-# encoding: utf-8
+# coding: utf-8
from __future__ import unicode_literals
import json
import itertools
from .common import InfoExtractor
-from .subtitles import SubtitlesInfoExtractor
from ..compat import (
compat_HTTPError,
- compat_urllib_parse,
- compat_urllib_request,
+ compat_str,
compat_urlparse,
)
from ..utils import (
+ determine_ext,
ExtractorError,
InAdvancePagedList,
int_or_none,
+ NO_DEFAULT,
RegexNotFoundError,
+ sanitized_Request,
+ smuggle_url,
std_headers,
+ unified_strdate,
unsmuggle_url,
urlencode_postdata,
+ unescapeHTML,
+ parse_filesize,
+ try_get,
)
class VimeoBaseInfoExtractor(InfoExtractor):
_NETRC_MACHINE = 'vimeo'
_LOGIN_REQUIRED = False
+ _LOGIN_URL = 'https://vimeo.com/log_in'
def _login(self):
(username, password) = self._get_login_info()
raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
return
self.report_login()
- login_url = 'https://vimeo.com/log_in'
- webpage = self._download_webpage(login_url, None, False)
- token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
+ webpage = self._download_webpage(self._LOGIN_URL, None, False)
+ token, vuid = self._extract_xsrft_and_vuid(webpage)
data = urlencode_postdata({
+ 'action': 'login',
'email': username,
'password': password,
- 'action': 'login',
'service': 'vimeo',
'token': token,
})
- login_request = compat_urllib_request.Request(login_url, data)
+ login_request = sanitized_Request(self._LOGIN_URL, data)
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
- login_request.add_header('Cookie', 'xsrft=%s' % token)
+ login_request.add_header('Referer', self._LOGIN_URL)
+ self._set_vimeo_cookie('vuid', vuid)
self._download_webpage(login_request, None, False, 'Wrong login info')
+ 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'(?:(?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 _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', 'format_id'))
+
+ def _parse_config(self, config, video_id):
+ # Extract title
+ video_title = config['video']['title']
+
+ # Extract uploader, uploader_url and uploader_id
+ video_uploader = config['video'].get('owner', {}).get('name')
+ video_uploader_url = config['video'].get('owner', {}).get('url')
+ video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_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]
+
+ # Extract video duration
+ video_duration = int_or_none(config['video'].get('duration'))
-class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
+ 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:
+ formats.extend(self._extract_m3u8_formats(
+ m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+
+ 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 = [
{
'info_dict': {
'id': '56015672',
'ext': 'mp4',
- "upload_date": "20121220",
- "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
- "uploader_id": "user7108434",
- "uploader": "Filippo Valsorda",
- "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
- "duration": 10,
+ 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
+ 'description': 'md5:2d3305bad981a06ff79f027f19865021',
+ 'upload_date': '20121220',
+ 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user7108434',
+ 'uploader_id': 'user7108434',
+ 'uploader': 'Filippo Valsorda',
+ 'duration': 10,
},
},
{
'info_dict': {
'id': '68093876',
'ext': 'mp4',
+ 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
'uploader_id': 'openstreetmapus',
'uploader': 'OpenStreetMap US',
'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
- 'description': 'md5:380943ec71b89736ff4bf27183233d09',
+ 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
'duration': 1595,
},
},
'ext': 'mp4',
'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
'uploader': 'The BLN & Business of Software',
+ 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
'uploader_id': 'theblnbusinessofsoftware',
'duration': 3610,
'description': None,
'ext': 'mp4',
'title': 'youtube-dl password protected test video',
'upload_date': '20130614',
+ 'uploader_url': '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 who love them.',
+ 'description': 'This is "youtube-dl password protected test video" by on Vimeo, the home for high quality videos and the people who love them.',
},
'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': 're:https?://(?:www\.)?vimeo\.com/atencio',
'uploader_id': 'atencio',
'uploader': 'Peter Atencio',
+ 'upload_date': '20130927',
'duration': 187,
},
},
{
'url': 'http://vimeo.com/76979871',
- 'md5': '3363dd6ffebe3784d56f4132317fd446',
'note': 'Video with subtitles',
'info_dict': {
'id': '76979871',
'title': 'The New Vimeo Player (You Know, For Videos)',
'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
'upload_date': '20131015',
+ 'uploader_url': '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': 're:https?://(?:www\.)?vimeo\.com/user28849593',
'uploader_id': 'user28849593',
},
},
+ {
+ # contains original format
+ 'url': 'https://vimeo.com/33951933',
+ 'md5': '2d9f5475e0537f013d0073e812ab89e6',
