 'uploader': 'Lindroth & Norin',
692 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user14430847',
693 'uploader_id': 'user14430847',
694 },
695 'params': {
696 'skip_download': True,
697 },
698 }, {
699 'url': 'https://vimeo.com/ondemand/nazmaalik',
700 'only_matching': True,
701 }, {
702 'url': 'https://vimeo.com/ondemand/141692381',
703 'only_matching': True,
704 }, {
705 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
706 'only_matching': True,
707 }]
708
709 def _real_extract(self, url):
710 video_id = self._match_id(url)
711 webpage = self._download_webpage(url, video_id)
712 return self.url_result(
713 # Some videos require Referer to be passed along with og:video:url
714 # similarly to generic vimeo embeds (e.g.
715 # https://vimeo.com/ondemand/36938/126682985).
716 VimeoIE._smuggle_referrer(self._og_search_video_url(webpage), url),
717 VimeoIE.ie_key())
718
719
720 class VimeoChannelIE(VimeoBaseInfoExtractor):
721 IE_NAME = 'vimeo:channel'
722 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
723 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
724 _TITLE = None
725 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
726 _TESTS = [{
727 'url': 'https://vimeo.com/channels/tributes',
728 'info_dict': {
729 'id': 'tributes',
730 'title': 'Vimeo Tributes',
731 },
732 'playlist_mincount': 25,
733 }]
734
735 def _page_url(self, base_url, pagenum):
736 return '%s/videos/page:%d/' % (base_url, pagenum)
737
738 def _extract_list_title(self, webpage):
739 return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
740
741 def _login_list_password(self, page_url, list_id, webpage):
742 login_form = self._search_regex(
743 r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
744 webpage, 'login form', default=None)
745 if not login_form:
746 return webpage
747
748 password = self._downloader.params.get('videopassword')
749 if password is None:
750 raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
751 fields = self._hidden_inputs(login_form)
752 token, vuid = self._extract_xsrft_and_vuid(webpage)
753 fields['token'] = token
754 fields['password'] = password
755 post = urlencode_postdata(fields)
756 password_path = self._search_regex(
757 r'action="([^"]+)"', login_form, 'password URL')
758 password_url = compat_urlparse.urljoin(page_url, password_path)
759 password_request = sanitized_Request(password_url, post)
760 password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
761 self._set_vimeo_cookie('vuid', vuid)
762 self._set_vimeo_cookie('xsrft', token)
763
764 return self._download_webpage(
765 password_request, list_id,
766 'Verifying the password', 'Wrong password')
767
768 def _title_and_entries(self, list_id, base_url):
769 for pagenum in itertools.count(1):
770 page_url = self._page_url(base_url, pagenum)
771 webpage = self._download_webpage(
772 page_url, list_id,
773 'Downloading page %s' % pagenum)
774
775 if pagenum == 1:
776 webpage = self._login_list_password(page_url, list_id, webpage)
777 yield self._extract_list_title(webpage)
778
779 # Try extracting href first since not all videos are available via
780 # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
781 clips = re.findall(
782 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
783 if clips:
784 for video_id, video_url, video_title in clips:
785 yield self.url_result(
786 compat_urlparse.urljoin(base_url, video_url),
787 VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
788 # More relaxed fallback
789 else:
790 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
791 yield self.url_result(
792 'https://vimeo.com/%s' % video_id,
793 VimeoIE.ie_key(), video_id=video_id)
794
795 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
796 break
797
798 def _extract_videos(self, list_id, base_url):
799 title_and_entries = self._title_and_entries(list_id, base_url)
800 list_title = next(title_and_entries)
801 return self.playlist_result(title_and_entries, list_id, list_title)
802
803 def _real_extract(self, url):
804 mobj = re.match(self._VALID_URL, url)
805 channel_id = mobj.group('id')
806 return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
807
808
809 class VimeoUserIE(VimeoChannelIE):
810 IE_NAME = 'vimeo:user'
811 _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
812 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
813 _TESTS = [{
814 'url': 'https://vimeo.com/nkistudio/videos',
815 'info_dict': {
816 'title': 'Nki',
817 'id': 'nkistudio',
818 },
819 'playlist_mincount': 66,
820 }]
821
822 def _real_extract(self, url):
823 mobj = re.match(self._VALID_URL, url)
824 name = mobj.group('name')
825 return self._extract_videos(name, 'https://vimeo.com/%s' % name)
826
827
828 class VimeoAlbumIE(VimeoChannelIE):
829 IE_NAME = 'vimeo:album'
830 _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)(?:$|[?#]|/(?!video))'
831 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
832 _TESTS = [{
833 'url': 'https://vimeo.com/album/2632481',
834 'info_dict': {
835 'id': '2632481',
836 'title': 'Staff Favorites: November 2013',
837 },
838 'playlist_mincount': 13,
839 }, {
840 'note': 'Password-protected album',
841 'url': 'https://vimeo.com/album/3253534',
842 'info_dict': {
843 'title': 'test',
844 'id': '3253534',
845 },
846 'playlist_count': 1,
847 'params': {
848 'videopassword': 'youtube-dl',
849 }
850 }, {
851 'url': 'https://vimeo.com/album/2632481/sort:plays/format:thumbnail',
852 'only_matching': True,
853 }, {
854 # TODO: respect page number
855 'url': 'https://vimeo.com/album/2632481/page:2/sort:plays/format:thumbnail',
856 'only_matching': True,
857 }]
858
859 def _page_url(self, base_url, pagenum):
860 return '%s/page:%d/' % (base_url, pagenum)
861
862 def _real_extract(self, url):
