]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vimeo.py
7e854f3265eac3312f1b63199ce8633a17eb7d04
[youtubedl] / youtube_dl / extractor / vimeo.py
1 # encoding: 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 unified_strdate,
25 unsmuggle_url,
26 urlencode_postdata,
27 unescapeHTML,
28 parse_filesize,
29 try_get,
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 self.report_login()
45 webpage = self._download_webpage(self._LOGIN_URL, None, False)
46 token, vuid = self._extract_xsrft_and_vuid(webpage)
47 data = urlencode_postdata({
48 'action': 'login',
49 'email': username,
50 'password': password,
51 'service': 'vimeo',
52 'token': token,
53 })
54 login_request = sanitized_Request(self._LOGIN_URL, data)
55 login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
56 login_request.add_header('Referer', self._LOGIN_URL)
57 self._set_vimeo_cookie('vuid', vuid)
58 self._download_webpage(login_request, None, False, 'Wrong login info')
59
60 def _verify_video_password(self, url, video_id, webpage):
61 password = self._downloader.params.get('videopassword')
62 if password is None:
63 raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
64 token, vuid = self._extract_xsrft_and_vuid(webpage)
65 data = urlencode_postdata({
66 'password': password,
67 'token': token,
68 })
69 if url.startswith('http://'):
70 # vimeo only supports https now, but the user can give an http url
71 url = url.replace('http://', 'https://')
72 password_request = sanitized_Request(url + '/password', data)
73 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
74 password_request.add_header('Referer', url)
75 self._set_vimeo_cookie('vuid', vuid)
76 return self._download_webpage(
77 password_request, video_id,
78 'Verifying the password', 'Wrong password')
79
80 def _extract_xsrft_and_vuid(self, webpage):
81 xsrft = self._search_regex(
82 r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
83 webpage, 'login token', group='xsrft')
84 vuid = self._search_regex(
85 r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
86 webpage, 'vuid', group='vuid')
87 return xsrft, vuid
88
89 def _set_vimeo_cookie(self, name, value):
90 self._set_cookie('vimeo.com', name, value)
91
92 def _vimeo_sort_formats(self, formats):
93 # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
94 # at the same time without actual units specified. This lead to wrong sorting.
95 self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id'))
96
97 def _parse_config(self, config, video_id):
98 # Extract title
99 video_title = config['video']['title']
100
101 # Extract uploader, uploader_url and uploader_id
102 video_uploader = config['video'].get('owner', {}).get('name')
103 video_uploader_url = config['video'].get('owner', {}).get('url')
104 video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
105
106 # Extract video thumbnail
107 video_thumbnail = config['video'].get('thumbnail')
108 if video_thumbnail is None:
109 video_thumbs = config['video'].get('thumbs')
110 if video_thumbs and isinstance(video_thumbs, dict):
111 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
112
113 # Extract video duration
114 video_duration = int_or_none(config['video'].get('duration'))
115
116 formats = []
117 config_files = config['video'].get('files') or config['request'].get('files', {})
118 for f in config_files.get('progressive', []):
119 video_url = f.get('url')
120 if not video_url:
121 continue
122 formats.append({
123 'url': video_url,
124 'format_id': 'http-%s' % f.get('quality'),
125 'width': int_or_none(f.get('width')),
126 'height': int_or_none(f.get('height')),
127 'fps': int_or_none(f.get('fps')),
128 'tbr': int_or_none(f.get('bitrate')),
129 })
130 m3u8_url = config_files.get('hls', {}).get('url')
131 if m3u8_url:
132 formats.extend(self._extract_m3u8_formats(
133 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
134
135 subtitles = {}
136 text_tracks = config['request'].get('text_tracks')
137 if text_tracks:
138 for tt in text_tracks:
139 subtitles[tt['lang']] = [{
140 'ext': 'vtt',
141 'url': 'https://vimeo.com' + tt['url'],
142 }]
143
144 return {
145 'title': video_title,
146 'uploader': video_uploader,
147 'uploader_id': video_uploader_id,
148 'uploader_url': video_uploader_url,
149 'thumbnail': video_thumbnail,
150 'duration': video_duration,
151 'formats': formats,
152 'subtitles': subtitles,
153 }
154
155
156 class VimeoIE(VimeoBaseInfoExtractor):
157 """Information extractor for vimeo.com."""
