From 472dcdd6e1897964c280ba956a7f0223502c1c28 Mon Sep 17 00:00:00 2001 From: bashonly Date: Thu, 14 Aug 2025 13:35:18 -0500 Subject: [PATCH 1/6] [ie/vimeo:album] Support embed-only albums Authored by: bashonly --- yt_dlp/extractor/vimeo.py | 175 ++++++++++++++++++++++---------------- 1 file changed, 103 insertions(+), 72 deletions(-) diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index b22bea5204..7de8c58711 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -117,13 +117,13 @@ class VimeoBaseInfoExtractor(InfoExtractor): def _jwt_is_expired(self, token): return jwt_decode_hs256(token)['exp'] - time.time() < 120 - def _fetch_viewer_info(self, display_id=None, fatal=True): + def _fetch_viewer_info(self, display_id=None): if self._viewer_info and not self._jwt_is_expired(self._viewer_info['jwt']): return self._viewer_info self._viewer_info = self._download_json( 'https://vimeo.com/_next/viewer', display_id, 'Downloading web token info', - 'Failed to download web token info', fatal=fatal, headers={'Accept': 'application/json'}) + 'Failed to download web token info', headers={'Accept': 'application/json'}) return self._viewer_info @@ -502,6 +502,43 @@ class VimeoBaseInfoExtractor(InfoExtractor): 'quality': 1, } + @staticmethod + def _get_embed_params(is_embed, referer): + return { + 'is_embed': 'true' if is_embed else 'false', + 'referrer': urllib.parse.urlparse(referer).hostname if referer and is_embed else '', + } + + def _get_album_data_and_hashed_pass(self, album_id, is_embed, referer): + viewer = self._fetch_viewer_info(album_id) + jwt = viewer['jwt'] + album = self._download_json( + 'https://api.vimeo.com/albums/' + album_id, + album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'}, + query={**self._get_embed_params(is_embed, referer), 'fields': 'description,name,privacy'}) + hashed_pass = None + if traverse_obj(album, ('privacy', 'view')) == 'password': + password = self.get_param('videopassword') + if not password: + raise ExtractorError( + 'This album is protected by a password, use the --video-password option', + expected=True) + try: + hashed_pass = self._download_json( + f'https://vimeo.com/showcase/{album_id}/auth', + album_id, 'Verifying the password', data=urlencode_postdata({ + 'password': password, + 'token': viewer['xsrft'], + }), headers={ + 'X-Requested-With': 'XMLHttpRequest', + })['hashed_pass'] + except ExtractorError as e: + if isinstance(e.cause, HTTPError) and e.cause.status == 401: + raise ExtractorError('Wrong password', expected=True) + raise + + return album, hashed_pass + class VimeoIE(VimeoBaseInfoExtractor): """Information extractor for vimeo.com.""" @@ -1188,41 +1225,12 @@ class VimeoIE(VimeoBaseInfoExtractor): info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total'])) return info - def _try_album_password(self, url): + def _try_album_password(self, url, is_embed, referer): album_id = self._search_regex( r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None) if not album_id: return - viewer = self._fetch_viewer_info(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*({.+?})', - webpage, 'bootstrap data'), album_id)['viewer'] - jwt = viewer['jwt'] - album = self._download_json( - 'https://api.vimeo.com/albums/' + album_id, - album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'}, - query={'fields': 'description,name,privacy'}) - if try_get(album, lambda x: x['privacy']['view']) == 'password': - password = self.get_param('videopassword') - if not password: - raise ExtractorError( - 'This album is protected by a password, use the --video-password option', - expected=True) - try: - self._download_json( - f'https://vimeo.com/showcase/{album_id}/auth', - album_id, 'Verifying the password', data=urlencode_postdata({ - 'password': password, - 'token': viewer['xsrft'], - }), headers={ - 'X-Requested-With': 'XMLHttpRequest', - }) - except ExtractorError as e: - if isinstance(e.cause, HTTPError) and e.cause.status == 401: - raise ExtractorError('Wrong password', expected=True) - raise + self._get_album_data_and_hashed_pass(album_id, is_embed, referer) def _real_extract(self, url): url, data, headers = self._unsmuggle_headers(url) @@ -1238,7 +1246,8 @@ class VimeoIE(VimeoBaseInfoExtractor): if any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')): url = 'https://vimeo.com/' + video_id - self._try_album_password(url) + is_player_url = urllib.parse.urlparse(url).hostname == 'player.vimeo.com' + self._try_album_password(url, is_player_url, headers['Referer']) is_secure = urllib.parse.urlparse(url).scheme == 'https' try: # Retrieve video webpage to extract further information @@ -1265,7 +1274,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 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) - if '://player.vimeo.com/video/' in url: + if is_player_url: config = self._search_json( r'\b(?:playerC|c)onfig\s*=', webpage, 'info section', video_id) if config.get('view') == 4: @@ -1531,7 +1540,7 @@ class VimeoUserIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE class VimeoAlbumIE(VimeoBaseInfoExtractor): IE_NAME = 'vimeo:album' - _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P\d+)(?:$|[?#]|/(?!video))' + _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P\d+)(?:$|[?#]|(?P/embed))' _TITLE_RE = r'
\n\s*

(.*?)

