-# encoding: utf-8
+# coding: utf-8
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
+ compat_str,
compat_urlparse,
)
from ..utils import (
- encode_dict,
+ determine_ext,
ExtractorError,
InAdvancePagedList,
int_or_none,
+ merge_dicts,
+ NO_DEFAULT,
RegexNotFoundError,
sanitized_Request,
smuggle_url,
std_headers,
- unified_strdate,
+ try_get,
+ unified_timestamp,
unsmuggle_url,
urlencode_postdata,
unescapeHTML,
+ parse_filesize,
)
_LOGIN_URL = 'https://vimeo.com/log_in'
def _login(self):
- (username, password) = self._get_login_info()
+ 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
- self.report_login()
- webpage = self._download_webpage(self._LOGIN_URL, None, False)
+ webpage = self._download_webpage(
+ self._LOGIN_URL, None, 'Downloading login page')
token, vuid = self._extract_xsrft_and_vuid(webpage)
- data = urlencode_postdata(encode_dict({
+ data = {
'action': 'login',
'email': username,
'password': password,
'service': 'vimeo',
'token': token,
- }))
- login_request = sanitized_Request(self._LOGIN_URL, data)
- login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
- login_request.add_header('Referer', self._LOGIN_URL)
+ }
self._set_vimeo_cookie('vuid', vuid)
- self._download_webpage(login_request, None, False, 'Wrong login info')
+ 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:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
+ raise ExtractorError(
+ 'Unable to log in: bad username or password',
+ expected=True)
+ raise ExtractorError('Unable to log in')
+
+ def _verify_video_password(self, url, video_id, webpage):
+ 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)
+ token, vuid = self._extract_xsrft_and_vuid(webpage)
+ data = urlencode_postdata({
+ 'password': password,
+ 'token': token,
+ })
+ 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')
def _extract_xsrft_and_vuid(self, webpage):
xsrft = self._search_regex(
- r'xsrft\s*[=:]\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
+ 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',
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']
+ # Extract title
+ video_title = video_data['title']
+
+ # Extract uploader, uploader_url and uploader_id
+ video_uploader = video_data.get('owner', {}).get('name')
+ video_uploader_url = video_data.get('owner', {}).get('url')
+ video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
+
+ # Extract video thumbnail
+ video_thumbnail = video_data.get('thumbnail')
+ if video_thumbnail is None:
+ video_thumbs = video_data.get('thumbs')
+ if video_thumbs and isinstance(video_thumbs, dict):
+ _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
+
+ # Extract video duration
+ video_duration = int_or_none(video_data.get('duration'))
+
+ 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')),
+ })
+
+ 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_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:
+ 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)
+
+ 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'],
+ }]
+
+ return {
+ 'title': video_title,
+ 'uploader': video_uploader,
+ 'uploader_id': video_uploader_id,
+ 'uploader_url': video_uploader_url,
+ 'thumbnail': video_thumbnail,
+ 'duration': video_duration,
+ 'formats': formats,
+ 'subtitles': subtitles,
+ }
+
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/[^/?#]+/?(?:$|[?#])|album/)
- (?:.*?/)?
- (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
- (?:videos?/)?
- (?P<id>[0-9]+)
- /?(?:[?&].*)?(?:[#].*)?$'''
+ https?://
+ (?:
+ (?:
+ www|
+ (?P<player>player)
+ )
+ \.
+ )?
+ vimeo(?P<pro>pro)?\.com/
+ (?!(?:channels|album)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
+ (?:.*?/)?
+ (?:
+ (?:
+ play_redirect_hls|
+ moogaloop\.swf)\?clip_id=
+ )?
+ (?:videos?/)?
+ (?P<id>[0-9]+)
+ (?:/[\da-f]+)?
