+ 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')
+
+ def _extract_xsrft_and_vuid(self, webpage):
+ xsrft = self._search_regex(
+ r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
+ webpage, 'login token', group='xsrft')
+ vuid = self._search_regex(
+ r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
+ webpage, 'vuid', group='vuid')
+ return xsrft, vuid
+
+ 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))
+ 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.
+ self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'tbr', 'format_id'))
+
+ def _parse_config(self, config, video_id):
+ video_data = config['video']
+ video_title = video_data['title']
+ live_event = video_data.get('live_event') or {}
+ is_live = live_event.get('status') == 'started'
+
+ formats = []
+ config_files = video_data.get('files') or config['request'].get('files', {})
+ for f in config_files.get('progressive', []):
+ video_url = f.get('url')
+ if not video_url:
+ continue
+ formats.append({
+ 'url': video_url,
+ 'format_id': 'http-%s' % f.get('quality'),
+ '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')),
+ })
+
+ # TODO: fix handling of 308 status code returned for live archive manifest requests
+ for files_type in ('hls', 'dash'):
+ for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items():
+ manifest_url = cdn_data.get('url')
+ if not manifest_url:
+ continue
+ format_id = '%s-%s' % (files_type, cdn_name)
+ if files_type == 'hls':
+ formats.extend(self._extract_m3u8_formats(
+ manifest_url, video_id, 'mp4',
+ 'm3u8' if is_live else 'm3u8_native', m3u8_id=format_id,
+ note='Downloading %s m3u8 information' % cdn_name,
+ fatal=False))
+ elif files_type == 'dash':
+ mpd_pattern = r'/%s/(?:sep/)?video/' % video_id
+ mpd_manifest_urls = []
+ if re.search(mpd_pattern, manifest_url):
+ for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
+ mpd_manifest_urls.append((format_id + suffix, re.sub(
+ mpd_pattern, '/%s/%s/' % (video_id, repl), manifest_url)))
+ else:
+ mpd_manifest_urls = [(format_id, manifest_url)]
+ for f_id, m_url in mpd_manifest_urls:
+ 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(
+ m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
+ 'Downloading %s MPD information' % cdn_name,
+ fatal=False)
+ for f in mpd_formats:
+ if f.get('vcodec') == 'none':
+ f['preference'] = -50
+ elif f.get('acodec') == 'none':
+ f['preference'] = -40
+ formats.extend(mpd_formats)
+
+ 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,
+ 'preference': 1,
+ })
+
+ subtitles = {}
+ text_tracks = config['request'].get('text_tracks')
+ if text_tracks:
+ for tt in text_tracks:
+ subtitles[tt['lang']] = [{
+ 'ext': 'vtt',
+ 'url': 'https://vimeo.com' + tt['url'],
+ }]
+
+ thumbnails = []
+ if not is_live:
+ for key, thumb in video_data.get('thumbs', {}).items():
+ 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')
+
+ return {
+ 'title': self._live_title(video_title) if is_live else 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')),
+ 'formats': formats,
+ 'subtitles': subtitles,
+ 'is_live': is_live,
+ }
+
+ def _extract_original_format(self, url, video_id):
+ download_data = self._download_json(
+ url, video_id, fatal=False,
+ query={'action': 'load_download_config'},
+ 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,
+ 'preference': 1,
+ }
+
+
+class VimeoIE(VimeoBaseInfoExtractor):
+ """Information extractor for vimeo.com."""
+
+ # _VALID_URL matches Vimeo URLs
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:
+ (?:
+ www|
+ (?P<player>player)
+ )
+ \.
+ )?
+ vimeo(?P<pro>pro)?\.com/
+ (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
+ (?:.*?/)?
+ (?:
+ (?:
+ play_redirect_hls|
+ moogaloop\.swf)\?clip_id=
+ )?
+ (?:videos?/)?
+ (?P<id>[0-9]+)
+ (?:/[\da-f]+)?
