+version 2020.03.24
+
+Core
+- [utils] Revert support for cookie files with spaces used instead of tabs
+
+Extractors
+* [teachable] Update upskillcourses and gns3 domains
+* [generic] Look for teachable embeds before wistia
++ [teachable] Extract chapter metadata (#24421)
++ [bilibili] Add support for player.bilibili.com (#24402)
++ [bilibili] Add support for new URL schema with BV ids (#24439, #24442)
+* [limelight] Remove disabled API requests (#24255)
+* [soundcloud] Fix download URL extraction (#24394)
++ [cbc:watch] Add support for authentication (#19160)
+* [hellporno] Fix extraction (#24399)
+* [xtube] Fix formats extraction (#24348)
+* [ndr] Fix extraction (#24326)
+* [nhk] Update m3u8 URL and use native HLS downloader (#24329)
+- [nhk] Remove obsolete rtmp formats (#24329)
+* [nhk] Relax URL regular expression (#24329)
+- [vimeo] Revert fix showcase password protected video extraction (#24224)
+
+
+version 2020.03.08
+
+Core
++ [utils] Add support for cookie files with spaces used instead of tabs
+
+Extractors
++ [pornhub] Add support for pornhubpremium.com (#24288)
+- [youtube] Remove outdated code and unnecessary requests
+* [youtube] Improve extraction in 429 HTTP error conditions (#24283)
+* [nhk] Update API version (#24270)
+
+
+version 2020.03.06
+
+Extractors
+* [youtube] Fix age-gated videos support without login (#24248)
+* [vimeo] Fix showcase password protected video extraction (#24224)
+* [pornhub] Improve title extraction (#24184)
+* [peertube] Improve extraction (#23657)
++ [servus] Add support for new URL schema (#23475, #23583, #24142)
+* [vimeo] Fix subtitles URLs (#24209)
+
+
+version 2020.03.01
+
+Core
+* [YoutubeDL] Force redirect URL to unicode on python 2
+- [options] Remove duplicate short option -v for --version (#24162)
+
+Extractors
+* [xhamster] Fix extraction (#24205)
+* [franceculture] Fix extraction (#24204)
++ [telecinco] Add support for article opening videos
+* [telecinco] Fix extraction (#24195)
+* [xtube] Fix metadata extraction (#21073, #22455)
+* [youjizz] Fix extraction (#24181)
+- Remove no longer needed compat_str around geturl
+* [pornhd] Fix extraction (#24128)
++ [teachable] Add support for multiple videos per lecture (#24101)
++ [wistia] Add support for multiple generic embeds (#8347, 11385)
+* [imdb] Fix extraction (#23443)
+* [tv2dk:bornholm:play] Fix extraction (#24076)
+
+
+version 2020.02.16
+
+Core
+* [YoutubeDL] Fix playlist entry indexing with --playlist-items (#10591,
+ #10622)
+* [update] Fix updating via symlinks (#23991)
++ [compat] Introduce compat_realpath (#23991)
+
+Extractors
++ [npr] Add support for streams (#24042)
++ [24video] Add support for porn.24video.net (#23779, #23784)
+- [jpopsuki] Remove extractor (#23858)
+* [nova] Improve extraction (#23690)
+* [nova:embed] Improve (#23690)
+* [nova:embed] Fix extraction (#23672)
++ [abc:iview] Add support for 720p (#22907, #22921)
+* [nytimes] Improve format sorting (#24010)
++ [toggle] Add support for mewatch.sg (#23895, #23930)
+* [thisoldhouse] Fix extraction (#23951)
++ [popcorntimes] Add support for popcorntimes.tv (#23949)
+* [sportdeutschland] Update to new API
+* [twitch:stream] Lowercase channel id for stream request (#23917)
+* [tv5mondeplus] Fix extraction (#23907, #23911)
+* [tva] Relax URL regular expression (#23903)
+* [vimeo] Fix album extraction (#23864)
+* [viewlift] Improve extraction
+ * Fix extraction (#23851)
+ + Add support for authentication
+ + Add support for more domains
+* [svt] Fix series extraction (#22297)
+* [svt] Fix article extraction (#22897, #22919)
+* [soundcloud] Imporve private playlist/set tracks extraction (#3707)
+
+
version 2020.01.24
Extractors
### HTTP Error 429: Too Many Requests or 402: Payment Required
-These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address.
+These two error codes indicate that the service is blocking your IP address because of overuse. Usually this is a soft block meaning that you can gain access again after solving CAPTCHA. Just open a browser and solve a CAPTCHA the service suggests you and after that [pass cookies](#how-do-i-pass-cookies-to-youtube-dl) to youtube-dl. Note that if your machine has multiple external IPs then you should also pass exactly the same IP you've used for solving CAPTCHA with [`--source-address`](#network-options). Also you may need to pass a `User-Agent` HTTP header of your browser with [`--user-agent`](#workarounds).
