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
34 (username, password) = self._get_login_info()
36 if self._LOGIN_REQUIRED:
37 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
40 login_url = 'https://vimeo.com/log_in'
41 webpage = self._download_webpage(login_url, None, False)
42 token = self._search_regex(r'xsrft":"(.*?)"', webpage, 'login token')
43 data = urlencode_postdata({
50 login_request = compat_urllib_request.Request(login_url, data)
51 login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
52 login_request.add_header('Cookie', 'xsrft=%s' % token)
53 self._download_webpage(login_request, None, False, 'Wrong login info')
56 class VimeoIE(VimeoBaseInfoExtractor):
57 """Information extractor for vimeo.com."""
59 # _VALID_URL matches Vimeo URLs
62 (?:(?:www|(?P<player>player))\.)?
63 vimeo(?P<pro>pro)?\.com/
64 (?!channels/[^/?#]+/?(?:$|[?#])|album/)
66 (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
69 /?(?:[?&].*)?(?:[#].*)?$'''
73 'url': 'http://vimeo.com/56015672#at=0',
74 'md5': '8879b6cc097e987f02484baf890129e5',
78 "upload_date": "20121220",
79 "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",
80 "uploader_id": "user7108434",
81 "uploader": "Filippo Valsorda",
82 "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
87 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
88 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
89 'note': 'Vimeo Pro video (#1197)',
93 'uploader_id': 'openstreetmapus',
94 'uploader': 'OpenStreetMap US',
95 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
96 'description': 'md5:380943ec71b89736ff4bf27183233d09',
101 'url': 'http://player.vimeo.com/video/54469442',
102 'md5': '619b811a4417aa4abe78dc653becf511',
103 'note': 'Videos that embed the url in the player page',
107 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
108 'uploader': 'The BLN & Business of Software',
109 'uploader_id': 'theblnbusinessofsoftware',
115 'url': 'http://vimeo.com/68375962',
116 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
117 'note': 'Video protected with password',
121 'title': 'youtube-dl password protected test video',
122 'upload_date': '20130614',
123 'uploader_id': 'user18948128',
124 'uploader': 'Jaime Marquínez Ferrándiz',
126 '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.',
129 'videopassword': 'youtube-dl',
133 'url': 'http://vimeo.com/channels/keypeele/75629013',
134 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
135 'note': 'Video is freely available via original URL '
136 'and protected with password when accessed via http://vimeo.com/75629013',
140 'title': 'Key & Peele: Terrorist Interrogation',
141 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
142 'uploader_id': 'atencio',
143 'uploader': 'Peter Atencio',
144 'upload_date': '20130927',
149 'url': 'http://vimeo.com/76979871',
150 'md5': '3363dd6ffebe3784d56f4132317fd446',
151 'note': 'Video with subtitles',
155 'title': 'The New Vimeo Player (You Know, For Videos)',
156 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
157 'upload_date': '20131015',
158 'uploader_id': 'staff',
159 'uploader': 'Vimeo Staff',
164 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
165 'url': 'https://player.vimeo.com/video/98044508',
166 'note': 'The js code contains assignments to the same variable as the config',
170 'title': 'Pier Solar OUYA Official Trailer',
171 'uploader': 'Tulio Gonçalves',
172 'uploader_id': 'user28849593',
178 def _extract_vimeo_url(url, webpage):
179 # Look for embedded (iframe) Vimeo player
181 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
183 player_url = unescapeHTML(mobj.group('url'))
184 surl = smuggle_url(player_url, {'Referer': url})
186 # Look for embedded (swf embed) Vimeo player
188 r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
192 def _verify_video_password(self, url, video_id, webpage):
193 password = self._downloader.params.get('videopassword', None)
195 raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
196 token = self._search_regex(r'xsrft[\s=:"\']+([^"\']+)', webpage, 'login token')
197 data = urlencode_postdata({
198 'password': password,
201 if url.startswith('http://'):
202 # vimeo only supports https now, but the user can give an http url
203 url = url.replace('http://', 'https://')
204 password_request = compat_urllib_request.Request(url + '/password', data)
205 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
206 password_request.add_header('Cookie', 'xsrft=%s' % token)
207 return self._download_webpage(
208 password_request, video_id,
209 'Verifying the password', 'Wrong password')