+ /?(?:[?&].*)?(?:[#].*)?$
+ '''
IE_NAME = 'vimeo'
_TESTS = [
{
'id': '56015672',
'ext': 'mp4',
'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
- 'description': 'md5:2d3305bad981a06ff79f027f19865021',
+ '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',
},
},
{
'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',
'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,
'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': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people\u2026',
+ 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
},
'params': {
'videopassword': 'youtube-dl',
{
'url': 'http://vimeo.com/channels/keypeele/75629013',
'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
- 'note': 'Video is freely available via original URL '
- 'and protected with password when accessed via http://vimeo.com/75629013',
'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',
- 'upload_date': '20130927',
+ 'timestamp': 1380339469,
+ 'upload_date': '20130928',
'duration': 187,
},
},
'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,
'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': 'mov',
+ 'title': 'Vimeo Tribute: The Shining',
+ 'uploader': 'Casey Donahue',
+ 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
+ 'uploader_id': 'caseydonahue',
+ '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://vimeo.com/moogaloop.swf?clip_id=2539741',
+ 'only_matching': True,
+ },
{
'url': 'https://vimeo.com/109815029',
'note': 'Video not completely processed, "failed" seed status',
'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,
+ }
]
@staticmethod
- def _extract_vimeo_url(url, webpage):
+ 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
- mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
- if mobj:
- player_url = unescapeHTML(mobj.group('url'))
- surl = smuggle_url(player_url, {'Referer': url})
- return surl
- # Look for embedded (swf embed) Vimeo player
- mobj = re.search(
- r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
- if mobj:
- return mobj.group(1)
+ 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
- def _verify_video_password(self, url, video_id, webpage):
- password = self._downloader.params.get('videopassword', None)
- 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(encode_dict({
- 'password': password,
- 'token': token,
- }))
- 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')
+ @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):
- password = self._downloader.params.get('videopassword', None)
+ 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(encode_dict({'password': password}))
+ data = urlencode_postdata({'password': password})
pass_url = url + '/check-password'
password_request = sanitized_Request(pass_url, data)
password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+ password_request.add_header('Referer', url)
return self._download_json(
password_request, video_id,
- 'Verifying the password',
- 'Wrong password')
+ 'Verifying the password', 'Wrong password')
def _real_initialize(self):
self._login()
def _real_extract(self, url):
- url, data = unsmuggle_url(url)
- headers = std_headers
- if data is not None:
- headers = headers.copy()
- headers.update(data)
+ 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
orig_url = url
if mobj.group('pro') or mobj.group('player'):
url = 'https://player.vimeo.com/video/' + video_id
- else:
+ elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
url = 'https://vimeo.com/' + video_id
# Retrieve video webpage to extract further information
- request = sanitized_Request(url, None, headers)
+ request = sanitized_Request(url, headers=headers)
try:
- webpage = self._download_webpage(request, video_id)
+ webpage, urlh = self._download_webpage_handle(request, video_id)
+ redirect_url = compat_str(urlh.geturl())
+ # Some URLs redirect to ondemand can't be extracted with
+ # this extractor right away thus should be passed through
+ # ondemand extractor (e.g. https://vimeo.com/73445910)
+ if VimeoOndemandIE.suitable(redirect_url):
+ return self.url_result(redirect_url, VimeoOndemandIE.ie_key())
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
errmsg = ee.cause.read()
'%s said: %s' % (self.IE_NAME, seed_status['title']),
expected=True)
+ cc_license = None
+ timestamp = None
+
# Extract the config JSON
try:
try:
vimeo_clip_page_config = self._search_regex(
r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
'vimeo clip page config')
- config_url = self._parse_json(
- vimeo_clip_page_config, video_id)['player']['config_url']
+ page_config = self._parse_json(vimeo_clip_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)
config_json = self._download_webpage(config_url, video_id)
config = json.loads(config_json)
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('(\w)\.video\.id', webpage)
+ 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:
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 data and '_video_password_verified' in data:
+ if '_video_password_verified' in data:
raise ExtractorError('video password verification failed!')
