2 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from ..compat import (
13 compat_urllib_request,
28 class VimeoBaseInfoExtractor(InfoExtractor):
29 _NETRC_MACHINE = 'vimeo'
30 _LOGIN_REQUIRED = False
33 (username, password) = self._get_login_info()
35 if self._LOGIN_REQUIRED:
36 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
39 login_url = 'https://vimeo.com/log_in'
40 webpage = self._download_webpage(login_url, None, False)
41 token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
42 data = urlencode_postdata({
49 login_request = compat_urllib_request.Request(login_url, data)
50 login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
51 login_request.add_header('Cookie', 'xsrft=%s' % token)
52 self._download_webpage(login_request, None, False, 'Wrong login info')
55 class VimeoIE(VimeoBaseInfoExtractor):
56 """Information extractor for vimeo.com."""
58 # _VALID_URL matches Vimeo URLs
61 (?:(?:www|(?P<player>player))\.)?
62 vimeo(?P<pro>pro)?\.com/
63 (?!channels/[^/?#]+/?(?:$|[?#])|album/)
65 (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
68 /?(?:[?&].*)?(?:[#].*)?$'''
72 'url': 'http://vimeo.com/56015672#at=0',
73 'md5': '8879b6cc097e987f02484baf890129e5',
77 "upload_date": "20121220",
78 "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",
79 "uploader_id": "user7108434",
80 "uploader": "Filippo Valsorda",
81 "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
86 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
87 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
88 'note': 'Vimeo Pro video (#1197)',
92 'uploader_id': 'openstreetmapus',
93 'uploader': 'OpenStreetMap US',
94 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
95 'description': 'md5:380943ec71b89736ff4bf27183233d09',
100 'url': 'http://player.vimeo.com/video/54469442',
101 'md5': '619b811a4417aa4abe78dc653becf511',
102 'note': 'Videos that embed the url in the player page',
106 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
107 'uploader': 'The BLN & Business of Software',
108 'uploader_id': 'theblnbusinessofsoftware',
114 'url': 'http://vimeo.com/68375962',
115 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
116 'note': 'Video protected with password',
120 'title': 'youtube-dl password protected test video',
121 'upload_date': '20130614',
122 'uploader_id': 'user18948128',
123 'uploader': 'Jaime Marquínez Ferrándiz',
125 '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.',
128 'videopassword': 'youtube-dl',
132 'url': 'http://vimeo.com/channels/keypeele/75629013',
133 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
134 'note': 'Video is freely available via original URL '
135 'and protected with password when accessed via http://vimeo.com/75629013',
139 'title': 'Key & Peele: Terrorist Interrogation',
140 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
141 'uploader_id': 'atencio',
142 'uploader': 'Peter Atencio',
147 'url': 'http://vimeo.com/76979871',
148 'md5': '3363dd6ffebe3784d56f4132317fd446',
149 'note': 'Video with subtitles',
153 'title': 'The New Vimeo Player (You Know, For Videos)',
154 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
155 'upload_date': '20131015',
156 'uploader_id': 'staff',
157 'uploader': 'Vimeo Staff',
162 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
163 'url': 'https://player.vimeo.com/video/98044508',
164 'note': 'The js code contains assignments to the same variable as the config',
168 'title': 'Pier Solar OUYA Official Trailer',
169 'uploader': 'Tulio Gonçalves',
170 'uploader_id': 'user28849593',
175 def _verify_video_password(self, url, video_id, webpage):
176 password = self._downloader.params.get('videopassword', None)
178 raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
179 token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
180 data = compat_urllib_parse.urlencode({
181 'password': password,
184 # I didn't manage to use the password with https
185 if url.startswith('https'):
186 pass_url = url.replace('https', 'http')
189 password_request = compat_urllib_request.Request(pass_url + '/password', data)
190 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
191 password_request.add_header('Cookie', 'xsrft=%s' % token)
192 return self._download_webpage(
193 password_request, video_id,
194 'Verifying the password', 'Wrong password')
196 def _verify_player_video_password(self, url, video_id):
197 password = self._downloader.params.get('videopassword', None)
199 raise ExtractorError('This video is protected by a password, use the --video-password option')
