2019-01-17 03:44:08 -05:00
|
|
|
|
import base64
|
2019-08-03 05:29:20 -04:00
|
|
|
|
import functools
|
2013-07-29 07:12:09 -04:00
|
|
|
|
import itertools
|
2024-07-05 14:32:53 -04:00
|
|
|
|
import json
|
2024-05-26 15:27:21 -04:00
|
|
|
|
import re
|
2024-06-11 19:09:58 -04:00
|
|
|
|
import urllib.parse
|
2013-06-23 14:18:21 -04:00
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2023-07-09 03:53:02 -04:00
|
|
|
|
from ..networking import HEADRequest, Request
|
|
|
|
|
from ..networking.exceptions import HTTPError
|
2014-11-02 05:23:40 -05:00
|
|
|
|
from ..utils import (
|
2024-05-26 15:27:21 -04:00
|
|
|
|
ExtractorError,
|
|
|
|
|
OnDemandPagedList,
|
2019-11-27 07:57:30 -05:00
|
|
|
|
clean_html,
|
2016-01-08 16:06:09 -05:00
|
|
|
|
determine_ext,
|
2021-10-21 20:27:15 -04:00
|
|
|
|
get_element_by_class,
|
2014-09-28 18:36:06 -04:00
|
|
|
|
int_or_none,
|
2024-07-05 14:32:53 -04:00
|
|
|
|
join_nonempty,
|
2024-05-26 15:27:21 -04:00
|
|
|
|
js_to_json,
|
2018-04-27 15:48:20 -04:00
|
|
|
|
merge_dicts,
|
2018-11-28 13:53:22 -05:00
|
|
|
|
parse_filesize,
|
2021-04-01 04:28:33 -04:00
|
|
|
|
parse_iso8601,
|
2021-08-22 15:02:00 -04:00
|
|
|
|
parse_qs,
|
2015-02-17 18:27:57 -05:00
|
|
|
|
smuggle_url,
|
2019-11-27 07:57:30 -05:00
|
|
|
|
str_or_none,
|
2024-03-01 19:41:32 -05:00
|
|
|
|
traverse_obj,
|
2017-01-31 12:58:02 -05:00
|
|
|
|
try_get,
|
|
|
|
|
unified_timestamp,
|
2013-10-15 06:05:13 -04:00
|
|
|
|
unsmuggle_url,
|
2014-04-24 08:44:27 -04:00
|
|
|
|
urlencode_postdata,
|
2021-11-05 16:45:08 -04:00
|
|
|
|
urlhandle_detect_ext,
|
2024-05-26 15:27:21 -04:00
|
|
|
|
urljoin,
|
2013-06-23 14:18:21 -04:00
|
|
|
|
)
|
|
|
|
|
|
2013-12-21 21:17:56 -05:00
|
|
|
|
|
2014-04-24 15:51:20 -04:00
|
|
|
|
class VimeoBaseInfoExtractor(InfoExtractor):
|
|
|
|
|
_NETRC_MACHINE = 'vimeo'
|
|
|
|
|
_LOGIN_REQUIRED = False
|
2015-08-10 13:35:08 -04:00
|
|
|
|
_LOGIN_URL = 'https://vimeo.com/log_in'
|
2014-04-24 15:51:20 -04:00
|
|
|
|
|
2022-05-17 19:41:47 -04:00
|
|
|
|
@staticmethod
|
|
|
|
|
def _smuggle_referrer(url, referrer_url):
|
2023-08-16 19:42:48 -04:00
|
|
|
|
return smuggle_url(url, {'referer': referrer_url})
|
2022-05-17 19:41:47 -04:00
|
|
|
|
|
|
|
|
|
def _unsmuggle_headers(self, url):
|
|
|
|
|
"""@returns (url, smuggled_data, headers)"""
|
|
|
|
|
url, data = unsmuggle_url(url, {})
|
|
|
|
|
headers = self.get_param('http_headers').copy()
|
2023-08-16 19:42:48 -04:00
|
|
|
|
if 'referer' in data:
|
|
|
|
|
headers['Referer'] = data['referer']
|
2022-05-17 19:41:47 -04:00
|
|
|
|
return url, data, headers
|
|
|
|
|
|
2022-03-18 16:53:33 -04:00
|
|
|
|
def _perform_login(self, username, password):
|
2024-02-24 18:09:04 -05:00
|
|
|
|
viewer = self._download_json('https://vimeo.com/_next/viewer', None, 'Downloading login token')
|
2018-03-05 10:45:47 -05:00
|
|
|
|
data = {
|
2015-08-10 13:35:08 -04:00
|
|
|
|
'action': 'login',
|
2014-04-24 15:51:20 -04:00
|
|
|
|
'email': username,
|
|
|
|
|
'password': password,
|
|
|
|
|
'service': 'vimeo',
|
2024-02-24 18:09:04 -05:00
|
|
|
|
'token': viewer['xsrft'],
|
2018-03-05 10:45:47 -05:00
|
|
|
|
}
|
2024-02-24 18:09:04 -05:00
|
|
|
|
self._set_vimeo_cookie('vuid', viewer['vuid'])
|
2018-03-05 10:45:47 -05:00
|
|
|
|
try:
|
|
|
|
|
self._download_webpage(
|
|
|
|
|
self._LOGIN_URL, None, 'Logging in',
|
|
|
|
|
data=urlencode_postdata(data), headers={
|
|
|
|
|
'Content-Type': 'application/x-www-form-urlencoded',
|
|
|
|
|
'Referer': self._LOGIN_URL,
|
|
|
|
|
})
|
|
|
|
|
except ExtractorError as e:
|
2023-07-09 03:53:02 -04:00
|
|
|
|
if isinstance(e.cause, HTTPError) and e.cause.status == 418:
|
2018-03-05 10:45:47 -05:00
|
|
|
|
raise ExtractorError(
|
|
|
|
|
'Unable to log in: bad username or password',
|
|
|
|
|
expected=True)
|
|
|
|
|
raise ExtractorError('Unable to log in')
|
2014-04-24 15:51:20 -04:00
|
|
|
|
|
2022-03-18 16:53:33 -04:00
|
|
|
|
def _real_initialize(self):
|
|
|
|
|
if self._LOGIN_REQUIRED and not self._get_cookies('https://vimeo.com').get('vuid'):
|
|
|
|
|
self._raise_login_required()
|
|
|
|
|
|
2021-04-01 04:28:33 -04:00
|
|
|
|
def _get_video_password(self):
|
2021-05-17 08:23:08 -04:00
|
|
|
|
password = self.get_param('videopassword')
|
2016-06-24 04:48:37 -04:00
|
|
|
|
if password is None:
|
2021-04-01 04:28:33 -04:00
|
|
|
|
raise ExtractorError(
|
|
|
|
|
'This video is protected by a password, use the --video-password option',
|
|
|
|
|
expected=True)
|
|
|
|
|
return password
|
|
|
|
|
|
2024-07-05 14:32:53 -04:00
|
|
|
|
def _verify_video_password(self, video_id, password, token):
|
|
|
|
|
url = f'https://vimeo.com/{video_id}'
|
|
|
|
|
try:
|
|
|
|
|
return self._download_webpage(
|
|
|
|
|
f'{url}/password', video_id,
|
|
|
|
|
'Submitting video password', data=json.dumps({
|
|
|
|
|
'password': password,
|
|
|
|
|
'token': token,
|
|
|
|
|
}, separators=(',', ':')).encode(), headers={
|
|
|
|
|
'Accept': '*/*',
|
|
|
|
|
'Content-Type': 'application/json',
|
|
|
|
|
'Referer': url,
|
|
|
|
|
}, impersonate=True)
|
|
|
|
|
except ExtractorError as error:
|
|
|
|
|
if isinstance(error.cause, HTTPError) and error.cause.status == 418:
|
|
|
|
|
raise ExtractorError('Wrong password', expected=True)
|
|
|
|
|
raise
|
2015-08-10 13:35:08 -04:00
|
|
|
|
|
2019-08-03 05:29:20 -04:00
|
|
|
|
def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
|
|
|
|
|
vimeo_config = self._search_regex(
|
|
|
|
|
r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
|
2022-04-11 16:09:26 -04:00
|
|
|
|
webpage, 'vimeo config', *args, **kwargs)
|
2019-08-03 05:29:20 -04:00
|
|
|
|
if vimeo_config:
|
|
|
|
|
return self._parse_json(vimeo_config, video_id)
|
|
|
|
|
|
2015-11-11 11:32:13 -05:00
|
|
|
|
def _set_vimeo_cookie(self, name, value):
|
|
|
|
|
self._set_cookie('vimeo.com', name, value)
|
|
|
|
|
|
2016-06-11 09:35:08 -04:00
|
|
|
|
def _parse_config(self, config, video_id):
|
2016-12-20 06:25:05 -05:00
|
|
|
|
video_data = config['video']
|
2022-05-16 10:06:36 -04:00
|
|
|
|
video_title = video_data.get('title')
|
2019-04-21 16:05:58 -04:00
|
|
|
|
live_event = video_data.get('live_event') or {}
|
2024-03-01 19:41:32 -05:00
|
|
|
|
live_status = {
|
|
|
|
|
'pending': 'is_upcoming',
|
|
|
|
|
'active': 'is_upcoming',
|
|
|
|
|
'started': 'is_live',
|
|
|
|
|
'ended': 'post_live',
|
|
|
|
|
}.get(live_event.get('status'))
|
|
|
|
|
is_live = live_status == 'is_live'
|
2021-10-21 20:27:15 -04:00
|
|
|
|
request = config.get('request') or {}
|
2016-06-11 09:35:08 -04:00
|
|
|
|
|
|
|
|
|
formats = []
|
2022-02-11 14:03:33 -05:00
|
|
|
|
subtitles = {}
|
|
|
|
|
|
2021-10-21 20:27:15 -04:00
|
|
|
|
config_files = video_data.get('files') or request.get('files') or {}
|
|
|
|
|
for f in (config_files.get('progressive') or []):
|
2016-06-11 09:35:08 -04:00
|
|
|
|
video_url = f.get('url')
|
|
|
|
|
if not video_url:
|
|
|
|
|
continue
|
|
|
|
|
formats.append({
|
|
|
|
|
'url': video_url,
|
2024-06-11 19:09:58 -04:00
|
|
|
|
'format_id': 'http-{}'.format(f.get('quality')),
|
2021-11-28 05:54:02 -05:00
|
|
|
|
'source_preference': 10,
|
2016-06-11 09:35:08 -04:00
|
|
|
|
'width': int_or_none(f.get('width')),
|
|
|
|
|
'height': int_or_none(f.get('height')),
|
|
|
|
|
'fps': int_or_none(f.get('fps')),
|
|
|
|
|
'tbr': int_or_none(f.get('bitrate')),
|
|
|
|
|
})
|
2016-12-20 06:25:05 -05:00
|
|
|
|
|
2019-04-21 16:05:58 -04:00
|
|
|
|
# TODO: fix handling of 308 status code returned for live archive manifest requests
|
2020-05-15 10:57:06 -04:00
|
|
|
|
sep_pattern = r'/sep/video/'
|
2016-12-20 06:25:05 -05:00
|
|
|
|
for files_type in ('hls', 'dash'):
|
2021-10-21 20:27:15 -04:00
|
|
|
|
for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
|
2016-12-20 06:25:05 -05:00
|
|
|
|
manifest_url = cdn_data.get('url')
|
|
|
|
|
if not manifest_url:
|
|
|
|
|
continue
|
2024-06-11 19:09:58 -04:00
|
|
|
|
format_id = f'{files_type}-{cdn_name}'
|
2020-05-15 10:57:06 -04:00
|
|
|
|
sep_manifest_urls = []
|
|
|
|
|
if re.search(sep_pattern, manifest_url):
|
|
|
|
|
for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
|
|
|
|
|
sep_manifest_urls.append((format_id + suffix, re.sub(
|
2024-06-11 19:09:58 -04:00
|
|
|
|