211 def _verify_player_video_password(self, url, video_id):
212 password = self._downloader.params.get('videopassword', None)
214 raise ExtractorError('This video is protected by a password, use the --video-password option')
215 data = compat_urllib_parse.urlencode({'password': password})
216 pass_url = url + '/check-password'
217 password_request = compat_urllib_request.Request(pass_url, data)
218 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
219 return self._download_json(
220 password_request, video_id,
221 'Verifying the password',
224 def _real_initialize(self):
227 def _real_extract(self, url):
228 url, data = unsmuggle_url(url)
229 headers = std_headers
231 headers = headers.copy()
233 if 'Referer' not in headers:
234 headers['Referer'] = url
236 # Extract ID from URL
237 mobj = re.match(self._VALID_URL, url)
238 video_id = mobj.group('id')
240 if mobj.group('pro') or mobj.group('player'):
241 url = 'https://player.vimeo.com/video/' + video_id
243 url = 'https://vimeo.com/' + video_id
245 # Retrieve video webpage to extract further information
246 request = compat_urllib_request.Request(url, None, headers)
248 webpage = self._download_webpage(request, video_id)
249 except ExtractorError as ee:
250 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
251 errmsg = ee.cause.read()
252 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
253 raise ExtractorError(
254 'Cannot download embed-only video without embedding '
255 'URL. Please call youtube-dl with the URL of the page '
256 'that embeds this video.',
260 # Now we begin extracting as much information as we can from what we
261 # retrieved. First we extract the information common to all extractors,
262 # and latter we extract those that are Vimeo specific.
263 self.report_extraction(video_id)
265 vimeo_config = self._search_regex(
266 r'vimeo\.config\s*=\s*({.+?});', webpage,
267 'vimeo config', default=None)
269 seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
270 if seed_status.get('state') == 'failed':
271 raise ExtractorError(
272 '%s returned error: %s' % (self.IE_NAME, seed_status['title']),
275 # Extract the config JSON
278 config_url = self._html_search_regex(
279 r' data-config-url="(.+?)"', webpage, 'config URL')
280 config_json = self._download_webpage(config_url, video_id)
281 config = json.loads(config_json)
282 except RegexNotFoundError:
283 # For pro videos or player.vimeo.com urls
284 # We try to find out to which variable is assigned the config dic
285 m_variable_name = re.search('(\w)\.video\.id', webpage)
286 if m_variable_name is not None:
287 config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
289 config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
290 config = self._search_regex(config_re, webpage, 'info section',
292 config = json.loads(config)
293 except Exception as e:
294 if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
295 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
297 if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
298 if data and '_video_password_verified' in data:
299 raise ExtractorError('video password verification failed!')
300 self._verify_video_password(url, video_id, webpage)
301 return self._real_extract(
302 smuggle_url(url, {'_video_password_verified': 'verified'}))
304 raise ExtractorError('Unable to extract info section',
307 if config.get('view') == 4:
308 config = self._verify_player_video_password(url, video_id)
311 video_title = config["video"]["title"]
313 # Extract uploader and uploader_id
314 video_uploader = config["video"]["owner"]["name"]
315 video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
317 # Extract video thumbnail
318 video_thumbnail = config["video"].get("thumbnail")
319 if video_thumbnail is None:
320 video_thumbs = config["video"].get("thumbs")
321 if video_thumbs and isinstance(video_thumbs, dict):
322 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
324 # Extract video description
326 video_description = self._html_search_regex(
327 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
328 webpage, 'description', default=None)
329 if not video_description:
330 video_description = self._html_search_meta(
331 'description', webpage, default=None)
332 if not video_description and mobj.group('pro'):
333 orig_webpage = self._download_webpage(
335 note='Downloading webpage for description',
338 video_description = self._html_search_meta(
339 'description', orig_webpage, default=None)
340 if not video_description and not mobj.group('player'):
341 self._downloader.report_warning('Cannot find video description')
343 # Extract video duration
344 video_duration = int_or_none(config["video"].get("duration"))