+
+If this is not the case (no CAPTCHA suggested to solve by the service) then you can contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address.
### SyntaxError: Non-ASCII character
HTTP Error 429: Too Many Requests or 402: Payment Required
These two error codes indicate that the service is blocking your IP
-address because of overuse. Contact the service and ask them to unblock
-your IP address, or - if you have acquired a whitelisted IP address
-already - use the --proxy or --source-address options to select another
-IP address.
+address because of overuse. Usually this is a soft block meaning that
+you can gain access again after solving CAPTCHA. Just open a browser and
+solve a CAPTCHA the service suggests you and after that pass cookies to
+youtube-dl. Note that if your machine has multiple external IPs then you
+should also pass exactly the same IP you've used for solving CAPTCHA
+with --source-address. Also you may need to pass a User-Agent HTTP
+header of your browser with --user-agent.
+
+If this is not the case (no CAPTCHA suggested to solve by the service)
+then you can contact the service and ask them to unblock your IP
+address, or - if you have acquired a whitelisted IP address already -
+use the --proxy or --source-address options to select another IP
+address.
SyntaxError: Non-ASCII character
- **BiliBili**
- **BilibiliAudio**
- **BilibiliAudioAlbum**
+ - **BiliBiliPlayer**
- **BioBioChileTV**
- **BIQLE**
- **BitChute**
- **JeuxVideo**
- **Joj**
- **Jove**
- - **jpopsuki.tv**
- **JWPlatform**
- **Kakao**
- **Kaltura**
- **Pokemon**
- **PolskieRadio**
- **PolskieRadioCategory**
+ - **Popcorntimes**
- **PopcornTV**
- **PornCom**
- **PornerBros**
- **Vidzi**
- **vier**: vier.be and vijf.be
- **vier:videos**
- - **ViewLift**
- - **ViewLiftEmbed**
+ - **viewlift**
+ - **viewlift:embed**
- **Viidea**
- **viki**
- **viki:channel**
'webpage_url': 'http://example.com',
}
- def get_ids(params):
+ def get_downloaded_info_dicts(params):
ydl = YDL(params)
- # make a copy because the dictionary can be modified
- ydl.process_ie_result(playlist.copy())
- return [int(v['id']) for v in ydl.downloaded_info_dicts]
+ # make a deep copy because the dictionary and nested entries
+ # can be modified
+ ydl.process_ie_result(copy.deepcopy(playlist))
+ return ydl.downloaded_info_dicts
+
+ def get_ids(params):
+ return [int(v['id']) for v in get_downloaded_info_dicts(params)]
result = get_ids({})
self.assertEqual(result, [1, 2, 3, 4])
result = get_ids({'playlist_items': '2-4,3-4,3'})
self.assertEqual(result, [2, 3, 4])
+ # Tests for https://github.com/ytdl-org/youtube-dl/issues/10591
+ # @{
+ result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'})
+ self.assertEqual(result[0]['playlist_index'], 2)
+ self.assertEqual(result[1]['playlist_index'], 3)
+
+ result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'})
+ self.assertEqual(result[0]['playlist_index'], 2)
+ self.assertEqual(result[1]['playlist_index'], 3)
+ self.assertEqual(result[2]['playlist_index'], 4)
+
+ result = get_downloaded_info_dicts({'playlist_items': '4,2'})
+ self.assertEqual(result[0]['playlist_index'], 4)
+ self.assertEqual(result[1]['playlist_index'], 2)
+ # @}
+
def test_urlopen_no_file_protocol(self):
# see https://github.com/ytdl-org/youtube-dl/issues/8227
ydl = YDL()
ThePlatformIE,
ThePlatformFeedIE,
RTVEALaCartaIE,
- FunnyOrDieIE,
DemocracynowIE,
)
self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca')
-class TestFunnyOrDieSubtitles(BaseTestSubtitles):
- url = 'http://www.funnyordie.com/videos/224829ff6d/judd-apatow-will-direct-your-vine'
- IE = FunnyOrDieIE
-
- def test_allsubtitles(self):
- self.DL.params['writesubtitles'] = True
- self.DL.params['allsubtitles'] = True
- subtitles = self.getSubtitles()
- self.assertEqual(set(subtitles.keys()), set(['en']))
- self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4')
-
-
class TestDemocracynowSubtitles(BaseTestSubtitles):
url = 'http://www.democracynow.org/shows/2015/7/3'
IE = DemocracynowIE
.PP
These two error codes indicate that the service is blocking your IP
address because of overuse.
-Contact the service and ask them to unblock your IP address, or \- if
-you have acquired a whitelisted IP address already \- use the
-\f[C]\-\-proxy\f[] or \f[C]\-\-source\-address\f[] options to select
-another IP address.