158
159 # _VALID_URL matches Vimeo URLs
160 _VALID_URL = r'''(?x)
161 https?://
162 (?:
163 (?:
164 www|
165 (?P<player>player)
166 )
167 \.
168 )?
169 vimeo(?P<pro>pro)?\.com/
170 (?!(?:channels|album)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
171 (?:.*?/)?
172 (?:
173 (?:
174 play_redirect_hls|
175 moogaloop\.swf)\?clip_id=
176 )?
177 (?:videos?/)?
178 (?P<id>[0-9]+)
179 (?:/[\da-f]+)?
180 /?(?:[?&].*)?(?:[#].*)?$
181 '''
182 IE_NAME = 'vimeo'
183 _TESTS = [
184 {
185 'url': 'http://vimeo.com/56015672#at=0',
186 'md5': '8879b6cc097e987f02484baf890129e5',
187 'info_dict': {
188 'id': '56015672',
189 'ext': 'mp4',
190 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
191 'description': 'md5:2d3305bad981a06ff79f027f19865021',
192 'upload_date': '20121220',
193 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user7108434',
194 'uploader_id': 'user7108434',
195 'uploader': 'Filippo Valsorda',
196 'duration': 10,
197 },
198 },
199 {
200 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
201 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
202 'note': 'Vimeo Pro video (#1197)',
203 'info_dict': {
204 'id': '68093876',
205 'ext': 'mp4',
206 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
207 'uploader_id': 'openstreetmapus',
208 'uploader': 'OpenStreetMap US',
209 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
210 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
211 'duration': 1595,
212 },
213 },
214 {
215 'url': 'http://player.vimeo.com/video/54469442',
216 'md5': '619b811a4417aa4abe78dc653becf511',
217 'note': 'Videos that embed the url in the player page',
218 'info_dict': {
219 'id': '54469442',
220 'ext': 'mp4',
221 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
222 'uploader': 'The BLN & Business of Software',
223 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
224 'uploader_id': 'theblnbusinessofsoftware',
225 'duration': 3610,
226 'description': None,
227 },
228 },
229 {
230 'url': 'http://vimeo.com/68375962',
231 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
232 'note': 'Video protected with password',
233 'info_dict': {
234 'id': '68375962',
235 'ext': 'mp4',
236 'title': 'youtube-dl password protected test video',
237 'upload_date': '20130614',
238 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user18948128',
239 'uploader_id': 'user18948128',
240 'uploader': 'Jaime Marquƭnez FerrƔndiz',
241 'duration': 10,
242 'description': 'This is "youtube-dl password protected test video" by on Vimeo, the home for high quality videos and the people who love them.',
243 },
244 'params': {
245 'videopassword': 'youtube-dl',
246 },
247 },
248 {
249 'url': 'http://vimeo.com/channels/keypeele/75629013',
250 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
251 'info_dict': {
252 'id': '75629013',
253 'ext': 'mp4',
254 'title': 'Key & Peele: Terrorist Interrogation',
255 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
256 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/atencio',
257 'uploader_id': 'atencio',
258 'uploader': 'Peter Atencio',
259 'upload_date': '20130927',
260 'duration': 187,
261 },
262 },
263 {
264 'url': 'http://vimeo.com/76979871',
265 'note': 'Video with subtitles',
266 'info_dict': {
267 'id': '76979871',
268 'ext': 'mp4',
269 'title': 'The New Vimeo Player (You Know, For Videos)',
270 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
271 'upload_date': '20131015',
272 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/staff',
273 'uploader_id': 'staff',
274 'uploader': 'Vimeo Staff',
275 'duration': 62,
276 }
277 },
278 {
279 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
280 'url': 'https://player.vimeo.com/video/98044508',
281 'note': 'The js code contains assignments to the same variable as the config',
282 'info_dict': {
283 'id': '98044508',
284 'ext': 'mp4',
285 'title': 'Pier Solar OUYA Official Trailer',
286 'uploader': 'Tulio GonƧalves',
287 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user28849593',
288 'uploader_id': 'user28849593',
289 },
290 },
291 {
292 # contains original format
293 'url': 'https://vimeo.com/33951933',
294 'md5': '2d9f5475e0537f013d0073e812ab89e6',
295 'info_dict': {
296 'id': '33951933',
297 'ext': 'mp4',
298 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
