from __future__ import unicode_literals
import base64
+import functools
import json
import re
import itertools
from .common import InfoExtractor
from ..compat import (
+ compat_kwargs,
compat_HTTPError,
compat_str,
compat_urlparse,
)
from ..utils import (
+ clean_html,
determine_ext,
+ dict_get,
ExtractorError,
js_to_json,
int_or_none,
merge_dicts,
- NO_DEFAULT,
+ OnDemandPagedList,
parse_filesize,
- qualities,
RegexNotFoundError,
sanitized_Request,
smuggle_url,
std_headers,
+ str_or_none,
try_get,
unified_timestamp,
unsmuggle_url,
webpage, 'vuid', group='vuid')
return xsrft, vuid
+ def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
+ vimeo_config = self._search_regex(
+ r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
+ webpage, 'vimeo config', *args, **compat_kwargs(kwargs))
+ if vimeo_config:
+ return self._parse_json(vimeo_config, video_id)
+
def _set_vimeo_cookie(self, name, value):
self._set_cookie('vimeo.com', name, value)
video_uploader_url = owner.get('url')
return {
+ 'id': str_or_none(video_data.get('id')) or video_id,
'title': self._live_title(video_title) if is_live else video_title,
'uploader': owner.get('name'),
'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
(?:
(?:
www|
- (?P<player>player)
+ player
)
\.
)?
- vimeo(?P<pro>pro)?\.com/
- (?!(?:channels|album)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
+ vimeo(?:pro)?\.com/
+ (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
(?:.*?/)?
(?:
(?:
'id': '56015672',
'ext': 'mp4',
'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
- 'description': 'md5:509a9ad5c9bf97c60faee9203aca4479',
+ 'description': 'md5:2d3305bad981a06ff79f027f19865021',
'timestamp': 1355990239,
'upload_date': '20121220',
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
'duration': 10,
'license': 'by-sa',
},
+ 'params': {
+ 'format': 'best[protocol=https]',
+ },
},
{
'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
'uploader_id': 'openstreetmapus',
'uploader': 'OpenStreetMap US',
'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
- 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
+ 'description': 'md5:2c362968038d4499f4d79f88458590c1',
'duration': 1595,
+ 'upload_date': '20130610',
+ 'timestamp': 1370893156,
+ },
+ 'params': {
+ 'format': 'best[protocol=https]',
},
},
{
'duration': 3610,
'description': None,
},
+ 'params': {
+ 'format': 'best[protocol=https]',
+ },
+ 'expected_warnings': ['Unable to download JSON metadata'],
},
{
'url': 'http://vimeo.com/68375962',
'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
},
'params': {
+ 'format': 'best[protocol=https]',
'videopassword': 'youtube-dl',
},
},
'uploader': '10Ft Films',
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
'uploader_id': 'tenfootfilms',
+ 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
+ 'upload_date': '20130830',
+ 'timestamp': 1377853339,
},
'params': {
'skip_download': True,
},
+ 'expected_warnings': ['Unable to download JSON metadata'],
},
{
'url': 'http://player.vimeo.com/video/68375962',
'duration': 10,
},
'params': {
+ 'format': 'best[protocol=https]',
'videopassword': 'youtube-dl',
},
},
def _verify_player_video_password(self, url, video_id, headers):
password = self._downloader.params.get('videopassword')
if password is None:
- raise ExtractorError('This video is protected by a password, use the --video-password option')
+ raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
data = urlencode_postdata({
'password': base64.b64encode(password.encode()),
})
r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
# Extract ID from URL
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
orig_url = url
- if mobj.group('pro'):
+ is_pro = 'vimeopro.com/' in url
+ is_player = '://player.vimeo.com/video/' in url
+ if is_pro:
# some videos require portfolio_id to be present in player url
# https://github.com/ytdl-org/youtube-dl/issues/20070
url = self._extract_url(url, self._download_webpage(url, video_id))
- elif mobj.group('player'):
+ if not url:
+ url = 'https://vimeo.com/' + video_id
+ elif is_player:
url = 'https://player.vimeo.com/video/' + video_id
elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
url = 'https://vimeo.com/' + video_id
- # Retrieve video webpage to extract further information
- request = sanitized_Request(url, headers=headers)
try:
- webpage, urlh = self._download_webpage_handle(request, video_id)
+ # Retrieve video webpage to extract further information
+ webpage, urlh = self._download_webpage_handle(
+ url, video_id, headers=headers)
redirect_url = compat_str(urlh.geturl())
- # Some URLs redirect to ondemand can't be extracted with
- # this extractor right away thus should be passed through
- # ondemand extractor (e.g. https://vimeo.com/73445910)
- if VimeoOndemandIE.suitable(redirect_url):
- return self.url_result(redirect_url, VimeoOndemandIE.ie_key())
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
errmsg = ee.cause.read()
