-# coding: utf-8
-from __future__ import unicode_literals
-
import base64
import functools
-import json
import re
import itertools
+import urllib.error
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,
+ get_element_by_class,
+ HEADRequest,
js_to_json,
int_or_none,
merge_dicts,
OnDemandPagedList,
parse_filesize,
- RegexNotFoundError,
+ parse_iso8601,
+ parse_qs,
sanitized_Request,
smuggle_url,
- std_headers,
str_or_none,
try_get,
unified_timestamp,
unsmuggle_url,
urlencode_postdata,
urljoin,
- unescapeHTML,
+ urlhandle_detect_ext,
)
_LOGIN_REQUIRED = False
_LOGIN_URL = 'https://vimeo.com/log_in'
- def _login(self):
- username, password = self._get_login_info()
- if username is None:
- if self._LOGIN_REQUIRED:
- raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
- return
+ @staticmethod
+ def _smuggle_referrer(url, referrer_url):
+ return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
+
+ def _unsmuggle_headers(self, url):
+ """@returns (url, smuggled_data, headers)"""
+ url, data = unsmuggle_url(url, {})
+ headers = self.get_param('http_headers').copy()
+ if 'http_headers' in data:
+ headers.update(data['http_headers'])
+ return url, data, headers
+
+ def _perform_login(self, username, password):
webpage = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
token, vuid = self._extract_xsrft_and_vuid(webpage)
expected=True)
raise ExtractorError('Unable to log in')
- def _verify_video_password(self, url, video_id, webpage):
- password = self._downloader.params.get('videopassword')
+ def _real_initialize(self):
+ if self._LOGIN_REQUIRED and not self._get_cookies('https://vimeo.com').get('vuid'):
+ self._raise_login_required()
+
+ def _get_video_password(self):
+ password = self.get_param('videopassword')
if password is None:
- raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
- token, vuid = self._extract_xsrft_and_vuid(webpage)
- data = urlencode_postdata({
- 'password': password,
- 'token': token,
- })
+ raise ExtractorError(
+ 'This video is protected by a password, use the --video-password option',
+ expected=True)
+ return password
+
+ def _verify_video_password(self, url, video_id, password, token, vuid):
if url.startswith('http://'):
# vimeo only supports https now, but the user can give an http url
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)
return self._download_webpage(
- password_request, video_id,
- 'Verifying the password', 'Wrong password')
+ url + '/password', video_id, 'Verifying the 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):
xsrft = self._search_regex(
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))
+ webpage, 'vimeo config', *args, **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)
- def _vimeo_sort_formats(self, formats):
- # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
- # at the same time without actual units specified. This lead to wrong sorting.
- # But since yt-dlp prefers 'res,fps' anyway, 'field_preference' is not needed
- self._sort_formats(formats)
-
def _parse_config(self, config, video_id):
video_data = config['video']
- video_title = video_data['title']
+ video_title = video_data.get('title')
live_event = video_data.get('live_event') or {}
is_live = live_event.get('status') == 'started'
+ request = config.get('request') or {}
formats = []
- config_files = video_data.get('files') or config['request'].get('files', {})
- for f in config_files.get('progressive', []):
+ subtitles = {}
+
+ config_files = video_data.get('files') or request.get('files') or {}
+ for f in (config_files.get('progressive') or []):
video_url = f.get('url')
if not video_url:
continue
formats.append({
'url': video_url,
'format_id': 'http-%s' % f.get('quality'),
+ 'source_preference': 10,
'width': int_or_none(f.get('width')),
'height': int_or_none(f.get('height')),
'fps': int_or_none(f.get('fps')),
# TODO: fix handling of 308 status code returned for live archive manifest requests
sep_pattern = r'/sep/video/'
for files_type in ('hls', 'dash'):
- for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items():
+ for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
manifest_url = cdn_data.get('url')
if not manifest_url:
continue
sep_manifest_urls = [(format_id, manifest_url)]
for f_id, m_url in sep_manifest_urls:
if files_type == 'hls':
- formats.extend(self._extract_m3u8_formats(