299 'uploader': 'The DMCI',
300 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/dmci',
301 'uploader_id': 'dmci',
302 'upload_date': '20111220',
303 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
304 },
305 },
306 {
307 # only available via https://vimeo.com/channels/tributes/6213729 and
308 # not via https://vimeo.com/6213729
309 'url': 'https://vimeo.com/channels/tributes/6213729',
310 'info_dict': {
311 'id': '6213729',
312 'ext': 'mp4',
313 'title': 'Vimeo Tribute: The Shining',
314 'uploader': 'Casey Donahue',
315 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/caseydonahue',
316 'uploader_id': 'caseydonahue',
317 'upload_date': '20090821',
318 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
319 },
320 'params': {
321 'skip_download': True,
322 },
323 'expected_warnings': ['Unable to download JSON metadata'],
324 },
325 {
326 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
327 'only_matching': True,
328 },
329 {
330 'url': 'https://vimeo.com/109815029',
331 'note': 'Video not completely processed, "failed" seed status',
332 'only_matching': True,
333 },
334 {
335 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
336 'only_matching': True,
337 },
338 {
339 'url': 'https://vimeo.com/album/2632481/video/79010983',
340 'only_matching': True,
341 },
342 {
343 # source file returns 403: Forbidden
344 'url': 'https://vimeo.com/7809605',
345 'only_matching': True,
346 },
347 {
348 'url': 'https://vimeo.com/160743502/abd0e13fb4',
349 'only_matching': True,
350 }
351 ]
352
353 @staticmethod
354 def _extract_vimeo_url(url, webpage):
355 # Look for embedded (iframe) Vimeo player
356 mobj = re.search(
357 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
358 if mobj:
359 player_url = unescapeHTML(mobj.group('url'))
360 surl = smuggle_url(player_url, {'http_headers': {'Referer': url}})
361 return surl
362 # Look for embedded (swf embed) Vimeo player
363 mobj = re.search(
364 r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
365 if mobj:
366 return mobj.group(1)
367 # Look more for non-standard embedded Vimeo player
368 mobj = re.search(
369 r'<video[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)(?P=q1)', webpage)
370 if mobj:
371 return mobj.group('url')
372
373 def _verify_player_video_password(self, url, video_id):
374 password = self._downloader.params.get('videopassword')
375 if password is None:
376 raise ExtractorError('This video is protected by a password, use the --video-password option')
377 data = urlencode_postdata({'password': password})
378 pass_url = url + '/check-password'
379 password_request = sanitized_Request(pass_url, data)
380 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
381 password_request.add_header('Referer', url)
382 return self._download_json(
383 password_request, video_id,
384 'Verifying the password', 'Wrong password')
385
386 def _real_initialize(self):
387 self._login()
388
389 def _real_extract(self, url):
390 url, data = unsmuggle_url(url, {})
391 headers = std_headers.copy()
392 if 'http_headers' in data:
393 headers.update(data['http_headers'])
394 if 'Referer' not in headers:
395 headers['Referer'] = url
396
397 # Extract ID from URL
398 mobj = re.match(self._VALID_URL, url)
399 video_id = mobj.group('id')
400 orig_url = url
401 if mobj.group('pro') or mobj.group('player'):
402 url = 'https://player.vimeo.com/video/' + video_id
403 elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
404 url = 'https://vimeo.com/' + video_id
405
406 # Retrieve video webpage to extract further information
407 request = sanitized_Request(url, headers=headers)
408 try:
409 webpage = self._download_webpage(request, video_id)
410 except ExtractorError as ee:
411 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
412 errmsg = ee.cause.read()
413 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
414 raise ExtractorError(
415 'Cannot download embed-only video without embedding '
416 'URL. Please call youtube-dl with the URL of the page '
417 'that embeds this video.',
418 expected=True)
419 raise
420
421 # Now we begin extracting as much information as we can from what we
422 # retrieved. First we extract the information common to all extractors,
423 # and latter we extract those that are Vimeo specific.