- self._verify_video_password(url, video_id, webpage)
+ self._verify_video_password(redirect_url, video_id, webpage)
return self._real_extract(
- smuggle_url(url, {'_video_password_verified': 'verified'}))
+ 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(url, video_id)
-
- # Extract title
- video_title = config["video"]["title"]
-
- # Extract uploader and uploader_id
- video_uploader = config["video"]["owner"]["name"]
- video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
-
- # Extract video thumbnail
- video_thumbnail = config["video"].get("thumbnail")
- if video_thumbnail is None:
- video_thumbs = config["video"].get("thumbs")
- if video_thumbs and isinstance(video_thumbs, dict):
- _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
+ config = self._verify_player_video_password(redirect_url, video_id)
+
+ def is_rented():
+ if '>You rented this title.<' in webpage:
+ return True
+ if config.get('user', {}).get('purchased'):
+ return True
+ label = try_get(
+ config, lambda x: x['video']['vod']['purchase_options'][0]['label_string'], compat_str)
+ if label and label.startswith('You rented this'):
+ return True
+ return False
+
+ if is_rented():
+ feature_id = config.get('video', {}).get('vod', {}).get('feature_id')
+ if feature_id and not data.get('force_feature_id', False):
+ return self.url_result(smuggle_url(
+ 'https://player.vimeo.com/player/%s' % feature_id,
+ {'force_feature_id': True}), 'Vimeo')
# Extract video description
if not video_description and not mobj.group('player'):
self._downloader.report_warning('Cannot find video description')
- # Extract video duration
- video_duration = int_or_none(config["video"].get("duration"))
-
# Extract upload date
- video_upload_date = None
- mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
- if mobj is not None:
- video_upload_date = unified_strdate(mobj.group(1))
+ 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'))
comment_count = None
formats = []
- config_files = config['video'].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')),
- })
- m3u8_url = config_files.get('hls', {}).get('url')
- if m3u8_url:
- m3u8_formats = self._extract_m3u8_formats(
- m3u8_url, video_id, 'mp4', 'm3u8_native', 0, 'hls', fatal=False)
- if m3u8_formats:
- formats.extend(m3u8_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=('height', 'width', 'fps', 'format_id'))
-
- 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'],
- }]
-
- return {
+ download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={
+ 'X-Requested-With': 'XMLHttpRequest'})
+ download_data = self._download_json(download_request, video_id, fatal=False)
+ 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()
+ formats.append({
+ '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,
+ })
+
+ info_dict_config = self._parse_config(config, video_id)
+ formats.extend(info_dict_config['formats'])
+ self._vimeo_sort_formats(formats)
+
+ json_ld = self._search_json_ld(webpage, video_id, default={})
+
+ if not cc_license:
+ cc_license = self._search_regex(
+ r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
+ webpage, 'license', default=None, group='license')
+
+ info_dict = {
'id': video_id,
- 'uploader': video_uploader,
- 'uploader_id': video_uploader_id,
- 'upload_date': video_upload_date,
- 'title': video_title,
- 'thumbnail': video_thumbnail,
- 'description': video_description,
- 'duration': video_duration,
'formats': formats,
+ 'timestamp': unified_timestamp(timestamp),
+ 'description': video_description,
'webpage_url': url,
'view_count': view_count,
'like_count': like_count,
'comment_count': comment_count,
- 'subtitles': subtitles,
+ 'license': cc_license,
}
+ info_dict = merge_dicts(info_dict, info_dict_config, json_ld)
+
+ return info_dict
+
+
+class VimeoOndemandIE(VimeoBaseInfoExtractor):
+ IE_NAME = 'vimeo:ondemand'
+ _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',
+ 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
+ 'info_dict': {
+ 'id': '105442900',
+ 'ext': 'mp4',
+ 'title': 'המעבדה - במאי יותם פלדמן',
+ 'uploader': 'גם סרטים',
+ 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
+ 'uploader_id': 'gumfilms',
+ },
+ 'params': {
+ 'format': 'best[protocol=https]',
+ },
+ }, {
+ # requires Referer to be passed along with og:video:url
+ 'url': 'https://vimeo.com/ondemand/36938/126682985',
+ 'info_dict': {
+ 'id': '126682985',
+ 'ext': 'mp4',
+ 'title': 'Rävlock, rätt läte på rätt plats',
+ 'uploader': 'Lindroth & Norin',
+ 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user14430847',
+ 'uploader_id': 'user14430847',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ '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,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+ return self.url_result(
+ # Some videos require Referer to be passed along with og:video:url
+ # similarly to generic vimeo embeds (e.g.
+ # https://vimeo.com/ondemand/36938/126682985).