- m_url, video_id, 'mp4',
- 'm3u8' if is_live else 'm3u8_native', m3u8_id=f_id,
+ fmts, subs = self._extract_m3u8_formats_and_subtitles(
+ m_url, video_id, 'mp4', live=is_live, m3u8_id=f_id,
note='Downloading %s m3u8 information' % cdn_name,
- fatal=False))
+ fatal=False)
+ formats.extend(fmts)
+ self._merge_subtitles(subs, target=subtitles)
elif files_type == 'dash':
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
- mpd_formats = self._extract_mpd_formats(
+ fmts, subs = self._extract_mpd_formats_and_subtitles(
m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
'Downloading %s MPD information' % cdn_name,
fatal=False)
- formats.extend(mpd_formats)
+ formats.extend(fmts)
+ self._merge_subtitles(subs, target=subtitles)
live_archive = live_event.get('archive') or {}
live_archive_source_url = live_archive.get('source_url')
'quality': 10,
})
- subtitles = {}
- text_tracks = config['request'].get('text_tracks')
- if text_tracks:
- for tt in text_tracks:
- subtitles[tt['lang']] = [{
- 'ext': 'vtt',
- 'url': urljoin('https://vimeo.com', tt['url']),
- }]
+ for tt in (request.get('text_tracks') or []):
+ subtitles.setdefault(tt['lang'], []).append({
+ 'ext': 'vtt',
+ 'url': urljoin('https://vimeo.com', tt['url']),
+ })
thumbnails = []
if not is_live:
- for key, thumb in video_data.get('thumbs', {}).items():
+ for key, thumb in (video_data.get('thumbs') or {}).items():
thumbnails.append({
'id': key,
'width': int_or_none(key),
owner = video_data.get('owner') or {}
video_uploader_url = owner.get('url')
+ duration = int_or_none(video_data.get('duration'))
+ chapter_data = try_get(config, lambda x: x['embed']['chapters']) or []
+ chapters = [{
+ 'title': current_chapter.get('title'),
+ 'start_time': current_chapter.get('timecode'),
+ 'end_time': next_chapter.get('timecode'),
+ } for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])]
+ if chapters and chapters[0]['start_time']: # Chapters may not start from 0
+ chapters[:0] = [{'title': '<Untitled>', 'start_time': 0, 'end_time': chapters[0]['start_time']}]
+
return {
'id': str_or_none(video_data.get('id')) or video_id,
- 'title': self._live_title(video_title) if is_live else video_title,
+ 'title': video_title,
'uploader': owner.get('name'),
'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
'uploader_url': video_uploader_url,
'thumbnails': thumbnails,
- 'duration': int_or_none(video_data.get('duration')),
+ 'duration': duration,
+ 'chapters': chapters or None,
'formats': formats,
'subtitles': subtitles,
'is_live': is_live,
+ # 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'),
}
def _extract_original_format(self, url, video_id, unlisted_hash=None):
query['unlisted_hash'] = unlisted_hash
download_data = self._download_json(
url, video_id, fatal=False, query=query,
- headers={'X-Requested-With': 'XMLHttpRequest'})
- if download_data:
- source_file = download_data.get('source_file')
- if isinstance(source_file, dict):
- download_url = source_file.get('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')
- if self._is_valid_url(download_url, video_id, '%s video' % source_name):
- ext = (try_get(
- source_file, lambda x: x['extension'],
- compat_str) or determine_ext(
- 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,
- }
+ 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')
+ if self._is_valid_url(download_url, video_id, '%s video' % source_name):
+ ext = (try_get(
+ source_file, lambda x: x['extension'],
+ compat_str) or determine_ext(
+ 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,
+ }
+
+ 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
+ headers = {'Authorization': 'jwt %s' % jwt_response['jwt']}
+ original_response = self._download_json(
+ f'https://api.vimeo.com/videos/{video_id}', video_id,
+ headers=headers, fatal=False, expected_status=(403, 404)) or {}
+ for download_data in original_response.get('download') or []:
+ download_url = download_data.get('link')
+ if not download_url or download_data.get('quality') != 'source':
+ continue
+ 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)
+ return {
+ 'url': download_url,
+ 'ext': ext or 'unknown_video',
+ '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,
+ }
class VimeoIE(VimeoBaseInfoExtractor):
# _VALID_URL matches Vimeo URLs
_VALID_URL = r'''(?x)
- https?://
- (?:
- (?:
- www|
- player
- )
- \.