424 self.report_extraction(video_id)
425
426 vimeo_config = self._search_regex(
427 r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
428 'vimeo config', default=None)
429 if vimeo_config:
430 seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
431 if seed_status.get('state') == 'failed':
432 raise ExtractorError(
433 '%s said: %s' % (self.IE_NAME, seed_status['title']),
434 expected=True)
435
436 # Extract the config JSON
437 try:
438 try:
439 config_url = self._html_search_regex(
440 r' data-config-url="(.+?)"', webpage,
441 'config URL', default=None)
442 if not config_url:
443 # Sometimes new react-based page is served instead of old one that require
444 # different config URL extraction approach (see
445 # https://github.com/rg3/youtube-dl/pull/7209)
446 vimeo_clip_page_config = self._search_regex(
447 r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
448 'vimeo clip page config')
449 config_url = self._parse_json(
450 vimeo_clip_page_config, video_id)['player']['config_url']
451 config_json = self._download_webpage(config_url, video_id)
452 config = json.loads(config_json)
453 except RegexNotFoundError:
454 # For pro videos or player.vimeo.com urls
455 # We try to find out to which variable is assigned the config dic
456 m_variable_name = re.search('(\w)\.video\.id', webpage)
457 if m_variable_name is not None:
458 config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
459 else:
460 config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
461 config = self._search_regex(config_re, webpage, 'info section',
462 flags=re.DOTALL)
463 config = json.loads(config)
464 except Exception as e:
465 if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
466 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
467
468 if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
469 if '_video_password_verified' in data:
470 raise ExtractorError('video password verification failed!')
471 self._verify_video_password(url, video_id, webpage)
472 return self._real_extract(
473 smuggle_url(url, {'_video_password_verified': 'verified'}))
474 else:
475 raise ExtractorError('Unable to extract info section',
476 cause=e)
477 else:
478 if config.get('view') == 4:
479 config = self._verify_player_video_password(url, video_id)
480
481 def is_rented():
482 if '>You rented this title.<' in webpage:
483 return True
484 if config.get('user', {}).get('purchased'):
485 return True
486 label = try_get(
487 config, lambda x: x['video']['vod']['purchase_options'][0]['label_string'], compat_str)
488 if label and label.startswith('You rented this'):
489 return True
490 return False
491
492 if is_rented():
493 feature_id = config.get('video', {}).get('vod', {}).get('feature_id')
494 if feature_id and not data.get('force_feature_id', False):
495 return self.url_result(smuggle_url(
496 'https://player.vimeo.com/player/%s' % feature_id,
497 {'force_feature_id': True}), 'Vimeo')
498
499 # Extract video description
500
501 video_description = self._html_search_regex(
502 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
503 webpage, 'description', default=None)
504 if not video_description:
505 video_description = self._html_search_meta(
506 'description', webpage, default=None)
507 if not video_description and mobj.group('pro'):
508 orig_webpage = self._download_webpage(
509 orig_url, video_id,
510 note='Downloading webpage for description',
511 fatal=False)
512 if orig_webpage:
513 video_description = self._html_search_meta(
514 'description', orig_webpage, default=None)
515 if not video_description and not mobj.group('player'):
516 self._downloader.report_warning('Cannot find video description')
517
518 # Extract upload date
519 video_upload_date = None
520 mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
521 if mobj is not None:
522 video_upload_date = unified_strdate(mobj.group(1))
523
524 try:
525 view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
526 like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
527 comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
528 except RegexNotFoundError:
529 # This info is only available in vimeo.com/{id} urls
530 view_count = None
531 like_count = None
532 comment_count = None
