]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vimeo.py
New upstream version 2018.11.07
[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 merge_dicts,
20 NO_DEFAULT,
21 RegexNotFoundError,
22 sanitized_Request,
23 smuggle_url,
24 std_headers,
25 try_get,
26 unified_timestamp,
27 unsmuggle_url,
28 urlencode_postdata,
29 unescapeHTML,
30 parse_filesize,
31 )
32
33
34 class VimeoBaseInfoExtractor(InfoExtractor):
35 _NETRC_MACHINE = 'vimeo'
36 _LOGIN_REQUIRED = False
37 _LOGIN_URL = 'https://vimeo.com/log_in'
38
39 def _login(self):
40 username, password = self._get_login_info()
41 if username is None:
42 if self._LOGIN_REQUIRED:
43 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
44 return
45 webpage = self._download_webpage(
46 self._LOGIN_URL, None, 'Downloading login page')
47 token, vuid = self._extract_xsrft_and_vuid(webpage)
48 data = {
49 'action': 'login',
50 'email': username,
51 'password': password,
52 'service': 'vimeo',
53 'token': token,
54 }
55 self._set_vimeo_cookie('vuid', vuid)
56 try:
57 self._download_webpage(
58 self._LOGIN_URL, None, 'Logging in',
59 data=urlencode_postdata(data), headers={
60 'Content-Type': 'application/x-www-form-urlencoded',
61 'Referer': self._LOGIN_URL,
62 })
63 except ExtractorError as e:
64 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
65 raise ExtractorError(
66 'Unable to log in: bad username or password',
67 expected=True)
68 raise ExtractorError('Unable to log in')
69
70 def _verify_video_password(self, url, video_id, webpage):
71 password = self._downloader.params.get('videopassword')
72 if password is None:
73 raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
74 token, vuid = self._extract_xsrft_and_vuid(webpage)
75 data = urlencode_postdata({
76 'password': password,
77 'token': token,
78 })
79 if url.startswith('http://'):
80 # vimeo only supports https now, but the user can give an http url
81 url = url.replace('http://', 'https://')
82 password_request = sanitized_Request(url + '/password', data)
83 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
84 password_request.add_header('Referer', url)
85 self._set_vimeo_cookie('vuid', vuid)
86 return self._download_webpage(
87 password_request, video_id,
88 'Verifying the password', 'Wrong password')
89
90 def _extract_xsrft_and_vuid(self, webpage):
91 xsrft = self._search_regex(
92 r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
93 webpage, 'login token', group='xsrft')
94 vuid = self._search_regex(
95 r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
96 webpage, 'vuid', group='vuid')
97 return xsrft, vuid
98
99 def _set_vimeo_cookie(self, name, value):
100 self._set_cookie('vimeo.com', name, value)
101
102 def _vimeo_sort_formats(self, formats):
103 # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
104 # at the same time without actual units specified. This lead to wrong sorting.
105 self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'tbr', 'format_id'))
106
107 def _parse_config(self, config, video_id):
108 video_data = config['video']
109 # Extract title
110 video_title = video_data['title']
111
112 # Extract uploader, uploader_url and uploader_id
113 video_uploader = video_data.get('owner', {}).get('name')
114 video_uploader_url = video_data.get('owner', {}).get('url')
115 video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
116
117 # Extract video thumbnail
118 video_thumbnail = video_data.get('thumbnail')
119 if video_thumbnail is None:
120 video_thumbs = video_data.get('thumbs')
121 if video_thumbs and isinstance(video_thumbs, dict):
122 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
123
124 # Extract video duration
125 video_duration = int_or_none(video_data.get('duration'))
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 for files_type in ('hls', 'dash'):
143 for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items():
144 manifest_url = cdn_data.get('url')
145 if not manifest_url:
146 continue
147 format_id = '%s-%s' % (files_type, cdn_name)
148 if files_type == 'hls':
149 formats.extend(self._extract_m3u8_formats(
150 manifest_url, video_id, 'mp4',
151 'm3u8_native', m3u8_id=format_id,
152 note='Downloading %s m3u8 information' % cdn_name,
153 fatal=False))
154 elif files_type == 'dash':
155 mpd_pattern = r'/%s/(?:sep/)?video/' % video_id
156 mpd_manifest_urls = []
157 if re.search(mpd_pattern, manifest_url):
158 for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