346 # Extract upload date
347 video_upload_date = None
348 mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
350 video_upload_date = unified_strdate(mobj.group(1))
353 view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
354 like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
355 comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
356 except RegexNotFoundError:
357 # This info is only available in vimeo.com/{id} urls
362 # Vimeo specific: extract request signature and timestamp
363 sig = config['request']['signature']
364 timestamp = config['request']['timestamp']
366 # Vimeo specific: extract video codec and quality information
367 # First consider quality, then codecs, then take everything
368 codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]
369 files = {'hd': [], 'sd': [], 'other': []}
370 config_files = config["video"].get("files") or config["request"].get("files")
371 for codec_name, codec_extension in codecs:
372 for quality in config_files.get(codec_name, []):
373 format_id = '-'.join((codec_name, quality)).lower()
374 key = quality if quality in files else 'other'
376 if isinstance(config_files[codec_name], dict):
377 file_info = config_files[codec_name][quality]
378 video_url = file_info.get('url')
381 if video_url is None:
382 video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
383 % (video_id, sig, timestamp, quality, codec_name.upper())
386 'ext': codec_extension,
388 'format_id': format_id,
389 'width': file_info.get('width'),
390 'height': file_info.get('height'),
393 for key in ('other', 'sd', 'hd'):
394 formats += files[key]
395 if len(formats) == 0:
396 raise ExtractorError('No known codec found')
399 text_tracks = config['request'].get('text_tracks')
401 for tt in text_tracks:
402 subtitles[tt['lang']] = [{
404 'url': 'https://vimeo.com' + tt['url'],
409 'uploader': video_uploader,
410 'uploader_id': video_uploader_id,
411 'upload_date': video_upload_date,
412 'title': video_title,
413 'thumbnail': video_thumbnail,
414 'description': video_description,
415 'duration': video_duration,
418 'view_count': view_count,
419 'like_count': like_count,
420 'comment_count': comment_count,
421 'subtitles': subtitles,
425 class VimeoChannelIE(InfoExtractor):
426 IE_NAME = 'vimeo:channel'
427 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
428 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
429 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
431 'url': 'https://vimeo.com/channels/tributes',
434 'title': 'Vimeo Tributes',
436 'playlist_mincount': 25,
439 def _page_url(self, base_url, pagenum):
440 return '%s/videos/page:%d/' % (base_url, pagenum)
442 def _extract_list_title(self, webpage):
443 return self._html_search_regex(self._TITLE_RE, webpage, 'list title')
445 def _login_list_password(self, page_url, list_id, webpage):
446 login_form = self._search_regex(
447 r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
448 webpage, 'login form', default=None)
452 password = self._downloader.params.get('videopassword', None)
454 raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
455 fields = dict(re.findall(r'''(?x)<input\s+
460 token = self._search_regex(r'xsrft[\s=:"\']+([^"\']+)', webpage, 'login token')
461 fields['token'] = token
462 fields['password'] = password
463 post = urlencode_postdata(fields)
464 password_path = self._search_regex(
465 r'action="([^"]+)"', login_form, 'password URL')
466 password_url = compat_urlparse.urljoin(page_url, password_path)
467 password_request = compat_urllib_request.Request(password_url, post)
468 password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
469 self._set_cookie('vimeo.com', 'xsrft', token)
471 return self._download_webpage(
472 password_request, list_id,
473 'Verifying the password', 'Wrong password')
475 def _extract_videos(self, list_id, base_url):
477 for pagenum in itertools.count(1):
478 page_url = self._page_url(base_url, pagenum)
479 webpage = self._download_webpage(
481 'Downloading page %s' % pagenum)
484 webpage = self._login_list_password(page_url, list_id, webpage)
486 video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
487 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
490 entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
491 for video_id in video_ids]
492 return {'_type': 'playlist',
494 'title': self._extract_list_title(webpage),
498 def _real_extract(self, url):
499 mobj = re.match(self._VALID_URL, url)
500 channel_id = mobj.group('id')
501 return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
504 class VimeoUserIE(VimeoChannelIE):