- )?
- vimeo(?:pro)?\.com/
- (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
- (?:.*?/)?
- (?:
- (?:
- play_redirect_hls|
- moogaloop\.swf)\?clip_id=
- )?
- (?:videos?/)?
- (?P<id>[0-9]+)
- (?:/[\da-f]+)?
- /?(?:[?&].*)?(?:[#].*)?$
- '''
+ https?://
+ (?:
+ (?:
+ www|
+ player
+ )
+ \.
+ )?
+ vimeo\.com/
+ (?:
+ (?P<u>user)|
+ (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
+ (?:.*?/)??
+ (?P<q>
+ (?:
+ play_redirect_hls|
+ moogaloop\.swf)\?clip_id=
+ )?
+ (?:videos?/)?
+ )
+ (?P<id>[0-9]+)
+ (?(u)
+ /(?!videos|likes)[^/?#]+/?|
+ (?(q)|/(?P<unlisted_hash>[\da-f]{10}))?
+ )
+ (?:(?(q)[&]|(?(u)|/?)[?]).*?)?(?:[#].*)?$
+ '''
IE_NAME = 'vimeo'
+ _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',
+ ]
_TESTS = [
{
'url': 'http://vimeo.com/56015672#at=0',
'info_dict': {
'id': '56015672',
'ext': 'mp4',
- 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
+ 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
'description': 'md5:2d3305bad981a06ff79f027f19865021',
'timestamp': 1355990239,
'upload_date': '20121220',
'params': {
'format': 'best[protocol=https]',
},
- },
- {
- '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,
- },
- 'params': {
- 'format': 'best[protocol=https]',
- },
+ 'skip': 'No longer available'
},
{
'url': 'http://player.vimeo.com/video/54469442',
'id': '54469442',
'ext': 'mp4',
'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
- 'uploader': 'The BLN & Business of Software',
- 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
- 'uploader_id': 'theblnbusinessofsoftware',
+ 'uploader': 'Business of Software',
+ 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
+ 'uploader_id': 'businessofsoftware',
'duration': 3610,
'description': None,
+ 'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d_1280',
},
'params': {
'format': 'best[protocol=https]',
},
- 'expected_warnings': ['Unable to download JSON metadata'],
},
{
'url': 'http://vimeo.com/68375962',
'uploader_id': 'user18948128',
'uploader': 'Jaime Marquínez Ferrándiz',
'duration': 10,
- 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
+ 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
+ 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
+ 'view_count': int,
+ 'comment_count': int,
+ 'like_count': int,
},
'params': {
'format': 'best[protocol=https]',
'id': '75629013',
'ext': 'mp4',
'title': 'Key & Peele: Terrorist Interrogation',
- 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
+ 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
'uploader_id': 'atencio',
'uploader': 'Peter Atencio',
'timestamp': 1380339469,
'upload_date': '20130928',
'duration': 187,
+ 'thumbnail': 'https://i.vimeocdn.com/video/450239872-a05512d9b1e55d707a7c04365c10980f327b06d966351bc403a5d5d65c95e572-d_1280',
+ 'view_count': int,
+ 'comment_count': int,
+ 'like_count': int,
},
- 'expected_warnings': ['Unable to download JSON metadata'],
+ 'params': {'format': 'http-1080p'},
},
{
'url': 'http://vimeo.com/76979871',
'note': 'Video with subtitles',
'info_dict': {
'id': '76979871',
- 'ext': 'mp4',
+ 'ext': 'mov',
'title': 'The New Vimeo Player (You Know, For Videos)',
'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
'timestamp': 1381846109,
'uploader_id': 'staff',
'uploader': 'Vimeo Staff',
'duration': 62,
- }
+ 'subtitles': {
+ 'de': [{'ext': 'vtt'}],
+ 'en': [{'ext': 'vtt'}],
+ 'es': [{'ext': 'vtt'}],
+ 'fr': [{'ext': 'vtt'}],
+ },
+ },
+ 'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
},
{
# from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
'uploader': 'Tulio Gonçalves',
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
'uploader_id': 'user28849593',
+ 'duration': 118,
+ 'thumbnail': 'https://i.vimeocdn.com/video/478636036-c18440305ef3df9decfb6bf207a61fe39d2d17fa462a96f6f2d93d30492b037d-d_1280',
},
},
{
'timestamp': 1324343742,
'upload_date': '20111220',
'description': 'md5:ae23671e82d05415868f7ad1aec21147',
+ 'duration': 60,
+ 'comment_count': int,
+ 'view_count': int,
+ 'thumbnail': 'https://i.vimeocdn.com/video/231174622-dd07f015e9221ff529d451e1cc31c982b5d87bfafa48c4189b1da72824ee289a-d_1280',
+ 'like_count': int,
+ },
+ },
+ {
+ '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',
+ 'duration': 176,
+ 'thumbnail': 'https://i.vimeocdn.com/video/859377297-836494a4ef775e9d4edbace83937d9ad34dc846c688c0c419c0e87f7ab06c4b3-d_1280',