159 mpd_manifest_urls.append((format_id + suffix, re.sub(
160 mpd_pattern, '/%s/%s/' % (video_id, repl), manifest_url)))
161 else:
162 mpd_manifest_urls = [(format_id, manifest_url)]
163 for f_id, m_url in mpd_manifest_urls:
164 mpd_formats = self._extract_mpd_formats(
165 m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
166 'Downloading %s MPD information' % cdn_name,
167 fatal=False)
168 for f in mpd_formats:
169 if f.get('vcodec') == 'none':
170 f['preference'] = -50
171 elif f.get('acodec') == 'none':
172 f['preference'] = -40
173 formats.extend(mpd_formats)
174
175 subtitles = {}
176 text_tracks = config['request'].get('text_tracks')
177 if text_tracks:
178 for tt in text_tracks:
179 subtitles[tt['lang']] = [{
180 'ext': 'vtt',
181 'url': 'https://vimeo.com' + tt['url'],
182 }]
183
184 return {
185 'title': video_title,
186 'uploader': video_uploader,
187 'uploader_id': video_uploader_id,
188 'uploader_url': video_uploader_url,
189 'thumbnail': video_thumbnail,
190 'duration': video_duration,
191 'formats': formats,
192 'subtitles': subtitles,
193 }
194
195
196 class VimeoIE(VimeoBaseInfoExtractor):
197 """Information extractor for vimeo.com."""
198
199 # _VALID_URL matches Vimeo URLs
200 _VALID_URL = r'''(?x)
201 https?://
202 (?:
203 (?:
204 www|
205 (?P<player>player)
206 )
207 \.
208 )?
209 vimeo(?P<pro>pro)?\.com/
210 (?!(?:channels|album)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
211 (?:.*?/)?
212 (?:
213 (?:
214 play_redirect_hls|
215 moogaloop\.swf)\?clip_id=
216 )?
217 (?:videos?/)?
218 (?P<id>[0-9]+)
219 (?:/[\da-f]+)?
220 /?(?:[?&].*)?(?:[#].*)?$
221 '''
222 IE_NAME = 'vimeo'
223 _TESTS = [
224 {
225 'url': 'http://vimeo.com/56015672#at=0',
226 'md5': '8879b6cc097e987f02484baf890129e5',
227 'info_dict': {
228 'id': '56015672',
229 'ext': 'mp4',
230 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
231 'description': 'md5:509a9ad5c9bf97c60faee9203aca4479',
232 'timestamp': 1355990239,
233 'upload_date': '20121220',
234 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
235 'uploader_id': 'user7108434',
236 'uploader': 'Filippo Valsorda',
237 'duration': 10,
238 'license': 'by-sa',
239 },
240 },
241 {
242 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
243 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
244 'note': 'Vimeo Pro video (#1197)',
245 'info_dict': {
246 'id': '68093876',
247 'ext': 'mp4',
248 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
249 'uploader_id': 'openstreetmapus',
250 'uploader': 'OpenStreetMap US',
251 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
252 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
253 'duration': 1595,
254 },
255 },
256 {
257 'url': 'http://player.vimeo.com/video/54469442',
258 'md5': '619b811a4417aa4abe78dc653becf511',
259 'note': 'Videos that embed the url in the player page',
260 'info_dict': {
261 'id': '54469442',
262 'ext': 'mp4',
263 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
264 'uploader': 'The BLN & Business of Software',
265 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
266 'uploader_id': 'theblnbusinessofsoftware',
267 'duration': 3610,
268 'description': None,
269 },
270 },
271 {
272 'url': 'http://vimeo.com/68375962',
273 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
274 'note': 'Video protected with password',
275 'info_dict': {
276 'id': '68375962',
277 'ext': 'mp4',
278 'title': 'youtube-dl password protected test video',
279 'timestamp': 1371200155,
280 'upload_date': '20130614',
281 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
282 'uploader_id': 'user18948128',
283 'uploader': 'Jaime Marquƭnez FerrƔndiz',
284 'duration': 10,
285 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
286 },
287 'params': {
288 'videopassword': 'youtube-dl',
289 },
290 },
291 {
292 'url': 'http://vimeo.com/channels/keypeele/75629013',
293 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
294 'info_dict': {
295 'id': '75629013',
296 'ext': 'mp4',
297 'title': 'Key & Peele: Terrorist Interrogation',
298 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
299 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
300 'uploader_id': 'atencio',
301 'uploader': 'Peter Atencio',
302 'channel_id': 'keypeele',
303 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
304 'timestamp': 1380339469,
305 'upload_date': '20130928',
306 'duration': 187,
307 },
308 'expected_warnings': ['Unable to download JSON metadata'],
309 },
310 {