' _TESTS = [{ 'url': 'https://vimeo.com/album/2632481', @@ -1549,12 +1558,54 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor): }, 'playlist_count': 1, 'params': {'videopassword': 'youtube-dl'}, + }, { + 'note': 'embedded album that requires "referrer" in query (smuggled)', + 'url': 'https://vimeo.com/showcase/10677689/embed#__youtubedl_smuggle=%7B%22referer%22%3A+%22https%3A%2F%2Fwww.riccardomutimusic.com%2F%22%7D', + 'info_dict': { + 'title': 'La Traviata - la serie completa', + 'id': '10677689', + }, + 'playlist': [{ + 'url': 'https://player.vimeo.com/video/505682113#__youtubedl_smuggle=%7B%22referer%22%3A+%22https%3A%2F%2Fwww.riccardomutimusic.com%2F%22%7D', + 'info_dict': { + 'id': '505682113', + 'ext': 'mp4', + 'title': 'La Traviata - Episodio 7', + 'uploader': 'RMMusic', + 'uploader_id': 'user62556494', + 'uploader_url': 'https://vimeo.com/user62556494', + 'duration': 3202, + 'thumbnail': r're:https?://i\.vimeocdn\.com/video/.+', + }, + }], + 'params': { + 'playlist_items': '1', + 'skip_download': 'm3u8', + }, + 'expected_warnings': ['Failed to parse XML: not well-formed'], + }, { + 'note': 'embedded album that requires "referrer" in query (passed as param)', + 'url': 'https://vimeo.com/showcase/10677689/embed', + 'info_dict': { + 'title': 'La Traviata - la serie completa', + 'id': '10677689', + }, + 'playlist_mincount': 9, + 'params': {'http_headers': {'Referer': 'https://www.riccardomutimusic.com/'}}, + }, { + 'url': 'https://vimeo.com/showcase/11803104/embed2', + 'info_dict': { + 'title': 'Romans Video Ministry', + 'id': '11803104', + }, + 'playlist_mincount': 41, }] _PAGE_SIZE = 100 - def _fetch_page(self, album_id, authorization, hashed_pass, page): + def _fetch_page(self, album_id, hashed_pass, is_embed, referer, page): api_page = page + 1 query = { + **self._get_embed_params(is_embed, referer), 'fields': 'link,uri', 'page': api_page, 'per_page': self._PAGE_SIZE, @@ -1565,7 +1616,7 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor): videos = self._download_json( f'https://api.vimeo.com/albums/{album_id}/videos', album_id, f'Downloading page {api_page}', query=query, headers={ - 'Authorization': 'jwt ' + authorization, + 'Authorization': 'jwt ' + self._fetch_viewer_info(album_id)['jwt'], 'Accept': 'application/json', })['data'] except ExtractorError as e: @@ -1577,44 +1628,24 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor): if not link: continue uri = video.get('uri') - video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None + video_id = self._search_regex(r'/videos/(\d+)', uri, 'id', default=None) if uri else None + if is_embed: + if not video_id: + self.report_warning(f'Skipping due to missing video ID: {link}') + continue + link = f'https://player.vimeo.com/video/{video_id}' + if referer: + link = self._smuggle_referrer(link, referer) yield self.url_result(link, VimeoIE.ie_key(), video_id) def _real_extract(self, url): - album_id = self._match_id(url) - viewer = self._fetch_viewer_info(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*({.+?})', - webpage, 'bootstrap data'), album_id)['viewer'] - jwt = viewer['jwt'] - album = self._download_json( - 'https://api.vimeo.com/albums/' + album_id, - album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'}, - query={'fields': 'description,name,privacy'}) - hashed_pass = None - if try_get(album, lambda x: x['privacy']['view']) == 'password': - password = self.get_param('videopassword') - if not password: - raise ExtractorError( - 'This album is protected by a password, use the --video-password option', - expected=True) - try: - hashed_pass = self._download_json( - f'https://vimeo.com/showcase/{album_id}/auth', - album_id, 'Verifying the password', data=urlencode_postdata({ - 'password': password, - 'token': viewer['xsrft'], - }), headers={ - 'X-Requested-With': 'XMLHttpRequest', - })['hashed_pass'] - except ExtractorError as e: - if isinstance(e.cause, HTTPError) and e.cause.status == 401: - raise ExtractorError('Wrong