+ 'uploader_url': 'https://vimeo.com/frameworkla',
},
},
{
'timestamp': 1250886430,
'upload_date': '20090821',
'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
+ 'duration': 321,
+ 'comment_count': int,
+ 'view_count': int,
+ 'thumbnail': 'https://i.vimeocdn.com/video/22728298-bfc22146f930de7cf497821c7b0b9f168099201ecca39b00b6bd31fcedfca7a6-d_1280',
+ 'like_count': int,
},
'params': {
'skip_download': True,
},
- 'expected_warnings': ['Unable to download JSON metadata'],
},
{
# redirects to ondemand extractor and should be passed through it
'params': {
'skip_download': True,
},
- 'expected_warnings': ['Unable to download JSON metadata'],
+ 'skip': 'this page is no longer available.',
},
{
'url': 'http://player.vimeo.com/video/68375962',
'id': '68375962',
'ext': 'mp4',
'title': 'youtube-dl password protected test video',
+ 'timestamp': 1371200155,
+ 'upload_date': '20130614',
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
'uploader_id': 'user18948128',
'uploader': 'Jaime Marquínez Ferrándiz',
'duration': 10,
+ 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
+ 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
+ 'view_count': int,
+ 'comment_count': int,
+ 'like_count': int,
},
'params': {
'format': 'best[protocol=https]',
'info_dict': {
'id': '119195465',
'ext': 'mp4',
- 'title': 'youtube-dl test video \'ä"BaW_jenozKc',
+ 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
'uploader': 'Philipp Hagemeister',
'uploader_id': 'user20132939',
'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
'upload_date': '20150209',
'timestamp': 1423518307,
+ '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,
},
'params': {
'format': 'best[protocol=https]',
'only_matching': True,
},
{
+ 'note': 'Direct URL with hash',
'url': 'https://vimeo.com/160743502/abd0e13fb4',
- 'only_matching': True,
+ 'info_dict': {
+ 'id': '160743502',
+ 'ext': 'mp4',
+ 'uploader': 'Julian Tryba',
+ 'uploader_id': 'aliniamedia',
+ 'title': 'Harrisville New Hampshire',
+ 'timestamp': 1459259666,
+ 'upload_date': '20160329',
+ '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',
+ },
+ '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',
+ },
+ },
+ {
+ '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',
+ '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',
+ },
+ 'params': {'skip_download': 'm3u8'},
},
{
# requires passing unlisted_hash(a52724358e) to load_download_config request
'url': 'https://vimeo.com/392479337/a52724358e',
'only_matching': True,
- }
+ },
+ {
+ # 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,
+ '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',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ {
+ # user playlist alias -> https://vimeo.com/258705797
+ 'url': 'https://vimeo.com/user26785108/newspiritualguide',
+ 'only_matching': True,
+ },
# https://gettingthingsdone.com/workflowmap/
# vimeo embed with check-password page protected by Referer header
]
- @staticmethod
- def _smuggle_referrer(url, referrer_url):
- return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
-
- @staticmethod
- def _extract_urls(url, webpage):
- urls = []
- # Look for embedded (iframe) Vimeo player
- for mobj in re.finditer(
- r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
- webpage):
- urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
- PLAIN_EMBED_RE = (
- # Look for embedded (swf embed) Vimeo player
- r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
- # Look more for non-standard embedded Vimeo player
- r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
- )
- for embed_re in PLAIN_EMBED_RE:
- for mobj in re.finditer(embed_re, webpage):
- urls.append(mobj.group('url'))
- return urls
+ @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)
- @staticmethod
- def _extract_url(url, webpage):
- urls = VimeoIE._extract_urls(url, webpage)
- return urls[0] if urls else None
+ @classmethod
+ def _extract_url(cls, url, webpage):
+ return next(cls._extract_embed_urls(url, webpage), None)
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', expected=True)
+ password = self._get_video_password()
data = urlencode_postdata({
'password': base64.b64encode(password.encode()),
})
'Content-Type': 'application/x-www-form-urlencoded',
})
checked = self._download_json(
- url + '/check-password', video_id,