533
534 formats = []
535 download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={
536 'X-Requested-With': 'XMLHttpRequest'})
537 download_data = self._download_json(download_request, video_id, fatal=False)
538 if download_data:
539 source_file = download_data.get('source_file')
540 if isinstance(source_file, dict):
541 download_url = source_file.get('download_url')
542 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
543 source_name = source_file.get('public_name', 'Original')
544 if self._is_valid_url(download_url, video_id, '%s video' % source_name):
545 ext = source_file.get('extension', determine_ext(download_url)).lower()
546 formats.append({
547 'url': download_url,
548 'ext': ext,
549 'width': int_or_none(source_file.get('width')),
550 'height': int_or_none(source_file.get('height')),
551 'filesize': parse_filesize(source_file.get('size')),
552 'format_id': source_name,
553 'preference': 1,
554 })
555
556 info_dict = self._parse_config(config, video_id)
557 formats.extend(info_dict['formats'])
558 self._vimeo_sort_formats(formats)
559 info_dict.update({
560 'id': video_id,
561 'formats': formats,
562 'upload_date': video_upload_date,
563 'description': video_description,
564 'webpage_url': url,
565 'view_count': view_count,
566 'like_count': like_count,
567 'comment_count': comment_count,
568 })
569
570 return info_dict
571
572
573 class VimeoOndemandIE(VimeoBaseInfoExtractor):
574 IE_NAME = 'vimeo:ondemand'
575 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)'
576 _TESTS = [{
577 # ondemand video not available via https://vimeo.com/id
578 'url': 'https://vimeo.com/ondemand/20704',
579 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
580 'info_dict': {
581 'id': '105442900',
582 'ext': 'mp4',
583 'title': 'המעבדה - במאי יו×Ŗם פלדמן',
584 'uploader': 'גם ×”×Øטים',
585 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/gumfilms',
586 'uploader_id': 'gumfilms',
587 },
588 }, {
589 'url': 'https://vimeo.com/ondemand/nazmaalik',
590 'only_matching': True,
591 }, {
592 'url': 'https://vimeo.com/ondemand/141692381',
593 'only_matching': True,
594 }, {
595 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
596 'only_matching': True,
597 }]
598
599 def _real_extract(self, url):
600 video_id = self._match_id(url)
601 webpage = self._download_webpage(url, video_id)
602 return self.url_result(self._og_search_video_url(webpage), VimeoIE.ie_key())
603
604
605 class VimeoChannelIE(VimeoBaseInfoExtractor):
606 IE_NAME = 'vimeo:channel'
607 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
608 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
609 _TITLE = None
610 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
611 _TESTS = [{
612 'url': 'https://vimeo.com/channels/tributes',
613 'info_dict': {
614 'id': 'tributes',
615 'title': 'Vimeo Tributes',
616 },
617 'playlist_mincount': 25,
618 }]
619
620 def _page_url(self, base_url, pagenum):
621 return '%s/videos/page:%d/' % (base_url, pagenum)
622
623 def _extract_list_title(self, webpage):
624 return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
625
626 def _login_list_password(self, page_url, list_id, webpage):
627 login_form = self._search_regex(
628 r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
629 webpage, 'login form', default=None)
630 if not login_form:
631 return webpage
632
633 password = self._downloader.params.get('videopassword')
634 if password is None:
635 raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
636 fields = self._hidden_inputs(login_form)
637 token, vuid = self._extract_xsrft_and_vuid(webpage)
638 fields['token'] = token
639 fields['password'] = password
640 post = urlencode_postdata(fields)
641 password_path = self._search_regex(
642 r'action="([^"]+)"', login_form, 'password URL')
643 password_url = compat_urlparse.urljoin(page_url, password_path)
644 password_request = sanitized_Request(password_url, post)
645 password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
646 self._set_vimeo_cookie('vuid', vuid)
647 self._set_vimeo_cookie('xsrft', token)
648
649 return self._download_webpage(
650 password_request, list_id,
651 'Verifying the password', 'Wrong password')
652
