|
|
|
@ -24,6 +24,7 @@ from ..utils import (
|
|
|
|
merge_dicts,
|
|
|
|
merge_dicts,
|
|
|
|
OnDemandPagedList,
|
|
|
|
OnDemandPagedList,
|
|
|
|
parse_filesize,
|
|
|
|
parse_filesize,
|
|
|
|
|
|
|
|
parse_iso8601,
|
|
|
|
RegexNotFoundError,
|
|
|
|
RegexNotFoundError,
|
|
|
|
sanitized_Request,
|
|
|
|
sanitized_Request,
|
|
|
|
smuggle_url,
|
|
|
|
smuggle_url,
|
|
|
|
@ -74,25 +75,28 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
|
|
|
expected=True)
|
|
|
|
expected=True)
|
|
|
|
raise ExtractorError('Unable to log in')
|
|
|
|
raise ExtractorError('Unable to log in')
|
|
|
|
|
|
|
|
|
|
|
|
def _verify_video_password(self, url, video_id, webpage):
|
|
|
|
def _get_video_password(self):
|
|
|
|
password = self._downloader.params.get('videopassword')
|
|
|
|
password = self._downloader.params.get('videopassword')
|
|
|
|
if password is None:
|
|
|
|
if password is None:
|
|
|
|
raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
|
|
|
|
raise ExtractorError(
|
|
|
|
token, vuid = self._extract_xsrft_and_vuid(webpage)
|
|
|
|
'This video is protected by a password, use the --video-password option',
|
|
|
|
data = urlencode_postdata({
|
|
|
|
expected=True)
|
|
|
|
'password': password,
|
|
|
|
return password
|
|
|
|
'token': token,
|
|
|
|
|
|
|
|
})
|
|
|
|
def _verify_video_password(self, url, video_id, password, token, vuid):
|
|
|
|
if url.startswith('http://'):
|
|
|
|
if url.startswith('http://'):
|
|
|
|
# vimeo only supports https now, but the user can give an http url
|
|
|
|
# vimeo only supports https now, but the user can give an http url
|
|
|
|
url = url.replace('http://', 'https://')
|
|
|
|
url = url.replace('http://', 'https://')
|
|
|
|
password_request = sanitized_Request(url + '/password', data)
|
|
|
|
|
|
|
|
password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
|
|
|
|
|
|
|
password_request.add_header('Referer', url)
|
|
|
|
|
|
|
|
self._set_vimeo_cookie('vuid', vuid)
|
|
|
|
self._set_vimeo_cookie('vuid', vuid)
|
|
|
|
return self._download_webpage(
|
|
|
|
return self._download_webpage(
|
|
|
|
password_request, video_id,
|
|
|
|
url + '/password', video_id, 'Verifying the password',
|
|
|
|
'Verifying the password', 'Wrong password')
|
|
|
|
'Wrong password', data=urlencode_postdata({
|
|
|
|
|
|
|
|
'password': password,
|
|
|
|
|
|
|
|
'token': token,
|
|
|
|
|
|
|
|
}), headers={
|
|
|
|
|
|
|
|
'Content-Type': 'application/x-www-form-urlencoded',
|
|
|
|
|
|
|
|
'Referer': url,
|
|
|
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
|
|
def _extract_xsrft_and_vuid(self, webpage):
|
|
|
|
def _extract_xsrft_and_vuid(self, webpage):
|
|
|
|
xsrft = self._search_regex(
|
|
|
|
xsrft = self._search_regex(
|
|
|
|
@ -273,7 +277,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
|
|
|
)?
|
|
|
|
)?
|
|
|
|
(?:videos?/)?
|
|
|
|
(?:videos?/)?
|
|
|
|
(?P<id>[0-9]+)
|
|
|
|
(?P<id>[0-9]+)
|
|
|
|
(?:/[\da-f]+)?
|
|
|
|
(?:/(?P<unlisted_hash>[\da-f]{10}))?
