2 from __future__ import unicode_literals
8 from .common import InfoExtractor
12 compat_urllib_request,
29 class VimeoBaseInfoExtractor(InfoExtractor):
30 _NETRC_MACHINE = 'vimeo'
31 _LOGIN_REQUIRED = False
32 _LOGIN_URL = 'https://vimeo.com/log_in'
35 (username, password) = self._get_login_info()
37 if self._LOGIN_REQUIRED:
38 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
41 webpage = self._download_webpage(self._LOGIN_URL, None, False)
42 token = self._extract_xsrft(webpage)
43 vuid = self._search_regex(
44 r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
45 webpage, 'vuid', group='vuid')
46 data = urlencode_postdata({
53 login_request = compat_urllib_request.Request(self._LOGIN_URL, data)
54 login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
55 login_request.add_header('Cookie', 'vuid=%s' % vuid)
56 login_request.add_header('Referer', self._LOGIN_URL)
57 self._download_webpage(login_request, None, False, 'Wrong login info')
59 def _extract_xsrft(self, webpage):
60 return self._search_regex(
61 r'xsrft\s*[=:]\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
62 webpage, 'login token', group='xsrft')
65 class VimeoIE(VimeoBaseInfoExtractor):
66 """Information extractor for vimeo.com."""
68 # _VALID_URL matches Vimeo URLs
71 (?:(?:www|(?P<player>player))\.)?
72 vimeo(?P<pro>pro)?\.com/
73 (?!channels/[^/?#]+/?(?:$|[?#])|album/)
75 (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
78 /?(?:[?&].*)?(?:[#].*)?$'''
82 'url': 'http://vimeo.com/56015672#at=0',
83 'md5': '8879b6cc097e987f02484baf890129e5',
87 "upload_date": "20121220",
88 "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
89 "uploader_id": "user7108434",
90 "uploader": "Filippo Valsorda",
91 "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
96 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
97 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
98 'note': 'Vimeo Pro video (#1197)',
102 'uploader_id': 'openstreetmapus',
103 'uploader': 'OpenStreetMap US',
104 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
105 'description': 'md5:380943ec71b89736ff4bf27183233d09',
110 'url': 'http://player.vimeo.com/video/54469442',
111 'md5': '619b811a4417aa4abe78dc653becf511',
112 'note': 'Videos that embed the url in the player page',
116 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
117 'uploader': 'The BLN & Business of Software',
118 'uploader_id': 'theblnbusinessofsoftware',
124 'url': 'http://vimeo.com/68375962',
125 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
126 'note': 'Video protected with password',
130 'title': 'youtube-dl password protected test video',
131 'upload_date': '20130614',
132 'uploader_id': 'user18948128',
133 'uploader': 'Jaime Marquínez Ferrándiz',
135 'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people who love them.',
138 'videopassword': 'youtube-dl',
142 'url': 'http://vimeo.com/channels/keypeele/75629013',
143 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
144 'note': 'Video is freely available via original URL '
145 'and protected with password when accessed via http://vimeo.com/75629013',
149 'title': 'Key & Peele: Terrorist Interrogation',
150 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
151 'uploader_id': 'atencio',
152 'uploader': 'Peter Atencio',
153 'upload_date': '20130927',
158 'url': 'http://vimeo.com/76979871',
159 'md5': '3363dd6ffebe3784d56f4132317fd446',
160 'note': 'Video with subtitles',
164 'title': 'The New Vimeo Player (You Know, For Videos)',
165 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
166 'upload_date': '20131015',
167 'uploader_id': 'staff',
168 'uploader': 'Vimeo Staff',
173 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
174 'url': 'https://player.vimeo.com/video/98044508',
175 'note': 'The js code contains assignments to the same variable as the config',
179 'title': 'Pier Solar OUYA Official Trailer',
180 'uploader': 'Tulio Gonçalves',
181 'uploader_id': 'user28849593',
187 def _extract_vimeo_url(url, webpage):
188 # Look for embedded (iframe) Vimeo player
190 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