653 def _title_and_entries(self, list_id, base_url):
654 for pagenum in itertools.count(1):
655 page_url = self._page_url(base_url, pagenum)
656 webpage = self._download_webpage(
657 page_url, list_id,
658 'Downloading page %s' % pagenum)
659
660 if pagenum == 1:
661 webpage = self._login_list_password(page_url, list_id, webpage)
662 yield self._extract_list_title(webpage)
663
664 # Try extracting href first since not all videos are available via
665 # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
666 clips = re.findall(
667 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)', webpage)
668 if clips:
669 for video_id, video_url in clips:
670 yield self.url_result(
671 compat_urlparse.urljoin(base_url, video_url),
672 VimeoIE.ie_key(), video_id=video_id)
673 # More relaxed fallback
674 else:
675 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
676 yield self.url_result(
677 'https://vimeo.com/%s' % video_id,
678 VimeoIE.ie_key(), video_id=video_id)
679
680 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
681 break
682
683 def _extract_videos(self, list_id, base_url):
684 title_and_entries = self._title_and_entries(list_id, base_url)
685 list_title = next(title_and_entries)
686 return self.playlist_result(title_and_entries, list_id, list_title)
687
688 def _real_extract(self, url):
689 mobj = re.match(self._VALID_URL, url)
690 channel_id = mobj.group('id')
691 return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
692
693
694 class VimeoUserIE(VimeoChannelIE):
695 IE_NAME = 'vimeo:user'
696 _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
697 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
698 _TESTS = [{
699 'url': 'https://vimeo.com/nkistudio/videos',
700 'info_dict': {
701 'title': 'Nki',
702 'id': 'nkistudio',
703 },
704 'playlist_mincount': 66,
705 }]
706
707 def _real_extract(self, url):
708 mobj = re.match(self._VALID_URL, url)
709 name = mobj.group('name')
710 return self._extract_videos(name, 'https://vimeo.com/%s' % name)
711
712
713 class VimeoAlbumIE(VimeoChannelIE):
714 IE_NAME = 'vimeo:album'
715 _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)(?:$|[?#]|/(?!video))'
716 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
717 _TESTS = [{
718 'url': 'https://vimeo.com/album/2632481',
719 'info_dict': {
720 'id': '2632481',
721 'title': 'Staff Favorites: November 2013',
722 },
723 'playlist_mincount': 13,
724 }, {
725 'note': 'Password-protected album',
726 'url': 'https://vimeo.com/album/3253534',
727 'info_dict': {
728 'title': 'test',
729 'id': '3253534',
730 },
731 'playlist_count': 1,
732 'params': {
733 'videopassword': 'youtube-dl',
734 }
735 }, {
736 'url': 'https://vimeo.com/album/2632481/sort:plays/format:thumbnail',
737 'only_matching': True,
738 }, {
739 # TODO: respect page number
740 'url': 'https://vimeo.com/album/2632481/page:2/sort:plays/format:thumbnail',
741 'only_matching': True,
742 }]
743
744 def _page_url(self, base_url, pagenum):
745 return '%s/page:%d/' % (base_url, pagenum)
746
747 def _real_extract(self, url):
748 album_id = self._match_id(url)
749 return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
750
751
752 class VimeoGroupsIE(VimeoAlbumIE):
753 IE_NAME = 'vimeo:group'
754 _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
755 _TESTS = [{
756 'url': 'https://vimeo.com/groups/rolexawards',
757 'info_dict': {
758 'id': 'rolexawards',
759 'title': 'Rolex Awards for Enterprise',
760 },
761 'playlist_mincount': 73,
762 }]
763
764 def _extract_list_title(self, webpage):
765 return self._og_search_title(webpage)
766
767 def _real_extract(self, url):
768 mobj = re.match(self._VALID_URL, url)
769 name = mobj.group('name')
770 return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
771
772
773 class VimeoReviewIE(VimeoBaseInfoExtractor):
774 IE_NAME = 'vimeo:review'
775 IE_DESC = 'Review pages on vimeo'
776 _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
777 _TESTS = [{
778 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
779 'md5': 'c507a72f780cacc12b2248bb4006d253',
780 'info_dict': {
781 'id': '75524534',
782 'ext': 'mp4',
783 'title': "DICK HARDWICK 'Comedian'",
784 'uploader': 'Richard Hardwick',
785 'uploader_id': 'user21297594',
786 }
787 }, {