password', expected=True) - raise + url, _, http_headers = self._unsmuggle_headers(url) + album_id, is_embed = self._match_valid_url(url).group('id', 'is_embed') + referer = http_headers.get('Referer') + album, hashed_pass = self._get_album_data_and_hashed_pass(album_id, is_embed, referer) + entries = OnDemandPagedList(functools.partial( - self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE) + self._fetch_page, album_id, hashed_pass, is_embed, referer), self._PAGE_SIZE) return self.playlist_result( entries, album_id, album.get('name'), album.get('description')) From 038fbf08a5302e6f194c06b3539ba251c7e0f236 Mon Sep 17 00:00:00 2001 From: bashonly Date: Thu, 14 Aug 2025 16:10:35 -0500 Subject: [PATCH 2/6] [ie/vimeo:album] Support URLs with non-numeric IDs Authored by: bashonly --- yt_dlp/extractor/vimeo.py | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index 7de8c58711..46f6ba9873 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -28,7 +28,6 @@ from ..utils import ( qualities, smuggle_url, str_or_none, - traverse_obj, try_call, try_get, unified_timestamp, @@ -39,6 +38,7 @@ from ..utils import ( urlhandle_detect_ext, urljoin, ) +from ..utils.traversal import require, traverse_obj class VimeoBaseInfoExtractor(InfoExtractor): @@ -1540,7 +1540,7 @@ class VimeoUserIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE class VimeoAlbumIE(VimeoBaseInfoExtractor): IE_NAME = 'vimeo:album' - _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P\d+)(?:$|[?#]|(?P/embed))' + _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P[^/?#]+)(?:$|[?#]|(?P/embed))' _TITLE_RE = r'
\n\s*

(.*?)

' _TESTS = [{ 'url': 'https://vimeo.com/album/2632481', @@ -1599,6 +1599,15 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor): 'id': '11803104', }, 'playlist_mincount': 41, + }, { + 'note': 'non-numeric slug, need to fetch numeric album ID', + 'url': 'https://vimeo.com/showcase/BethelTally-Homegoing-Services', + 'info_dict': { + 'title': 'BethelTally Homegoing Services', + 'id': '11547429', + 'description': 'Bethel Missionary Baptist Church\nTallahassee, FL', + }, + 'playlist_mincount': 8, }] _PAGE_SIZE = 100 @@ -1642,6 +1651,15 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor): url, _, http_headers = self._unsmuggle_headers(url) album_id, is_embed = self._match_valid_url(url).group('id', 'is_embed') referer = http_headers.get('Referer') + + if not re.fullmatch(r'[0-9]+', album_id): + auth_info = self._download_json( + f'https://vimeo.com/showcase/{album_id}/auth', album_id, 'Downloading album info', + headers={'X-Requested-With': 'XMLHttpRequest', 'Referer': referer}, + expected_status=(401, 403)) + album_id = traverse_obj(auth_info, ( + 'metadata', 'id', {int}, {str_or_none}, {require('album ID')})) + album, hashed_pass = self._get_album_data_and_hashed_pass(album_id, is_embed, referer) entries = OnDemandPagedList(functools.partial( From 3dc964795a027f69c1784b8b9b78284b7fe17e06 Mon Sep 17 00:00:00 2001 From: bashonly Date: Thu, 14 Aug 2025 16:57:39 -0500 Subject: [PATCH 3/6] catch and raise for referer required Authored by: bashonly --- yt_dlp/extractor/vimeo.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index 46f6ba9873..722fc0a5a0 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -1660,7 +1660,12 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor): album_id = traverse_obj(auth_info, ( 'metadata', 'id', {int}, {str_or_none}, {require('album ID')})) - album, hashed_pass = self._get_album_data_and_hashed_pass(album_id, is_embed, referer) + try: + album, hashed_pass = self._get_album_data_and_hashed_pass(album_id, is_embed, referer) + except ExtractorError as e: + if is_embed and not referer and isinstance(e.cause, HTTPError) and e.cause.status == 403: + raise ExtractorError(self._REFERER_HINT, expected=True) + raise entries = OnDemandPagedList(functools.partial( self._fetch_page, album_id, hashed_pass, is_embed, referer), self._PAGE_SIZE) From 4ad3288345a9e0c28fceb17f68a572934c8942d0 Mon Sep 17 00:00:00 2001 From: bashonly Date: Thu, 14 Aug 2025 17:23:32 -0500 Subject: [PATCH 4/6] cleanup Authored by: bashonly --- yt_dlp/extractor/vimeo.