# and latter we extract those that are Vimeo specific.
self.report_extraction(video_id)
- vimeo_config = self._search_regex(
- r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
- 'vimeo config', default=None)
+ vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
if vimeo_config:
- seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
+ seed_status = vimeo_config.get('seed_status', {})
if seed_status.get('state') == 'failed':
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, seed_status['title']),
cc_license = None
timestamp = None
+ video_description = None
# Extract the config JSON
try:
# Sometimes new react-based page is served instead of old one that require
# different config URL extraction approach (see
# https://github.com/ytdl-org/youtube-dl/pull/7209)
- vimeo_clip_page_config = self._search_regex(
- r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
- 'vimeo clip page config')
- page_config = self._parse_json(vimeo_clip_page_config, video_id)
+ page_config = self._parse_json(self._search_regex(
+ r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
+ webpage, 'page config'), video_id)
config_url = page_config['player']['config_url']
cc_license = page_config.get('cc_license')
timestamp = try_get(
page_config, lambda x: x['clip']['uploaded_on'],
compat_str)
- config_json = self._download_webpage(config_url, video_id)
- config = json.loads(config_json)
+ video_description = clean_html(dict_get(
+ page_config, ('description', 'description_html_escaped')))
+ config = self._download_json(config_url, video_id)
except RegexNotFoundError:
# For pro videos or player.vimeo.com urls
# We try to find out to which variable is assigned the config dic
{'force_feature_id': True}), 'Vimeo')
# Extract video description
-
- video_description = self._html_search_regex(
- r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
- webpage, 'description', default=None)
+ if not video_description:
+ video_description = self._html_search_regex(
+
r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
+ webpage, 'description', default=None)
if not video_description:
video_description = self._html_search_meta(
'description', webpage, default=None)
- if not video_description and mobj.group('pro'):
+ if not video_description and is_pro:
orig_webpage = self._download_webpage(
orig_url, video_id,
note='Downloading webpage for description',
if orig_webpage:
video_description = self._html_search_meta(
'description', orig_webpage, default=None)
- if not video_description and not mobj.group('player'):
+ if not video_description and not is_player:
self._downloader.report_warning('Cannot find video description')
# Extract upload date
channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
info_dict = {
- 'id': video_id,
'formats': formats,
'timestamp': unified_timestamp(timestamp),
'description': video_description,
return info_dict
-class VimeoOndemandIE(VimeoBaseInfoExtractor):
+class VimeoOndemandIE(VimeoIE):
IE_NAME = 'vimeo:ondemand'
- _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)'
+ _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/([^/]+/)?(?P<id>[^/?#&]+)'
_TESTS = [{
# ondemand video not available via https://vimeo.com/id
'url': 'https://vimeo.com/ondemand/20704',
'uploader': 'גם סרטים',
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
'uploader_id': 'gumfilms',
+ 'description': 'md5:4c027c965e439de4baab621e48b60791',
+ 'upload_date': '20140906',
+ 'timestamp': 1410032453,
},
'params': {
'format': 'best[protocol=https]',
},
+ 'expected_warnings': ['Unable to download JSON metadata'],
}, {
# requires Referer to be passed along with og:video:url
'url': 'https://vimeo.com/ondemand/36938/126682985',
'info_dict': {
- 'id': '126682985',
+ 'id': '126584684',
'ext': 'mp4',
'title': 'Rävlock, rätt läte på rätt plats',
'uploader': 'Lindroth & Norin',
- 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user14430847',
- 'uploader_id': 'user14430847',
+ 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
+ 'uploader_id': 'lindrothnorin',
+ 'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
+ 'upload_date': '20150502',
+ 'timestamp': 1430586422,
},
'params': {
'skip_download': True,
},
+ 'expected_warnings': ['Unable to download JSON metadata'],
}, {
'url': 'https://vimeo.com/ondemand/nazmaalik',
'only_matching': True,
'only_matching': True,
}]
- def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
- return self.url_result(
- # Some videos require Referer to be passed along with og:video:url
- # similarly to generic vimeo embeds (e.g.
- # https://vimeo.com/ondemand/36938/126682985).