+Usually this is a soft block meaning that you can gain access again
+after solving CAPTCHA.
+Just open a browser and solve a CAPTCHA the service suggests you and
+after that pass cookies to youtube\-dl.
+Note that if your machine has multiple external IPs then you should also
+pass exactly the same IP you\[aq]ve used for solving CAPTCHA with
+\f[C]\-\-source\-address\f[].
+Also you may need to pass a \f[C]User\-Agent\f[] HTTP header of your
+browser with \f[C]\-\-user\-agent\f[].
+.PP
+If this is not the case (no CAPTCHA suggested to solve by the service)
+then you can contact the service and ask them to unblock your IP
+address, or \- if you have acquired a whitelisted IP address already \-
+use the \f[C]\-\-proxy\f[] or \f[C]\-\-source\-address\f[] options to
+select another IP address.
.SS SyntaxError: Non\-ASCII character
.PP
The error
YoutubeDLCookieJar,
YoutubeDLCookieProcessor,
YoutubeDLHandler,
+ YoutubeDLRedirectHandler,
)
from .cache import Cache
from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER
'playlist_title': ie_result.get('title'),
'playlist_uploader': ie_result.get('uploader'),
'playlist_uploader_id': ie_result.get('uploader_id'),
- 'playlist_index': i + playliststart,
+ 'playlist_index': playlistitems[i - 1] if playlistitems else i + playliststart,
'extractor': ie_result['extractor'],
'webpage_url': ie_result['webpage_url'],
'webpage_url_basename': url_basename(ie_result['webpage_url']),
debuglevel = 1 if self.params.get('debug_printtraffic') else 0
https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
+ redirect_handler = YoutubeDLRedirectHandler()
data_handler = compat_urllib_request_DataHandler()
# When passing our own FileHandler instance, build_opener won't add the
file_handler.file_open = file_open
opener = compat_urllib_request.build_opener(
- proxy_handler, https_handler, cookie_processor, ydlh, data_handler, file_handler)
+ proxy_handler, https_handler, cookie_processor, ydlh, redirect_handler, data_handler, file_handler)
# Delete the default user-agent header, which would otherwise apply in
# cases where our custom HTTP handler doesn't come into play
compat_expanduser = os.path.expanduser
+if compat_os_name == 'nt' and sys.version_info < (3, 8):
+ # os.path.realpath on Windows does not follow symbolic links
+ # prior to Python 3.8 (see https://bugs.python.org/issue9949)
+ def compat_realpath(path):
+ while os.path.islink(path):
+ path = os.path.abspath(os.readlink(path))
+ return path
+else:
+ compat_realpath = os.path.realpath
+
+
if sys.version_info < (3, 0):
def compat_print(s):
from .utils import preferredencoding
'compat_os_name',
'compat_parse_qs',
'compat_print',
+ 'compat_realpath',
'compat_setenv',
'compat_shlex_quote',
'compat_shlex_split',
# ABC iview programs are normally available for 14 days only.
_TESTS = [{
- 'url': 'https://iview.abc.net.au/show/ben-and-hollys-little-kingdom/series/0/video/ZX9371A050S00',
- 'md5': 'cde42d728b3b7c2b32b1b94b4a548afc',
+ 'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00',
+ 'md5': '67715ce3c78426b11ba167d875ac6abf',
'info_dict': {
- 'id': 'ZX9371A050S00',
+ 'id': 'LE1927H001S00',
'ext': 'mp4',
- 'title': "Gaston's Birthday",
- 'series': "Ben And Holly's Little Kingdom",
- 'description': 'md5:f9de914d02f226968f598ac76f105bcf',
- 'upload_date': '20180604',
- 'uploader_id': 'abc4kids',
- 'timestamp': 1528140219,
+ 'title': "Series 11 Ep 1",
+ 'series': "Gruen",
+ 'description': 'md5:52cc744ad35045baf6aded2ce7287f67',
+ 'upload_date': '20190925',
+ 'uploader_id': 'abc1',
+ 'timestamp': 1569445289,
},
'params': {
'skip_download': True,
'hdnea': token,
})
- for sd in ('sd', 'sd-low'):
+ for sd in ('720', 'sd', 'sd-low'):
sd_url = try_get(
stream, lambda x: x['streams']['hls'][sd], compat_str)
if not sd_url:
class BiliBiliIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/(?P<anime_id>\d+)/play#)(?P<id>\d+)'
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:(?:www|bangumi)\.)?