311 'url': 'http://vimeo.com/76979871',
312 'note': 'Video with subtitles',
313 'info_dict': {
314 'id': '76979871',
315 'ext': 'mp4',
316 'title': 'The New Vimeo Player (You Know, For Videos)',
317 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
318 'timestamp': 1381846109,
319 'upload_date': '20131015',
320 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
321 'uploader_id': 'staff',
322 'uploader': 'Vimeo Staff',
323 'duration': 62,
324 }
325 },
326 {
327 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
328 'url': 'https://player.vimeo.com/video/98044508',
329 'note': 'The js code contains assignments to the same variable as the config',
330 'info_dict': {
331 'id': '98044508',
332 'ext': 'mp4',
333 'title': 'Pier Solar OUYA Official Trailer',
334 'uploader': 'Tulio GonƧalves',
335 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
336 'uploader_id': 'user28849593',
337 },
338 },
339 {
340 # contains original format
341 'url': 'https://vimeo.com/33951933',
342 'md5': '53c688fa95a55bf4b7293d37a89c5c53',
343 'info_dict': {
344 'id': '33951933',
345 'ext': 'mp4',
346 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
347 'uploader': 'The DMCI',
348 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
349 'uploader_id': 'dmci',
350 'timestamp': 1324343742,
351 'upload_date': '20111220',
352 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
353 },
354 },
355 {
356 # only available via https://vimeo.com/channels/tributes/6213729 and
357 # not via https://vimeo.com/6213729
358 'url': 'https://vimeo.com/channels/tributes/6213729',
359 'info_dict': {
360 'id': '6213729',
361 'ext': 'mp4',
362 'title': 'Vimeo Tribute: The Shining',
363 'uploader': 'Casey Donahue',
364 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
365 'uploader_id': 'caseydonahue',
366 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
367 'channel_id': 'tributes',
368 'timestamp': 1250886430,
369 'upload_date': '20090821',
370 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
371 },
372 'params': {
373 'skip_download': True,
374 },
375 'expected_warnings': ['Unable to download JSON metadata'],
376 },
377 {
378 # redirects to ondemand extractor and should be passed through it
379 # for successful extraction
380 'url': 'https://vimeo.com/73445910',
381 'info_dict': {
382 'id': '73445910',
383 'ext': 'mp4',
384 'title': 'The Reluctant Revolutionary',
385 'uploader': '10Ft Films',
386 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
387 'uploader_id': 'tenfootfilms',
388 },
389 'params': {
390 'skip_download': True,
391 },
392 },
393 {
394 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
395 'only_matching': True,
396 },
397 {
398 'url': 'https://vimeo.com/109815029',
399 'note': 'Video not completely processed, "failed" seed status',
400 'only_matching': True,
401 },
402 {
403 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
404 'only_matching': True,
405 },
406 {
407 'url': 'https://vimeo.com/album/2632481/video/79010983',
408 'only_matching': True,
409 },
410 {
411 # source file returns 403: Forbidden
412 'url': 'https://vimeo.com/7809605',
413 'only_matching': True,
414 },
415 {
416 'url': 'https://vimeo.com/160743502/abd0e13fb4',
417 'only_matching': True,
418 }
419 ]
420
421 @staticmethod
422 def _smuggle_referrer(url, referrer_url):
423 return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
424
425 @staticmethod
426 def _extract_urls(url, webpage):
427 urls = []
428 # Look for embedded (iframe) Vimeo player
429 for mobj in re.finditer(
430 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
431 webpage):
432 urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
433 PLAIN_EMBED_RE = (
434 # Look for embedded (swf embed) Vimeo player
435 r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
436 # Look more for non-standard embedded Vimeo player
437 r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
438 )
439 for embed_re in PLAIN_EMBED_RE:
440 for mobj in re.finditer(embed_re, webpage):
441 urls.append(mobj.group('url'))
442 return urls
443
444 @staticmethod
445 def _extract_url(url, webpage):
446 urls = VimeoIE._extract_urls(url, webpage)
447 return urls[0] if urls else None
448
449 def _verify_player_video_password(self, url, video_id):
450 password = self._downloader.params.get('videopassword')
451 if password is None:
452 raise ExtractorError('This video is protected by a password, use the --video-password option')
453 data = urlencode_postdata({'password': password})
