determine_ext,
ExtractorError,
get_element_by_class,
+ HEADRequest,
js_to_json,
int_or_none,
merge_dicts,
parse_qs,
sanitized_Request,
smuggle_url,
- std_headers,
str_or_none,
try_get,
unified_timestamp,
urlencode_postdata,
urljoin,
unescapeHTML,
+ urlhandle_detect_ext,
)
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)
+ # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
+ # at the same time without actual units specified.
+ self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source'))
def _parse_config(self, config, video_id):
video_data = config['video']
request = config.get('request') or {}
formats = []
+ 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')
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')),
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 = {}
for tt in (request.get('text_tracks') or []):
- subtitles[tt['lang']] = [{
+ subtitles.setdefault(tt['lang'], []).append({
'ext': 'vtt',
'url': urljoin('https://vimeo.com', tt['url']),
- }]
+ })
thumbnails = []
if not is_live:
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,
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 {}
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) or {}
- for download_data in original_response.get('download') or {}:
+ 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
- query = parse_qs(download_url)
+ 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': determine_ext(query.get('filename', [''])[0].lower()),
+ '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')),
)?
vimeo(?:pro)?\.com/
(?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
- (?:.*?/)?
+ (?:[^/]+/)*?
(?:
(?:
play_redirect_hls|
'params': {
'format': 'best[protocol=https]',
},
- 'expected_warnings': ['Unable to download JSON metadata'],
},
{
'url': 'http://vimeo.com/68375962',
'upload_date': '20130928',
'duration': 187,
},
- 'expected_warnings': ['Unable to download JSON metadata'],
+ 'params': {'format': 'http-1080p'},
},
{
'url': 'http://vimeo.com/76979871',
'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/
'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
'upload_date': '20200225',
},
- 'expected_warnings': ['Unable to download JSON metadata'],
},
{
# only available via https://vimeo.com/channels/tributes/6213729 and
'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.',
},
{
'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',
+ },
+ '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',
+ },
+ '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',
+ # these have to be provided but we don't care
+ 'ext': 'mp4',
+ 'timestamp': 1627621014,
+ 'title': 're:.+',
+ 'uploader_id': 're:.+',
+ 'uploader': 're:.+',
+ 'upload_date': r're:\d+',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
}
# https://gettingthingsdone.com/workflowmap/
# vimeo embed with check-password page protected by Referer header
def _real_extract(self, url):
url, data = unsmuggle_url(url, {})
- headers = std_headers.copy()
+ headers = self.get_param('http_headers').copy()
if 'http_headers' in data:
headers.update(data['http_headers'])
if 'Referer' not in headers:
headers['Referer'] = url
# Extract ID from URL
- video_id, unlisted_hash = self._match_valid_url(url).groups()
+ 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)
timestamp = None
video_description = None
info_dict = {}
+ config_url = None
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')
+ 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,
})
- else:
+ 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)
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_id': 'user21297594',
'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
},
- 'expected_warnings': ['Unable to download JSON metadata'],
}, {
'note': 'video player needs Referer',
'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
projects / yt-dlp.git / blobdiff