- 'Verifying the password', data=data, headers=headers)
+ f'{compat_urlparse.urlsplit(url)._replace(query=None).geturl()}/check-password',
+ video_id, 'Verifying the password', data=data, headers=headers)
if checked is False:
raise ExtractorError('Wrong video password', expected=True)
return checked
- def _real_initialize(self):
- self._login()
+ def _extract_from_api(self, video_id, unlisted_hash=None):
+ token = self._download_json(
+ 'https://vimeo.com/_rv/jwt', video_id, headers={
+ 'X-Requested-With': 'XMLHttpRequest'
+ })['token']
+ api_url = 'https://api.vimeo.com/videos/' + video_id
+ if unlisted_hash:
+ api_url += ':' + unlisted_hash
+ video = self._download_json(
+ api_url, 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)
+ 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
def _try_album_password(self, url):
album_id = self._search_regex(
album_id, headers={'Authorization': 'jwt ' + jwt},
query={'fields': 'description,name,privacy'})
if try_get(album, lambda x: x['privacy']['view']) == 'password':
- password = self._downloader.params.get('videopassword')
+ password = self.get_param('videopassword')
if not password:
raise ExtractorError(
'This album is protected by a password, use the --video-password option',
raise
def _real_extract(self, url):
- url, data = unsmuggle_url(url, {})
- headers = std_headers.copy()
- if 'http_headers' in data:
- headers.update(data['http_headers'])
+ url, data, headers = self._unsmuggle_headers(url)
if 'Referer' not in headers:
headers['Referer'] = url
- channel_id = self._search_regex(
- r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
-
# Extract ID from URL
- video_id = self._match_id(url)
- orig_url = url
- 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))
- 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')):
+ mobj = self._match_valid_url(url).groupdict()
+ video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
+ if unlisted_hash:
+ return self._extract_from_api(video_id, unlisted_hash)
+
+ if any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
url = 'https://vimeo.com/' + video_id
self._try_album_password(url)
expected=True)
raise
- # Now we begin extracting as much information as we can from what we
- # retrieved. First we extract the information common to all extractors,
- # and latter we extract those that are Vimeo specific.
- self.report_extraction(video_id)
+ if '://player.vimeo.com/video/' in url:
+ config = self._search_json(
+ r'\b(?:playerC|c)onfig\s*=', webpage, 'info section', video_id)
+ if config.get('view') == 4:
+ config = self._verify_player_video_password(
+ redirect_url, video_id, headers)
+ return self._parse_config(config, video_id)
+
+ if re.search(r'<form[^>]+?id="pw_form"', webpage):
+ video_password = self._get_video_password()
+ token, vuid = self._extract_xsrft_and_vuid(webpage)
+ webpage = self._verify_video_password(
+ redirect_url, video_id, video_password, token, vuid)
vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
if vimeo_config:
- seed_status = vimeo_config.get('seed_status', {})
+ seed_status = vimeo_config.get('seed_status') or {}
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
+ info_dict = {}
+ config_url = None
- # Extract the config JSON
- try:
- try:
- config_url = self._html_search_regex(
- r' data-config-url="(.+?)"', webpage,
- 'config URL', default=None)
- if not config_url:
- # 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)
- 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)
- 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
- m_variable_name = re.search(r'(\w)\.video\.id', webpage)
- if m_variable_name is not None:
- config_re = [r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))]
- else:
- config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
- config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;')
- config_re.append(r'\bconfig\s*=\s*({.+?})\s*;')
- config = self._search_regex(config_re, webpage, 'info section',
- flags=re.DOTALL)
- config = json.loads(config)
- except Exception as e:
- if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
- raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
-
- if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
- if '_video_password_verified' in data:
- raise ExtractorError('video password verification failed!')