454 pass_url = url + '/check-password'
455 password_request = sanitized_Request(pass_url, data)
456 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
457 password_request.add_header('Referer', url)
458 return self._download_json(
459 password_request, video_id,
460 'Verifying the password', 'Wrong password')
461
462 def _real_initialize(self):
463 self._login()
464
465 def _real_extract(self, url):
466 url, data = unsmuggle_url(url, {})
467 headers = std_headers.copy()
468 if 'http_headers' in data:
469 headers.update(data['http_headers'])
470 if 'Referer' not in headers:
471 headers['Referer'] = url
472
473 channel_id = self._search_regex(
474 r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
475
476 # Extract ID from URL
477 mobj = re.match(self._VALID_URL, url)
478 video_id = mobj.group('id')
479 orig_url = url
480 if mobj.group('pro') or mobj.group('player'):
481 url = 'https://player.vimeo.com/video/' + video_id
482 elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
483 url = 'https://vimeo.com/' + video_id
484
485 # Retrieve video webpage to extract further information
486 request = sanitized_Request(url, headers=headers)
487 try:
488 webpage, urlh = self._download_webpage_handle(request, video_id)
489 redirect_url = compat_str(urlh.geturl())
490 # Some URLs redirect to ondemand can't be extracted with
491 # this extractor right away thus should be passed through
492 # ondemand extractor (e.g. https://vimeo.com/73445910)
493 if VimeoOndemandIE.suitable(redirect_url):
494 return self.url_result(redirect_url, VimeoOndemandIE.ie_key())
495 except ExtractorError as ee:
496 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
497 errmsg = ee.cause.read()
498 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
499 raise ExtractorError(
500 'Cannot download embed-only video without embedding '
501 'URL. Please call youtube-dl with the URL of the page '
502 'that embeds this video.',
503 expected=True)
504 raise
505
506 # Now we begin extracting as much information as we can from what we
507 # retrieved. First we extract the information common to all extractors,
508 # and latter we extract those that are Vimeo specific.
509 self.report_extraction(video_id)
510
511 vimeo_config = self._search_regex(
512 r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
513 'vimeo config', default=None)
514 if vimeo_config:
515 seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
516 if seed_status.get('state') == 'failed':
517 raise ExtractorError(
518 '%s said: %s' % (self.IE_NAME, seed_status['title']),
519 expected=True)
520
521 cc_license = None
522 timestamp = None
523
524 # Extract the config JSON
525 try:
526 try:
527 config_url = self._html_search_regex(
528 r' data-config-url="(.+?)"', webpage,
529 'config URL', default=None)
530 if not config_url:
531 # Sometimes new react-based page is served instead of old one that require
532 # different config URL extraction approach (see
533 # https://github.com/rg3/youtube-dl/pull/7209)
534 vimeo_clip_page_config = self._search_regex(
535 r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
536 'vimeo clip page config')
537 page_config = self._parse_json(vimeo_clip_page_config, video_id)
538 config_url = page_config['player']['config_url']
539 cc_license = page_config.get('cc_license')
540 timestamp = try_get(
541 page_config, lambda x: x['clip']['uploaded_on'],
542 compat_str)
543 config_json = self._download_webpage(config_url, video_id)
544 config = json.loads(config_json)
545 except RegexNotFoundError:
546 # For pro videos or player.vimeo.com urls
547 # We try to find out to which variable is assigned the config dic
548 m_variable_name = re.search(r'(\w)\.video\.id', webpage)
549 if m_variable_name is not None:
550 config_re = [r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))]
551 else:
552 config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
553 config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;')
554 config_re.append(r'\bconfig\s*=\s*({.+?})\s*;')
555 config = self._search_regex(config_re, webpage, 'info section',
556 flags=re.DOTALL)
557 config = json.loads(config)
558 except Exception as e:
559 if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
560 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
561
562 if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
563 if '_video_password_verified' in data:
564 raise ExtractorError('video password verification failed!')
