2 from __future__
import unicode_literals
9 from .common
import InfoExtractor
10 from .subtitles
import SubtitlesInfoExtractor
11 from ..compat
import (
14 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, SubtitlesInfoExtractor):
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',
148 'url': 'http://vimeo.com/76979871',
149 'md5': '3363dd6ffebe3784d56f4132317fd446',
150 'note': 'Video with subtitles',
154 'title': 'The New Vimeo Player (You Know, For Videos)',
155 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
156 'upload_date': '20131015',
157 'uploader_id': 'staff',
158 'uploader': 'Vimeo Staff',
163 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
164 'url': 'https://player.vimeo.com/video/98044508',
165 'note': 'The js code contains assignments to the same variable as the config',
169 'title': 'Pier Solar OUYA Official Trailer',
170 'uploader': 'Tulio Gonçalves',
171 'uploader_id': 'user28849593',
176 def _verify_video_password(self
, url
, video_id
, webpage
):
177 password
= self
._downloader
.params
.get('videopassword', None)
179 raise ExtractorError('This video is protected by a password, use the --video-password option', expected
=True)
180 token
= self
._search
_regex
(r
'xsrft: \'(.*?
)\'', webpage, 'login token
')
181 data = compat_urllib_parse.urlencode({
182 'password
': password,
185 # I didn't manage to use the password
with https
186 if url
.startswith('https'):
187 pass_url
= url
.replace('https', 'http')
190 password_request
= compat_urllib_request
.Request(pass_url
+ '/password', data
)
191 password_request
.add_header('Content-Type', 'application/x-www-form-urlencoded')
192 password_request
.add_header('Cookie', 'xsrft=%s' % token
)
193 return self
._download
_webpage
(
194 password_request
, video_id
,
195 'Verifying the password', 'Wrong password')
197 def _verify_player_video_password(self
, url
, video_id
):
198 password
= self
._downloader
.params
.get('videopassword', None)
200 raise ExtractorError('This video is protected by a password, use the --video-password option')
201 data
= compat_urllib_parse
.urlencode({'password': password}
)
202 pass_url
= url
+ '/check-password'
203 password_request
= compat_urllib_request
.Request(pass_url
, data
)
204 password_request
.add_header('Content-Type', 'application/x-www-form-urlencoded')
205 return self
._download
_json
(
206 password_request
, video_id
,
207 'Verifying the password',
210 def _real_initialize(self
):
213 def _real_extract(self
, url
):
214 url
, data
= unsmuggle_url(url
)
215 headers
= std_headers
217 headers
= headers
.copy()
219 if 'Referer' not in headers
:
220 headers
['Referer'] = url
222 # Extract ID from URL
223 mobj
= re
.match(self
._VALID
_URL
, url
)
224 video_id
= mobj
.group('id')
226 if mobj
.group('pro') or mobj
.group('player'):
227 url
= 'http://player.vimeo.com/video/' + video_id
229 password
= self
._downloader
.params
.get('videopassword', None)
231 headers
['Cookie'] = '%s_password=%s' % (video_id
, hashlib
.md5(password
).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']] = 'http://vimeo.com' + tt
['url']
382 video_subtitles
= self
.extract_subtitles(video_id
, subtitles
)
383 if self
._downloader
.params
.get('listsubtitles', False):
384 self
._list
_available
_subtitles
(video_id
, subtitles
)
389 'uploader': video_uploader
,
390 'uploader_id': video_uploader_id
,
391 'upload_date': video_upload_date
,
392 'title': video_title
,
393 'thumbnail': video_thumbnail
,
394 'description': video_description
,
395 'duration': video_duration
,
398 'view_count': view_count
,
399 'like_count': like_count
,
400 'comment_count': comment_count
,
401 'subtitles': video_subtitles
,
405 class VimeoChannelIE(InfoExtractor
):
406 IE_NAME
= 'vimeo:channel'
407 _VALID_URL
= r
'https?://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
408 _MORE_PAGES_INDICATOR
= r
'<a.+?rel="next"'
409 _TITLE_RE
= r
'<link rel="alternate"[^>]+?title="(.*?)"'
411 'url': 'http://vimeo.com/channels/tributes',
414 'title': 'Vimeo Tributes',
416 'playlist_mincount': 25,
419 def _page_url(self
, base_url
, pagenum
):
420 return '%s/videos/page:%d/' % (base_url
, pagenum
)
422 def _extract_list_title(self
, webpage
):
423 return self
._html
_search
_regex
(self
._TITLE
_RE
, webpage
, 'list title')
425 def _login_list_password(self
, page_url
, list_id
, webpage
):
426 login_form
= self
._search
_regex
(
427 r
'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
428 webpage
, 'login form', default
=None)
432 password
= self
._downloader
.params
.get('videopassword', None)
434 raise ExtractorError('This album is protected by a password, use the --video-password option', expected
=True)
435 fields
= dict(re
.findall(r
'''(?x)<input\s+
440 token
= self
._search
_regex
(r
'xsrft: \'(.*?
)\'', webpage, 'login token
')
441 fields['token
'] = token
442 fields['password
'] = password
443 post = compat_urllib_parse.urlencode(fields)
444 password_path = self._search_regex(
445 r'action
="([^"]+)"', login_form, 'password URL')
446 password_url = compat_urlparse.urljoin(page_url, password_path)
447 password_request = compat_urllib_request.Request(password_url, post)
448 password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
449 self._set_cookie('vimeo.com', 'xsrft', token)
451 return self._download_webpage(
452 password_request, list_id,
453 'Verifying the password', 'Wrong password')
455 def _extract_videos(self, list_id, base_url):
457 for pagenum in itertools.count(1):
458 page_url = self._page_url(base_url, pagenum)
459 webpage = self._download_webpage(
461 'Downloading page %s' % pagenum)
464 webpage = self._login_list_password(page_url, list_id, webpage)
466 video_ids.extend(re.findall(r'id="clip_(\d
+?