sep_pattern, f'/{repl}/', manifest_url)))
|
2020-05-15 10:57:06 -04:00
|
|
|
|
else:
|
|
|
|
|
sep_manifest_urls = [(format_id, manifest_url)]
|
|
|
|
|
for f_id, m_url in sep_manifest_urls:
|
|
|
|
|
if files_type == 'hls':
|
2022-02-11 14:03:33 -05:00
|
|
|
|
fmts, subs = self._extract_m3u8_formats_and_subtitles(
|
2022-03-02 12:29:01 -05:00
|
|
|
|
m_url, video_id, 'mp4', live=is_live, m3u8_id=f_id,
|
2024-06-11 19:09:58 -04:00
|
|
|
|
note=f'Downloading {cdn_name} m3u8 information',
|
2022-02-11 14:03:33 -05:00
|
|
|
|
fatal=False)
|
|
|
|
|
formats.extend(fmts)
|
|
|
|
|
self._merge_subtitles(subs, target=subtitles)
|
2020-05-15 10:57:06 -04:00
|
|
|
|
elif files_type == 'dash':
|
2019-04-21 12:20:28 -04:00
|
|
|
|
if 'json=1' in m_url:
|
|
|
|
|
real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
|
|
|
|
|
if real_m_url:
|
|
|
|
|
m_url = real_m_url
|
2022-02-11 14:03:33 -05:00
|
|
|
|
fmts, subs = self._extract_mpd_formats_and_subtitles(
|
2017-01-31 08:47:56 -05:00
|
|
|
|
m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
|
2024-06-11 19:09:58 -04:00
|
|
|
|
f'Downloading {cdn_name} MPD information',
|
2017-05-24 11:58:16 -04:00
|
|
|
|
fatal=False)
|
2022-02-11 14:03:33 -05:00
|
|
|
|
formats.extend(fmts)
|
|
|
|
|
self._merge_subtitles(subs, target=subtitles)
|
2016-06-11 09:35:08 -04:00
|
|
|
|
|
2019-04-21 16:05:58 -04:00
|
|
|
|
live_archive = live_event.get('archive') or {}
|
|
|
|
|
live_archive_source_url = live_archive.get('source_url')
|
|
|
|
|
if live_archive_source_url and live_archive.get('status') == 'done':
|
|
|
|
|
formats.append({
|
|
|
|
|
'format_id': 'live-archive-source',
|
|
|
|
|
'url': live_archive_source_url,
|
2021-02-18 17:03:16 -05:00
|
|
|
|
'quality': 10,
|
2019-04-21 16:05:58 -04:00
|
|
|
|
})
|
|
|
|
|
|
2021-10-21 20:27:15 -04:00
|
|
|
|
for tt in (request.get('text_tracks') or []):
|
2022-02-11 14:03:33 -05:00
|
|
|
|
subtitles.setdefault(tt['lang'], []).append({
|
2021-10-21 20:27:15 -04:00
|
|
|
|
'ext': 'vtt',
|
|
|
|
|
'url': urljoin('https://vimeo.com', tt['url']),
|
2022-02-11 14:03:33 -05:00
|
|
|
|
})
|
2016-06-11 09:35:08 -04:00
|
|
|
|
|
2019-04-21 12:20:28 -04:00
|
|
|
|
thumbnails = []
|
|
|
|
|
if not is_live:
|
2021-10-21 20:27:15 -04:00
|
|
|
|
for key, thumb in (video_data.get('thumbs') or {}).items():
|
2019-04-21 12:20:28 -04:00
|
|
|
|
thumbnails.append({
|
|
|
|
|
'id': key,
|
|
|
|
|
'width': int_or_none(key),
|
|
|
|
|
'url': thumb,
|
|
|
|
|
})
|
|
|
|
|
thumbnail = video_data.get('thumbnail')
|
|
|
|
|
if thumbnail:
|
|
|
|
|
thumbnails.append({
|
|
|
|
|
'url': thumbnail,
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
owner = video_data.get('owner') or {}
|
|
|
|
|
video_uploader_url = owner.get('url')
|
|
|
|
|
|
2016-06-11 09:35:08 -04:00
|
|
|
|
return {
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'id': str_or_none(video_data.get('id')) or video_id,
|
2021-12-15 11:00:46 -05:00
|
|
|
|
'title': video_title,
|
2019-04-21 12:20:28 -04:00
|
|
|
|
'uploader': owner.get('name'),
|
|
|
|
|
'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
|
2016-06-11 09:35:08 -04:00
|
|
|
|
'uploader_url': video_uploader_url,
|
2019-04-21 12:20:28 -04:00
|
|
|
|
'thumbnails': thumbnails,
|
2024-07-23 18:00:57 -04:00
|
|
|
|
'duration': int_or_none(video_data.get('duration')),
|
|
|
|
|
'chapters': sorted(traverse_obj(config, (
|
|
|
|
|
'embed', 'chapters', lambda _, v: int(v['timecode']) is not None, {
|
|
|
|
|
'title': ('title', {str}),
|
|
|
|
|
'start_time': ('timecode', {int_or_none}),
|
|
|
|
|
})), key=lambda c: c['start_time']) or None,
|
2016-06-11 09:35:08 -04:00
|
|
|
|
'formats': formats,
|
|
|
|
|
'subtitles': subtitles,
|
2024-03-01 19:41:32 -05:00
|
|
|
|
'live_status': live_status,
|
|
|
|
|
'release_timestamp': traverse_obj(live_event, ('ingest', 'scheduled_start_time', {parse_iso8601})),
|
2022-11-17 00:10:03 -05:00
|
|
|
|
# Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
|
|
|
|
|
# at the same time without actual units specified.
|
|
|
|
|
'_format_sort_fields': ('quality', 'res', 'fps', 'hdr:12', 'source'),
|
2016-06-11 09:35:08 -04:00
|
|
|
|
}
|
|
|
|
|
|
2021-02-19 15:44:36 -05:00
|
|
|
|
def _extract_original_format(self, url, video_id, unlisted_hash=None):
|
|
|
|
|
query = {'action': 'load_download_config'}
|
|
|
|
|
if unlisted_hash:
|
|
|
|
|
query['unlisted_hash'] = unlisted_hash
|
2019-03-10 10:03:32 -04:00
|
|
|
|
download_data = self._download_json(
|
2021-02-19 15:44:36 -05:00
|
|
|
|
url, video_id, fatal=False, query=query,
|
2021-11-05 16:45:08 -04:00
|
|
|
|
headers={'X-Requested-With': 'XMLHttpRequest'},
|
|
|
|
|
expected_status=(403, 404)) or {}
|
|
|
|
|
source_file = download_data.get('source_file')
|
|
|
|
|
download_url = try_get(source_file, lambda x: x['download_url'])
|
|
|
|
|
if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
|
|
|
|
|
source_name = source_file.get('public_name', 'Original')
|
2024-06-11 19:09:58 -04:00
|
|
|
|
if self._is_valid_url(download_url, video_id, f'{source_name} video'):
|
2021-11-05 16:45:08 -04:00
|
|
|
|
ext = (try_get(
|
|
|
|
|
source_file, lambda x: x['extension'],
|
2024-06-11 19:09:58 -04:00
|
|
|
|
str) or determine_ext(
|
2021-11-05 16:45:08 -04:00
|
|
|
|
download_url, None) or 'mp4').lower()
|
|
|
|
|
return {
|
|
|
|
|
'url': download_url,
|
|
|
|
|
'ext': ext,
|
|
|
|
|
'width': int_or_none(source_file.get('width')),
|
|
|
|
|
'height': int_or_none(source_file.get('height')),
|
|
|
|
|
'filesize': parse_filesize(source_file.get('size')),
|
|
|
|
|
'format_id': source_name,
|
|
|
|
|
'quality': 1,
|
|
|
|
|
}
|
2019-03-10 10:03:32 -04:00
|
|
|
|
|
2021-08-01 21:53:12 -04:00
|
|
|
|
jwt_response = self._download_json(
|
|
|
|
|
'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
|
|
|
|
|
if not jwt_response.get('jwt'):
|
|
|
|
|
return
|
2024-06-11 19:09:58 -04:00
|
|
|
|
headers = {'Authorization': 'jwt {}'.format(jwt_response['jwt']), 'Accept': 'application/json'}
|
2021-08-01 21:53:12 -04:00
|
|
|
|
original_response = self._download_json(
|
|
|
|
|
f'https://api.vimeo.com/videos/{video_id}', video_id,
|
2021-11-05 16:45:08 -04:00
|
|
|
|
headers=headers, fatal=False, expected_status=(403, 404)) or {}
|
|
|
|
|
for download_data in original_response.get('download') or []:
|
2021-08-01 21:53:12 -04:00
|
|
|
|
download_url = download_data.get('link')
|
|
|
|
|
if not download_url or download_data.get('quality') != 'source':
|
|
|
|
|
continue
|
2021-11-05 16:45:08 -04:00
|
|
|
|
ext = determine_ext(parse_qs(download_url).get('filename', [''])[0].lower(), default_ext=None)
|
|
|
|
|
if not ext:
|
|
|
|
|
urlh = self._request_webpage(
|
|
|
|
|
HEADRequest(download_url), video_id, fatal=False, note='Determining source extension')
|
|
|
|
|
ext = urlh and urlhandle_detect_ext(urlh)
|
2021-08-01 21:53:12 -04:00
|
|
|
|
return {
|
|
|
|
|
'url': download_url,
|
2021-11-05 16:45:08 -04:00
|
|
|
|
'ext': ext or 'unknown_video',
|
2021-08-01 21:53:12 -04:00
|
|
|
|
'format_id': download_data.get('public_name', 'Original'),
|
|
|
|
|
'width': int_or_none(download_data.get('width')),
|
|
|
|
|
'height': int_or_none(download_data.get('height')),
|
|
|
|
|
'fps': int_or_none(download_data.get('fps')),
|
|
|
|
|
'filesize': int_or_none(download_data.get('size')),
|
|
|
|
|
'quality': 1,
|
|
|
|
|
}
|
|
|
|
|
|
2014-04-24 15:51:20 -04:00
|
|
|
|
|
2015-02-15 12:52:07 -05:00
|
|
|
|
class VimeoIE(VimeoBaseInfoExtractor):
|
2013-06-23 14:18:21 -04:00
|
|
|
|
"""Information extractor for vimeo.com."""
|
|
|
|
|
|
|
|
|
|
# _VALID_URL matches Vimeo URLs
|
2013-12-21 21:17:56 -05:00
|
|
|
|
_VALID_URL = r'''(?x)
|
2023-02-17 06:21:34 -05:00
|
|
|
|
https?://
|
|
|
|
|
(?:
|
|
|
|
|
(?:
|
|
|
|
|
www|
|
|
|
|
|
player
|
|
|
|
|
)
|
|
|
|
|
\.
|
|
|
|
|
)?
|
|
|
|
|
vimeo\.com/
|
|
|
|
|
(?:
|
|
|
|
|
(?P<u>user)|
|
|
|
|
|
(?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
|
|
|
|
|
(?:.*?/)??
|
|
|
|
|
(?P<q>
|
|
|
|
|
(?:
|
|
|
|
|
play_redirect_hls|
|
|
|
|
|
moogaloop\.swf)\?clip_id=
|
|
|
|
|
)?
|
|
|
|
|
(?:videos?/)?
|
|
|
|
|
)
|
|
|
|
|
(?P<id>[0-9]+)
|
|
|
|
|
(?(u)
|
|
|
|
|
/(?!videos|likes)[^/?#]+/?|
|
|
|
|
|
(?(q)|/(?P<unlisted_hash>[\da-f]{10}))?