+ 'info_dict': {
+ 'id': '33951933',
+ 'ext': 'mp4',
+ 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
+ 'uploader': 'The DMCI',
+ 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/dmci',
+ 'uploader_id': 'dmci',
+ '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': 're:https?://(?:www\.)?vimeo\.com/caseydonahue',
+ 'uploader_id': 'caseydonahue',
+ '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 throught it
+ # for successful extraction
+ 'url': 'https://vimeo.com/73445910',
+ 'info_dict': {
+ 'id': '73445910',
+ 'ext': 'mp4',
+ 'title': 'The Reluctant Revolutionary',
+ 'uploader': '10Ft Films',
+ 'uploader_url': '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',
+ '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,
+ }
]
- 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')
- token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
- data = compat_urllib_parse.urlencode({
- 'password': password,
- 'token': token,
- })
- # I didn't manage to use the password with https
- if url.startswith('https'):
- pass_url = url.replace('https', 'http')
- else:
- pass_url = url
- password_request = compat_urllib_request.Request(pass_url + '/password', data)
- password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
- password_request.add_header('Cookie', 'xsrft=%s' % token)
- self._download_webpage(password_request, video_id,
- 'Verifying the password',
- 'Wrong password')
+ @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/.+?)\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):
- 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 = compat_urllib_parse.urlencode({'password': password})
+ data = urlencode_postdata({'password': password})
pass_url = url + '/check-password'
- password_request = compat_urllib_request.Request(pass_url, data)
+ 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
video_id = mobj.group('id')
orig_url = url
if mobj.group('pro') or mobj.group('player'):
- url = 'http://player.vimeo.com/video/' + video_id
+ url = 'https://player.vimeo.com/video/' + video_id
+ 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 = compat_urllib_request.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)
+ # 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(urlh.geturl()):
+ return self.url_result(urlh.geturl(), VimeoOndemandIE.ie_key())
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
errmsg = ee.cause.read()
# and latter we extract those that are Vimeo specific.
self.report_extraction(video_id)
+ vimeo_config = self._search_regex(
+ r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
+ 'vimeo config', default=None)
+ if vimeo_config:
+ seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
+ if seed_status.get('state') == 'failed':
+ raise ExtractorError(
+ '%s said: %s' % (self.IE_NAME, seed_status['title']),
+ expected=True)
+
# Extract the config JSON
try:
try:
config_url = self._html_search_regex(
- r' data-config-url="(.+?)"', webpage, 'config URL')
+ 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/rg3/youtube-dl/pull/7209)
+ 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']
config_json = self._download_webpage(config_url, video_id)
config = json.loads(config_json)
except RegexNotFoundError:
else:
config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
config = self._search_regex(config_re, webpage, 'info section',
- flags=re.DOTALL)
+ 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('<form[^>]+?id="pw_form"', webpage) is not None:
+ 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(url, video_id, webpage)
- return self._real_extract(url)
+ return self._real_extract(
+ smuggle_url(url, {'_video_password_verified': 'verified'}))
else:
raise ExtractorError('Unable to extract info section',
cause=e)
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]
+ 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'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
+ mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
if mobj is not None:
- video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
+ video_upload_date = unified_strdate(mobj.group(1))
try:
view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
like_count = None
comment_count = None
- # Vimeo specific: extract request signature and timestamp
- sig = config['request']['signature']
- timestamp = config['request']['timestamp']
-
- # Vimeo specific: extract video codec and quality information
- # First consider quality, then codecs, then take everything
- codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]
- files = {'hd': [], 'sd': [], 'other': []}
- config_files = config["video"].get("files") or config["request"].get("files")
- for codec_name, codec_extension in codecs:
- for quality in config_files.get(codec_name, []):
- format_id = '-'.join((codec_name, quality)).lower()
- key = quality if quality in files else 'other'
- video_url = None
- if isinstance(config_files[codec_name], dict):