)"', webpage))
467 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
470 entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
471 for video_id in video_ids]
472 return {'_type': 'playlist',
474 'title': self._extract_list_title(webpage),
478 def _real_extract(self, url):
479 mobj = re.match(self._VALID_URL, url)
480 channel_id = mobj.group('id')
481 return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id)
484 class VimeoUserIE(VimeoChannelIE):
485 IE_NAME = 'vimeo:user'
486 _VALID_URL = r'https?://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
487 _TITLE_RE = r'<a[^>]+?class="user
">([^<>]+?)</a>'
489 'url': 'http://vimeo.com/nkistudio/videos',
494 'playlist_mincount': 66,
497 def _real_extract(self, url):
498 mobj = re.match(self._VALID_URL, url)
499 name = mobj.group('name')
500 return self._extract_videos(name, 'http://vimeo.com/%s' % name)
503 class VimeoAlbumIE(VimeoChannelIE):
504 IE_NAME = 'vimeo:album'
505 _VALID_URL = r'https?://vimeo\.com/album/(?P<id>\d+)'
506 _TITLE_RE = r'<header id="page_header
">\n\s*<h1>(.*?)</h1>'
508 'url': 'http://vimeo.com/album/2632481',
511 'title': 'Staff Favorites: November 2013',
513 'playlist_mincount': 13,
515 'note': 'Password-protected album',
516 'url': 'https://vimeo.com/album/3253534',
523 'videopassword': 'youtube-dl',
527 def _page_url(self, base_url, pagenum):
528 return '%s/page:%d/' % (base_url, pagenum)
530 def _real_extract(self, url):
531 album_id = self._match_id(url)
532 return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_id)
535 class VimeoGroupsIE(VimeoAlbumIE):
536 IE_NAME = 'vimeo:group'
537 _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)'
539 'url': 'http://vimeo.com/groups/rolexawards',
542 'title': 'Rolex Awards for Enterprise',
544 'playlist_mincount': 73,
547 def _extract_list_title(self, webpage):
548 return self._og_search_title(webpage)
550 def _real_extract(self, url):
551 mobj = re.match(self._VALID_URL, url)
552 name = mobj.group('name')
553 return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name)
556 class VimeoReviewIE(InfoExtractor):
557 IE_NAME = 'vimeo:review'
558 IE_DESC = 'Review pages on vimeo'
559 _VALID_URL = r'https?://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
561 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
562 'md5': 'c507a72f780cacc12b2248bb4006d253',
566 'title': "DICK HARDWICK
'Comedian'",
567 'uploader': 'Richard Hardwick',
570 'note': 'video player needs Referer',
571 'url': 'http://vimeo.com/user22258446/review/91613211/13f927e053',
572 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
576 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
577 'uploader': 'DevWeek Events',
579 'thumbnail': 're:^https?://.*\.jpg$',
583 def _real_extract(self, url):
584 mobj = re.match(self._VALID_URL, url)
585 video_id = mobj.group('id')
586 player_url = 'https://player.vimeo.com/player/' + video_id
587 return self.url_result(player_url, 'Vimeo', video_id)
590 class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
591 IE_NAME = 'vimeo:watchlater'
592 IE_DESC = 'Vimeo watch later list, "vimeowatchlater
" keyword (requires authentication)'
593 _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater'
594 _LOGIN_REQUIRED = True
595 _TITLE_RE = r'href="/home
/watchlater
".*?>(.*?)<'
597 'url': 'http://vimeo.com/home/watchlater',
598 'only_matching': True,
601 def _real_initialize(self):
604 def _page_url(self, base_url, pagenum):
605 url = '%s/page:%d/' % (base_url, pagenum)
606 request = compat_urllib_request.Request(url)
607 # Set the header to get a partial html page with the ids,
608 # the normal page doesn't contain them.
609 request.add_header('X-Requested-With', 'XMLHttpRequest')
612 def _real_extract(self, url):
613 return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater')
616 class VimeoLikesIE(InfoExtractor):
617 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
618 IE_NAME = 'vimeo:likes'
619 IE_DESC = 'Vimeo user likes'
621 'url': 'https://vimeo.com/user755559/likes/',
622 'playlist_mincount': 293,
624 'id': 'user755559_likes',
625 "description
": "See all the videos urza likes
",
626 "title
": 'Videos urza likes',
630 def _real_extract(self, url):
631 user_id = self._match_id(url)
632 webpage = self._download_webpage(url, user_id)
633 page_count = self._int(
635 r'''(?x)<li><a\s+href="[^
"]+"\s
+data
-page
="([0-9]+)">
636 .*?
</a
></li
>\s
*<li\s
+class="pagination_next">
637 ''', webpage, 'page count'),
638 'page count', fatal=True)
640 title = self._html_search_regex(
641 r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
642 description = self._html_search_meta('description', webpage)
645 page_url = '%s//vimeo.com/user%s/likes/page:%d/sort:date' % (
646 self.http_scheme(), user_id, idx + 1)
647 webpage = self._download_webpage(
649 note='Downloading page %d/%d' % (idx + 1, page_count))
650 video_list = self._search_regex(
651 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
652 webpage, 'video content')
654 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
658 'url': compat_urlparse.urljoin(page_url, path),
661 pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
665 'id': 'user%s_likes' % user_id,
667 'description': description,