|
|
|
|
|
)
|
|
|
|
|
(?:(?(q)[&]|(?(u)|/?)[?]).*?)?(?:[#].*)?$
|
|
|
|
|
'''
|
2014-01-06 17:38:16 -05:00
|
|
|
|
IE_NAME = 'vimeo'
|
2022-07-31 21:23:25 -04:00
|
|
|
|
_EMBED_REGEX = [
|
|
|
|
|
# iframe
|
|
|
|
|
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
|
|
|
|
|
# Embedded (swf embed) Vimeo player
|
|
|
|
|
r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
|
|
|
|
|
# Non-standard embedded Vimeo player
|
|
|
|
|
r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
|
|
|
|
|
]
|
2013-08-21 07:48:19 -04:00
|
|
|
|
_TESTS = [
|
|
|
|
|
{
|
2014-01-06 17:38:16 -05:00
|
|
|
|
'url': 'http://vimeo.com/56015672#at=0',
|
|
|
|
|
'md5': '8879b6cc097e987f02484baf890129e5',
|
|
|
|
|
'info_dict': {
|
2014-02-17 05:44:24 -05:00
|
|
|
|
'id': '56015672',
|
|
|
|
|
'ext': 'mp4',
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'description': 'md5:2d3305bad981a06ff79f027f19865021',
|
2017-01-31 12:58:02 -05:00
|
|
|
|
'timestamp': 1355990239,
|
2015-10-10 16:22:42 -04:00
|
|
|
|
'upload_date': '20121220',
|
2017-01-02 07:08:07 -05:00
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
|
2015-10-10 16:22:42 -04:00
|
|
|
|
'uploader_id': 'user7108434',
|
|
|
|
|
'uploader': 'Filippo Valsorda',
|
|
|
|
|
'duration': 10,
|
2017-01-31 12:49:28 -05:00
|
|
|
|
'license': 'by-sa',
|
2013-08-21 07:48:19 -04:00
|
|
|
|
},
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'params': {
|
|
|
|
|
'format': 'best[protocol=https]',
|
|
|
|
|
},
|
2024-06-11 19:09:58 -04:00
|
|
|
|
'skip': 'No longer available',
|
2013-08-21 07:48:19 -04:00
|
|
|
|
},
|
2013-09-03 04:48:56 -04:00
|
|
|
|
{
|
2014-01-06 17:38:16 -05:00
|
|
|
|
'url': 'http://player.vimeo.com/video/54469442',
|
2023-02-10 08:50:29 -05:00
|
|
|
|
'md5': '619b811a4417aa4abe78dc653becf511',
|
2014-01-06 17:38:16 -05:00
|
|
|
|
'note': 'Videos that embed the url in the player page',
|
|
|
|
|
'info_dict': {
|
2014-05-04 16:27:56 -04:00
|
|
|
|
'id': '54469442',
|
|
|
|
|
'ext': 'mp4',
|
2014-07-21 07:11:24 -04:00
|
|
|
|
'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
|
2021-04-01 04:28:33 -04:00
|
|
|
|
'uploader': 'Business of Software',
|
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
|
|
|
|
|
'uploader_id': 'businessofsoftware',
|
2014-05-09 14:46:40 -04:00
|
|
|
|
'duration': 3610,
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d_1280',
|
2013-09-03 04:48:56 -04:00
|
|
|
|
},
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'params': {
|
|
|
|
|
'format': 'best[protocol=https]',
|
|
|
|
|
},
|
2013-10-23 10:31:53 -04:00
|
|
|
|
},
|
|
|
|
|
{
|
2014-01-06 17:38:16 -05:00
|
|
|
|
'url': 'http://vimeo.com/68375962',
|
|
|
|
|
'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
|
|
|
|
|
'note': 'Video protected with password',
|
|
|
|
|
'info_dict': {
|
2014-05-04 16:27:56 -04:00
|
|
|
|
'id': '68375962',
|
|
|
|
|
'ext': 'mp4',
|
2020-09-02 16:37:35 -04:00
|
|
|
|
'title': 'youtube-dl password protected test video',
|
2017-01-31 12:58:02 -05:00
|
|
|
|
'timestamp': 1371200155,
|
2014-01-06 17:38:16 -05:00
|
|
|
|
'upload_date': '20130614',
|
2017-01-02 07:08:07 -05:00
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
|
2014-01-06 17:38:16 -05:00
|
|
|
|
'uploader_id': 'user18948128',
|
|
|
|
|
'uploader': 'Jaime Marquínez Ferrándiz',
|
2014-05-09 14:46:40 -04:00
|
|
|
|
'duration': 10,
|
2023-02-10 08:50:29 -05:00
|
|
|
|
'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
|
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'view_count': int,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'like_count': int,
|
2013-10-23 10:31:53 -04:00
|
|
|
|
},
|
2014-01-06 17:38:16 -05:00
|
|
|
|
'params': {
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'format': 'best[protocol=https]',
|
2020-09-02 16:37:35 -04:00
|
|
|
|
'videopassword': 'youtube-dl',
|
2013-10-23 10:31:53 -04:00
|
|
|
|
},
|
|
|
|
|
},
|
2014-08-03 13:04:47 -04:00
|
|
|
|
{
|
|
|
|
|
'url': 'http://vimeo.com/channels/keypeele/75629013',
|
|
|
|
|
'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '75629013',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Key & Peele: Terrorist Interrogation',
|
2023-02-10 08:50:29 -05:00
|
|
|
|
'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
|
2017-01-02 07:08:07 -05:00
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
|
2014-08-03 13:04:47 -04:00
|
|
|
|
'uploader_id': 'atencio',
|
|
|
|
|
'uploader': 'Peter Atencio',
|
2018-09-14 14:24:48 -04:00
|
|
|
|
'channel_id': 'keypeele',
|
|
|
|
|
'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
|
2017-01-31 12:58:02 -05:00
|
|
|
|
'timestamp': 1380339469,
|
|
|
|
|
'upload_date': '20130928',
|
2014-08-03 13:04:47 -04:00
|
|
|
|
'duration': 187,
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/450239872-a05512d9b1e55d707a7c04365c10980f327b06d966351bc403a5d5d65c95e572-d_1280',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'like_count': int,
|
2014-08-03 13:04:47 -04:00
|
|
|
|
},
|
2021-11-05 16:45:08 -04:00
|
|
|
|
'params': {'format': 'http-1080p'},
|
2014-08-03 13:04:47 -04:00
|
|
|
|
},
|
2014-02-03 08:02:58 -05:00
|
|
|
|
{
|
|
|
|
|
'url': 'http://vimeo.com/76979871',
|
|
|
|
|
'note': 'Video with subtitles',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '76979871',
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'ext': 'mov',
|
2014-02-03 08:02:58 -05:00
|
|
|
|
'title': 'The New Vimeo Player (You Know, For Videos)',
|
|
|
|
|
'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
|
2017-01-31 12:58:02 -05:00
|
|
|
|
'timestamp': 1381846109,
|
2014-02-03 08:02:58 -05:00
|
|
|
|
'upload_date': '20131015',
|
2017-01-02 07:08:07 -05:00
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
|
2014-02-03 08:02:58 -05:00
|
|
|
|
'uploader_id': 'staff',
|
|
|
|
|
'uploader': 'Vimeo Staff',
|
2014-05-09 14:46:40 -04:00
|
|
|
|
'duration': 62,
|
2021-10-21 20:27:15 -04:00
|
|
|
|
'subtitles': {
|
|
|
|
|
'de': [{'ext': 'vtt'}],
|
|
|
|
|
'en': [{'ext': 'vtt'}],
|
|
|
|
|
'es': [{'ext': 'vtt'}],
|
|
|
|
|
'fr': [{'ext': 'vtt'}],
|
|
|
|
|
},
|
2021-11-05 16:45:08 -04:00
|
|
|
|
},
|
|
|
|
|
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
|
2014-02-03 08:02:58 -05:00
|
|
|
|
},
|
2014-10-17 09:49:16 -04:00
|
|
|
|
{
|
|
|
|
|
# from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
|
|
|
|
|
'url': 'https://player.vimeo.com/video/98044508',
|
|
|
|
|
'note': 'The js code contains assignments to the same variable as the config',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '98044508',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Pier Solar OUYA Official Trailer',
|
|
|
|
|
'uploader': 'Tulio Gonçalves',
|
2017-01-02 07:08:07 -05:00
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
|
2014-10-17 09:49:16 -04:00
|
|
|
|
'uploader_id': 'user28849593',
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'duration': 118,
|
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/478636036-c18440305ef3df9decfb6bf207a61fe39d2d17fa462a96f6f2d93d30492b037d-d_1280',
|
2014-10-17 09:49:16 -04:00
|
|
|
|
},
|
|
|
|
|
},
|
2015-12-16 11:00:17 -05:00
|
|
|
|
{
|
|
|
|
|
# contains original format
|
|
|
|
|
'url': 'https://vimeo.com/33951933',
|
2017-01-11 10:57:08 -05:00
|
|
|
|
'md5': '53c688fa95a55bf4b7293d37a89c5c53',
|
2015-12-16 11:00:17 -05:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '33951933',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
|
|
|
|
|
'uploader': 'The DMCI',
|
2017-01-02 07:08:07 -05:00
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
|
2015-12-16 11:00:17 -05:00
|
|
|
|
'uploader_id': 'dmci',
|
2017-01-31 12:58:02 -05:00
|
|
|
|
'timestamp': 1324343742,
|
2015-12-16 11:00:17 -05:00
|
|
|
|
'upload_date': '20111220',
|
|
|
|
|
'description': 'md5:ae23671e82d05415868f7ad1aec21147',
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'duration': 60,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/231174622-dd07f015e9221ff529d451e1cc31c982b5d87bfafa48c4189b1da72824ee289a-d_1280',
|
|
|
|
|
'like_count': int,
|
2015-12-16 11:00:17 -05:00
|
|
|
|
},
|
|
|
|
|
},
|
2021-08-01 21:53:12 -04:00
|
|
|
|
{
|
|
|
|
|
'note': 'Contains original format not accessible in webpage',
|
|
|
|
|
'url': 'https://vimeo.com/393756517',
|
|
|
|
|
'md5': 'c464af248b592190a5ffbb5d33f382b0',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '393756517',
|
|
|
|
|
'ext': 'mov',
|
|
|
|
|
'timestamp': 1582642091,
|
|
|
|
|
'uploader_id': 'frameworkla',
|
|
|
|
|
'title': 'Straight To Hell - Sabrina: Netflix',
|
|
|
|
|
'uploader': 'Framework Studio',
|
|
|
|
|
'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
|
|
|
|
|
'upload_date': '20200225',
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'duration': 176,
|
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/859377297-836494a4ef775e9d4edbace83937d9ad34dc846c688c0c419c0e87f7ab06c4b3-d_1280',
|
|
|
|
|
'uploader_url': 'https://vimeo.com/frameworkla',
|
2021-08-01 21:53:12 -04:00
|
|
|
|
},
|
|
|
|
|
},
|
2016-06-22 13:51:36 -04:00
|
|
|
|
{
|
|
|
|
|
# only available via https://vimeo.com/channels/tributes/6213729 and
|
|
|
|
|
# not via https://vimeo.com/6213729
|
|
|
|
|
'url': 'https://vimeo.com/channels/tributes/6213729',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '6213729',
|
2018-09-14 14:24:48 -04:00
|
|
|
|
'ext': 'mp4',
|
2016-06-22 13:51:36 -04:00
|
|
|
|
'title': 'Vimeo Tribute: The Shining',
|
|
|
|
|
'uploader': 'Casey Donahue',
|
2017-01-02 07:08:07 -05:00
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
|
2016-06-22 13:51:36 -04:00
|
|
|
|
'uploader_id': 'caseydonahue',
|
2018-09-14 14:24:48 -04:00
|
|
|
|
'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
|
|
|
|
|
'channel_id': 'tributes',
|
2017-01-31 12:58:02 -05:00
|
|
|
|
'timestamp': 1250886430,
|
2016-06-22 13:51:36 -04:00
|
|
|
|
'upload_date': '20090821',
|
|
|
|
|
'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'duration': 321,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/22728298-bfc22146f930de7cf497821c7b0b9f168099201ecca39b00b6bd31fcedfca7a6-d_1280',