565 self._verify_video_password(redirect_url, video_id, webpage)
566 return self._real_extract(
567 smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
568 else:
569 raise ExtractorError('Unable to extract info section',
570 cause=e)
571 else:
572 if config.get('view') == 4:
573 config = self._verify_player_video_password(redirect_url, video_id)
574
575 vod = config.get('video', {}).get('vod', {})
576
577 def is_rented():
578 if '>You rented this title.<' in webpage:
579 return True
580 if config.get('user', {}).get('purchased'):
581 return True
582 for purchase_option in vod.get('purchase_options', []):
583 if purchase_option.get('purchased'):
584 return True
585 label = purchase_option.get('label_string')
586 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
587 return True
588 return False
589
590 if is_rented() and vod.get('is_trailer'):
591 feature_id = vod.get('feature_id')
592 if feature_id and not data.get('force_feature_id', False):
593 return self.url_result(smuggle_url(
594 'https://player.vimeo.com/player/%s' % feature_id,
595 {'force_feature_id': True}), 'Vimeo')
596
597 # Extract video description
598
599 video_description = self._html_search_regex(
600 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
601 webpage, 'description', default=None)
602 if not video_description:
603 video_description = self._html_search_meta(
604 'description', webpage, default=None)
605 if not video_description and mobj.group('pro'):
606 orig_webpage = self._download_webpage(
607 orig_url, video_id,
608 note='Downloading webpage for description',
609 fatal=False)
610 if orig_webpage:
611 video_description = self._html_search_meta(
612 'description', orig_webpage, default=None)
613 if not video_description and not mobj.group('player'):
614 self._downloader.report_warning('Cannot find video description')
615
616 # Extract upload date
617 if not timestamp:
618 timestamp = self._search_regex(
619 r'<time[^>]+datetime="([^"]+)"', webpage,
620 'timestamp', default=None)
621
622 try:
623 view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
624 like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
625 comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
626 except RegexNotFoundError:
627 # This info is only available in vimeo.com/{id} urls
628 view_count = None
629 like_count = None
630 comment_count = None
631
632 formats = []
633 download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={
634 'X-Requested-With': 'XMLHttpRequest'})
635 download_data = self._download_json(download_request, video_id, fatal=False)
636 if download_data:
637 source_file = download_data.get('source_file')
638 if isinstance(source_file, dict):
639 download_url = source_file.get('download_url')
640 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
641 source_name = source_file.get('public_name', 'Original')
642 if self._is_valid_url(download_url, video_id, '%s video' % source_name):
643 ext = (try_get(
644 source_file, lambda x: x['extension'],
645 compat_str) or determine_ext(
646 download_url, None) or 'mp4').lower()
647 formats.append({
648 'url': download_url,
649 'ext': ext,
650 'width': int_or_none(source_file.get('width')),
651 'height': int_or_none(source_file.get('height')),
652 'filesize': parse_filesize(source_file.get('size')),
653 'format_id': source_name,
654 'preference': 1,
655 })
656
657 info_dict_config = self._parse_config(config, video_id)
658 formats.extend(info_dict_config['formats'])
659 self._vimeo_sort_formats(formats)
660
661 json_ld = self._search_json_ld(webpage, video_id, default={})
662
663 if not cc_license:
664 cc_license = self._search_regex(
665 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
666 webpage, 'license', default=None, group='license')
667
668 channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
669
670 info_dict = {
671 'id': video_id,
672 'formats': formats,
673 'timestamp': unified_timestamp(timestamp),
674 'description': video_description,
675 'webpage_url': url,
676 'view_count': view_count,
677 'like_count': like_count,
678 'comment_count': comment_count,
679 'license': cc_license,
680 'channel_id': channel_id,
681 'channel_url': channel_url,