200 data = compat_urllib_parse.urlencode({'password': password})
201 pass_url = url + '/check-password'
202 password_request = compat_urllib_request.Request(pass_url, data)
203 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
204 return self._download_json(
205 password_request, video_id,
206 'Verifying the password',
209 def _real_initialize(self):
212 def _real_extract(self, url):
213 url, data = unsmuggle_url(url)
214 headers = std_headers
216 headers = headers.copy()
218 if 'Referer' not in headers:
219 headers['Referer'] = url
221 # Extract ID from URL
222 mobj = re.match(self._VALID_URL, url)
223 video_id = mobj.group('id')
225 if mobj.group('pro') or mobj.group('player'):
226 url = 'http://player.vimeo.com/video/' + video_id
228 password = self._downloader.params.get('videopassword', None)
230 headers['Cookie'] = '%s_password=%s' % (
231 video_id, hashlib.md5(password.encode('utf-8')).hexdigest())
233 # Retrieve video webpage to extract further information
234 request = compat_urllib_request.Request(url, None, headers)
236 webpage = self._download_webpage(request, video_id)
237 except ExtractorError as ee:
238 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
239 errmsg = ee.cause.read()
240 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
241 raise ExtractorError(
242 'Cannot download embed-only video without embedding '
243 'URL. Please call youtube-dl with the URL of the page '
244 'that embeds this video.',
248 # Now we begin extracting as much information as we can from what we
249 # retrieved. First we extract the information common to all extractors,
250 # and latter we extract those that are Vimeo specific.
251 self.report_extraction(video_id)
253 # Extract the config JSON
256 config_url = self._html_search_regex(
257 r' data-config-url="(.+?)"', webpage, 'config URL')
258 config_json = self._download_webpage(config_url, video_id)
259 config = json.loads(config_json)
260 except RegexNotFoundError:
261 # For pro videos or player.vimeo.com urls
262 # We try to find out to which variable is assigned the config dic
263 m_variable_name = re.search('(\w)\.video\.id', webpage)
264 if m_variable_name is not None:
265 config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
267 config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
268 config = self._search_regex(config_re, webpage, 'info section',
270 config = json.loads(config)
271 except Exception as e:
272 if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
273 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
275 if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
276 if data and '_video_password_verified' in data:
277 raise ExtractorError('video password verification failed!')
278 self._verify_video_password(url, video_id, webpage)
279 return self._real_extract(
280 smuggle_url(url, {'_video_password_verified': 'verified'}))
282 raise ExtractorError('Unable to extract info section',
285 if config.get('view') == 4:
286 config = self._verify_player_video_password(url, video_id)
289 video_title = config["video"]["title"]
291 # Extract uploader and uploader_id
292 video_uploader = config["video"]["owner"]["name"]
293 video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
295 # Extract video thumbnail
296 video_thumbnail = config["video"].get("thumbnail")
297 if video_thumbnail is None:
298 video_thumbs = config["video"].get("thumbs")
299 if video_thumbs and isinstance(video_thumbs, dict):
300 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
302 # Extract video description
304 video_description = self._html_search_regex(
305 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
306 webpage, 'description', default=None)
307 if not video_description:
308 video_description = self._html_search_meta(
309 'description', webpage, default=None)
310 if not video_description and mobj.group('pro'):
311 orig_webpage = self._download_webpage(
313 note='Downloading webpage for description',
316 video_description = self._html_search_meta(
317 'description', orig_webpage, default=None)
318 if not video_description and not mobj.group('player'):
319 self._downloader.report_warning('Cannot find video description')
321 # Extract video duration
322 video_duration = int_or_none(config["video"].get("duration"))
324 # Extract upload date
325 video_upload_date = None
326 mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
328 video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
331 view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