- self._verify_video_password(redirect_url, video_id, webpage)
- return self._real_extract(
- smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
- else:
- raise ExtractorError('Unable to extract info section',
- cause=e)
- else:
- if config.get('view') == 4:
- config = self._verify_player_video_password(redirect_url, video_id, headers)
-
+ channel_id = self._search_regex(
+ r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
+ if channel_id:
+ config_url = self._html_search_regex(
+ r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
+ 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,
+ })
+ if not config_url:
+ 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)
video = config.get('video') or {}
vod = video.get('vod') or {}
def is_rented():
if '>You rented this title.<' in webpage:
return True
- if config.get('user', {}).get('purchased'):
+ if try_get(config, lambda x: x['user']['purchased']):
return True
- for purchase_option in vod.get('purchase_options', []):
+ for purchase_option in (vod.get('purchase_options') or []):
if purchase_option.get('purchased'):
return True
label = purchase_option.get('label_string')
'https://player.vimeo.com/player/%s' % feature_id,
{'force_feature_id': True}), 'Vimeo')
- # Extract video description
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 is_pro:
- orig_webpage = self._download_webpage(
- orig_url, video_id,
- note='Downloading webpage for description',
- fatal=False)
- if orig_webpage:
- video_description = self._html_search_meta(
- 'description', orig_webpage, default=None)
- if not video_description and not is_player:
- self._downloader.report_warning('Cannot find video description')
-
- # Extract upload date
+ ['description', 'og:description', 'twitter:description'],
+ webpage, default=None)
+ if not video_description:
+ self.report_warning('Cannot find video description')
+
if not timestamp:
timestamp = self._search_regex(
r'<time[^>]+datetime="([^"]+)"', webpage,
'timestamp', default=None)
- try:
- view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
- like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
- comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
- except RegexNotFoundError:
- # This info is only available in vimeo.com/{id} urls
- view_count = None
- like_count = None
- comment_count = None
+ 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))
formats = []
info_dict_config = self._parse_config(config, video_id)
formats.extend(info_dict_config['formats'])
- self._vimeo_sort_formats(formats)
+ info_dict['_format_sort_fields'] = info_dict_config['_format_sort_fields']
json_ld = self._search_json_ld(webpage, video_id, default={})
r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
webpage, 'license', default=None, group='license')
- channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
-
- info_dict = {
+ info_dict.update({
'formats': formats,
'timestamp': unified_timestamp(timestamp),
'description': video_description,
'like_count': like_count,
'comment_count': comment_count,
'license': cc_license,
- 'channel_id': channel_id,
- 'channel_url': channel_url,
- }
+ })
- info_dict = merge_dicts(info_dict, info_dict_config, json_ld)
+ return merge_dicts(info_dict, info_dict_config, json_ld)
- return info_dict
-
-class VimeoOndemandIE(VimeoIE):
+class VimeoOndemandIE(VimeoIE): # XXX: Do not subclass from concrete IE
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',
+ 'description': 'md5:aeeba3dbd4d04b0fa98a4fdc9c639998',
'upload_date': '20140906',
'timestamp': 1410032453,
+ '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,
},
'params': {
'format': 'best[protocol=https]',
'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
'upload_date': '20150502',
'timestamp': 1430586422,
+ 'duration': 121,
+ 'comment_count': int,
+ 'view_count': int,
+ 'thumbnail': 'https://i.vimeocdn.com/video/517077723-7066ae1d9a79d3eb361334fb5d58ec13c8f04b52f8dd5eadfbd6fb0bcf11f613-d_1280',
+ 'like_count': int,
},
'params': {
'skip_download': True,
'id': 'tributes',
'title': 'Vimeo Tributes',
},
- 'playlist_mincount': 25,
+ 'playlist_mincount': 22,
}]
_BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