863 album_id = self._match_id(url)
864 return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
865
866
867 class VimeoGroupsIE(VimeoAlbumIE):
868 IE_NAME = 'vimeo:group'
869 _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
870 _TESTS = [{
871 'url': 'https://vimeo.com/groups/rolexawards',
872 'info_dict': {
873 'id': 'rolexawards',
874 'title': 'Rolex Awards for Enterprise',
875 },
876 'playlist_mincount': 73,
877 }]
878
879 def _extract_list_title(self, webpage):
880 return self._og_search_title(webpage)
881
882 def _real_extract(self, url):
883 mobj = re.match(self._VALID_URL, url)
884 name = mobj.group('name')
885 return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
886
887
888 class VimeoReviewIE(VimeoBaseInfoExtractor):
889 IE_NAME = 'vimeo:review'
890 IE_DESC = 'Review pages on vimeo'
891 _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
892 _TESTS = [{
893 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
894 'md5': 'c507a72f780cacc12b2248bb4006d253',
895 'info_dict': {
896 'id': '75524534',
897 'ext': 'mp4',
898 'title': "DICK HARDWICK 'Comedian'",
899 'uploader': 'Richard Hardwick',
900 'uploader_id': 'user21297594',
901 }
902 }, {
903 'note': 'video player needs Referer',
904 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
905 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
906 'info_dict': {
907 'id': '91613211',
908 'ext': 'mp4',
909 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
910 'uploader': 'DevWeek Events',
911 'duration': 2773,
912 'thumbnail': r're:^https?://.*\.jpg$',
913 'uploader_id': 'user22258446',
914 }
915 }, {
916 'note': 'Password protected',
917 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
918 'info_dict': {
919 'id': '138823582',
920 'ext': 'mp4',
921 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
922 'uploader': 'TMB',
923 'uploader_id': 'user37284429',
924 },
925 'params': {
926 'videopassword': 'holygrail',
927 },
928 'skip': 'video gone',
929 }]
930
931 def _real_initialize(self):
932 self._login()
933
934 def _get_config_url(self, webpage_url, video_id, video_password_verified=False):
935 webpage = self._download_webpage(webpage_url, video_id)
936 config_url = self._html_search_regex(
937 r'data-config-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
938 'config URL', default=None, group='url')
939 if not config_url:
940 data = self._parse_json(self._search_regex(
941 r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data',
942 default=NO_DEFAULT if video_password_verified else '{}'), video_id)
943 config_url = data.get('vimeo_esi', {}).get('config', {}).get('configUrl')
944 if config_url is None:
945 self._verify_video_password(webpage_url, video_id, webpage)
946 config_url = self._get_config_url(
947 webpage_url, video_id, video_password_verified=True)
948 return config_url
949
950 def _real_extract(self, url):
951 video_id = self._match_id(url)
952 config_url = self._get_config_url(url, video_id)
953 config = self._download_json(config_url, video_id)
954 info_dict = self._parse_config(config, video_id)
955 self._vimeo_sort_formats(info_dict['formats'])
956 info_dict['id'] = video_id
957 return info_dict
958
959
960 class VimeoWatchLaterIE(VimeoChannelIE):
961 IE_NAME = 'vimeo:watchlater'
962 IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
963 _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
964 _TITLE = 'Watch Later'
965 _LOGIN_REQUIRED = True
966 _TESTS = [{
967 'url': 'https://vimeo.com/watchlater',
968 'only_matching': True,
969 }]
970
971 def _real_initialize(self):
972 self._login()
973
974 def _page_url(self, base_url, pagenum):
975 url = '%s/page:%d/' % (base_url, pagenum)
976 request = sanitized_Request(url)
977 # Set the header to get a partial html page with the ids,
978 # the normal page doesn't contain them.
979 request.add_header('X-Requested-With', 'XMLHttpRequest')
980 return request
981
982 def _real_extract(self, url):
983 return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
984
985
986 class VimeoLikesIE(InfoExtractor):
987 _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
988 IE_NAME = 'vimeo:likes'
989 IE_DESC = 'Vimeo user likes'
990 _TEST = {
991 'url': 'https://vimeo.com/user755559/likes/',
992 'playlist_mincount': 293,
993 'info_dict': {
994 'id': 'user755559_likes',
995 'description': 'See all the videos urza likes',
996 'title': 'Videos urza likes',
997 },
998 }
999
1000 def _real_extract(self, url):
1001 user_id = self._match_id(url)
1002 webpage = self._download_webpage(url, user_id)
1003 page_count = self._int(
1004 self._search_regex(
1005 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
1006 .*?</a></li>\s*<li\s+class="pagination_next">
1007 ''', webpage, 'page count'),
1008 'page count', fatal=True)
1009 PAGE_SIZE = 12
1010 title = self._html_search_regex(
1011 r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
1012 description = self._html_search_meta('description', webpage)
1013
1014 def _get_page(idx):
1015 page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
1016 user_id, idx + 1)
1017 webpage = self._download_webpage(
1018 page_url, user_id,
1019 note='Downloading page %d/%d' % (idx + 1, page_count))
1020 video_list = self._search_regex(
1021 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
1022 webpage, 'video content')
1023 paths = re.findall(
1024 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
1025 for path in paths:
1026 yield {
1027 '_type': 'url',
1028 'url': compat_urlparse.urljoin(page_url, path),
1029 }
1030
1031 pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
1032
1033 return {
1034 '_type': 'playlist',
1035 'id': 'user%s_likes' % user_id,
1036 'title': title,
1037 'description': description,
1038 'entries': pl,
1039 }