+ bilibili\.(?:tv|com)/
+ (?:
+ (?:
+ video/[aA][vV]|
+ anime/(?P<anime_id>\d+)/play\#
+ )(?P<id_bv>\d+)|
+ video/[bB][vV](?P<id>[^/?#&]+)
+ )
+ '''
_TESTS = [{
'url': 'http://www.bilibili.tv/video/av1074402/',
'skip_download': True, # Test metadata only
},
}]
+ }, {
+ # new BV video id format
+ 'url': 'https://www.bilibili.com/video/BV1JE411F741',
+ 'only_matching': True,
}]
_APP_KEY = 'iVGUTjsxvpLeuDCf'
url, smuggled_data = unsmuggle_url(url, {})
mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = mobj.group('id') or mobj.group('id_bv')
anime_id = mobj.group('anime_id')
webpage = self._download_webpage(url, video_id)
entries, am_id, album_title, album_data.get('intro'))
return self.playlist_result(entries, am_id)
+
+
+class BiliBiliPlayerIE(InfoExtractor):
+ _VALID_URL = r'https?://player\.bilibili\.com/player\.html\?.*?\baid=(?P<id>\d+)'
+ _TEST = {
+ 'url': 'http://player.bilibili.com/player.html?aid=92494333&cid=157926707&page=1',
+ 'only_matching': True,
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ return self.url_result(
+ 'http://www.bilibili.tv/video/av%s/' % video_id,
+ ie=BiliBiliIE.ie_key(), video_id=video_id)
# coding: utf-8
from __future__ import unicode_literals
+import hashlib
import json
import re
+from xml.sax.saxutils import escape
from .common import InfoExtractor
from ..compat import (
'clearleap': 'http://www.clearleap.com/namespace/clearleap/1.0/',
}
_GEO_COUNTRIES = ['CA']
+ _LOGIN_URL = 'https://api.loginradius.com/identity/v2/auth/login'
+ _TOKEN_URL = 'https://cloud-api.loginradius.com/sso/jwt/api/token'
+ _API_KEY = '3f4beddd-2061-49b0-ae80-6f1f2ed65b37'
+ _NETRC_MACHINE = 'cbcwatch'
+
+ def _signature(self, email, password):
+ data = json.dumps({
+ 'email': email,
+ 'password': password,
+ }).encode()
+ headers = {'content-type': 'application/json'}
+ query = {'apikey': self._API_KEY}
+ resp = self._download_json(self._LOGIN_URL, None, data=data, headers=headers, query=query)
+ access_token = resp['access_token']
+
+ # token
+ query = {
+ 'access_token': access_token,
+ 'apikey': self._API_KEY,
+ 'jwtapp': 'jwt',
+ }
+ resp = self._download_json(self._TOKEN_URL, None, headers=headers, query=query)
+ return resp['signature']
def _call_api(self, path, video_id):
url = path if path.startswith('http') else self._API_BASE_URL + path
def _real_initialize(self):
if self._valid_device_token():
return
- device = self._downloader.cache.load('cbcwatch', 'device') or {}
+ device = self._downloader.cache.load(
+ 'cbcwatch', self._cache_device_key()) or {}
self._device_id, self._device_token = device.get('id'), device.get('token')
if self._valid_device_token():
return
def _valid_device_token(self):
return self._device_id and self._device_token
+ def _cache_device_key(self):
+ email, _ = self._get_login_info()
+ return '%s_device' % hashlib.sha256(email.encode()).hexdigest() if email else 'device'
+
def _register_device(self):
- self._device_id = self._device_token = None
result = self._download_xml(
self._API_BASE_URL + 'device/register',
None, 'Acquiring device token',
data=b'<device><type>web</type></device>')
self._device_id = xpath_text(result, 'deviceId', fatal=True)
- self._device_token = xpath_text(result, 'deviceToken', fatal=True)
+ email, password = self._get_login_info()
+ if email and password:
+ signature = self._signature(email, password)
+ data = '<login><token>{0}</token><device><deviceId>{1}</deviceId><type>web</type></device></login>'.format(
+ escape(signature), escape(self._device_id)).encode()
+ url = self._API_BASE_URL + 'device/login'
+ result = self._download_xml(
+ url, None, data=data,
+ headers={'content-type': 'application/xml'})
+ self._device_token = xpath_text(result, 'token', fatal=True)
+ else:
+ self._device_token = xpath_text(result, 'deviceToken', fatal=True)
self._downloader.cache.store(
- 'cbcwatch', 'device', {
+ 'cbcwatch', self._cache_device_key(), {
'id': self._device_id,
'token': self._device_token,
})
import re
from .common import InfoExtractor
-from ..compat import compat_str
from ..utils import (
encode_base_n,
ExtractorError,
webpage, urlh = self._download_webpage_handle(url, display_id)
- video_id = self._match_id(compat_str(urlh.geturl()))
+ video_id = self._match_id(urlh.geturl())
hash = self._search_regex(
r'hash\s*:\s*["\']([\da-f]{32})', webpage, 'hash')
BiliBiliBangumiIE,
BilibiliAudioIE,
BilibiliAudioAlbumIE,
+ BiliBiliPlayerIE,
)
from .biobiochiletv import BioBioChileTVIE
from .bitchute import (
from .jove import JoveIE
from .joj import JojIE
from .jwplatform import JWPlatformIE
-from .jpopsukitv import JpopsukiIE
from .kakao import KakaoIE
from .kaltura import KalturaIE
from .kanalplay import KanalPlayIE
PolskieRadioIE,
PolskieRadioCategoryIE,
)
+from .popcorntimes import PopcorntimesIE
from .popcorntv import PopcornTVIE
from .porn91 import Porn91IE
from .porncom import PornComIE
webpage = self._download_webpage(url, display_id)
video_data = extract_attributes(self._search_regex(
- r'(?s)<div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>.*?(<button[^>]+data-asset-source="[^"]+"[^>]+>)',
+ r'''(?sx)
+ (?:
+ </h1>|
+ <div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>
+ ).*?