- file_info = config_files[codec_name][quality]
- video_url = file_info.get('url')
- else:
- file_info = {}
- if video_url is None:
- video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
- % (video_id, sig, timestamp, quality, codec_name.upper())
-
- files[key].append({
- 'ext': codec_extension,
- 'url': video_url,
- 'format_id': format_id,
- 'width': file_info.get('width'),
- 'height': file_info.get('height'),
- })
formats = []
- for key in ('other', 'sd', 'hd'):
- formats += files[key]
- if len(formats) == 0:
- raise ExtractorError('No known codec found')
-
- subtitles = {}
- text_tracks = config['request'].get('text_tracks')
- if text_tracks:
- for tt in text_tracks:
- subtitles[tt['lang']] = 'http://vimeo.com' + tt['url']
-
- video_subtitles = self.extract_subtitles(video_id, subtitles)
- if self._downloader.params.get('listsubtitles', False):
- self._list_available_subtitles(video_id, subtitles)
- return
-
- 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 = source_file.get('extension', determine_ext(download_url)).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 = self._parse_config(config, video_id)
+ formats.extend(info_dict['formats'])
+ self._vimeo_sort_formats(formats)
+ info_dict.update({
'id': video_id,
- 'uploader': video_uploader,
- 'uploader_id': video_uploader_id,
+ 'formats': formats,
'upload_date': video_upload_date,
- 'title': video_title,
- 'thumbnail': video_thumbnail,
'description': video_description,
- 'duration': video_duration,
- 'formats': formats,
'webpage_url': url,
'view_count': view_count,
'like_count': like_count,
'comment_count': comment_count,
- 'subtitles': video_subtitles,
- }
+ })
+
+ 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': 're:https?://(?:www\.)?vimeo\.com/gumfilms',
+ 'uploader_id': 'gumfilms',
+ },
+ }, {
+ # 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': '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(InfoExtractor):
+
+class VimeoChannelIE(VimeoBaseInfoExtractor):
IE_NAME = 'vimeo:channel'
- _VALID_URL = r'https?://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
+ _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
_MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
+ _TITLE = None
_TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
_TESTS = [{
- 'url': 'http://vimeo.com/channels/tributes',
+ 'url': 'https://vimeo.com/channels/tributes',
'info_dict': {
+ 'id': 'tributes',
'title': 'Vimeo Tributes',
},
'playlist_mincount': 25,
return '%s/videos/page:%d/' % (base_url, pagenum)
def _extract_list_title(self, webpage):
- return self._html_search_regex(self._TITLE_RE, webpage, 'list title')
+ return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
- def _extract_videos(self, list_id, base_url):
- video_ids = []
+ def _login_list_password(self, page_url, list_id, webpage):
+ login_form = self._search_regex(
+ r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
+ webpage, 'login form', default=None)
+ if not login_form:
+ return webpage
+
+ 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(fields)
+ password_path = self._search_regex(
+ r'action="([^"]+)"', login_form, 'password URL')
+ password_url = compat_urlparse.urljoin(page_url, password_path)
+ password_request = sanitized_Request(password_url, post)
+ password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
+ self._set_vimeo_cookie('vuid', vuid)
+ self._set_vimeo_cookie('xsrft', token)
+
+ return self._download_webpage(
+ password_request, list_id,
+ 'Verifying the password', 'Wrong password')
+
+ def _title_and_entries(self, list_id, base_url):
for pagenum in itertools.count(1):
+ page_url = self._page_url(base_url, pagenum)
webpage = self._download_webpage(
- self._page_url(base_url, pagenum), list_id,
+ page_url, list_id,
'Downloading page %s' % pagenum)
- video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
+
+ if pagenum == 1:
+ webpage = self._login_list_password(page_url, list_id, webpage)
+ yield self._extract_list_title(webpage)
+
+ # 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)', webpage)
+ if clips:
+ for video_id, video_url in clips:
+ yield self.url_result(
+ compat_urlparse.urljoin(base_url, video_url),
+ VimeoIE.ie_key(), video_id=video_id)
+ # 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
- entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
- for video_id in video_ids]
- return {'_type': 'playlist',
- 'id': list_id,
- 'title': self._extract_list_title(webpage),
- 'entries': entries,
- }
+ def _extract_videos(self, list_id, base_url):
+ title_and_entries = self._title_and_entries(list_id, base_url)
+ list_title = next(title_and_entries)
+ return self.playlist_result(title_and_entries, list_id, list_title)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
channel_id = mobj.group('id')
- return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id)
+ return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
class VimeoUserIE(VimeoChannelIE):