|
|
|
|
|
'like_count': int,
|
2016-06-22 13:51:36 -04:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
|
|
|
|
},
|
2016-10-23 07:48:50 -04:00
|
|
|
|
{
|
2017-01-19 04:18:13 -05:00
|
|
|
|
# redirects to ondemand extractor and should be passed through it
|
2016-10-23 07:48:50 -04:00
|
|
|
|
# for successful extraction
|
|
|
|
|
'url': 'https://vimeo.com/73445910',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '73445910',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'The Reluctant Revolutionary',
|
|
|
|
|
'uploader': '10Ft Films',
|
2017-01-02 07:08:07 -05:00
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
|
2016-10-23 07:48:50 -04:00
|
|
|
|
'uploader_id': 'tenfootfilms',
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
|
|
|
|
|
'upload_date': '20130830',
|
|
|
|
|
'timestamp': 1377853339,
|
2016-10-23 07:48:50 -04:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2021-04-01 04:28:33 -04:00
|
|
|
|
'skip': 'this page is no longer available.',
|
2016-10-23 07:48:50 -04:00
|
|
|
|
},
|
2019-01-17 03:44:08 -05:00
|
|
|
|
{
|
|
|
|
|
'url': 'http://player.vimeo.com/video/68375962',
|
|
|
|
|
'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '68375962',
|
|
|
|
|
'ext': 'mp4',
|
2020-09-02 16:37:35 -04:00
|
|
|
|
'title': 'youtube-dl password protected test video',
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'timestamp': 1371200155,
|
|
|
|
|
'upload_date': '20130614',
|
2019-01-17 03:44:08 -05:00
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
|
|
|
|
|
'uploader_id': 'user18948128',
|
|
|
|
|
'uploader': 'Jaime Marquínez Ferrándiz',
|
|
|
|
|
'duration': 10,
|
2023-02-10 08:50:29 -05:00
|
|
|
|
'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
|
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'view_count': int,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'like_count': int,
|
2019-01-17 03:44:08 -05:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'format': 'best[protocol=https]',
|
2020-09-02 16:37:35 -04:00
|
|
|
|
'videopassword': 'youtube-dl',
|
2019-01-17 03:44:08 -05:00
|
|
|
|
},
|
|
|
|
|
},
|
2016-06-22 13:51:36 -04:00
|
|
|
|
{
|
|
|
|
|
'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2015-10-20 10:38:44 -04:00
|
|
|
|
{
|
|
|
|
|
'url': 'https://vimeo.com/109815029',
|
|
|
|
|
'note': 'Video not completely processed, "failed" seed status',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2015-11-19 11:31:16 -05:00
|
|
|
|
{
|
|
|
|
|
'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2016-06-22 14:28:36 -04:00
|
|
|
|
{
|
|
|
|
|
'url': 'https://vimeo.com/album/2632481/video/79010983',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2021-01-28 07:33:48 -05:00
|
|
|
|
{
|
|
|
|
|
'url': 'https://vimeo.com/showcase/3253534/video/119195465',
|
|
|
|
|
'note': 'A video in a password protected album (showcase)',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '119195465',
|
|
|
|
|
'ext': 'mp4',
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
|
2021-01-28 07:33:48 -05:00
|
|
|
|
'uploader': 'Philipp Hagemeister',
|
|
|
|
|
'uploader_id': 'user20132939',
|
|
|
|
|
'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
|
|
|
|
|
'upload_date': '20150209',
|
|
|
|
|
'timestamp': 1423518307,
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/default_1280',
|
|
|
|
|
'duration': 10,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'uploader_url': 'https://vimeo.com/user20132939',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'comment_count': int,
|
2021-01-28 07:33:48 -05:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'format': 'best[protocol=https]',
|
|
|
|
|
'videopassword': 'youtube-dl',
|
|
|
|
|
},
|
|
|
|
|
},
|
2016-01-08 16:07:29 -05:00
|
|
|
|
{
|
|
|
|
|
# source file returns 403: Forbidden
|
|
|
|
|
'url': 'https://vimeo.com/7809605',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2016-04-18 11:40:28 -04:00
|
|
|
|
{
|
2021-11-05 16:24:05 -04:00
|
|
|
|
'note': 'Direct URL with hash',
|
2016-04-18 11:40:28 -04:00
|
|
|
|
'url': 'https://vimeo.com/160743502/abd0e13fb4',
|
2021-11-05 16:24:05 -04:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '160743502',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'uploader': 'Julian Tryba',
|
|
|
|
|
'uploader_id': 'aliniamedia',
|
|
|
|
|
'title': 'Harrisville New Hampshire',
|
|
|
|
|
'timestamp': 1459259666,
|
|
|
|
|
'upload_date': '20160329',
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'release_timestamp': 1459259666,
|
|
|
|
|
'license': 'by-nc',
|
|
|
|
|
'duration': 159,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/562802436-585eeb13b5020c6ac0f171a2234067938098f84737787df05ff0d767f6d54ee9-d_1280',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'uploader_url': 'https://vimeo.com/aliniamedia',
|
|
|
|
|
'release_date': '20160329',
|
2021-11-05 16:24:05 -04:00
|
|
|
|
},
|
2021-11-05 16:45:08 -04:00
|
|
|
|
'params': {'skip_download': True},
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
'url': 'https://vimeo.com/138909882',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '138909882',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Eastnor Castle 2015 Firework Champions - The Promo!',
|
|
|
|
|
'description': 'md5:5967e090768a831488f6e74b7821b3c1',
|
|
|
|
|
'uploader_id': 'fireworkchampions',
|
|
|
|
|
'uploader': 'Firework Champions',
|
|
|
|
|
'upload_date': '20150910',
|
|
|
|
|
'timestamp': 1441901895,
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
'format': 'Original',
|
|
|
|
|
},
|
2021-02-19 15:44:36 -05:00
|
|
|
|
},
|
2021-11-22 14:39:17 -05:00
|
|
|
|
{
|
|
|
|
|
'url': 'https://vimeo.com/channels/staffpicks/143603739',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '143603739',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'uploader': 'Karim Huu Do',
|
|
|
|
|
'timestamp': 1445846953,
|
|
|
|
|
'upload_date': '20151026',
|
|
|
|
|
'title': 'The Shoes - Submarine Feat. Blaine Harrison',
|
|
|
|
|
'uploader_id': 'karimhd',
|
|
|
|
|
'description': 'md5:8e2eea76de4504c2e8020a9bcfa1e843',
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'channel_id': 'staffpicks',
|
|
|
|
|
'duration': 336,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/541243181-b593db36a16db2f0096f655da3f5a4dc46b8766d77b0f440df937ecb0c418347-d_1280',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'uploader_url': 'https://vimeo.com/karimhd',
|
|
|
|
|
'channel_url': 'https://vimeo.com/channels/staffpicks',
|
2021-11-22 14:39:17 -05:00
|
|
|
|
},
|
|
|
|
|
'params': {'skip_download': 'm3u8'},
|
|
|
|
|
},
|
2021-02-19 15:44:36 -05:00
|
|
|
|
{
|
|
|
|
|
# requires passing unlisted_hash(a52724358e) to load_download_config request
|
|
|
|
|
'url': 'https://vimeo.com/392479337/a52724358e',
|
|
|
|
|
'only_matching': True,
|
2021-11-05 16:45:08 -04:00
|
|
|
|
},
|
2022-03-04 12:01:04 -05:00
|
|
|
|
{
|
|
|
|
|
# similar, but all numeric: ID must be 581039021, not 9603038895
|
|
|
|
|
# issue #29690
|
|
|
|
|
'url': 'https://vimeo.com/581039021/9603038895',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '581039021',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'timestamp': 1627621014,
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'release_timestamp': 1627621014,
|
|
|
|
|
'duration': 976,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/1202249320-4ddb2c30398c0dc0ee059172d1bd5ea481ad12f0e0e3ad01d2266f56c744b015-d_1280',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'uploader_url': 'https://vimeo.com/txwestcapital',
|
|
|
|
|
'release_date': '20210730',
|
|
|
|
|
'uploader': 'Christopher Inks',
|
|
|
|
|
'title': 'Thursday, July 29, 2021 BMA Evening Video Update',
|
|
|
|
|
'uploader_id': 'txwestcapital',
|
|
|
|
|
'upload_date': '20210730',
|
2022-03-04 12:01:04 -05:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2023-02-17 06:21:34 -05:00
|
|
|
|
},
|
2024-07-23 18:00:57 -04:00
|
|
|
|
{
|
|
|
|
|
# chapters must be sorted, see: https://github.com/yt-dlp/yt-dlp/issues/5308
|
|
|
|
|
'url': 'https://player.vimeo.com/video/756714419',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '756714419',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Dr Arielle Schwartz - Therapeutic yoga for optimum sleep',
|
|
|
|
|
'uploader': 'Alex Howard',
|
|
|
|
|
'uploader_id': 'user54729178',
|
|
|
|
|
'uploader_url': 'https://vimeo.com/user54729178',
|
|
|
|
|
'thumbnail': r're:https://i\.vimeocdn\.com/video/1520099929-[\da-f]+-d_1280',
|
|
|
|
|
'duration': 2636,
|
|
|
|
|
'chapters': [
|
|
|
|
|
{'start_time': 0, 'end_time': 10, 'title': '<Untitled Chapter 1>'},
|
|
|
|
|
{'start_time': 10, 'end_time': 106, 'title': 'Welcoming Dr Arielle Schwartz'},
|
|
|
|
|
{'start_time': 106, 'end_time': 305, 'title': 'What is therapeutic yoga?'},
|
|
|
|
|
{'start_time': 305, 'end_time': 594, 'title': 'Vagal toning practices'},
|
|
|
|
|
{'start_time': 594, 'end_time': 888, 'title': 'Trauma and difficulty letting go'},
|
|
|
|
|
{'start_time': 888, 'end_time': 1059, 'title': "Dr Schwartz' insomnia experience"},
|
|
|
|
|
{'start_time': 1059, 'end_time': 1471, 'title': 'A strategy for helping sleep issues'},
|
|
|
|
|
{'start_time': 1471, 'end_time': 1667, 'title': 'Yoga nidra'},
|
|
|
|
|
{'start_time': 1667, 'end_time': 2121, 'title': 'Wisdom in stillness'},
|
|
|
|
|
{'start_time': 2121, 'end_time': 2386, 'title': 'What helps us be more able to let go?'},
|
|
|
|
|
{'start_time': 2386, 'end_time': 2510, 'title': 'Practical tips to help ourselves'},
|
|
|
|
|
{'start_time': 2510, 'end_time': 2636, 'title': 'Where to find out more'},
|
|
|
|
|
],
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'http_headers': {'Referer': 'https://sleepsuperconference.com'},
|
|
|
|
|
'skip_download': 'm3u8',
|
|
|
|
|
},
|
|
|
|
|
'expected_warnings': ['Failed to parse XML: not well-formed'],
|
|
|
|
|
},
|
2023-02-17 06:21:34 -05:00
|
|
|
|
{
|
|
|
|
|
# user playlist alias -> https://vimeo.com/258705797
|