+ (<button[^>]+data-asset-source="[^"]+"[^>]+>)
+ ''',
webpage, 'video data'))
video_url = video_data['data-asset-source']
if head_response is not False:
# Check for redirect
- new_url = compat_str(head_response.geturl())
+ new_url = head_response.geturl()
if url != new_url:
self.report_following_redirect(new_url)
if force_videoid:
return self.playlist_result(
self._parse_xspf(
doc, video_id, xspf_url=url,
- xspf_base_url=compat_str(full_response.geturl())),
+ xspf_base_url=full_response.geturl()),
video_id)
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
info_dict['formats'] = self._parse_mpd_formats(
doc,
- mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
+ mpd_base_url=full_response.geturl().rpartition('/')[0],
mpd_url=url)
self._sort_formats(info_dict['formats'])
return info_dict
return self.playlist_from_matches(
dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
+ # Look for Teachable embeds, must be before Wistia
+ teachable_url = TeachableIE._extract_url(webpage, url)
+ if teachable_url:
+ return self.url_result(teachable_url)
+
# Look for embedded Wistia player
- wistia_url = WistiaIE._extract_url(webpage)
- if wistia_url:
- return {
- '_type': 'url_transparent',
- 'url': self._proto_relative_url(wistia_url),
- 'ie_key': WistiaIE.ie_key(),
- 'uploader': video_uploader,
- }
+ wistia_urls = WistiaIE._extract_urls(webpage)
+ if wistia_urls:
+ playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
+ for entry in playlist['entries']:
+ entry.update({
+ '_type': 'url_transparent',
+ 'uploader': video_uploader,
+ })
+ return playlist
# Look for SVT player
svt_url = SVTIE._extract_url(webpage)
return self.playlist_from_matches(
peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
- teachable_url = TeachableIE._extract_url(webpage, url)
- if teachable_url:
- return self.url_result(teachable_url)
-
indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
if indavideo_urls:
return self.playlist_from_matches(
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import (
- js_to_json,
+ int_or_none,
+ merge_dicts,
remove_end,
- determine_ext,
+ unified_timestamp,
)
_VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
- 'md5': '1fee339c610d2049699ef2aa699439f1',
+ 'md5': 'f0a46ebc0bed0c72ae8fe4629f7de5f3',
'info_dict': {
'id': '149116',
'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
'ext': 'mp4',
'title': 'Dixie is posing with naked ass very erotic',
+ 'description': 'md5:9a72922749354edb1c4b6e540ad3d215',
+ 'categories': list,
'thumbnail': r're:https?://.*\.jpg$',
+ 'duration': 240,
+ 'timestamp': 1398762720,
+ 'upload_date': '20140429',
+ 'view_count': int,
'age_limit': 18,
- }
+ },
}, {
'url': 'http://hellporno.net/v/186271/',
'only_matching': True,
title = remove_end(self._html_search_regex(
r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno')
- flashvars = self._parse_json(self._search_regex(
- r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
- display_id, transform_source=js_to_json)
-
- video_id = flashvars.get('video_id')
- thumbnail = flashvars.get('preview_url')
- ext = determine_ext(flashvars.get('postfix'), 'mp4')
-
- formats = []
- for video_url_key in ['video_url', 'video_alt_url']:
- video_url = flashvars.get(video_url_key)
- if not video_url:
- continue
- video_text = flashvars.get('%s_text' % video_url_key)
- fmt = {
- 'url': video_url,
- 'ext': ext,
- 'format_id': video_text,
- }
- m = re.search(r'^(?P<height>\d+)[pP]', video_text)
- if m:
- fmt['height'] = int(m.group('height'))
- formats.append(fmt)
- self._sort_formats(formats)
+ info = self._parse_html5_media_entries(url, webpage, display_id)[0]
+ self._sort_formats(info['formats'])
- categories = self._html_search_meta(
- 'keywords', webpage, 'categories', default='').split(',')
+ video_id = self._search_regex(
+ (r'chs_object\s*=\s*["\'](\d+)',
+ r'params\[["\']video_id["\']\]\s*=\s*(\d+)'), webpage, 'video id',
+ default=display_id)
+ description = self._search_regex(
+ r'class=["\']desc_video_view_v2[^>]+>([^<]+)', webpage,
+ 'description', fatal=False)
+ categories = [
+ c.strip()
+ for c in self._html_search_meta(