192 player_url = unescapeHTML(mobj.group('url'))
193 surl = smuggle_url(player_url, {'Referer': url})
195 # Look for embedded (swf embed) Vimeo player
197 r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
201 def _verify_video_password(self, url, video_id, webpage):
202 password = self._downloader.params.get('videopassword', None)
204 raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
205 token = self._extract_xsrft(webpage)
206 data = urlencode_postdata({
207 'password': password,
210 if url.startswith('http://'):
211 # vimeo only supports https now, but the user can give an http url
212 url = url.replace('http://', 'https://')
213 password_request = compat_urllib_request.Request(url + '/password', data)
214 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
215 password_request.add_header('Referer', url)
216 return self._download_webpage(
217 password_request, video_id,
218 'Verifying the password', 'Wrong password')
220 def _verify_player_video_password(self, url, video_id):
221 password = self._downloader.params.get('videopassword', None)
223 raise ExtractorError('This video is protected by a password, use the --video-password option')
224 data = compat_urllib_parse.urlencode({'password': password})
225 pass_url = url + '/check-password'
226 password_request = compat_urllib_request.Request(pass_url, data)
227 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
228 return self._download_json(
229 password_request, video_id,
230 'Verifying the password',
233 def _real_initialize(self):
236 def _real_extract(self, url):
237 url, data = unsmuggle_url(url)
238 headers = std_headers
240 headers = headers.copy()
242 if 'Referer' not in headers:
243 headers['Referer'] = url
245 # Extract ID from URL
246 mobj = re.match(self._VALID_URL, url)
247 video_id = mobj.group('id')
249 if mobj.group('pro') or mobj.group('player'):
250 url = 'https://player.vimeo.com/video/' + video_id
252 url = 'https://vimeo.com/' + video_id
254 # Retrieve video webpage to extract further information
255 request = compat_urllib_request.Request(url, None, headers)
257 webpage = self._download_webpage(request, video_id)
258 except ExtractorError as ee:
259 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
260 errmsg = ee.cause.read()
261 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
262 raise ExtractorError(
263 'Cannot download embed-only video without embedding '
264 'URL. Please call youtube-dl with the URL of the page '
265 'that embeds this video.',
269 # Now we begin extracting as much information as we can from what we
270 # retrieved. First we extract the information common to all extractors,
271 # and latter we extract those that are Vimeo specific.
272 self.report_extraction(video_id)
274 vimeo_config = self._search_regex(
275 r'vimeo\.config\s*=\s*({.+?});', webpage,
276 'vimeo config', default=None)
278 seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
279 if seed_status.get('state') == 'failed':
280 raise ExtractorError(
281 '%s returned error: %s' % (self.IE_NAME, seed_status['title']),
284 # Extract the config JSON
287 config_url = self._html_search_regex(
288 r' data-config-url="(.+?)"', webpage, 'config URL')
289 config_json = self._download_webpage(config_url, video_id)
290 config = json.loads(config_json)
291 except RegexNotFoundError:
292 # For pro videos or player.vimeo.com urls
293 # We try to find out to which variable is assigned the config dic
294 m_variable_name = re.search('(\w)\.video\.id', webpage)
295 if m_variable_name is not None:
296 config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
298 config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
299 config = self._search_regex(config_re, webpage, 'info section',
301 config = json.loads(config)
302 except Exception as e:
303 if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
304 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
306 if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
307 if data and '_video_password_verified' in data:
308 raise ExtractorError('video password verification failed!')