|
|
|
|
'url': 'https://vimeo.com/user26785108/newspiritualguide',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2019-01-20 06:21:31 -05:00
|
|
|
|
# https://gettingthingsdone.com/workflowmap/
|
|
|
|
|
# vimeo embed with check-password page protected by Referer header
|
2013-08-21 07:48:19 -04:00
|
|
|
|
]
|
2013-06-23 14:18:21 -04:00
|
|
|
|
|
2022-07-31 21:23:25 -04:00
|
|
|
|
@classmethod
|
|
|
|
|
def _extract_embed_urls(cls, url, webpage):
|
|
|
|
|
for embed_url in super()._extract_embed_urls(url, webpage):
|
|
|
|
|
yield cls._smuggle_referrer(embed_url, url)
|
2015-06-21 06:23:58 -04:00
|
|
|
|
|
2022-08-04 06:15:17 -04:00
|
|
|
|
@classmethod
|
|
|
|
|
def _extract_url(cls, url, webpage):
|
|
|
|
|
return next(cls._extract_embed_urls(url, webpage), None)
|
|
|
|
|
|
2019-01-20 06:21:31 -05:00
|
|
|
|
def _verify_player_video_password(self, url, video_id, headers):
|
2021-04-01 04:28:33 -04:00
|
|
|
|
password = self._get_video_password()
|
2019-01-17 03:44:08 -05:00
|
|
|
|
data = urlencode_postdata({
|
|
|
|
|
'password': base64.b64encode(password.encode()),
|
|
|
|
|
})
|
2019-01-20 06:21:31 -05:00
|
|
|
|
headers = merge_dicts(headers, {
|
|
|
|
|
'Content-Type': 'application/x-www-form-urlencoded',
|
|
|
|
|
})
|
|
|
|
|
checked = self._download_json(
|
2024-06-11 19:09:58 -04:00
|
|
|
|
f'{urllib.parse.urlsplit(url)._replace(query=None).geturl()}/check-password',
|
2022-05-17 19:41:47 -04:00
|
|
|
|
video_id, 'Verifying the password', data=data, headers=headers)
|
2019-01-20 06:21:31 -05:00
|
|
|
|
if checked is False:
|
|
|
|
|
raise ExtractorError('Wrong video password', expected=True)
|
|
|
|
|
return checked
|
2014-01-07 03:51:57 -05:00
|
|
|
|
|
2024-07-05 14:32:53 -04:00
|
|
|
|
def _call_videos_api(self, video_id, jwt_token, unlisted_hash=None):
|
|
|
|
|
return self._download_json(
|
|
|
|
|
join_nonempty(f'https://api.vimeo.com/videos/{video_id}', unlisted_hash, delim=':'),
|
|
|
|
|
video_id, 'Downloading API JSON', headers={
|
|
|
|
|
'Authorization': f'jwt {jwt_token}',
|
2024-02-02 16:15:04 -05:00
|
|
|
|
'Accept': 'application/json',
|
2021-10-21 20:27:15 -04:00
|
|
|
|
}, query={
|
|
|
|
|
'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
|
|
|
|
|
})
|
2024-07-05 14:32:53 -04:00
|
|
|
|
|
|
|
|
|
def _extract_from_api(self, video_id, unlisted_hash=None):
|
|
|
|
|
viewer = self._download_json(
|
|
|
|
|
'https://vimeo.com/_next/viewer', video_id, 'Downloading viewer info')
|
|
|
|
|
|
|
|
|
|
for retry in (False, True):
|
|
|
|
|
try:
|
|
|
|
|
video = self._call_videos_api(video_id, viewer['jwt'], unlisted_hash)
|
|
|
|
|
except ExtractorError as e:
|
|
|
|
|
if (not retry and isinstance(e.cause, HTTPError) and e.cause.status == 400
|
|
|
|
|
and 'password' in traverse_obj(
|
|
|
|
|
e.cause.response.read(),
|
|
|
|
|
({bytes.decode}, {json.loads}, 'invalid_parameters', ..., 'field'),
|
|
|
|
|
)):
|
|
|
|
|
self._verify_video_password(
|
|
|
|
|
video_id, self._get_video_password(), viewer['xsrft'])
|
|
|
|
|
continue
|
|
|
|
|
raise
|
|
|
|
|
|
2021-10-21 20:27:15 -04:00
|
|
|
|
info = self._parse_config(self._download_json(
|
|
|
|
|
video['config_url'], video_id), video_id)
|
|
|
|
|
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
|
|
|
|
|
|
2021-01-28 07:33:48 -05:00
|
|
|
|
def _try_album_password(self, url):
|
|
|
|
|
album_id = self._search_regex(
|
|
|
|
|
r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
|
|
|
|
|
if not album_id:
|
|
|
|
|
return
|
|
|
|
|
viewer = self._download_json(
|
|
|
|
|
'https://vimeo.com/_rv/viewer', album_id, fatal=False)
|
|
|
|
|
if not viewer:
|
|
|
|
|
webpage = self._download_webpage(url, album_id)
|
|
|
|
|
viewer = self._parse_json(self._search_regex(
|
|
|
|
|
r'bootstrap_data\s*=\s*({.+?})</script>',
|
|
|
|
|
webpage, 'bootstrap data'), album_id)['viewer']
|
|
|
|
|
jwt = viewer['jwt']
|
|
|
|
|
album = self._download_json(
|
|
|
|
|
'https://api.vimeo.com/albums/' + album_id,
|
2024-02-02 16:15:04 -05:00
|
|
|
|
album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
|
2021-01-28 07:33:48 -05:00
|
|
|
|
query={'fields': 'description,name,privacy'})
|
|
|
|
|
if try_get(album, lambda x: x['privacy']['view']) == 'password':
|
2021-05-17 08:23:08 -04:00
|
|
|
|
password = self.get_param('videopassword')
|
2021-01-28 07:33:48 -05:00
|
|
|
|
if not password:
|
|
|
|
|
raise ExtractorError(
|
|
|
|
|
'This album is protected by a password, use the --video-password option',
|
|
|
|
|
expected=True)
|
|
|
|
|
self._set_vimeo_cookie('vuid', viewer['vuid'])
|
|
|
|
|
try:
|
|
|
|
|
self._download_json(
|
2024-06-11 19:09:58 -04:00
|
|
|
|
f'https://vimeo.com/showcase/{album_id}/auth',
|
2021-01-28 07:33:48 -05:00
|
|
|
|
album_id, 'Verifying the password', data=urlencode_postdata({
|
|
|
|
|
'password': password,
|
|
|
|
|
'token': viewer['xsrft'],
|
|
|
|
|
}), headers={
|
|
|
|
|
'X-Requested-With': 'XMLHttpRequest',
|
|
|
|
|
})
|
|
|
|
|
except ExtractorError as e:
|
2023-07-09 03:53:02 -04:00
|
|
|
|
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
|
2021-01-28 07:33:48 -05:00
|
|
|
|
raise ExtractorError('Wrong password', expected=True)
|
|
|
|
|
raise
|
|
|
|
|
|
2013-12-10 14:43:16 -05:00
|
|
|
|
def _real_extract(self, url):
|
2022-05-17 19:41:47 -04:00
|
|
|
|
url, data, headers = self._unsmuggle_headers(url)
|
2014-08-25 03:35:37 -04:00
|
|
|
|
if 'Referer' not in headers:
|
|
|
|
|
headers['Referer'] = url
|
2013-10-15 06:05:13 -04:00
|
|
|
|
|
2013-06-23 14:18:21 -04:00
|
|
|
|
# Extract ID from URL
|
2021-11-05 16:24:05 -04:00
|
|
|
|
mobj = self._match_valid_url(url).groupdict()
|
|
|
|
|
video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
|
2021-04-01 04:28:33 -04:00
|
|
|
|
if unlisted_hash:
|
2021-10-21 20:27:15 -04:00
|
|
|
|
return self._extract_from_api(video_id, unlisted_hash)
|
2021-04-01 04:28:33 -04:00
|
|
|
|
|
2022-11-20 19:55:57 -05:00
|
|
|
|
if any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
|
2015-04-28 08:56:48 -04:00
|
|
|
|
url = 'https://vimeo.com/' + video_id
|
2013-06-23 14:18:21 -04:00
|
|
|
|
|
2021-01-28 07:33:48 -05:00
|
|
|
|
self._try_album_password(url)
|
2024-07-01 16:55:18 -04:00
|
|
|
|
is_secure = urllib.parse.urlparse(url).scheme == 'https'
|
2014-03-08 06:24:43 -05:00
|
|
|
|
try:
|
2019-11-27 07:57:30 -05:00
|
|
|
|
# Retrieve video webpage to extract further information
|
|
|
|
|
webpage, urlh = self._download_webpage_handle(
|
2024-07-01 16:55:18 -04:00
|
|
|
|
url, video_id, headers=headers, impersonate=is_secure)
|
2023-07-09 03:53:02 -04:00
|
|
|
|
redirect_url = urlh.url
|
2024-07-01 16:55:18 -04:00
|
|
|
|
except ExtractorError as error:
|
|
|
|
|
if not isinstance(error.cause, HTTPError) or error.cause.status not in (403, 429):
|
|
|
|
|
raise
|
|
|
|
|
errmsg = error.cause.response.read()
|
|
|
|
|
if b'Because of its privacy settings, this video cannot be played here' in errmsg:
|
|
|
|
|
raise ExtractorError(
|
|
|
|
|
'Cannot download embed-only video without embedding URL. Please call yt-dlp '
|
|
|
|
|
'with the URL of the page that embeds this video.', expected=True)
|
|
|
|
|
# 403 == vimeo.com TLS fingerprint or DC IP block; 429 == player.vimeo.com TLS FP block
|
|
|
|
|
status = error.cause.status
|
|
|
|
|
dcip_msg = 'If you are using a data center IP or VPN/proxy, your IP may be blocked'
|
|
|
|
|
if target := error.cause.response.extensions.get('impersonate'):
|
|
|
|
|
raise ExtractorError(
|
|
|
|
|
f'Got HTTP Error {status} when using impersonate target "{target}". {dcip_msg}')
|
|
|
|
|
elif not is_secure:
|
|
|
|
|
raise ExtractorError(f'Got HTTP Error {status}. {dcip_msg}', expected=True)
|
|
|
|
|
raise ExtractorError(
|
|
|
|
|
'This request has been blocked due to its TLS fingerprint. Install a '
|
|
|
|
|
'required impersonation dependency if possible, or else if you are okay with '
|
|
|
|
|
f'{self._downloader._format_err("compromising your security/cookies", "light red")}, '
|
|
|
|
|
f'try replacing "https:" with "http:" in the input URL. {dcip_msg}.', expected=True)
|
2013-06-23 14:18:21 -04:00
|
|
|
|
|
2021-10-21 20:27:15 -04:00
|
|
|
|
if '://player.vimeo.com/video/' in url:
|
2023-02-10 08:50:29 -05:00
|
|
|
|
config = self._search_json(
|
|
|
|
|
r'\b(?:playerC|c)onfig\s*=', webpage, 'info section', video_id)
|
2021-10-21 20:27:15 -04:00
|
|
|
|
if config.get('view') == 4:
|
|
|
|
|
config = self._verify_player_video_password(
|
|
|
|
|
redirect_url, video_id, headers)
|
2022-11-17 00:10:03 -05:00
|
|
|
|
return self._parse_config(config, video_id)
|
2021-10-21 20:27:15 -04:00
|
|
|
|
|
2019-08-03 05:29:20 -04:00
|
|
|
|
vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
|
2015-03-26 17:05:08 -04:00
|
|
|
|
if vimeo_config:
|
2021-10-21 20:27:15 -04:00
|
|
|
|
seed_status = vimeo_config.get('seed_status') or {}
|
2015-03-26 17:05:08 -04:00
|
|
|
|
if seed_status.get('state') == 'failed':
|
|
|
|
|
raise ExtractorError(
|
2024-06-11 19:09:58 -04:00
|
|
|
|
'{} said: {}'.format(self.IE_NAME, seed_status['title']),
|
2015-03-26 17:05:08 -04:00
|
|
|
|
expected=True)
|
|
|
|
|
|
2017-01-31 12:49:28 -05:00
|
|
|
|
cc_license = None
|
2017-01-31 12:58:02 -05:00
|
|
|
|
timestamp = None
|
2019-11-27 07:57:30 -05:00
|
|
|
|
video_description = None
|
2021-10-21 20:27:15 -04:00
|
|
|
|
info_dict = {}
|
2021-11-22 14:39:17 -05:00
|
|
|
|
config_url = None
|
2017-01-31 12:49:28 -05:00
|
|
|
|
|
2021-10-21 20:27:15 -04:00
|
|
|
|
channel_id = self._search_regex(
|
|
|
|
|
r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
|
|
|
|
|
if channel_id:
|
|
|
|
|
config_url = self._html_search_regex(
|
2021-11-22 14:39:17 -05:00
|
|
|
|
r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
|
2021-10-21 20:27:15 -04:00
|
|
|
|
video_description = clean_html(get_element_by_class('description', webpage))
|
|
|
|
|
info_dict.update({
|
|
|
|
|
'channel_id': channel_id,
|
|
|
|
|
'channel_url': 'https://vimeo.com/channels/' + channel_id,
|
|
|
|
|
})
|
2021-11-22 14:39:17 -05:00