|
|
|
|
/?(?:[?&].*)?(?:[#].*)?$
|
|
|
|
/?(?:[?&].*)?(?:[#].*)?$
|
|
|
|
'''
|
|
|
|
'''
|
|
|
|
IE_NAME = 'vimeo'
|
|
|
|
IE_NAME = 'vimeo'
|
|
|
|
@ -326,9 +330,9 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
|
|
|
'id': '54469442',
|
|
|
|
'id': '54469442',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
|
|
|
|
'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
|
|
|
|
'uploader': 'The BLN & Business of Software',
|
|
|
|
'uploader': 'Business of Software',
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
|
|
|
|
'uploader_id': 'theblnbusinessofsoftware',
|
|
|
|
'uploader_id': 'businessofsoftware',
|
|
|
|
'duration': 3610,
|
|
|
|
'duration': 3610,
|
|
|
|
'description': None,
|
|
|
|
'description': None,
|
|
|
|
},
|
|
|
|
},
|
|
|
|
@ -463,6 +467,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
|
|
|
'skip_download': True,
|
|
|
|
'skip_download': True,
|
|
|
|
},
|
|
|
|
},
|
|
|
|
'expected_warnings': ['Unable to download JSON metadata'],
|
|
|
|
'expected_warnings': ['Unable to download JSON metadata'],
|
|
|
|
|
|
|
|
'skip': 'this page is no longer available.',
|
|
|
|
},
|
|
|
|
},
|
|
|
|
{
|
|
|
|
{
|
|
|
|
'url': 'http://player.vimeo.com/video/68375962',
|
|
|
|
'url': 'http://player.vimeo.com/video/68375962',
|
|
|
|
@ -563,9 +568,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
|
|
|
return urls[0] if urls else None
|
|
|
|
return urls[0] if urls else None
|
|
|
|
|
|
|
|
|
|
|
|
def _verify_player_video_password(self, url, video_id, headers):
|
|
|
|
def _verify_player_video_password(self, url, video_id, headers):
|
|
|
|
password = self._downloader.params.get('videopassword')
|
|
|
|
password = self._get_video_password()
|
|
|
|
if password is None:
|
|
|
|
|
|
|
|
raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
|
|
|
|
|
|
|
|
data = urlencode_postdata({
|
|
|
|
data = urlencode_postdata({
|
|
|
|
'password': base64.b64encode(password.encode()),
|
|
|
|
'password': base64.b64encode(password.encode()),
|
|
|
|
})
|
|
|
|
})
|
|
|
|
@ -628,11 +631,37 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
|
|
|
if 'Referer' not in headers:
|
|
|
|
if 'Referer' not in headers:
|
|
|
|
headers['Referer'] = url
|
|
|
|
headers['Referer'] = url
|
|
|
|
|
|
|
|
|
|
|
|
channel_id = self._search_regex(
|
|
|
|
|
|
|
|
r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# Extract ID from URL
|
|
|
|
# Extract ID from URL
|
|
|
|
video_id = self._match_id(url)
|
|
|
|
video_id, unlisted_hash = re.match(self._VALID_URL, url).groups()
|
|
|
|
|
|
|
|
if unlisted_hash:
|
|
|
|
|
|
|
|
token = self._download_json(
|
|
|
|
|
|
|
|
'https://vimeo.com/_rv/jwt', video_id, headers={
|
|
|
|
|
|
|
|
'X-Requested-With': 'XMLHttpRequest'
|
|
|
|
|
|
|
|
})['token']
|
|
|
|
|
|
|
|
video = self._download_json(
|
|
|
|
|
|
|
|
'https://api.vimeo.com/videos/%s:%s' % (video_id, unlisted_hash),
|
|
|
|
|
|
|
|
video_id, headers={
|
|
|
|
|
|
|
|
'Authorization': 'jwt ' + token,
|
|
|
|
|
|
|
|
}, query={
|
|
|
|
|
|
|
|
'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
|
|
|
|
|
|
|
|
})
|
|
|
|
|
|
|
|
info = self._parse_config(self._download_json(
|
|
|
|
|
|
|
|
video['config_url'], video_id), video_id)
|
|
|
|
|
|
|
|
self._vimeo_sort_formats(info['formats'])
|
|
|
|
|
|
|
|
get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
|
|
|
|
|
|
|
|
info.update({
|
|
|
|
|
|
|
|
'description': video.get('description'),
|
|
|
|
|
|
|
|
'license': video.get('license'),
|
|
|
|
|
|
|
|
'release_timestamp': get_timestamp('release'),
|
|
|
|
|
|
|
|
'timestamp': get_timestamp('created'),
|
|
|
|
|
|
|
|
'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
|
|
|
|
|
|
|
|
})
|
|
|
|
|
|
|
|
connections = try_get(
|
|
|
|
|
|
|
|
video, lambda x: x['metadata']['connections'], dict) or {}
|
|
|
|
|
|
|
|
for k in ('comment', 'like'):
|
|
|
|
|
|
|
|
info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
|
|
|
|
|
|
|
|
return info
|
|
|
|
|
|
|
|
|
|
|
|
orig_url = url
|
|
|
|
orig_url = url
|
|
|
|
is_pro = 'vimeopro.com/' in url
|
|
|
|
is_pro = 'vimeopro.com/' in url
|
|
|
|
is_player = '://player.vimeo.com/video/' in url
|
|
|
|
is_player = '://player.vimeo.com/video/' in url
|
|
|
|
@ -722,7 +751,10 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
|
|
|
if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
|
|
|
|
if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
|
|
|
|
if '_video_password_verified' in data:
|
|
|
|
if '_video_password_verified' in data:
|
|
|
|
raise ExtractorError('video password verification failed!')