- VimeoIE._smuggle_referrer(self._og_search_video_url(webpage), url),
- VimeoIE.ie_key())
-
class VimeoChannelIE(VimeoBaseInfoExtractor):
IE_NAME = 'vimeo:channel'
},
'playlist_mincount': 25,
}]
+ _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
def _page_url(self, base_url, pagenum):
return '%s/videos/page:%d/' % (base_url, pagenum)
return self.playlist_result(title_and_entries, list_id, list_title)
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- channel_id = mobj.group('id')
- return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
+ channel_id = self._match_id(url)
+ return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
class VimeoUserIE(VimeoChannelIE):
IE_NAME = 'vimeo:user'
- _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
+ _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
_TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
_TESTS = [{
'url': 'https://vimeo.com/nkistudio/videos',
},
'playlist_mincount': 66,
}]
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- name = mobj.group('name')
- return self._extract_videos(name, 'https://vimeo.com/%s' % name)
+ _BASE_URL_TEMPL = 'https://vimeo.com/%s'
class VimeoAlbumIE(VimeoChannelIE):
IE_NAME = 'vimeo:album'
- _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)(?:$|[?#]|/(?!video))'
+ _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
_TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
_TESTS = [{
'url': 'https://vimeo.com/album/2632481',
'params': {
'videopassword': 'youtube-dl',
}
- }, {
- 'url': 'https://vimeo.com/album/2632481/sort:plays/format:thumbnail',
- 'only_matching': True,
- }, {
- # TODO: respect page number
- 'url': 'https://vimeo.com/album/2632481/page:2/sort:plays/format:thumbnail',
- 'only_matching': True,
}]
-
- def _page_url(self, base_url, pagenum):
- return '%s/page:%d/' % (base_url, pagenum)
+ _PAGE_SIZE = 100
+
+ def _fetch_page(self, album_id, authorizaion, hashed_pass, page):
+ api_page = page + 1
+ query = {
+ 'fields': 'link,uri',
+ 'page': api_page,
+ 'per_page': self._PAGE_SIZE,
+ }
+ if hashed_pass:
+ query['_hashed_pass'] = hashed_pass
+ videos = self._download_json(
+ 'https://api.vimeo.com/albums/%s/videos' % album_id,
+ album_id, 'Downloading page %d' % api_page, query=query, headers={
+ 'Authorization': 'jwt ' + authorizaion,
+ })['data']
+ for video in videos:
+ link = video.get('link')
+ if not link:
+ continue
+ uri = video.get('uri')
+ video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
+ yield self.url_result(link, VimeoIE.ie_key(), video_id)
def _real_extract(self, url):
album_id = self._match_id(url)
- return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
+ webpage = self._download_webpage(url, album_id)
+ webpage = self._login_list_password(url, album_id, webpage)
+ api_config = self._extract_vimeo_config(webpage, album_id)['api']
+ entries = OnDemandPagedList(functools.partial(
+ self._fetch_page, album_id, api_config['jwt'],
+ api_config.get('hashed_pass')), self._PAGE_SIZE)
+ return self.playlist_result(entries, album_id, self._html_search_regex(
+ r'<title>\s*(.+?)(?:\s+on Vimeo)?</title>', webpage, 'title', fatal=False))
-class VimeoGroupsIE(VimeoAlbumIE):
+class VimeoGroupsIE(VimeoChannelIE):
IE_NAME = 'vimeo:group'
- _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
+ _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
_TESTS = [{
- 'url': 'https://vimeo.com/groups/rolexawards',
+ 'url': 'https://vimeo.com/groups/kattykay',
'info_dict': {
- 'id': 'rolexawards',
- 'title': 'Rolex Awards for Enterprise',
+ 'id': 'kattykay',
+ 'title': 'Katty Kay',
},
- 'playlist_mincount': 73,
+ 'playlist_mincount': 27,
}]
-
- def _extract_list_title(self, webpage):
- return self._og_search_title(webpage, fatal=False)
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- name = mobj.group('name')
- return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
+ _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
class VimeoReviewIE(VimeoBaseInfoExtractor):
'title': "DICK HARDWICK 'Comedian'",
'uploader': 'Richard Hardwick',
'uploader_id': 'user21297594',
- }
+ 'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
+ },
+ 'expected_warnings': ['Unable to download JSON metadata'],
}, {
'note': 'video player needs Referer',
'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
'duration': 2773,
'thumbnail': r're:^https?://.*\.jpg$',
'uploader_id': 'user22258446',
- }
+ },
+ 'skip': 'video gone',
}, {
'note': 'Password protected',
'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
def _real_initialize(self):
self._login()
- def _get_config_url(self, webpage_url, video_id, video_password_verified=False):