309 self._verify_video_password(url, video_id, webpage)
310 return self._real_extract(
311 smuggle_url(url, {'_video_password_verified': 'verified'}))
313 raise ExtractorError('Unable to extract info section',
316 if config.get('view') == 4:
317 config = self._verify_player_video_password(url, video_id)
320 video_title = config["video"]["title"]
322 # Extract uploader and uploader_id
323 video_uploader = config["video"]["owner"]["name"]
324 video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
326 # Extract video thumbnail
327 video_thumbnail = config["video"].get("thumbnail")
328 if video_thumbnail is None:
329 video_thumbs = config["video"].get("thumbs")
330 if video_thumbs and isinstance(video_thumbs, dict):
331 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
333 # Extract video description
335 video_description = self._html_search_regex(
336 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
337 webpage, 'description', default=None)
338 if not video_description:
339 video_description = self._html_search_meta(
340 'description', webpage, default=None)
341 if not video_description and mobj.group('pro'):
342 orig_webpage = self._download_webpage(
344 note='Downloading webpage for description',
347 video_description = self._html_search_meta(
348 'description', orig_webpage, default=None)
349 if not video_description and not mobj.group('player'):
350 self._downloader.report_warning('Cannot find video description')
352 # Extract video duration
353 video_duration = int_or_none(config["video"].get("duration"))
355 # Extract upload date
356 video_upload_date = None
357 mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
359 video_upload_date = unified_strdate(mobj.group(1))
362 view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
363 like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
364 comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
365 except RegexNotFoundError:
366 # This info is only available in vimeo.com/{id} urls
371 # Vimeo specific: extract request signature and timestamp
372 sig = config['request']['signature']
373 timestamp = config['request']['timestamp']
375 # Vimeo specific: extract video codec and quality information
376 # First consider quality, then codecs, then take everything
377 codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]
378 files = {'hd': [], 'sd': [], 'other': []}
379 config_files = config["video"].get("files") or config["request"].get("files")
380 for codec_name, codec_extension in codecs:
381 for quality in config_files.get(codec_name, []):
382 format_id = '-'.join((codec_name, quality)).lower()
383 key = quality if quality in files else 'other'
385 if isinstance(config_files[codec_name], dict):
386 file_info = config_files[codec_name][quality]
387 video_url = file_info.get('url')
390 if video_url is None:
391 video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
392 % (video_id, sig, timestamp, quality, codec_name.upper())
395 'ext': codec_extension,
397 'format_id': format_id,
398 'width': file_info.get('width'),
399 'height': file_info.get('height'),
400 'tbr': file_info.get('bitrate'),
403 hls = config_files.get("hls")
405 formats = self._extract_m3u8_formats(hls['all'], video_id, 'mp4', 'm3u8_native', 0, 'hls', fatal=False)
406 for key in ('other', 'sd', 'hd'):
407 formats += files[key]
408 if len(formats) == 0:
409 raise ExtractorError('No known codec found')
410 self._sort_formats(formats)
413 text_tracks = config['request'].get('text_tracks')
415 for tt in text_tracks:
416 subtitles[tt['lang']] = [{
418 'url': 'https://vimeo.com' + tt['url'],
423 'uploader': video_uploader,
424 'uploader_id': video_uploader_id,
425 'upload_date': video_upload_date,
426 'title': video_title,
427 'thumbnail': video_thumbnail,
428 'description': video_description,
429 'duration': video_duration,
432 'view_count': view_count,
433 'like_count': like_count,
434 'comment_count': comment_count,
435 'subtitles': subtitles,
439 class VimeoChannelIE(VimeoBaseInfoExtractor):
440 IE_NAME = 'vimeo:channel'
441 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
442 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
444 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
446 'url': 'https://vimeo.com/channels/tributes',
449 'title': 'Vimeo Tributes',
451 'playlist_mincount': 25,
454 def _page_url(self, base_url, pagenum):
455 return '%s/videos/page:%d/' % (base_url, pagenum)
457 def _extract_list_title(self, webpage):
458 return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
460 def _login_list_password(self, page_url, list_id, webpage):
461 login_form = self._search_regex(
462 r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
463 webpage, 'login form', default=None)
467 password = self._downloader.params.get('videopassword', None)
469 raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
470 fields = self._hidden_inputs(login_form)
471 token = self._extract_xsrft(webpage)
472 fields['token'] = token
473 fields['password'] = password
474 post = urlencode_postdata(fields)
475 password_path = self._search_regex(
476 r'action="([^"]+)"', login_form, 'password URL')
477 password_url = compat_urlparse.urljoin(page_url, password_path)
478 password_request = compat_urllib_request.Request(password_url, post)
479 password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
480 self._set_cookie('vimeo.com', 'xsrft', token)
482 return self._download_webpage(