682 }
683
684 info_dict = merge_dicts(info_dict, info_dict_config, json_ld)
685
686 return info_dict
687
688
689 class VimeoOndemandIE(VimeoBaseInfoExtractor):
690 IE_NAME = 'vimeo:ondemand'
691 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)'
692 _TESTS = [{
693 # ondemand video not available via https://vimeo.com/id
694 'url': 'https://vimeo.com/ondemand/20704',
695 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
696 'info_dict': {
697 'id': '105442900',
698 'ext': 'mp4',
699 'title': 'המעבדה - במאי יו×Ŗם פלדמן',
700 'uploader': 'גם ×”×Øטים',
701 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
702 'uploader_id': 'gumfilms',
703 },
704 'params': {
705 'format': 'best[protocol=https]',
706 },
707 }, {
708 # requires Referer to be passed along with og:video:url
709 'url': 'https://vimeo.com/ondemand/36938/126682985',
710 'info_dict': {
711 'id': '126682985',
712 'ext': 'mp4',
713 'title': 'RƤvlock, rƤtt lƤte pƄ rƤtt plats',
714 'uploader': 'Lindroth & Norin',
715 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user14430847',
716 'uploader_id': 'user14430847',
717 },
718 'params': {
719 'skip_download': True,
720 },
721 }, {
722 'url': 'https://vimeo.com/ondemand/nazmaalik',
723 'only_matching': True,
724 }, {
725 'url': 'https://vimeo.com/ondemand/141692381',
726 'only_matching': True,
727 }, {
728 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
729 'only_matching': True,
730 }]
731
732 def _real_extract(self, url):
733 video_id = self._match_id(url)
734 webpage = self._download_webpage(url, video_id)
735 return self.url_result(
736 # Some videos require Referer to be passed along with og:video:url
737 # similarly to generic vimeo embeds (e.g.
738 # https://vimeo.com/ondemand/36938/126682985).
739 VimeoIE._smuggle_referrer(self._og_search_video_url(webpage), url),
740 VimeoIE.ie_key())
741
742
743 class VimeoChannelIE(VimeoBaseInfoExtractor):
744 IE_NAME = 'vimeo:channel'
745 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
746 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
747 _TITLE = None
748 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
749 _TESTS = [{
750 'url': 'https://vimeo.com/channels/tributes',
751 'info_dict': {
752 'id': 'tributes',
753 'title': 'Vimeo Tributes',
754 },
755 'playlist_mincount': 25,
756 }]
757
758 def _page_url(self, base_url, pagenum):
759 return '%s/videos/page:%d/' % (base_url, pagenum)
760
761 def _extract_list_title(self, webpage):
762 return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
763
764 def _login_list_password(self, page_url, list_id, webpage):
765 login_form = self._search_regex(
766 r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
767 webpage, 'login form', default=None)
768 if not login_form:
769 return webpage
770
771 password = self._downloader.params.get('videopassword')
772 if password is None:
773 raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
774 fields = self._hidden_inputs(login_form)
775 token, vuid = self._extract_xsrft_and_vuid(webpage)
776 fields['token'] = token
777 fields['password'] = password
778 post = urlencode_postdata(fields)
779 password_path = self._search_regex(
780 r'action="([^"]+)"', login_form, 'password URL')
781 password_url = compat_urlparse.urljoin(page_url, password_path)
782 password_request = sanitized_Request(password_url, post)
783 password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
784 self._set_vimeo_cookie('vuid', vuid)
785 self._set_vimeo_cookie('xsrft', token)
786
787 return self._download_webpage(
788 password_request, list_id,
789 'Verifying the password', 'Wrong password')
790
791 def _title_and_entries(self, list_id, base_url):
792 for pagenum in itertools.count(1):
793 page_url = self._page_url(base_url, pagenum)
794 webpage = self._download_webpage(
795 page_url, list_id,
796 'Downloading page %s' % pagenum)
797
798 if pagenum == 1:
799 webpage = self._login_list_password(page_url, list_id, webpage)
800 yield self._extract_list_title(webpage)
801
802 # Try extracting href first since not all videos are available via
803 # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
804 clips = re.findall(
805 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