505 IE_NAME = 'vimeo:user'
506 _VALID_URL = r'https://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
507 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
509 'url': 'https://vimeo.com/nkistudio/videos',
514 'playlist_mincount': 66,
517 def _real_extract(self, url):
518 mobj = re.match(self._VALID_URL, url)
519 name = mobj.group('name')
520 return self._extract_videos(name, 'https://vimeo.com/%s' % name)
523 class VimeoAlbumIE(VimeoChannelIE):
524 IE_NAME = 'vimeo:album'
525 _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
526 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
528 'url': 'https://vimeo.com/album/2632481',
531 'title': 'Staff Favorites: November 2013',
533 'playlist_mincount': 13,
535 'note': 'Password-protected album',
536 'url': 'https://vimeo.com/album/3253534',
543 'videopassword': 'youtube-dl',
547 def _page_url(self, base_url, pagenum):
548 return '%s/page:%d/' % (base_url, pagenum)
550 def _real_extract(self, url):
551 album_id = self._match_id(url)
552 return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
555 class VimeoGroupsIE(VimeoAlbumIE):
556 IE_NAME = 'vimeo:group'
557 _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)'
559 'url': 'https://vimeo.com/groups/rolexawards',
562 'title': 'Rolex Awards for Enterprise',
564 'playlist_mincount': 73,
567 def _extract_list_title(self, webpage):
568 return self._og_search_title(webpage)
570 def _real_extract(self, url):
571 mobj = re.match(self._VALID_URL, url)
572 name = mobj.group('name')
573 return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
576 class VimeoReviewIE(InfoExtractor):
577 IE_NAME = 'vimeo:review'
578 IE_DESC = 'Review pages on vimeo'
579 _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
581 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
582 'md5': 'c507a72f780cacc12b2248bb4006d253',
586 'title': "DICK HARDWICK 'Comedian'",
587 'uploader': 'Richard Hardwick',
590 'note': 'video player needs Referer',
591 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
592 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
596 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
597 'uploader': 'DevWeek Events',
599 'thumbnail': 're:^https?://.*\.jpg$',
603 def _real_extract(self, url):
604 mobj = re.match(self._VALID_URL, url)
605 video_id = mobj.group('id')
606 player_url = 'https://player.vimeo.com/player/' + video_id
607 return self.url_result(player_url, 'Vimeo', video_id)
610 class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
611 IE_NAME = 'vimeo:watchlater'
612 IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
613 _VALID_URL = r'https://vimeo\.com/home/watchlater|:vimeowatchlater'
614 _LOGIN_REQUIRED = True
615 _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<'
617 'url': 'https://vimeo.com/home/watchlater',
618 'only_matching': True,
621 def _real_initialize(self):
624 def _page_url(self, base_url, pagenum):
625 url = '%s/page:%d/' % (base_url, pagenum)
626 request = compat_urllib_request.Request(url)
627 # Set the header to get a partial html page with the ids,
628 # the normal page doesn't contain them.
629 request.add_header('X-Requested-With', 'XMLHttpRequest')
632 def _real_extract(self, url):
633 return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater')
636 class VimeoLikesIE(InfoExtractor):
637 _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
638 IE_NAME = 'vimeo:likes'
639 IE_DESC = 'Vimeo user likes'
641 'url': 'https://vimeo.com/user755559/likes/',
642 'playlist_mincount': 293,
644 'id': 'user755559_likes',
645 "description": "See all the videos urza likes",
646 "title": 'Videos urza likes',
650 def _real_extract(self, url):
651 user_id = self._match_id(url)
652 webpage = self._download_webpage(url, user_id)
653 page_count = self._int(
655 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
656 .*?</a></li>\s*<li\s+class="pagination_next">
657 ''', webpage, 'page count'),
658 'page count', fatal=True)
660 title = self._html_search_regex(
661 r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
662 description = self._html_search_meta('description', webpage)
665 page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
667 webpage = self._download_webpage(
669 note='Downloading page %d/%d' % (idx + 1, page_count))
670 video_list = self._search_regex(
671 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
672 webpage, 'video content')
674 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
678 'url': compat_urlparse.urljoin(page_url, path),
681 pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
685 'id': 'user%s_likes' % user_id,
687 'description': description,