|
|
|
|
if not config_url:
|
2021-10-21 20:27:15 -04:00
|
|
|
|
page_config = self._parse_json(self._search_regex(
|
|
|
|
|
r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
|
|
|
|
|
webpage, 'page config', default='{}'), video_id, fatal=False)
|
|
|
|
|
if not page_config:
|
|
|
|
|
return self._extract_from_api(video_id)
|
|
|
|
|
config_url = page_config['player']['config_url']
|
|
|
|
|
cc_license = page_config.get('cc_license')
|
|
|
|
|
clip = page_config.get('clip') or {}
|
|
|
|
|
timestamp = clip.get('uploaded_on')
|
|
|
|
|
video_description = clean_html(
|
|
|
|
|
clip.get('description') or page_config.get('description_html_escaped'))
|
|
|
|
|
config = self._download_json(config_url, video_id)
|
2021-02-19 15:44:36 -05:00
|
|
|
|
video = config.get('video') or {}
|
|
|
|
|
vod = video.get('vod') or {}
|
2018-09-15 01:30:57 -04:00
|
|
|
|
|
2016-06-18 16:56:01 -04:00
|
|
|
|
def is_rented():
|
|
|
|
|
if '>You rented this title.<' in webpage:
|
|
|
|
|
return True
|
2021-10-21 20:27:15 -04:00
|
|
|
|
if try_get(config, lambda x: x['user']['purchased']):
|
2016-06-18 16:56:01 -04:00
|
|
|
|
return True
|
2021-10-21 20:27:15 -04:00
|
|
|
|
for purchase_option in (vod.get('purchase_options') or []):
|
2018-09-15 01:30:57 -04:00
|
|
|
|
if purchase_option.get('purchased'):
|
|
|
|
|
return True
|
|
|
|
|
label = purchase_option.get('label_string')
|
|
|
|
|
if label and (label.startswith('You rented this') or label.endswith(' remaining')):
|
|
|
|
|
return True
|
2016-06-18 16:56:01 -04:00
|
|
|
|
return False
|
|
|
|
|
|
2018-09-15 01:30:57 -04:00
|
|
|
|
if is_rented() and vod.get('is_trailer'):
|
|
|
|
|
feature_id = vod.get('feature_id')
|
2016-01-07 23:41:24 -05:00
|
|
|
|
if feature_id and not data.get('force_feature_id', False):
|
|
|
|
|
return self.url_result(smuggle_url(
|
2024-06-11 19:09:58 -04:00
|
|
|
|
f'https://player.vimeo.com/player/{feature_id}',
|
2016-01-07 23:41:24 -05:00
|
|
|
|
{'force_feature_id': True}), 'Vimeo')
|
|
|
|
|
|
2019-11-27 07:57:30 -05:00
|
|
|
|
if not video_description:
|
|
|
|
|
video_description = self._html_search_regex(
|
|
|
|
|
r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
|
|
|
|
|
webpage, 'description', default=None)
|
2014-09-29 16:23:21 -04:00
|
|
|
|
if not video_description:
|
|
|
|
|
video_description = self._html_search_meta(
|
2021-10-21 20:27:15 -04:00
|
|
|
|
['description', 'og:description', 'twitter:description'],
|
|
|
|
|
webpage, default=None)
|
|
|
|
|
if not video_description:
|
2021-04-16 06:01:10 -04:00
|
|
|
|
self.report_warning('Cannot find video description')
|
2013-06-23 14:18:21 -04:00
|
|
|
|
|
2017-01-31 12:58:02 -05:00
|
|
|
|
if not timestamp:
|
|
|
|
|
timestamp = self._search_regex(
|
|
|
|
|
r'<time[^>]+datetime="([^"]+)"', webpage,
|
|
|
|
|
'timestamp', default=None)
|
2013-06-23 14:18:21 -04:00
|
|
|
|
|
2021-10-21 20:27:15 -04:00
|
|
|
|
view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None))
|
|
|
|
|
like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None))
|
|
|
|
|
comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None))
|
2013-12-06 07:03:08 -05:00
|
|
|
|
|
2013-07-05 12:10:57 -04:00
|
|
|
|
formats = []
|
2019-03-10 10:03:32 -04:00
|
|
|
|
|
|
|
|
|
source_format = self._extract_original_format(
|
2021-02-19 15:44:36 -05:00
|
|
|
|
'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
|
2019-03-10 10:03:32 -04:00
|
|
|
|
if source_format:
|
|
|
|
|
formats.append(source_format)
|
2014-02-03 08:02:58 -05:00
|
|
|
|
|
2018-04-27 15:48:20 -04:00
|
|
|
|
info_dict_config = self._parse_config(config, video_id)
|
|
|
|
|
formats.extend(info_dict_config['formats'])
|
2022-11-17 00:10:03 -05:00
|
|
|
|
info_dict['_format_sort_fields'] = info_dict_config['_format_sort_fields']
|
2017-01-31 12:49:28 -05:00
|
|
|
|
|
2018-04-27 15:48:20 -04:00
|
|
|
|
json_ld = self._search_json_ld(webpage, video_id, default={})
|
|
|
|
|
|
2017-01-31 12:49:28 -05:00
|
|
|
|
if not cc_license:
|
|
|
|
|
cc_license = self._search_regex(
|
|
|
|
|
r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
|
|
|
|
|
webpage, 'license', default=None, group='license')
|
|
|
|
|
|
2021-10-21 20:27:15 -04:00
|
|
|
|
info_dict.update({
|
2016-06-11 09:35:08 -04:00
|
|
|
|
'formats': formats,
|
2017-01-31 12:58:02 -05:00
|
|
|
|
'timestamp': unified_timestamp(timestamp),
|
2014-02-03 08:24:11 -05:00
|
|
|
|
'description': video_description,
|
2013-11-03 06:11:13 -05:00
|
|
|
|
'webpage_url': url,
|
2013-12-06 07:03:08 -05:00
|
|
|
|
'view_count': view_count,
|
|
|
|
|
'like_count': like_count,
|
|
|
|
|
'comment_count': comment_count,
|
2017-01-31 12:49:28 -05:00
|
|
|
|
'license': cc_license,
|
2021-10-21 20:27:15 -04:00
|
|
|
|
})
|
2016-06-11 09:35:08 -04:00
|
|
|
|
|
2021-10-21 20:27:15 -04:00
|
|
|
|
return merge_dicts(info_dict, info_dict_config, json_ld)
|
2013-07-29 07:12:09 -04:00
|
|
|
|
|
|
|
|
|
|
2022-11-15 19:57:43 -05:00
|
|
|
|
class VimeoOndemandIE(VimeoIE): # XXX: Do not subclass from concrete IE
|
2016-03-09 13:52:52 -05:00
|
|
|
|
IE_NAME = 'vimeo:ondemand'
|
2021-10-21 20:27:15 -04:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
|
2016-03-09 13:51:07 -05:00
|
|
|
|
_TESTS = [{
|
|
|
|
|
# ondemand video not available via https://vimeo.com/id
|
|
|
|
|
'url': 'https://vimeo.com/ondemand/20704',
|
|
|
|
|
'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '105442900',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'המעבדה - במאי יותם פלדמן',
|
|
|
|
|
'uploader': 'גם סרטים',
|
2017-01-02 07:08:07 -05:00
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
|
2016-03-09 13:51:07 -05:00
|
|
|
|
'uploader_id': 'gumfilms',
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'description': 'md5:aeeba3dbd4d04b0fa98a4fdc9c639998',
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'upload_date': '20140906',
|
|
|
|
|
'timestamp': 1410032453,
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/488238335-d7bf151c364cff8d467f1b73784668fe60aae28a54573a35d53a1210ae283bd8-d_1280',
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'license': 'https://creativecommons.org/licenses/by-nc-nd/3.0/',
|
|
|
|
|
'duration': 53,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'like_count': int,
|
2016-03-09 13:51:07 -05:00
|
|
|
|
},
|
2017-01-11 10:51:03 -05:00
|
|
|
|
'params': {
|
|
|
|
|
'format': 'best[protocol=https]',
|
|
|
|
|
},
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'expected_warnings': ['Unable to download JSON metadata'],
|
2016-09-12 10:48:45 -04:00
|
|
|
|
}, {
|
|
|
|
|
# requires Referer to be passed along with og:video:url
|
|
|
|
|
'url': 'https://vimeo.com/ondemand/36938/126682985',
|
|
|
|
|
'info_dict': {
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'id': '126584684',
|
2016-09-12 10:48:45 -04:00
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Rävlock, rätt läte på rätt plats',
|
|
|
|
|
'uploader': 'Lindroth & Norin',
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
|
|
|
|
|
'uploader_id': 'lindrothnorin',
|
|
|
|
|
'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
|
|
|
|
|
'upload_date': '20150502',
|
|
|
|
|
'timestamp': 1430586422,
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'duration': 121,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/517077723-7066ae1d9a79d3eb361334fb5d58ec13c8f04b52f8dd5eadfbd6fb0bcf11f613-d_1280',
|
|
|
|
|
'like_count': int,
|
2016-09-12 10:48:45 -04:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'expected_warnings': ['Unable to download JSON metadata'],
|
2016-03-09 13:51:07 -05:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://vimeo.com/ondemand/nazmaalik',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://vimeo.com/ondemand/141692381',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
|
2015-08-10 13:35:08 -04:00
|
|
|
|
class VimeoChannelIE(VimeoBaseInfoExtractor):
|
2014-01-06 17:38:16 -05:00
|
|
|
|
IE_NAME = 'vimeo:channel'
|
2015-03-12 14:08:16 -04:00
|
|
|
|
_VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
|
2013-07-29 07:12:09 -04:00
|
|
|
|
_MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
|
2015-08-10 13:58:01 -04:00
|
|
|
|
_TITLE = None
|
2013-12-01 16:36:18 -05:00
|
|
|
|
_TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
|
2014-08-27 05:36:01 -04:00
|
|
|
|
_TESTS = [{
|
2015-03-12 14:08:16 -04:00
|
|
|
|
'url': 'https://vimeo.com/channels/tributes',
|
2014-08-27 05:36:01 -04:00
|
|
|
|
'info_dict': {
|
2015-02-17 18:33:31 -05:00
|
|
|
|
'id': 'tributes',
|
2014-08-27 05:36:01 -04:00
|
|
|
|
'title': 'Vimeo Tributes',
|
|
|
|
|
},
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'playlist_mincount': 22,
|
2014-08-27 05:36:01 -04:00
|
|
|
|
}]
|
2019-11-27 07:57:30 -05:00
|
|
|
|
_BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
|
2013-07-29 07:12:09 -04:00
|
|
|
|
|
2013-12-06 15:47:32 -05:00
|
|
|
|
def _page_url(self, base_url, pagenum):
|
2024-06-11 19:09:58 -04:00
|
|
|
|
return f'{base_url}/videos/page:{pagenum}/'
|
2013-12-06 15:47:32 -05:00
|
|
|
|
|
2013-12-06 16:01:41 -05:00
|
|
|
|
def _extract_list_title(self, webpage):
|
2019-06-22 15:16:09 -04:00
|
|
|
|
return self._TITLE or self._html_search_regex(
|
|
|
|
|
self._TITLE_RE, webpage, 'list title', fatal=False)
|
2013-12-06 16:01:41 -05:00
|
|
|
|
|
2015-11-19 10:29:32 -05:00
|
|
|
|
def _title_and_entries(self, list_id, base_url):
|
2013-07-29 07:12:09 -04:00
|
|
|
|
for pagenum in itertools.count(1):
|
2015-02-09 22:53:21 -05:00
|
|
|
|
page_url = self._page_url(base_url, pagenum)
|
2013-12-01 16:36:18 -05:00
|
|
|
|
webpage = self._download_webpage(
|
2015-02-09 22:53:21 -05:00
|
|
|
|
page_url, list_id,
|
2024-06-11 19:09:58 -04:00
|
|
|
|
f'Downloading page {pagenum}')
|
2015-02-09 22:53:21 -05:00
|
|
|
|
|
|
|
|
|
if pagenum == 1:
|
2015-11-19 10:29:32 -05:00
|
|
|
|
yield self._extract_list_title(webpage)
|
|
|
|
|
|
2016-06-22 14:28:36 -04:00
|
|
|
|
# Try extracting href first since not all videos are available via
|
|
|