|
|
|
|
raise ExtractorError('video password verification failed!')
|
|
|
|
self._verify_video_password(redirect_url, video_id, webpage)
|
|
|
|
video_password = self._get_video_password()
|
|
|
|
|
|
|
|
token, vuid = self._extract_xsrft_and_vuid(webpage)
|
|
|
|
|
|
|
|
self._verify_video_password(
|
|
|
|
|
|
|
|
redirect_url, video_id, video_password, token, vuid)
|
|
|
|
return self._real_extract(
|
|
|
|
return self._real_extract(
|
|
|
|
smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
|
|
|
|
smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
|
|
|
|
else:
|
|
|
|
else:
|
|
|
|
@ -808,6 +840,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
|
|
|
r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
|
|
|
|
r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
|
|
|
|
webpage, 'license', default=None, group='license')
|
|
|
|
webpage, 'license', default=None, group='license')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
channel_id = self._search_regex(
|
|
|
|
|
|
|
|
r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
|
|
|
|
channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
|
|
|
|
channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
|
|
|
|
|
|
|
|
|
|
|
|
info_dict = {
|
|
|
|
info_dict = {
|
|
|
|
@ -1114,10 +1148,23 @@ class VimeoReviewIE(VimeoBaseInfoExtractor):
|
|
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
def _real_extract(self, url):
|
|
|
|
page_url, video_id = re.match(self._VALID_URL, url).groups()
|
|
|
|
page_url, video_id = re.match(self._VALID_URL, url).groups()
|
|
|
|
clip_data = self._download_json(
|
|
|
|
data = self._download_json(
|
|
|
|
page_url.replace('/review/', '/review/data/'),
|
|
|
|
page_url.replace('/review/', '/review/data/'), video_id)
|
|
|
|
video_id)['clipData']
|
|
|
|
if data.get('isLocked') is True:
|
|
|
|
config_url = clip_data['configUrl']
|
|
|
|
video_password = self._get_video_password()
|
|
|
|
|
|
|
|
viewer = self._download_json(
|
|
|
|
|
|
|
|
'https://vimeo.com/_rv/viewer', video_id)
|
|
|
|
|
|
|
|
webpage = self._verify_video_password(
|
|
|
|
|
|
|
|
'https://vimeo.com/' + video_id, video_id,
|
|
|
|
|
|
|
|
video_password, viewer['xsrft'], viewer['vuid'])
|
|
|
|
|
|
|
|
clip_page_config = self._parse_json(self._search_regex(
|
|
|
|
|
|
|
|
r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
|
|
|
|
|
|
|
|
webpage, 'clip page config'), video_id)
|
|
|
|
|
|
|
|
config_url = clip_page_config['player']['config_url']
|
|
|
|
|
|
|
|
clip_data = clip_page_config.get('clip') or {}
|
|
|
|
|
|
|
|
else:
|
|
|
|
|
|
|
|
clip_data = data['clipData']
|
|
|
|
|
|
|
|
config_url = clip_data['configUrl']
|
|
|
|
config = self._download_json(config_url, video_id)
|
|
|
|
config = self._download_json(config_url, video_id)
|
|
|
|
info_dict = self._parse_config(config, video_id)
|
|
|
|
info_dict = self._parse_config(config, video_id)
|
|
|
|
source_format = self._extract_original_format(
|
|
|
|
source_format = self._extract_original_format(
|
|
|
|
|
pukkandan
4 years ago