-class VimeoUserIE(VimeoChannelIE):
+class VimeoUserIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'vimeo:user'
- _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
+ _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',
'id': 'nkistudio',
},
'playlist_mincount': 66,
+ }, {
+ 'url': 'https://vimeo.com/nkistudio/',
+ 'only_matching': True,
}]
_BASE_URL_TEMPL = 'https://vimeo.com/%s'
query={'fields': 'description,name,privacy'})
hashed_pass = None
if try_get(album, lambda x: x['privacy']['view']) == 'password':
- password = self._downloader.params.get('videopassword')
+ password = self.get_param('videopassword')
if not password:
raise ExtractorError(
'This album is protected by a password, use the --video-password option',
entries, album_id, album.get('name'), album.get('description'))
-class VimeoGroupsIE(VimeoChannelIE):
+class VimeoGroupsIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'vimeo:group'
_VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
_TESTS = [{
- 'url': 'https://vimeo.com/groups/kattykay',
+ 'url': 'https://vimeo.com/groups/meetup',
'info_dict': {
- 'id': 'kattykay',
- 'title': 'Katty Kay',
+ 'id': 'meetup',
+ 'title': 'Vimeo Meetup!',
},
'playlist_mincount': 27,
}]
'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",
+ 'duration': 304,
+ 'thumbnail': 'https://i.vimeocdn.com/video/450115033-43303819d9ebe24c2630352e18b7056d25197d09b3ae901abdac4c4f1d68de71-d_1280',
+ 'uploader_url': 'https://vimeo.com/user21297594',
},
- 'expected_warnings': ['Unable to download JSON metadata'],
}, {
'note': 'video player needs Referer',
'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
'skip': 'video gone',
}]
- def _real_initialize(self):
- self._login()
-
def _real_extract(self, url):
- page_url, video_id = re.match(self._VALID_URL, url).groups()
- clip_data = self._download_json(
- page_url.replace('/review/', '/review/data/'),
- video_id)['clipData']
- config_url = clip_data['configUrl']
+ page_url, video_id = self._match_valid_url(url).groups()
+ data = self._download_json(
+ page_url.replace('/review/', '/review/data/'), video_id)
+ if data.get('isLocked') is True:
+ 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)
info_dict = self._parse_config(config, 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['description'] = clean_html(clip_data.get('description'))
return info_dict
-class VimeoWatchLaterIE(VimeoChannelIE):
+class VimeoWatchLaterIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'vimeo:watchlater'
- IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
+ IE_DESC = 'Vimeo watch later list, ":vimeowatchlater" keyword (requires authentication)'
_VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
_TITLE = 'Watch Later'
_LOGIN_REQUIRED = True
'only_matching': True,
}]
- def _real_initialize(self):
- self._login()
-
def _page_url(self, base_url, pagenum):
url = '%s/page:%d/' % (base_url, pagenum)
request = sanitized_Request(url)
return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
-class VimeoLikesIE(VimeoChannelIE):
+class VimeoLikesIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
_VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
IE_NAME = 'vimeo:likes'
IE_DESC = 'Vimeo user likes'
class VHXEmbedIE(VimeoBaseInfoExtractor):
IE_NAME = 'vhx:embed'
_VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
+ _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://embed\.vhx\.tv/videos/\d+[^"]*)"']
- @staticmethod
- def _extract_url(webpage):
- mobj = re.search(
- r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage)
- return unescapeHTML(mobj.group(1)) if mobj else None
+ @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)
def _real_extract(self, url):
video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
+ url, _, headers = self._unsmuggle_headers(url)
+ webpage = self._download_webpage(url, video_id, headers=headers)
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)
info['id'] = video_id
- self._vimeo_sort_formats(info['formats'])
return info
+
+
+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:
+ if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 418:
+ 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)