|
|
# short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
|
|
|
|
|
clips = re.findall(
|
2017-01-21 02:47:39 -05:00
|
|
|
|
r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
|
2016-06-22 14:28:36 -04:00
|
|
|
|
if clips:
|
2017-01-21 02:47:39 -05:00
|
|
|
|
for video_id, video_url, video_title in clips:
|
2016-06-22 14:28:36 -04:00
|
|
|
|
yield self.url_result(
|
2024-06-11 19:09:58 -04:00
|
|
|
|
urllib.parse.urljoin(base_url, video_url),
|
2017-01-21 02:47:39 -05:00
|
|
|
|
VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
|
2016-06-22 14:28:36 -04:00
|
|
|
|
# More relaxed fallback
|
|
|
|
|
else:
|
|
|
|
|
for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
|
|
|
|
|
yield self.url_result(
|
2024-06-11 19:09:58 -04:00
|
|
|
|
f'https://vimeo.com/{video_id}',
|
2016-06-22 14:28:36 -04:00
|
|
|
|
VimeoIE.ie_key(), video_id=video_id)
|
2015-02-09 22:53:21 -05:00
|
|
|
|
|
2013-07-29 07:12:09 -04:00
|
|
|
|
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
|
|
|
|
|
break
|
|
|
|
|
|
2015-11-19 10:29:32 -05:00
|
|
|
|
def _extract_videos(self, list_id, base_url):
|
|
|
|
|
title_and_entries = self._title_and_entries(list_id, base_url)
|
|
|
|
|
list_title = next(title_and_entries)
|
|
|
|
|
return self.playlist_result(title_and_entries, list_id, list_title)
|
2013-12-01 16:36:18 -05:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2019-11-27 07:57:30 -05:00
|
|
|
|
channel_id = self._match_id(url)
|
|
|
|
|
return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
|
2013-12-01 16:36:18 -05:00
|
|
|
|
|
|
|
|
|
|
2022-11-15 19:57:43 -05:00
|
|
|
|
class VimeoUserIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
|
2014-01-06 17:38:16 -05:00
|
|
|
|
IE_NAME = 'vimeo:user'
|
2022-08-25 20:58:37 -04:00
|
|
|
|
_VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos)?/?(?:$|[?#])'
|
2013-12-01 16:36:18 -05:00
|
|
|
|
_TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
|
2014-08-27 05:36:01 -04:00
|
|
|
|
_TESTS = [{
|
2015-03-12 14:08:16 -04:00
|
|
|
|
'url': 'https://vimeo.com/nkistudio/videos',
|
2014-08-27 05:36:01 -04:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'title': 'Nki',
|
2015-02-17 18:33:31 -05:00
|
|
|
|
'id': 'nkistudio',
|
2014-08-27 05:36:01 -04:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 66,
|
2022-08-25 20:58:37 -04:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://vimeo.com/nkistudio/',
|
|
|
|
|
'only_matching': True,
|
2014-08-27 05:36:01 -04:00
|
|
|
|
}]
|
2019-11-27 07:57:30 -05:00
|
|
|
|
_BASE_URL_TEMPL = 'https://vimeo.com/%s'
|
2013-12-06 15:47:32 -05:00
|
|
|
|
|
|
|
|
|
|
2020-01-27 17:37:29 -05:00
|
|
|
|
class VimeoAlbumIE(VimeoBaseInfoExtractor):
|
2014-01-06 17:38:16 -05:00
|
|
|
|
IE_NAME = 'vimeo:album'
|
2019-08-03 05:29:20 -04:00
|
|
|
|
_VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
|
2013-12-06 15:47:32 -05:00
|
|
|
|
_TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
|
2014-08-27 05:36:01 -04:00
|
|
|
|
_TESTS = [{
|
2015-03-06 16:16:26 -05:00
|
|
|
|
'url': 'https://vimeo.com/album/2632481',
|
2014-08-27 05:36:01 -04:00
|
|
|
|
'info_dict': {
|
2015-02-17 18:33:31 -05:00
|
|
|
|
'id': '2632481',
|
2014-08-27 05:36:01 -04:00
|
|
|
|
'title': 'Staff Favorites: November 2013',
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 13,
|
2015-02-09 22:53:21 -05:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'Password-protected album',
|
|
|
|
|
'url': 'https://vimeo.com/album/3253534',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'title': 'test',
|
|
|
|
|
'id': '3253534',
|
|
|
|
|
},
|
|
|
|
|
'playlist_count': 1,
|
|
|
|
|
'params': {
|
2020-09-02 16:37:35 -04:00
|
|
|
|
'videopassword': 'youtube-dl',
|
2024-06-11 19:09:58 -04:00
|
|
|
|
},
|
2014-08-27 05:36:01 -04:00
|
|
|
|
}]
|
2019-08-03 05:29:20 -04:00
|
|
|
|
_PAGE_SIZE = 100
|
|
|
|
|
|
2020-11-21 09:50:42 -05:00
|
|
|
|
def _fetch_page(self, album_id, authorization, hashed_pass, page):
|
2019-08-03 05:29:20 -04:00
|
|
|
|
api_page = page + 1
|
|
|
|
|
query = {
|
2019-10-15 16:01:59 -04:00
|
|
|
|
'fields': 'link,uri',
|
2019-08-03 05:29:20 -04:00
|
|
|
|
'page': api_page,
|
|
|
|
|
'per_page': self._PAGE_SIZE,
|
|
|
|
|
}
|
|
|
|
|
if hashed_pass:
|
|
|
|
|
query['_hashed_pass'] = hashed_pass
|
2021-03-21 14:57:54 -04:00
|
|
|
|
try:
|
|
|
|
|
videos = self._download_json(
|
2024-06-11 19:09:58 -04:00
|
|
|
|
f'https://api.vimeo.com/albums/{album_id}/videos',
|
|
|
|
|
album_id, f'Downloading page {api_page}', query=query, headers={
|
2021-03-21 14:57:54 -04:00
|
|
|
|
'Authorization': 'jwt ' + authorization,
|
2024-02-02 16:15:04 -05:00
|
|
|
|
'Accept': 'application/json',
|
2021-03-21 14:57:54 -04:00
|
|
|
|
})['data']
|
|
|
|
|
except ExtractorError as e:
|
2023-07-09 03:53:02 -04:00
|
|
|
|
if isinstance(e.cause, HTTPError) and e.cause.status == 400:
|
2021-03-21 14:57:54 -04:00
|
|
|
|
return
|
2024-02-02 16:15:04 -05:00
|
|
|
|
raise
|
2019-08-03 05:29:20 -04:00
|
|
|
|
for video in videos:
|
|
|
|
|
link = video.get('link')
|
|
|
|
|
if not link:
|
|
|
|
|
continue
|
2019-10-15 16:01:59 -04:00
|
|
|
|
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)
|
2013-12-06 15:47:32 -05:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2015-02-09 22:53:21 -05:00
|
|
|
|
album_id = self._match_id(url)
|
2020-11-19 14:22:59 -05:00
|
|
|
|
viewer = self._download_json(
|
|
|
|
|
'https://vimeo.com/_rv/viewer', album_id, fatal=False)
|
|
|
|
|
if not viewer:
|
|
|
|
|
webpage = self._download_webpage(url, album_id)
|
|
|
|
|
viewer = self._parse_json(self._search_regex(
|
|
|
|
|
r'bootstrap_data\s*=\s*({.+?})</script>',
|
|
|
|
|
webpage, 'bootstrap data'), album_id)['viewer']
|
2020-01-27 17:37:29 -05:00
|
|
|
|
jwt = viewer['jwt']
|
|
|
|
|
album = self._download_json(
|
|
|
|
|
'https://api.vimeo.com/albums/' + album_id,
|
2024-02-02 16:15:04 -05:00
|
|
|
|
album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
|
2020-01-27 17:37:29 -05:00
|
|
|
|
query={'fields': 'description,name,privacy'})
|
|
|
|
|
hashed_pass = None
|
|
|
|
|
if try_get(album, lambda x: x['privacy']['view']) == 'password':
|
2021-05-17 08:23:08 -04:00
|
|
|
|
password = self.get_param('videopassword')
|
2020-01-27 17:37:29 -05:00
|
|
|
|
if not password:
|
|
|
|
|
raise ExtractorError(
|
|
|
|
|
'This album is protected by a password, use the --video-password option',
|
|
|
|
|
expected=True)
|
|
|
|
|
self._set_vimeo_cookie('vuid', viewer['vuid'])
|
|
|
|
|
try:
|
|
|
|
|
hashed_pass = self._download_json(
|
2024-06-11 19:09:58 -04:00
|
|
|
|
f'https://vimeo.com/showcase/{album_id}/auth',
|
2020-01-27 17:37:29 -05:00
|
|
|
|
album_id, 'Verifying the password', data=urlencode_postdata({
|
|
|
|
|
'password': password,
|
|
|
|
|
'token': viewer['xsrft'],
|
|
|
|
|
}), headers={
|
|
|
|
|
'X-Requested-With': 'XMLHttpRequest',
|
|
|
|
|
})['hashed_pass']
|
|
|
|
|
except ExtractorError as e:
|
2023-07-09 03:53:02 -04:00
|
|
|
|
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
|
2020-01-27 17:37:29 -05:00
|
|
|
|
raise ExtractorError('Wrong password', expected=True)
|
|
|
|
|
raise
|
2019-08-03 05:29:20 -04:00
|
|
|
|
entries = OnDemandPagedList(functools.partial(
|
2020-01-27 17:37:29 -05:00
|
|
|
|
self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
|
|
|
|
|
return self.playlist_result(
|
|
|
|
|
entries, album_id, album.get('name'), album.get('description'))
|
2013-12-06 16:01:41 -05:00
|
|
|
|
|
|
|
|
|
|
2022-11-15 19:57:43 -05:00
|
|
|
|
class VimeoGroupsIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
|
2014-01-06 17:38:16 -05:00
|
|
|
|
IE_NAME = 'vimeo:group'
|
2019-11-27 07:57:30 -05:00
|
|
|
|
_VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
|
2014-08-27 05:36:01 -04:00
|
|
|
|
_TESTS = [{
|
2021-11-05 16:45:08 -04:00
|
|
|
|
'url': 'https://vimeo.com/groups/meetup',
|
2014-08-27 05:36:01 -04:00
|
|
|
|
'info_dict': {
|
2021-11-05 16:45:08 -04:00
|
|
|
|
'id': 'meetup',
|
|
|
|
|
'title': 'Vimeo Meetup!',
|
2014-08-27 05:36:01 -04:00
|
|
|
|
},
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'playlist_mincount': 27,
|
2014-08-27 05:36:01 -04:00
|
|
|
|
}]
|
2019-11-27 07:57:30 -05:00
|
|
|
|
_BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
|
2014-01-06 11:31:47 -05:00
|
|
|
|
|
|
|
|
|
|
2016-06-11 09:35:08 -04:00
|
|
|
|
class VimeoReviewIE(VimeoBaseInfoExtractor):
|
2014-01-06 17:38:16 -05:00
|
|
|
|
IE_NAME = 'vimeo:review'
|
|
|
|
|
IE_DESC = 'Review pages on vimeo'
|
2024-07-29 17:55:06 -04:00
|
|
|
|
_VALID_URL = r'https?://vimeo\.com/(?P<user>[^/?#]+)/review/(?P<id>\d+)/(?P<hash>[\da-f]{10})'
|
2014-08-27 05:13:42 -04:00
|
|
|
|
_TESTS = [{
|
2014-01-06 11:31:47 -05:00
|
|
|
|
'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
|
|
|
|
|
'md5': 'c507a72f780cacc12b2248bb4006d253',
|
|
|
|
|
'info_dict': {
|
2015-02-01 06:12:27 -05:00
|
|
|
|
'id': '75524534',
|
|
|
|
|
'ext': 'mp4',
|
2014-01-06 11:31:47 -05:00
|
|
|
|
'title': "DICK HARDWICK 'Comedian'",
|
|
|
|
|
'uploader': 'Richard Hardwick',
|
2016-06-11 09:35:08 -04:00
|
|
|
|
'uploader_id': 'user21297594',
|
2019-11-27 07:57:30 -05:00
|
|
|
|
'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
|
2022-03-22 18:23:39 -04:00
|
|
|
|
'duration': 304,
|
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/450115033-43303819d9ebe24c2630352e18b7056d25197d09b3ae901abdac4c4f1d68de71-d_1280',
|
|
|
|
|
'uploader_url': 'https://vimeo.com/user21297594',
|
2019-11-27 07:57:30 -05:00
|
|
|
|
},
|
2014-08-27 05:13:42 -04:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'video player needs Referer',
|
2015-03-12 14:08:16 -04:00
|
|
|
|
'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
|
2014-08-27 05:13:42 -04:00
|
|
|
|
'md5': '6295fdab8f4bf6a002d058b2c6dce276',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '91613211',
|
|
|
|
|
'ext': 'mp4',
|
2014-10-26 19:13:40 -04:00
|
|
|
|
'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
|
2014-08-27 05:13:42 -04:00
|
|
|
|
'uploader': 'DevWeek Events',