+ 'keywords', webpage, 'categories', default='').split(',')
+ if c.strip()]
+ duration = int_or_none(self._og_search_property(
+ 'video:duration', webpage, fatal=False))
+ timestamp = unified_timestamp(self._og_search_property(
+ 'video:release_date', webpage, fatal=False))
+ view_count = int_or_none(self._search_regex(
+ r'>Views\s+(\d+)', webpage, 'view count', fatal=False))
- return {
+ return merge_dicts(info, {
'id': video_id,
'display_id': display_id,
'title': title,
- 'thumbnail': thumbnail,
+ 'description': description,
'categories': categories,
+ 'duration': duration,
+ 'timestamp': timestamp,
+ 'view_count': view_count,
'age_limit': 18,
- 'formats': formats,
- }
+ })
from __future__ import unicode_literals
+import base64
+import json
import re
from .common import InfoExtractor
mimetype2ext,
parse_duration,
qualities,
+ try_get,
url_or_none,
)
class ImdbIE(InfoExtractor):
IE_NAME = 'imdb'
IE_DESC = 'Internet Movie Database trailers'
- _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).+?[/-]vi(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).*?[/-]vi(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
'info_dict': {
'id': '2524815897',
'ext': 'mp4',
- 'title': 'No. 2 from Ice Age: Continental Drift (2012)',
+ 'title': 'No. 2',
'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7',
+ 'duration': 152,
}
}, {
'url': 'http://www.imdb.com/video/_/vi2524815897',
def _real_extract(self, url):
video_id = self._match_id(url)
- webpage = self._download_webpage(
- 'https://www.imdb.com/videoplayer/vi' + video_id, video_id)
- video_metadata = self._parse_json(self._search_regex(
- r'window\.IMDbReactInitialState\.push\(({.+?})\);', webpage,
- 'video metadata'), video_id)['videos']['videoMetadata']['vi' + video_id]
- title = self._html_search_meta(
- ['og:title', 'twitter:title'], webpage) or self._html_search_regex(
- r'<title>(.+?)</title>', webpage, 'title', fatal=False) or video_metadata['title']
+
+ data = self._download_json(
+ 'https://www.imdb.com/ve/data/VIDEO_PLAYBACK_DATA', video_id,
+ query={
+ 'key': base64.b64encode(json.dumps({
+ 'type': 'VIDEO_PLAYER',
+ 'subType': 'FORCE_LEGACY',
+ 'id': 'vi%s' % video_id,
+ }).encode()).decode(),
+ })[0]
quality = qualities(('SD', '480p', '720p', '1080p'))
formats = []
- for encoding in video_metadata.get('encodings', []):
+ for encoding in data['videoLegacyEncodings']:
if not encoding or not isinstance(encoding, dict):
continue
- video_url = url_or_none(encoding.get('videoUrl'))
+ video_url = url_or_none(encoding.get('url'))
if not video_url:
continue
ext = mimetype2ext(encoding.get(
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
- m3u8_id='hls', fatal=False))
+ preference=1, m3u8_id='hls', fatal=False))
continue
format_id = encoding.get('definition')
formats.append({
})
self._sort_formats(formats)
+ webpage = self._download_webpage(
+ 'https://www.imdb.com/video/vi' + video_id, video_id)
+ video_metadata = self._parse_json(self._search_regex(
+ r'args\.push\(\s*({.+?})\s*\)\s*;', webpage,
+ 'video metadata'), video_id)
+
+ video_info = video_metadata.get('VIDEO_INFO')
+ if video_info and isinstance(video_info, dict):
+ info = try_get(
+ video_info, lambda x: x[list(video_info.keys())[0]][0], dict)
+ else:
+ info = {}
+
+ title = self._html_search_meta(
+ ['og:title', 'twitter:title'], webpage) or self._html_search_regex(
+ r'<title>(.+?)</title>', webpage, 'title',
+ default=None) or info['videoTitle']
+
return {
'id': video_id,
'title': title,
+ 'alt_title': info.get('videoSubTitle'),
'formats': formats,
- 'description': video_metadata.get('description'),
- 'thumbnail': video_metadata.get('slate', {}).get('url'),
- 'duration': parse_duration(video_metadata.get('duration')),
+ 'description': info.get('videoDescription'),
+ 'thumbnail': url_or_none(try_get(
+ video_metadata, lambda x: x['videoSlate']['source'])),
+ 'duration': parse_duration(info.get('videoRuntime')),
}
+++ /dev/null
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import (
- int_or_none,
- unified_strdate,
-)
-
-
-class JpopsukiIE(InfoExtractor):
- IE_NAME = 'jpopsuki.tv'