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index 722fc0a5a0..fa2e217962 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -1655,8 +1655,7 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor): if not re.fullmatch(r'[0-9]+', album_id): auth_info = self._download_json( f'https://vimeo.com/showcase/{album_id}/auth', album_id, 'Downloading album info', - headers={'X-Requested-With': 'XMLHttpRequest', 'Referer': referer}, - expected_status=(401, 403)) + headers={'X-Requested-With': 'XMLHttpRequest'}, expected_status=(401, 403)) album_id = traverse_obj(auth_info, ( 'metadata', 'id', {int}, {str_or_none}, {require('album ID')})) From d5311a82622da3cb67b9c38b9338d00666a00ed7 Mon Sep 17 00:00:00 2001 From: bashonly Date: Thu, 14 Aug 2025 17:45:32 -0500 Subject: [PATCH 5/6] more cleanup Authored by: bashonly --- yt_dlp/extractor/vimeo.py | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index fa2e217962..014d75292e 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -1225,13 +1225,6 @@ class VimeoIE(VimeoBaseInfoExtractor): info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total'])) return info - def _try_album_password(self, url, is_embed, referer): - album_id = self._search_regex( - r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None) - if not album_id: - return - self._get_album_data_and_hashed_pass(album_id, is_embed, referer) - def _real_extract(self, url): url, data, headers = self._unsmuggle_headers(url) if 'Referer' not in headers: @@ -1246,9 +1239,14 @@ class VimeoIE(VimeoBaseInfoExtractor): if any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')): url = 'https://vimeo.com/' + video_id - is_player_url = urllib.parse.urlparse(url).hostname == 'player.vimeo.com' - self._try_album_password(url, is_player_url, headers['Referer']) - is_secure = urllib.parse.urlparse(url).scheme == 'https' + album_id = self._search_regex( + r'vimeo\.com/(?:album|showcase)/([0-9]+)/', url, 'album id', default=None) + if album_id: + # Detect password-protected showcase video => POST album password => set cookies + self._get_album_data_and_hashed_pass(album_id, '/embed' in url, headers['Referer']) + + parsed_url = urllib.parse.urlparse(url) + is_secure = parsed_url.scheme == 'https' try: # Retrieve video webpage to extract further information webpage, urlh = self._download_webpage_handle( @@ -1274,7 +1272,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 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) - if is_player_url: + if parsed_url.hostname == 'player.vimeo.com': config = self._search_json( r'\b(?:playerC|c)onfig\s*=', webpage, 'info section', video_id) if config.get('view') == 4: @@ -1302,7 +1300,7 @@ class VimeoIE(VimeoBaseInfoExtractor): config_url = None channel_id = self._search_regex( - r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None) + r'vimeo\.com/channels/([^/?#]+)', url, 'channel id', default=None) if channel_id: config_url = self._extract_config_url(webpage, default=None) video_description = clean_html(get_element_by_class('description', webpage)) From 00dd39eb2b277b6b789caae117eaa7f72d92a95f Mon Sep 17 00:00:00 2001 From: bashonly Date: Thu, 14 Aug 2025 17:47:39 -0500 Subject: [PATCH 6/6] even more cleanup Authored by: bashonly --- yt_dlp/extractor/vimeo.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index 014d75292e..a438d148ab 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -1243,7 +1243,7 @@ class VimeoIE(VimeoBaseInfoExtractor): r'vimeo\.com/(?:album|showcase)/([0-9]+)/', url, 'album id', default=None) if album_id: # Detect password-protected showcase video => POST album password => set cookies - self._get_album_data_and_hashed_pass(album_id, '/embed' in url, headers['Referer']) + self._get_album_data_and_hashed_pass(album_id, False, None) parsed_url = urllib.parse.urlparse(url) is_secure = parsed_url.scheme == 'https'