+ /?(?:[?&].*)?(?:[#].*)?$
+ '''
+ IE_NAME = 'vimeo'
+ _TESTS = [
+ {
+ 'url': 'http://vimeo.com/56015672#at=0',
+ 'md5': '8879b6cc097e987f02484baf890129e5',
+ 'info_dict': {
+ 'id': '56015672',
+ 'ext': 'mp4',
+ 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
+ 'description': 'md5:509a9ad5c9bf97c60faee9203aca4479',
+ 'timestamp': 1355990239,
+ 'upload_date': '20121220',
+ 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
+ 'uploader_id': 'user7108434',
+ 'uploader': 'Filippo Valsorda',
+ 'duration': 10,
+ 'license': 'by-sa',
+ },
+ },
+ {
+ '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:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
+ 'duration': 1595,
+ },
+ },
+ {
+ 'url': 'http://player.vimeo.com/video/54469442',
+ 'md5': '619b811a4417aa4abe78dc653becf511',
+ 'note': 'Videos that embed the url in the player page',
+ 'info_dict': {
+ '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',
+ 'duration': 3610,
+ 'description': None,
+ },
+ },
+ {
+ 'url': 'http://vimeo.com/68375962',
+ 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
+ 'note': 'Video protected with password',
+ 'info_dict': {
+ '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:dca3ea23adb29ee387127bc4ddfce63f',
+ },
+ 'params': {
+ 'videopassword': 'youtube-dl',
+ },
+ },
+ {
+ 'url': 'http://vimeo.com/channels/keypeele/75629013',
+ 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
+ 'info_dict': {
+ 'id': '75629013',
+ 'ext': 'mp4',
+ 'title': 'Key & Peele: Terrorist Interrogation',
+ 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
+ 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
+ 'uploader_id': 'atencio',
+ 'uploader': 'Peter Atencio',
+ 'channel_id': 'keypeele',
+ 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
+ 'timestamp': 1380339469,
+ 'upload_date': '20130928',
+ 'duration': 187,
+ },
+ 'expected_warnings': ['Unable to download JSON metadata'],
+ },
+ {
+ 'url': 'http://vimeo.com/76979871',
+ 'note': 'Video with subtitles',
+ 'info_dict': {
+ 'id': '76979871',
+ 'ext': 'mp4',
+ 'title': 'The New Vimeo Player (You Know, For Videos)',
+ 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
+ 'timestamp': 1381846109,
+ 'upload_date': '20131015',
+ 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
+ 'uploader_id': 'staff',
+ 'uploader': 'Vimeo Staff',
+ 'duration': 62,
+ }
+ },
+ {
+ # 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',
+ 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
+ 'uploader_id': 'user28849593',
+ },
+ },
+ {
+ # contains original format
+ 'url': 'https://vimeo.com/33951933',
+ 'md5': '53c688fa95a55bf4b7293d37a89c5c53',
+ 'info_dict': {
+ 'id': '33951933',
+ 'ext': 'mp4',
+ 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
+ 'uploader': 'The DMCI',
+ 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
+ 'uploader_id': 'dmci',
+ 'timestamp': 1324343742,
+ 'upload_date': '20111220',
+ 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
+ },
+ },
+ {
+ # 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',
+ 'ext': 'mp4',
+ 'title': 'Vimeo Tribute: The Shining',
+ 'uploader': 'Casey Donahue',
+ 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
+ 'uploader_id': 'caseydonahue',
+ 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
+ 'channel_id': 'tributes',
+ 'timestamp': 1250886430,
+ 'upload_date': '20090821',
+ 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'expected_warnings': ['Unable to download JSON metadata'],
+ },
+ {
+ # redirects to ondemand extractor and should be passed through it
+ # for successful extraction
+ 'url': 'https://vimeo.com/73445910',
+ 'info_dict': {
+ 'id': '73445910',
+ 'ext': 'mp4',
+ 'title': 'The Reluctant Revolutionary',
+ 'uploader': '10Ft Films',
+ 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
+ 'uploader_id': 'tenfootfilms',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ {
+ 'url': 'http://player.vimeo.com/video/68375962',
+ 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
+ 'info_dict': {
+ 'id': '68375962',
+ 'ext': 'mp4',
+ 'title': 'youtube-dl password protected test video',
+ 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
+ 'uploader_id': 'user18948128',
+ 'uploader': 'Jaime Marquínez Ferrándiz',
+ 'duration': 10,
+ },
+ 'params': {
+ 'videopassword': 'youtube-dl',
+ },
+ },
+ {
+ 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
+ 'only_matching': True,
+ },
+ {
+ 'url': 'https://vimeo.com/109815029',
+ 'note': 'Video not completely processed, "failed" seed status',
+ 'only_matching': True,
+ },
+ {
+ 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
+ 'only_matching': True,
+ },
+ {
+ 'url': 'https://vimeo.com/album/2632481/video/79010983',
+ 'only_matching': True,
+ },
+ {
+ # source file returns 403: Forbidden
+ 'url': 'https://vimeo.com/7809605',
+ 'only_matching': True,
+ },
+ {
+ 'url': 'https://vimeo.com/160743502/abd0e13fb4',
+ '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
+
+ @staticmethod
+ def _extract_url(url, webpage):
+ urls = VimeoIE._extract_urls(url, webpage)
+ return urls[0] if urls else 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')
+ data = urlencode_postdata({
+ 'password': base64.b64encode(password.encode()),
+ })
+ headers = merge_dicts(headers, {
+ 'Content-Type': 'application/x-www-form-urlencoded',
+ })
+ checked = self._download_json(
+ url + '/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 _real_extract(self, url):
+ url, data = unsmuggle_url(url, {})
+ headers = std_headers.copy()
+ if 'http_headers' in data:
+ headers.update(data['http_headers'])
+ if 'Referer' not in headers:
+ headers['Referer'] = url
+
+ channel_id = self._search_regex(
+ r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
Rapsys Git / youtubedl / blobdiff