332 like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
333 comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
334 except RegexNotFoundError:
335 # This info is only available in vimeo.com/{id} urls
340 # Vimeo specific: extract request signature and timestamp
341 sig = config['request']['signature']
342 timestamp = config['request']['timestamp']
344 # Vimeo specific: extract video codec and quality information
345 # First consider quality, then codecs, then take everything
346 codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]
347 files = {'hd': [], 'sd': [], 'other': []}
348 config_files = config["video"].get("files") or config["request"].get("files")
349 for codec_name, codec_extension in codecs:
350 for quality in config_files.get(codec_name, []):
351 format_id = '-'.join((codec_name, quality)).lower()
352 key = quality if quality in files else 'other'
354 if isinstance(config_files[codec_name], dict):
355 file_info = config_files[codec_name][quality]
356 video_url = file_info.get('url')
359 if video_url is None:
360 video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
361 % (video_id, sig, timestamp, quality, codec_name.upper())
364 'ext': codec_extension,
366 'format_id': format_id,
367 'width': file_info.get('width'),
368 'height': file_info.get('height'),
371 for key in ('other', 'sd', 'hd'):
372 formats += files[key]
373 if len(formats) == 0:
374 raise ExtractorError('No known codec found')
377 text_tracks = config['request'].get('text_tracks')
379 for tt in text_tracks:
380 subtitles[tt['lang']] = [{
382 'url': 'http://vimeo.com' + tt['url'],
387 'uploader': video_uploader,
388 'uploader_id': video_uploader_id,
389 'upload_date': video_upload_date,
390 'title': video_title,
391 'thumbnail': video_thumbnail,
392 'description': video_description,
393 'duration': video_duration,
396 'view_count': view_count,
397 'like_count': like_count,
398 'comment_count': comment_count,
399 'subtitles': subtitles,
403 class VimeoChannelIE(InfoExtractor):
404 IE_NAME = 'vimeo:channel'
405 _VALID_URL = r'https?://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
406 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
407 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
409 'url': 'http://vimeo.com/channels/tributes',
412 'title': 'Vimeo Tributes',
414 'playlist_mincount': 25,
417 def _page_url(self, base_url, pagenum):
418 return '%s/videos/page:%d/' % (base_url, pagenum)
420 def _extract_list_title(self, webpage):
421 return self._html_search_regex(self._TITLE_RE, webpage, 'list title')
423 def _login_list_password(self, page_url, list_id, webpage):
424 login_form = self._search_regex(
425 r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
426 webpage, 'login form', default=None)
430 password = self._downloader.params.get('videopassword', None)
432 raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
433 fields = dict(re.findall(r'''(?x)<input\s+
438 token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
439 fields['token'] = token
440 fields['password'] = password
441 post = compat_urllib_parse.urlencode(fields)
442 password_path = self._search_regex(
443 r'action="([^"]+)"', login_form, 'password URL')
444 password_url = compat_urlparse.urljoin(page_url, password_path)
445 password_request = compat_urllib_request.Request(password_url, post)
446 password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
447 self._set_cookie('vimeo.com', 'xsrft', token)
449 return self._download_webpage(
450 password_request, list_id,
451 'Verifying the password', 'Wrong password')
453 def _extract_videos(self, list_id, base_url):
455 for pagenum in itertools.count(1):
456 page_url = self._page_url(base_url, pagenum)
457 webpage = self._download_webpage(
459 'Downloading page %s' % pagenum)
462 webpage = self._login_list_password(page_url, list_id, webpage)
464 video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
465 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
468 entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
469 for video_id in video_ids]
470 return {'_type': 'playlist',
472 'title': self._extract_list_title(webpage),
476 def _real_extract(self, url):
477 mobj = re.match(self._VALID_URL, url)
478 channel_id = mobj.group('id')
479 return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id)
482 class VimeoUserIE(VimeoChannelIE):
483 IE_NAME = 'vimeo:user'
484 _VALID_URL = r'https?://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
485 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