- _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/(?:category/)?video/[^/]+/(?P<id>\S+)'
-
- _TEST = {
- 'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771',
- 'md5': '88018c0c1a9b1387940e90ec9e7e198e',
- 'info_dict': {
- 'id': '00be659d23b0b40508169cdee4545771',
- 'ext': 'mp4',
- 'title': 'ayumi hamasaki - evolution',
- 'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution',
- 'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg',
- 'uploader': 'plama_chan',
- 'uploader_id': '404',
- 'upload_date': '20121101'
- }
- }
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
-
- webpage = self._download_webpage(url, video_id)
-
- video_url = 'http://www.jpopsuki.tv' + self._html_search_regex(
- r'<source src="(.*?)" type', webpage, 'video url')
-
- video_title = self._og_search_title(webpage)
- description = self._og_search_description(webpage)
- thumbnail = self._og_search_thumbnail(webpage)
- uploader = self._html_search_regex(
- r'<li>from: <a href="/user/view/user/(.*?)/uid/',
- webpage, 'video uploader', fatal=False)
- uploader_id = self._html_search_regex(
- r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)',
- webpage, 'video uploader_id', fatal=False)
- upload_date = unified_strdate(self._html_search_regex(
- r'<li>uploaded: (.*?)</li>', webpage, 'video upload_date',
- fatal=False))
- view_count_str = self._html_search_regex(
- r'<li>Hits: ([0-9]+?)</li>', webpage, 'video view_count',
- fatal=False)
- comment_count_str = self._html_search_regex(
- r'<h2>([0-9]+?) comments</h2>', webpage, 'video comment_count',
- fatal=False)
-
- return {
- 'id': video_id,
- 'url': video_url,
- 'title': video_title,
- 'description': description,
- 'thumbnail': thumbnail,
- 'uploader': uploader,
- 'uploader_id': uploader_id,
- 'upload_date': upload_date,
- 'view_count': int_or_none(view_count_str),
- 'comment_count': int_or_none(comment_count_str),
- }
import re
from .common import InfoExtractor
-from ..compat import compat_str
from ..utils import (
clean_html,
determine_ext,
self._LOGIN_URL, None, 'Downloading login popup')
def is_logged(url_handle):
- return self._LOGIN_URL not in compat_str(url_handle.geturl())
+ return self._LOGIN_URL not in url_handle.geturl()
# Already logged in
if is_logged(urlh):
class LimelightBaseIE(InfoExtractor):
_PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s'
- _API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json'
@classmethod
def _extract_urls(cls, webpage, source_url):
try:
return self._download_json(
self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method),
- item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers)
+ item_id, 'Downloading PlaylistService %s JSON' % method,
+ fatal=fatal, headers=headers)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission']
raise ExtractorError(error, expected=True)
raise
- def _call_api(self, organization_id, item_id, method):
- return self._download_json(
- self._API_URL % (organization_id, self._API_PATH, item_id, method),
- item_id, 'Downloading API %s JSON' % method)
-
- def _extract(self, item_id, pc_method, mobile_method, meta_method, referer=None):
+ def _extract(self, item_id, pc_method, mobile_method, referer=None):
pc = self._call_playlist_service(item_id, pc_method, referer=referer)
- metadata = self._call_api(pc['orgId'], item_id, meta_method)
- mobile = self._call_playlist_service(item_id, mobile_method, fatal=False, referer=referer)
- return pc, mobile, metadata
+ mobile = self._call_playlist_service(
+ item_id, mobile_method, fatal=False, referer=referer)
+ return pc, mobile
+
+ def _extract_info(self, pc, mobile, i, referer):
+ get_item = lambda x, y: try_get(x, lambda x: x[y][i], dict) or {}
+ pc_item = get_item(pc, 'playlistItems')
+ mobile_item = get_item(mobile, 'mediaList')
+ video_id = pc_item.get('mediaId') or mobile_item['mediaId']
+ title = pc_item.get('title') or mobile_item['title']
- def _extract_info(self, streams, mobile_urls, properties):
- video_id = properties['media_id']
formats = []
urls = []
- for stream in streams:
+ for stream in pc_item.get('streams', []):
stream_url = stream.get('url')