IE_NAME = 'vimeo:user'
- _VALID_URL = r'https?://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
+ _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
_TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
_TESTS = [{
- 'url': 'http://vimeo.com/nkistudio/videos',
+ 'url': 'https://vimeo.com/nkistudio/videos',
'info_dict': {
'title': 'Nki',
+ 'id': 'nkistudio',
},
'playlist_mincount': 66,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name = mobj.group('name')
- return self._extract_videos(name, 'http://vimeo.com/%s' % name)
+ return self._extract_videos(name, 'https://vimeo.com/%s' % name)
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+)(?:$|[?#]|/(?!video))'
_TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
_TESTS = [{
- 'url': 'http://vimeo.com/album/2632481',
+ 'url': 'https://vimeo.com/album/2632481',
'info_dict': {
+ 'id': '2632481',
'title': 'Staff Favorites: November 2013',
},
'playlist_mincount': 13,
+ }, {
+ 'note': 'Password-protected album',
+ 'url': 'https://vimeo.com/album/3253534',
+ 'info_dict': {
+ 'title': 'test',
+ 'id': '3253534',
+ },
+ 'playlist_count': 1,
+ 'params': {
+ 'videopassword': 'youtube-dl',
+ }
+ }, {
+ 'url': 'https://vimeo.com/album/2632481/sort:plays/format:thumbnail',
+ 'only_matching': True,
+ }, {
+ # TODO: respect page number
+ 'url': 'https://vimeo.com/album/2632481/page:2/sort:plays/format:thumbnail',
+ 'only_matching': True,
}]
def _page_url(self, base_url, pagenum):
return '%s/page:%d/' % (base_url, pagenum)
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- album_id = mobj.group('id')
- return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_id)
+ album_id = self._match_id(url)
+ return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
class VimeoGroupsIE(VimeoAlbumIE):
IE_NAME = 'vimeo:group'
- _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)'
+ _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
_TESTS = [{
- 'url': 'http://vimeo.com/groups/rolexawards',
+ 'url': 'https://vimeo.com/groups/rolexawards',
'info_dict': {
+ 'id': 'rolexawards',
'title': 'Rolex Awards for Enterprise',
},
'playlist_mincount': 73,
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name = mobj.group('name')
- return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name)
+ 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>[^/]+)'
+ _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
- 'file': '75524534.mp4',
'md5': 'c507a72f780cacc12b2248bb4006d253',
'info_dict': {
+ 'id': '75524534',
+ 'ext': 'mp4',
'title': "DICK HARDWICK 'Comedian'",
'uploader': 'Richard Hardwick',
+ 'uploader_id': 'user21297594',
}
}, {
'note': 'video player needs Referer',
- 'url': 'http://vimeo.com/user22258446/review/91613211/13f927e053',
+ 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
'md5': '6295fdab8f4bf6a002d058b2c6dce276',
'info_dict': {
'id': '91613211',
'uploader': 'DevWeek Events',
'duration': 2773,
'thumbnail': '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)
+ 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(VimeoBaseInfoExtractor, VimeoChannelIE):
+class VimeoWatchLaterIE(VimeoChannelIE):
IE_NAME = 'vimeo:watchlater'
IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
- _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater'
+ _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
+ _TITLE = 'Watch Later'
_LOGIN_REQUIRED = True
- _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<'
_TESTS = [{
- 'url': 'http://vimeo.com/home/watchlater',
+ 'url': 'https://vimeo.com/watchlater',
'only_matching': True,
}]
def _page_url(self, base_url, pagenum):
url = '%s/page:%d/' % (base_url, pagenum)
- request = compat_urllib_request.Request(url)
+ request = sanitized_Request(url)
# Set the header to get a partial html page with the ids,
# the normal page doesn't contain them.
request.add_header('X-Requested-With', 'XMLHttpRequest')
return request
def _real_extract(self, url):
- return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater')
+ return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
class VimeoLikesIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
+ _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
IE_NAME = 'vimeo:likes'
IE_DESC = 'Vimeo user likes'
_TEST = {
'url': 'https://vimeo.com/user755559/likes/',
'playlist_mincount': 293,
- "info_dict": {
- "description": "See all the videos urza likes",
- "title": 'Videos urza likes',
+ 'info_dict': {
+ 'id': 'user755559_likes',
+ 'description': 'See all the videos urza likes',
+ 'title': 'Videos urza likes',
},
}
description = self._html_search_meta('description', webpage)
def _get_page(idx):
- page_url = '%s//vimeo.com/user%s/likes/page:%d/sort:date' % (
- self.http_scheme(), user_id, idx + 1)
+ page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
+ user_id, idx + 1)
webpage = self._download_webpage(
page_url, user_id,
note='Downloading page %d/%d' % (idx + 1, page_count))
Rapsys Git / youtubedl / blobdiff