487 'url': 'http://vimeo.com/nkistudio/videos',
492 'playlist_mincount': 66,
495 def _real_extract(self, url):
496 mobj = re.match(self._VALID_URL, url)
497 name = mobj.group('name')
498 return self._extract_videos(name, 'http://vimeo.com/%s' % name)
501 class VimeoAlbumIE(VimeoChannelIE):
502 IE_NAME = 'vimeo:album'
503 _VALID_URL = r'https?://vimeo\.com/album/(?P<id>\d+)'
504 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
506 'url': 'http://vimeo.com/album/2632481',
509 'title': 'Staff Favorites: November 2013',
511 'playlist_mincount': 13,
513 'note': 'Password-protected album',
514 'url': 'https://vimeo.com/album/3253534',
521 'videopassword': 'youtube-dl',
525 def _page_url(self, base_url, pagenum):
526 return '%s/page:%d/' % (base_url, pagenum)
528 def _real_extract(self, url):
529 album_id = self._match_id(url)
530 return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_id)
533 class VimeoGroupsIE(VimeoAlbumIE):
534 IE_NAME = 'vimeo:group'
535 _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)'
537 'url': 'http://vimeo.com/groups/rolexawards',
540 'title': 'Rolex Awards for Enterprise',
542 'playlist_mincount': 73,
545 def _extract_list_title(self, webpage):
546 return self._og_search_title(webpage)
548 def _real_extract(self, url):
549 mobj = re.match(self._VALID_URL, url)
550 name = mobj.group('name')
551 return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name)
554 class VimeoReviewIE(InfoExtractor):
555 IE_NAME = 'vimeo:review'
556 IE_DESC = 'Review pages on vimeo'
557 _VALID_URL = r'https?://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
559 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
560 'md5': 'c507a72f780cacc12b2248bb4006d253',
564 'title': "DICK HARDWICK 'Comedian'",
565 'uploader': 'Richard Hardwick',
568 'note': 'video player needs Referer',
569 'url': 'http://vimeo.com/user22258446/review/91613211/13f927e053',
570 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
574 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
575 'uploader': 'DevWeek Events',
577 'thumbnail': 're:^https?://.*\.jpg$',
581 def _real_extract(self, url):
582 mobj = re.match(self._VALID_URL, url)
583 video_id = mobj.group('id')
584 player_url = 'https://player.vimeo.com/player/' + video_id
585 return self.url_result(player_url, 'Vimeo', video_id)
588 class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
589 IE_NAME = 'vimeo:watchlater'
590 IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
591 _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater'
592 _LOGIN_REQUIRED = True
593 _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<'
595 'url': 'http://vimeo.com/home/watchlater',
596 'only_matching': True,
599 def _real_initialize(self):
602 def _page_url(self, base_url, pagenum):
603 url = '%s/page:%d/' % (base_url, pagenum)
604 request = compat_urllib_request.Request(url)
605 # Set the header to get a partial html page with the ids,
606 # the normal page doesn't contain them.
607 request.add_header('X-Requested-With', 'XMLHttpRequest')
610 def _real_extract(self, url):
611 return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater')
614 class VimeoLikesIE(InfoExtractor):
615 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
616 IE_NAME = 'vimeo:likes'
617 IE_DESC = 'Vimeo user likes'
619 'url': 'https://vimeo.com/user755559/likes/',
620 'playlist_mincount': 293,
622 'id': 'user755559_likes',
623 "description": "See all the videos urza likes",
624 "title": 'Videos urza likes',
628 def _real_extract(self, url):
629 user_id = self._match_id(url)
630 webpage = self._download_webpage(url, user_id)
631 page_count = self._int(
633 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
634 .*?</a></li>\s*<li\s+class="pagination_next">
635 ''', webpage, 'page count'),
636 'page count', fatal=True)
638 title = self._html_search_regex(
639 r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
640 description = self._html_search_meta('description', webpage)
643 page_url = '%s//vimeo.com/user%s/likes/page:%d/sort:date' % (
644 self.http_scheme(), user_id, idx + 1)
645 webpage = self._download_webpage(
647 note='Downloading page %d/%d' % (idx + 1, page_count))
648 video_list = self._search_regex(
649 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
650 webpage, 'video content')
652 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
656 'url': compat_urlparse.urljoin(page_url, path),
659 pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
663 'id': 'user%s_likes' % user_id,
665 'description': description,