806 if clips:
807 for video_id, video_url, video_title in clips:
808 yield self.url_result(
809 compat_urlparse.urljoin(base_url, video_url),
810 VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
811 # More relaxed fallback
812 else:
813 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
814 yield self.url_result(
815 'https://vimeo.com/%s' % video_id,
816 VimeoIE.ie_key(), video_id=video_id)
817
818 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
819 break
820
821 def _extract_videos(self, list_id, base_url):
822 title_and_entries = self._title_and_entries(list_id, base_url)
823 list_title = next(title_and_entries)
824 return self.playlist_result(title_and_entries, list_id, list_title)
825
826 def _real_extract(self, url):
827 mobj = re.match(self._VALID_URL, url)
828 channel_id = mobj.group('id')
829 return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
830
831
832 class VimeoUserIE(VimeoChannelIE):
833 IE_NAME = 'vimeo:user'
834 _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
835 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
836 _TESTS = [{
837 'url': 'https://vimeo.com/nkistudio/videos',
838 'info_dict': {
839 'title': 'Nki',
840 'id': 'nkistudio',
841 },
842 'playlist_mincount': 66,
843 }]
844
845 def _real_extract(self, url):
846 mobj = re.match(self._VALID_URL, url)
847 name = mobj.group('name')
848 return self._extract_videos(name, 'https://vimeo.com/%s' % name)
849
850
851 class VimeoAlbumIE(VimeoChannelIE):
852 IE_NAME = 'vimeo:album'
853 _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)(?:$|[?#]|/(?!video))'
854 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
855 _TESTS = [{
856 'url': 'https://vimeo.com/album/2632481',
857 'info_dict': {
858 'id': '2632481',
859 'title': 'Staff Favorites: November 2013',
860 },
861 'playlist_mincount': 13,
862 }, {
863 'note': 'Password-protected album',
864 'url': 'https://vimeo.com/album/3253534',
865 'info_dict': {
866 'title': 'test',
867 'id': '3253534',
868 },
869 'playlist_count': 1,
870 'params': {
871 'videopassword': 'youtube-dl',
872 }
873 }, {
874 'url': 'https://vimeo.com/album/2632481/sort:plays/format:thumbnail',
875 'only_matching': True,
876 }, {
877 # TODO: respect page number
878 'url': 'https://vimeo.com/album/2632481/page:2/sort:plays/format:thumbnail',
879 'only_matching': True,
880 }]
881
882 def _page_url(self, base_url, pagenum):
883 return '%s/page:%d/' % (base_url, pagenum)
884
885 def _real_extract(self, url):
886 album_id = self._match_id(url)
887 return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
888
889
890 class VimeoGroupsIE(VimeoAlbumIE):
891 IE_NAME = 'vimeo:group'
892 _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
893 _TESTS = [{
894 'url': 'https://vimeo.com/groups/rolexawards',
895 'info_dict': {
896 'id': 'rolexawards',
897 'title': 'Rolex Awards for Enterprise',
898 },
899 'playlist_mincount': 73,
900 }]
901
902 def _extract_list_title(self, webpage):
903 return self._og_search_title(webpage)
904
905 def _real_extract(self, url):
906 mobj = re.match(self._VALID_URL, url)
907 name = mobj.group('name')
908 return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
909
910
911 class VimeoReviewIE(VimeoBaseInfoExtractor):
912 IE_NAME = 'vimeo:review'
913 IE_DESC = 'Review pages on vimeo'
914 _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
915 _TESTS = [{
916 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
917 'md5': 'c507a72f780cacc12b2248bb4006d253',
918 'info_dict': {
919 'id': '75524534',
920 'ext': 'mp4',
921 'title': "DICK HARDWICK 'Comedian'",
922 'uploader': 'Richard Hardwick',
923 'uploader_id': 'user21297594',
924 }
925 }, {
926 'note': 'video player needs Referer',
927 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
928 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
929 'info_dict': {
930 'id': '91613211',
931 'ext': 'mp4',
932 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
933 'uploader': 'DevWeek Events',
934 'duration': 2773,
935 'thumbnail': r're:^https?://.*\.jpg$',
936 'uploader_id': 'user22258446',
937 }
938 }, {
939 'note': 'Password protected',
940 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