483 password_request, list_id,
484 'Verifying the password', 'Wrong password')
486 def _extract_videos(self, list_id, base_url):
488 for pagenum in itertools.count(1):
489 page_url = self._page_url(base_url, pagenum)
490 webpage = self._download_webpage(
492 'Downloading page %s' % pagenum)
495 webpage = self._login_list_password(page_url, list_id, webpage)
497 video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
498 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
501 entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
502 for video_id in video_ids]
503 return {'_type': 'playlist',
505 'title': self._extract_list_title(webpage),
509 def _real_extract(self, url):
510 mobj = re.match(self._VALID_URL, url)
511 channel_id = mobj.group('id')
512 return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
515 class VimeoUserIE(VimeoChannelIE):
516 IE_NAME = 'vimeo:user'
517 _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
518 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
520 'url': 'https://vimeo.com/nkistudio/videos',
525 'playlist_mincount': 66,
528 def _real_extract(self, url):
529 mobj = re.match(self._VALID_URL, url)
530 name = mobj.group('name')
531 return self._extract_videos(name, 'https://vimeo.com/%s' % name)
534 class VimeoAlbumIE(VimeoChannelIE):
535 IE_NAME = 'vimeo:album'
536 _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
537 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
539 'url': 'https://vimeo.com/album/2632481',
542 'title': 'Staff Favorites: November 2013',
544 'playlist_mincount': 13,
546 'note': 'Password-protected album',
547 'url': 'https://vimeo.com/album/3253534',
554 'videopassword': 'youtube-dl',
558 def _page_url(self, base_url, pagenum):
559 return '%s/page:%d/' % (base_url, pagenum)
561 def _real_extract(self, url):
562 album_id = self._match_id(url)
563 return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
566 class VimeoGroupsIE(VimeoAlbumIE):
567 IE_NAME = 'vimeo:group'
568 _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)'
570 'url': 'https://vimeo.com/groups/rolexawards',
573 'title': 'Rolex Awards for Enterprise',
575 'playlist_mincount': 73,
578 def _extract_list_title(self, webpage):
579 return self._og_search_title(webpage)
581 def _real_extract(self, url):
582 mobj = re.match(self._VALID_URL, url)
583 name = mobj.group('name')
584 return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
587 class VimeoReviewIE(InfoExtractor):
588 IE_NAME = 'vimeo:review'
589 IE_DESC = 'Review pages on vimeo'
590 _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
592 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
593 'md5': 'c507a72f780cacc12b2248bb4006d253',
597 'title': "DICK HARDWICK 'Comedian'",
598 'uploader': 'Richard Hardwick',
601 'note': 'video player needs Referer',
602 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
603 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
607 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
608 'uploader': 'DevWeek Events',
610 'thumbnail': 're:^https?://.*\.jpg$',
614 def _real_extract(self, url):
615 mobj = re.match(self._VALID_URL, url)
616 video_id = mobj.group('id')
617 player_url = 'https://player.vimeo.com/player/' + video_id
618 return self.url_result(player_url, 'Vimeo', video_id)
621 class VimeoWatchLaterIE(VimeoChannelIE):
622 IE_NAME = 'vimeo:watchlater'
623 IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
624 _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
625 _TITLE = 'Watch Later'
626 _LOGIN_REQUIRED = True
628 'url': 'https://vimeo.com/watchlater',
629 'only_matching': True,
632 def _real_initialize(self):
635 def _page_url(self, base_url, pagenum):
636 url = '%s/page:%d/' % (base_url, pagenum)
637 request = compat_urllib_request.Request(url)
638 # Set the header to get a partial html page with the ids,
639 # the normal page doesn't contain them.
640 request.add_header('X-Requested-With', 'XMLHttpRequest')
643 def _real_extract(self, url):
644 return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
647 class VimeoLikesIE(InfoExtractor):
648 _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
649 IE_NAME = 'vimeo:likes'
650 IE_DESC = 'Vimeo user likes'
652 'url': 'https://vimeo.com/user755559/likes/',
653 'playlist_mincount': 293,
655 'id': 'user755559_likes',
656 "description": "See all the videos urza likes",
657 "title": 'Videos urza likes',
661 def _real_extract(self, url):
662 user_id = self._match_id(url)
663 webpage = self._download_webpage(url, user_id)
664 page_count = self._int(
666 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
667 .*?</a></li>\s*<li\s+class="pagination_next">
668 ''', webpage, 'page count'),
669 'page count', fatal=True)
671 title = self._html_search_regex(
672 r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
673 description = self._html_search_meta('description', webpage)
676 page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
678 webpage = self._download_webpage(
680 note='Downloading page %d/%d' % (idx + 1, page_count))
681 video_list = self._search_regex(
682 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
683 webpage, 'video content')
685 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
689 'url': compat_urlparse.urljoin(page_url, path),
692 pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
696 'id': 'user%s_likes' % user_id,
698 'description': description,