+ VimeoIE._smuggle_referrer(self._og_search_video_url(webpage), url),
+ VimeoIE.ie_key())
+
class VimeoChannelIE(VimeoBaseInfoExtractor):
IE_NAME = 'vimeo:channel'
if not login_form:
return webpage
- password = self._downloader.params.get('videopassword', None)
+ password = self._downloader.params.get('videopassword')
if password is None:
raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
fields = self._hidden_inputs(login_form)
token, vuid = self._extract_xsrft_and_vuid(webpage)
fields['token'] = token
fields['password'] = password
- post = urlencode_postdata(encode_dict(fields))
+ post = urlencode_postdata(fields)
password_path = self._search_regex(
r'action="([^"]+)"', login_form, 'password URL')
password_url = compat_urlparse.urljoin(page_url, password_path)
webpage = self._login_list_password(page_url, list_id, webpage)
yield self._extract_list_title(webpage)
- for video_id in re.findall(r'id="clip_(\d+?)"', webpage):
- yield self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
+ # 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(
+ r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
+ if clips:
+ for video_id, video_url, video_title in clips:
+ yield self.url_result(
+ compat_urlparse.urljoin(base_url, video_url),
+ VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
+ # More relaxed fallback
+ else:
+ for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
+ yield self.url_result(
+ 'https://vimeo.com/%s' % video_id,
+ VimeoIE.ie_key(), video_id=video_id)
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
break
class VimeoAlbumIE(VimeoChannelIE):
IE_NAME = 'vimeo:album'
- _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
+ _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)(?:$|[?#]|/(?!video))'
_TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
_TESTS = [{
'url': 'https://vimeo.com/album/2632481',
'params': {
'videopassword': 'youtube-dl',
}
+ }, {
+ 'url': 'https://vimeo.com/album/2632481/sort:plays/format:thumbnail',
+ 'only_matching': True,
+ }, {
+ # TODO: respect page number
+ 'url': 'https://vimeo.com/album/2632481/page:2/sort:plays/format:thumbnail',
+ 'only_matching': True,
}]
def _page_url(self, base_url, pagenum):
return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
-class VimeoReviewIE(InfoExtractor):
+class VimeoReviewIE(VimeoBaseInfoExtractor):
IE_NAME = 'vimeo:review'
IE_DESC = 'Review pages on vimeo'
_VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
'ext': 'mp4',
'title': "DICK HARDWICK 'Comedian'",
'uploader': 'Richard Hardwick',
+ 'uploader_id': 'user21297594',
}
}, {
'note': 'video player needs Referer',
'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
'uploader': 'DevWeek Events',
'duration': 2773,
- 'thumbnail': 're:^https?://.*\.jpg$',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ 'uploader_id': 'user22258446',
}
+ }, {
+ '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',
+ },
+ 'skip': 'video gone',
}]
+ def _real_initialize(self):
+ self._login()
+
+ def _get_config_url(self, webpage_url, video_id, video_password_verified=False):
+ webpage = self._download_webpage(webpage_url, video_id)
+ config_url = self._html_search_regex(
+ r'data-config-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+ 'config URL', default=None, group='url')
+ if not config_url:
+ data = self._parse_json(self._search_regex(
+ r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data',
+ default=NO_DEFAULT if video_password_verified else '{}'), video_id)
+ config_url = data.get('vimeo_esi', {}).get('config', {}).get('configUrl')
+ if config_url is None:
+ self._verify_video_password(webpage_url, video_id, webpage)
+ config_url = self._get_config_url(
+ webpage_url, video_id, video_password_verified=True)
+ return config_url
+
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
- player_url = 'https://player.vimeo.com/player/' + video_id
- return self.url_result(player_url, 'Vimeo', video_id)
+ video_id = self._match_id(url)
+ config_url = self._get_config_url(url, video_id)
+ config = self._download_json(config_url, video_id)
+ info_dict = self._parse_config(config, video_id)
+ self._vimeo_sort_formats(info_dict['formats'])
+ info_dict['id'] = video_id
+ return info_dict
class VimeoWatchLaterIE(VimeoChannelIE):
class VimeoLikesIE(InfoExtractor):
- _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
+ _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
IE_NAME = 'vimeo:likes'
IE_DESC = 'Vimeo user likes'
- _TEST = {
+ _TESTS = [{
'url': 'https://vimeo.com/user755559/likes/',
'playlist_mincount': 293,
- "info_dict": {
+ 'info_dict': {
'id': 'user755559_likes',
- "description": "See all the videos urza likes",
- "title": 'Videos urza likes',
+ 'description': 'See all the videos urza likes',
+ 'title': 'Videos urza likes',
},
- }
+ }, {
+ 'url': 'https://vimeo.com/stormlapse/likes',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
user_id = self._match_id(url)
self._search_regex(
r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
.*?</a></li>\s*<li\s+class="pagination_next">
- ''', webpage, 'page count'),
+ ''', webpage, 'page count', default=1),
'page count', fatal=True)
PAGE_SIZE = 12
title = self._html_search_regex(
description = self._html_search_meta('description', webpage)
def _get_page(idx):
- page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
+ page_url = 'https://vimeo.com/%s/likes/page:%d/sort:date' % (
user_id, idx + 1)
webpage = self._download_webpage(
page_url, user_id,
return {
'_type': 'playlist',
- 'id': 'user%s_likes' % user_id,
+ 'id': '%s_likes' % user_id,
'title': title,
'description': description,
'entries': pl,
Rapsys Git / youtubedl / blobdiff