|
|
|
|
|
'duration': 2773,
|
2017-01-02 07:08:07 -05:00
|
|
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
2016-06-11 09:35:08 -04:00
|
|
|
|
'uploader_id': 'user22258446',
|
2019-11-27 07:57:30 -05:00
|
|
|
|
},
|
|
|
|
|
'skip': 'video gone',
|
2016-06-24 04:48:37 -04:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'Password protected',
|
|
|
|
|
'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '138823582',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
|
|
|
|
|
'uploader': 'TMB',
|
|
|
|
|
'uploader_id': 'user37284429',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'videopassword': 'holygrail',
|
|
|
|
|
},
|
2016-10-11 13:48:06 -04:00
|
|
|
|
'skip': 'video gone',
|
2014-08-27 05:13:42 -04:00
|
|
|
|
}]
|
2014-01-06 11:31:47 -05:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2024-07-29 17:55:06 -04:00
|
|
|
|
user, video_id, review_hash = self._match_valid_url(url).group('user', 'id', 'hash')
|
|
|
|
|
data_url = f'https://vimeo.com/{user}/review/data/{video_id}/{review_hash}'
|
|
|
|
|
data = self._download_json(data_url, video_id)
|
2021-04-01 04:28:33 -04:00
|
|
|
|
if data.get('isLocked') is True:
|
|
|
|
|
video_password = self._get_video_password()
|
|
|
|
|
viewer = self._download_json(
|
|
|
|
|
'https://vimeo.com/_rv/viewer', video_id)
|
2024-07-29 17:55:06 -04:00
|
|
|
|
self._verify_video_password(video_id, video_password, viewer['xsrft'])
|
|
|
|
|
data = self._download_json(data_url, video_id)
|
|
|
|
|
clip_data = data['clipData']
|
|
|
|
|
config_url = clip_data['configUrl']
|
2016-06-24 04:48:37 -04:00
|
|
|
|
config = self._download_json(config_url, video_id)
|
2016-06-11 09:35:08 -04:00
|
|
|
|
info_dict = self._parse_config(config, video_id)
|
2019-11-27 07:57:30 -05:00
|
|
|
|
source_format = self._extract_original_format(
|
2024-07-29 17:55:06 -04:00
|
|
|
|
f'https://vimeo.com/{user}/review/{video_id}/{review_hash}/action', video_id,
|
|
|
|
|
unlisted_hash=traverse_obj(config_url, ({parse_qs}, 'h', -1)))
|
2019-03-10 10:03:32 -04:00
|
|
|
|
if source_format:
|
|
|
|
|
info_dict['formats'].append(source_format)
|
2019-11-27 07:57:30 -05:00
|
|
|
|
info_dict['description'] = clean_html(clip_data.get('description'))
|
2016-06-11 09:35:08 -04:00
|
|
|
|
return info_dict
|
2014-04-24 15:51:20 -04:00
|
|
|
|
|
|
|
|
|
|
2022-11-15 19:57:43 -05:00
|
|
|
|
class VimeoWatchLaterIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
|
2014-04-24 15:51:20 -04:00
|
|
|
|
IE_NAME = 'vimeo:watchlater'
|
2022-05-09 00:32:17 -04:00
|
|
|
|
IE_DESC = 'Vimeo watch later list, ":vimeowatchlater" keyword (requires authentication)'
|
2015-08-10 13:58:01 -04:00
|
|
|
|
_VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
|
|
|
|
|
_TITLE = 'Watch Later'
|
2014-04-24 15:51:20 -04:00
|
|
|
|
_LOGIN_REQUIRED = True
|
2014-08-27 05:36:01 -04:00
|
|
|
|
_TESTS = [{
|
2015-08-10 13:58:01 -04:00
|
|
|
|
'url': 'https://vimeo.com/watchlater',
|
2014-08-27 05:36:01 -04:00
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
2014-04-24 15:51:20 -04:00
|
|
|
|
|
|
|
|
|
def _page_url(self, base_url, pagenum):
|
2024-06-11 19:09:58 -04:00
|
|
|
|
url = f'{base_url}/page:{pagenum}/'
|
2023-07-09 03:53:02 -04:00
|
|
|
|
request = Request(url)
|
2014-04-24 15:51:20 -04:00
|
|
|
|
# Set the header to get a partial html page with the ids,
|
|
|
|
|
# the normal page doesn't contain them.
|
2023-07-09 03:53:02 -04:00
|
|
|
|
request.headers['X-Requested-With'] = 'XMLHttpRequest'
|
2014-04-24 15:51:20 -04:00
|
|
|
|
return request
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2015-08-10 13:58:01 -04:00
|
|
|
|
return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
|
2014-09-28 06:14:16 -04:00
|
|
|
|
|
|
|
|
|
|
2022-11-15 19:57:43 -05:00
|
|
|
|
class VimeoLikesIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
|
2018-05-17 12:21:40 -04:00
|
|
|
|
_VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
|
2014-09-28 06:14:16 -04:00
|
|
|
|
IE_NAME = 'vimeo:likes'
|
|
|
|
|
IE_DESC = 'Vimeo user likes'
|
2018-05-17 12:21:40 -04:00
|
|
|
|
_TESTS = [{
|
2014-09-28 18:36:06 -04:00
|
|
|
|
'url': 'https://vimeo.com/user755559/likes/',
|
|
|
|
|
'playlist_mincount': 293,
|
2016-02-14 04:37:17 -05:00
|
|
|
|
'info_dict': {
|
2019-06-22 15:13:46 -04:00
|
|
|
|
'id': 'user755559',
|
|
|
|
|
'title': 'urza’s Likes',
|
2014-09-28 06:14:16 -04:00
|
|
|
|
},
|
2018-05-17 12:21:40 -04:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://vimeo.com/stormlapse/likes',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
2014-09-28 06:14:16 -04:00
|
|
|
|
|
2019-06-22 15:13:46 -04:00
|
|
|
|
def _page_url(self, base_url, pagenum):
|
2024-06-11 19:09:58 -04:00
|
|
|
|
return f'{base_url}/page:{pagenum}/'
|
2019-06-22 15:13:46 -04:00
|
|
|
|
|
2014-09-28 06:14:16 -04:00
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
user_id = self._match_id(url)
|
2024-06-11 19:09:58 -04:00
|
|
|
|
return self._extract_videos(user_id, f'https://vimeo.com/{user_id}/likes')
|
2018-11-28 13:53:22 -05:00
|
|
|
|
|
|
|
|
|
|
2019-10-14 13:37:35 -04:00
|
|
|
|
class VHXEmbedIE(VimeoBaseInfoExtractor):
|
2018-11-28 13:53:22 -05:00
|
|
|
|
IE_NAME = 'vhx:embed'
|
|
|
|
|
_VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
|
2022-07-31 21:23:25 -04:00
|
|
|
|
_EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://embed\.vhx\.tv/videos/\d+[^"]*)"']
|
2018-11-28 13:53:22 -05:00
|
|
|
|
|
2022-07-31 21:23:25 -04:00
|
|
|
|
@classmethod
|
|
|
|
|
def _extract_embed_urls(cls, url, webpage):
|
|
|
|
|
for embed_url in super()._extract_embed_urls(url, webpage):
|
|
|
|
|
yield cls._smuggle_referrer(embed_url, url)
|
2021-01-01 07:26:37 -05:00
|
|
|
|
|
2018-11-28 13:53:22 -05:00
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
video_id = self._match_id(url)
|
2022-05-17 19:41:47 -04:00
|
|
|
|
url, _, headers = self._unsmuggle_headers(url)
|
|
|
|
|
webpage = self._download_webpage(url, video_id, headers=headers)
|
2019-10-14 13:37:35 -04:00
|
|
|
|
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)
|
2021-01-01 07:26:37 -05:00
|
|
|
|
info['id'] = video_id
|
2019-10-14 13:37:35 -04:00
|
|
|
|
return info
|
2022-11-20 19:55:57 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class VimeoProIE(VimeoBaseInfoExtractor):
|
|
|
|
|
IE_NAME = 'vimeo:pro'
|
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?vimeopro\.com/[^/?#]+/(?P<slug>[^/?#]+)(?:(?:/videos?/(?P<id>[0-9]+)))?'
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
# Vimeo URL derived from video_id
|
|
|
|
|
'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
|
|
|
|
|
'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
|
|
|
|
|
'note': 'Vimeo Pro video (#1197)',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '68093876',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
|
|
|
|
|
'uploader_id': 'openstreetmapus',
|
|
|
|
|
'uploader': 'OpenStreetMap US',
|
|
|
|
|
'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
|
|
|
|
|
'description': 'md5:2c362968038d4499f4d79f88458590c1',
|
|
|
|
|
'duration': 1595,
|
|
|
|
|
'upload_date': '20130610',
|
|
|
|
|
'timestamp': 1370893156,
|
|
|
|
|
'license': 'by',
|
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/440260469-19b0d92fca3bd84066623b53f1eb8aaa3980c6c809e2d67b6b39ab7b4a77a344-d_960',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'tags': 'count:1',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'format': 'best[protocol=https]',
|
|
|
|
|
},
|
|
|
|
|
}, {
|
|
|
|
|
# password-protected VimeoPro page with Vimeo player embed
|
|
|
|
|
'url': 'https://vimeopro.com/cadfem/simulation-conference-mechanische-systeme-in-perfektion',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '764543723',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Mechanische Systeme in Perfektion: Realität erfassen, Innovation treiben',
|
|
|
|
|
'thumbnail': 'https://i.vimeocdn.com/video/1543784598-a1a750494a485e601110136b9fe11e28c2131942452b3a5d30391cb3800ca8fd-d_1280',
|
|
|
|
|
'description': 'md5:2a9d195cd1b0f6f79827107dc88c2420',
|
|
|
|
|
'uploader': 'CADFEM',
|
|
|
|
|
'uploader_id': 'cadfem',
|
|
|
|
|
'uploader_url': 'https://vimeo.com/cadfem',
|
|
|
|
|
'duration': 12505,
|
|
|
|
|
'chapters': 'count:10',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'videopassword': 'Conference2022',
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
display_id, video_id = self._match_valid_url(url).group('slug', 'id')
|
|
|
|
|
if video_id:
|
|
|
|
|
display_id = video_id
|
|
|
|
|
webpage = self._download_webpage(url, display_id)
|
|
|
|
|
|
|
|
|
|
password_form = self._search_regex(
|
|
|
|
|
r'(?is)<form[^>]+?method=["\']post["\'][^>]*>(.+?password.+?)</form>',
|
|
|
|
|
webpage, 'password form', default=None)
|
|
|
|
|
if password_form:
|
|
|
|
|
try:
|
|
|
|
|
webpage = self._download_webpage(url, display_id, data=urlencode_postdata({
|
|
|
|
|
'password': self._get_video_password(),
|
|
|
|
|
**self._hidden_inputs(password_form),
|
|
|
|
|
}), note='Logging in with video password')
|
|
|
|
|
except ExtractorError as e:
|
2023-07-09 03:53:02 -04:00
|
|
|
|
if isinstance(e.cause, HTTPError) and e.cause.status == 418:
|
2022-11-20 19:55:57 -05:00
|
|
|
|
raise ExtractorError('Wrong video password', expected=True)
|
|
|
|
|
raise
|
|
|
|
|
|
|
|
|
|
description = None
|
|
|
|
|
# even if we have video_id, some videos require player URL with portfolio_id query param
|
|
|
|
|
# https://github.com/ytdl-org/youtube-dl/issues/20070
|
|
|
|
|
vimeo_url = VimeoIE._extract_url(url, webpage)
|
|
|
|
|
if vimeo_url:
|
|
|
|
|
description = self._html_search_meta('description', webpage, default=None)
|
|
|
|
|
elif video_id:
|
|
|
|
|
vimeo_url = f'https://vimeo.com/{video_id}'
|
|
|
|
|
else:
|
|
|
|
|
raise ExtractorError(
|
|
|
|
|
'No Vimeo embed or video ID could be found in VimeoPro page', expected=True)
|
|
|
|
|
|
|
|
|
|
return self.url_result(vimeo_url, VimeoIE, video_id, url_transparent=True,
|
|
|
|
|
description=description)
|