788 'note': 'video player needs Referer',
789 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
790 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
791 'info_dict': {
792 'id': '91613211',
793 'ext': 'mp4',
794 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
795 'uploader': 'DevWeek Events',
796 'duration': 2773,
797 'thumbnail': 're:^https?://.*\.jpg$',
798 'uploader_id': 'user22258446',
799 }
800 }, {
801 'note': 'Password protected',
802 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
803 'info_dict': {
804 'id': '138823582',
805 'ext': 'mp4',
806 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
807 'uploader': 'TMB',
808 'uploader_id': 'user37284429',
809 },
810 'params': {
811 'videopassword': 'holygrail',
812 },
813 }]
814
815 def _real_initialize(self):
816 self._login()
817
818 def _get_config_url(self, webpage_url, video_id, video_password_verified=False):
819 webpage = self._download_webpage(webpage_url, video_id)
820 config_url = self._html_search_regex(
821 r'data-config-url="([^"]+)"', webpage, 'config URL',
822 default=NO_DEFAULT if video_password_verified else None)
823 if config_url is None:
824 self._verify_video_password(webpage_url, video_id, webpage)
825 config_url = self._get_config_url(
826 webpage_url, video_id, video_password_verified=True)
827 return config_url
828
829 def _real_extract(self, url):
830 video_id = self._match_id(url)
831 config_url = self._get_config_url(url, video_id)
832 config = self._download_json(config_url, video_id)
833 info_dict = self._parse_config(config, video_id)
834 self._vimeo_sort_formats(info_dict['formats'])
835 info_dict['id'] = video_id
836 return info_dict
837
838
839 class VimeoWatchLaterIE(VimeoChannelIE):
840 IE_NAME = 'vimeo:watchlater'
841 IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
842 _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
843 _TITLE = 'Watch Later'
844 _LOGIN_REQUIRED = True
845 _TESTS = [{
846 'url': 'https://vimeo.com/watchlater',
847 'only_matching': True,
848 }]
849
850 def _real_initialize(self):
851 self._login()
852
853 def _page_url(self, base_url, pagenum):
854 url = '%s/page:%d/' % (base_url, pagenum)
855 request = sanitized_Request(url)
856 # Set the header to get a partial html page with the ids,
857 # the normal page doesn't contain them.
858 request.add_header('X-Requested-With', 'XMLHttpRequest')
859 return request
860
861 def _real_extract(self, url):
862 return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
863
864
865 class VimeoLikesIE(InfoExtractor):
866 _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
867 IE_NAME = 'vimeo:likes'
868 IE_DESC = 'Vimeo user likes'
869 _TEST = {
870 'url': 'https://vimeo.com/user755559/likes/',
871 'playlist_mincount': 293,
872 'info_dict': {
873 'id': 'user755559_likes',
874 'description': 'See all the videos urza likes',
875 'title': 'Videos urza likes',
876 },
877 }
878
879 def _real_extract(self, url):
880 user_id = self._match_id(url)
881 webpage = self._download_webpage(url, user_id)
882 page_count = self._int(
883 self._search_regex(
884 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
885 .*?</a></li>\s*<li\s+class="pagination_next">
886 ''', webpage, 'page count'),
887 'page count', fatal=True)
888 PAGE_SIZE = 12
889 title = self._html_search_regex(
890 r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
891 description = self._html_search_meta('description', webpage)
892
893 def _get_page(idx):
894 page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
895 user_id, idx + 1)
896 webpage = self._download_webpage(
897 page_url, user_id,
898 note='Downloading page %d/%d' % (idx + 1, page_count))
899 video_list = self._search_regex(
900 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
901 webpage, 'video content')
902 paths = re.findall(
903 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
904 for path in paths:
905 yield {
906 '_type': 'url',
907 'url': compat_urlparse.urljoin(page_url, path),
908 }
909
910 pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
911
912 return {
913 '_type': 'playlist',
914 'id': 'user%s_likes' % user_id,
915 'title': title,
916 'description': description,
917 'entries': pl,
918 }