941 'info_dict': {
942 'id': '138823582',
943 'ext': 'mp4',
944 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
945 'uploader': 'TMB',
946 'uploader_id': 'user37284429',
947 },
948 'params': {
949 'videopassword': 'holygrail',
950 },
951 'skip': 'video gone',
952 }]
953
954 def _real_initialize(self):
955 self._login()
956
957 def _get_config_url(self, webpage_url, video_id, video_password_verified=False):
958 webpage = self._download_webpage(webpage_url, video_id)
959 config_url = self._html_search_regex(
960 r'data-config-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
961 'config URL', default=None, group='url')
962 if not config_url:
963 data = self._parse_json(self._search_regex(
964 r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data',
965 default=NO_DEFAULT if video_password_verified else '{}'), video_id)
966 config_url = data.get('vimeo_esi', {}).get('config', {}).get('configUrl')
967 if config_url is None:
968 self._verify_video_password(webpage_url, video_id, webpage)
969 config_url = self._get_config_url(
970 webpage_url, video_id, video_password_verified=True)
971 return config_url
972
973 def _real_extract(self, url):
974 video_id = self._match_id(url)
975 config_url = self._get_config_url(url, video_id)
976 config = self._download_json(config_url, video_id)
977 info_dict = self._parse_config(config, video_id)
978 self._vimeo_sort_formats(info_dict['formats'])
979 info_dict['id'] = video_id
980 return info_dict
981
982
983 class VimeoWatchLaterIE(VimeoChannelIE):
984 IE_NAME = 'vimeo:watchlater'
985 IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
986 _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
987 _TITLE = 'Watch Later'
988 _LOGIN_REQUIRED = True
989 _TESTS = [{
990 'url': 'https://vimeo.com/watchlater',
991 'only_matching': True,
992 }]
993
994 def _real_initialize(self):
995 self._login()
996
997 def _page_url(self, base_url, pagenum):
998 url = '%s/page:%d/' % (base_url, pagenum)
999 request = sanitized_Request(url)
1000 # Set the header to get a partial html page with the ids,
1001 # the normal page doesn't contain them.
1002 request.add_header('X-Requested-With', 'XMLHttpRequest')
1003 return request
1004
1005 def _real_extract(self, url):
1006 return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1007
1008
1009 class VimeoLikesIE(InfoExtractor):
1010 _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1011 IE_NAME = 'vimeo:likes'
1012 IE_DESC = 'Vimeo user likes'
1013 _TESTS = [{
1014 'url': 'https://vimeo.com/user755559/likes/',
1015 'playlist_mincount': 293,
1016 'info_dict': {
1017 'id': 'user755559_likes',
1018 'description': 'See all the videos urza likes',
1019 'title': 'Videos urza likes',
1020 },
1021 }, {
1022 'url': 'https://vimeo.com/stormlapse/likes',
1023 'only_matching': True,
1024 }]
1025
1026 def _real_extract(self, url):
1027 user_id = self._match_id(url)
1028 webpage = self._download_webpage(url, user_id)
1029 page_count = self._int(
1030 self._search_regex(
1031 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
1032 .*?</a></li>\s*<li\s+class="pagination_next">
1033 ''', webpage, 'page count', default=1),
1034 'page count', fatal=True)
1035 PAGE_SIZE = 12
1036 title = self._html_search_regex(
1037 r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
1038 description = self._html_search_meta('description', webpage)
1039
1040 def _get_page(idx):
1041 page_url = 'https://vimeo.com/%s/likes/page:%d/sort:date' % (
1042 user_id, idx + 1)
1043 webpage = self._download_webpage(
1044 page_url, user_id,
1045 note='Downloading page %d/%d' % (idx + 1, page_count))
1046 video_list = self._search_regex(
1047 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
1048 webpage, 'video content')
1049 paths = re.findall(
1050 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
1051 for path in paths:
1052 yield {
1053 '_type': 'url',
1054 'url': compat_urlparse.urljoin(page_url, path),
1055 }
1056
1057 pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
1058
1059 return {
1060 '_type': 'playlist',
1061 'id': '%s_likes' % user_id,
1062 'title': title,
1063 'description': description,
1064 'entries': pl,
1065 }