- webpage = self._download_webpage(webpage_url, video_id)
- config_url = self._html_search_regex(
- r'data-config-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
- 'config URL', default=None, group='url')
- if not config_url:
- data = self._parse_json(self._search_regex(
- r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data',
- default=NO_DEFAULT if video_password_verified else '{}'), video_id)
- config = data.get('vimeo_esi', {}).get('config', {})
- config_url = config.get('configUrl') or try_get(config, lambda x: x['clipData']['configUrl'])
- if config_url is None:
- self._verify_video_password(webpage_url, video_id, webpage)
- config_url = self._get_config_url(
- webpage_url, video_id, video_password_verified=True)
- return config_url
-
def _real_extract(self, url):
page_url, video_id = re.match(self._VALID_URL, url).groups()
- config_url = self._get_config_url(url, video_id)
+ clip_data = self._download_json(
+ page_url.replace('/review/', '/review/data/'),
+ video_id)['clipData']
+ config_url = clip_data['configUrl']
config = self._download_json(config_url, video_id)
info_dict = self._parse_config(config, video_id)
- source_format = self._extract_original_format(page_url, video_id)
+ source_format = self._extract_original_format(
+ page_url + '/action', video_id)
if source_format:
info_dict['formats'].append(source_format)
self._vimeo_sort_formats(info_dict['formats'])
- info_dict['id'] = video_id
+ info_dict['description'] = clean_html(clip_data.get('description'))
return info_dict
return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
-class VHXEmbedIE(InfoExtractor):
+class VHXEmbedIE(VimeoBaseInfoExtractor):
IE_NAME = 'vhx:embed'
_VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
- def _call_api(self, video_id, access_token, path='', query=None):
- return self._download_json(
- 'https://api.vhx.tv/videos/' + video_id + path, video_id, headers={
- 'Authorization': 'Bearer ' + access_token,
- }, query=query)
-
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- credentials = self._parse_json(self._search_regex(
- r'(?s)credentials\s*:\s*({.+?}),', webpage,
- 'config'), video_id, js_to_json)
- access_token = credentials['access_token']
-
- query = {}
- for k, v in credentials.items():
- if k in ('authorization', 'authUserToken', 'ticket') and v and v != 'undefined':
- if k == 'authUserToken':
- query['auth_user_token'] = v
- else:
- query[k] = v
- files = self._call_api(video_id, access_token, '/files', query)
-
- formats = []
- for f in files:
- href = try_get(f, lambda x: x['_links']['source']['href'])
- if not href:
- continue
- method = f.get('method')
- if method == 'hls':
- formats.extend(self._extract_m3u8_formats(
- href, video_id, 'mp4', 'm3u8_native',
- m3u8_id='hls', fatal=False))
- elif method == 'dash':
- formats.extend(self._extract_mpd_formats(
- href, video_id, mpd_id='dash', fatal=False))
- else:
- fmt = {
- 'filesize': int_or_none(try_get(f, lambda x: x['size']['bytes'])),
- 'format_id': 'http',
- 'preference': 1,
- 'url': href,
- 'vcodec': f.get('codec'),
- }
- quality = f.get('quality')
- if quality:
- fmt.update({
- 'format_id': 'http-' + quality,
- 'height': int_or_none(self._search_regex(r'(\d+)p', quality, 'height', default=None)),
- })
- formats.append(fmt)
- self._sort_formats(formats)
-
- video_data = self._call_api(video_id, access_token)
- title = video_data.get('title') or video_data['name']
-
- subtitles = {}
- for subtitle in try_get(video_data, lambda x: x['tracks']['subtitles'], list) or []:
- lang = subtitle.get('srclang') or subtitle.get('label')
- for _link in subtitle.get('_links', {}).values():
- href = _link.get('href')
- if not href:
- continue
- subtitles.setdefault(lang, []).append({
- 'url': href,
- })
-
- q = qualities(['small', 'medium', 'large', 'source'])
- thumbnails = []
- for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items():
- thumbnails.append({
- 'id': thumbnail_id,
- 'url': thumbnail_url,
- 'preference': q(thumbnail_id),
- })
-
- return {
- 'id': video_id,
- 'title': title,
- 'description': video_data.get('description'),
- 'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])),
- 'formats': formats,
- 'subtitles': subtitles,
- 'thumbnails': thumbnails,
- 'timestamp': unified_timestamp(video_data.get('created_at')),
- 'view_count': int_or_none(video_data.get('plays_count')),
- }
+ config_url = self._parse_json(self._search_regex(
+ r'window\.OTTData\s*=\s*({.+})', webpage,
+ 'ott data'), video_id, js_to_json)['config_url']
+ config = self._download_json(config_url, video_id)
+ info = self._parse_config(config, video_id)
+ self._vimeo_sort_formats(info['formats'])
+ return info
Rapsys Git / youtubedl / blobdiff