if not stream_url or stream.get('drmProtected') or stream_url in urls:
continue
})
formats.append(fmt)
- for mobile_url in mobile_urls:
+ for mobile_url in mobile_item.get('mobileUrls', []):
media_url = mobile_url.get('mobileUrl')
format_id = mobile_url.get('targetMediaPlatform')
if not media_url or format_id in ('Widevine', 'SmoothStreaming') or media_url in urls:
self._sort_formats(formats)
- title = properties['title']
- description = properties.get('description')
- timestamp = int_or_none(properties.get('publish_date') or properties.get('create_date'))
- duration = float_or_none(properties.get('duration_in_milliseconds'), 1000)
- filesize = int_or_none(properties.get('total_storage_in_bytes'))
- categories = [properties.get('category')]
- tags = properties.get('tags', [])
- thumbnails = [{
- 'url': thumbnail['url'],
- 'width': int_or_none(thumbnail.get('width')),
- 'height': int_or_none(thumbnail.get('height')),
- } for thumbnail in properties.get('thumbnails', []) if thumbnail.get('url')]
-
subtitles = {}
- for caption in properties.get('captions', []):
- lang = caption.get('language_code')
- subtitles_url = caption.get('url')
- if lang and subtitles_url:
- subtitles.setdefault(lang, []).append({
- 'url': subtitles_url,
- })
- closed_captions_url = properties.get('closed_captions_url')
- if closed_captions_url:
- subtitles.setdefault('en', []).append({
- 'url': closed_captions_url,
- 'ext': 'ttml',
- })
+ for flag in mobile_item.get('flags'):
+ if flag == 'ClosedCaptions':
+ closed_captions = self._call_playlist_service(
+ video_id, 'getClosedCaptionsDetailsByMediaId',
+ False, referer) or []
+ for cc in closed_captions:
+ cc_url = cc.get('webvttFileUrl')
+ if not cc_url:
+ continue
+ lang = cc.get('languageCode') or self._search_regex(r'/[a-z]{2}\.vtt', cc_url, 'lang', default='en')
+ subtitles.setdefault(lang, []).append({
+ 'url': cc_url,
+ })
+ break
+
+ get_meta = lambda x: pc_item.get(x) or mobile_item.get(x)
return {
'id': video_id,
'title': title,
- 'description': description,
+ 'description': get_meta('description'),
'formats': formats,
- 'timestamp': timestamp,
- 'duration': duration,
- 'filesize': filesize,
- 'categories': categories,
- 'tags': tags,
- 'thumbnails': thumbnails,
+ 'duration': float_or_none(get_meta('durationInMilliseconds'), 1000),
+ 'thumbnail': get_meta('previewImageUrl') or get_meta('thumbnailImageUrl'),
'subtitles': subtitles,
}
- def _extract_info_helper(self, pc, mobile, i, metadata):
- return self._extract_info(
- try_get(pc, lambda x: x['playlistItems'][i]['streams'], list) or [],
- try_get(mobile, lambda x: x['mediaList'][i]['mobileUrls'], list) or [],
- metadata)
-
class LimelightMediaIE(LimelightBaseIE):
IE_NAME = 'limelight'
'description': 'md5:8005b944181778e313d95c1237ddb640',
'thumbnail': r're:^https?://.*\.jpeg$',
'duration': 144.23,
- 'timestamp': 1244136834,
- 'upload_date': '20090604',
},
'params': {
# m3u8 download
'title': '3Play Media Overview Video',
'thumbnail': r're:^https?://.*\.jpeg$',
'duration': 78.101,
- 'timestamp': 1338929955,
- 'upload_date': '20120605',
- 'subtitles': 'mincount:9',
+ # TODO: extract all languages that were accessible via API
+ # 'subtitles': 'mincount:9',
+ 'subtitles': 'mincount:1',
},
}, {
'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452',
'only_matching': True,
}]
_PLAYLIST_SERVICE_PATH = 'media'
- _API_PATH = 'media'
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
video_id = self._match_id(url)
+ source_url = smuggled_data.get('source_url')
self._initialize_geo_bypass({
'countries': smuggled_data.get('geo_countries'),
})
- pc, mobile, metadata = self._extract(
+ pc, mobile = self._extract(
video_id, 'getPlaylistByMediaId',
- 'getMobilePlaylistByMediaId', 'properties',
- smuggled_data.get('source_url'))
+ 'getMobilePlaylistByMediaId', source_url)
- return self._extract_info_helper(pc, mobile, 0, metadata)
+ return self._extract_info(pc, mobile, 0, source_url)
class LimelightChannelIE(LimelightBaseIE):
'info_dict': {
'id': 'ab6a524c379342f9b23642917020c082',
'title': 'Javascript Sample Code',
+ 'description': 'Javascript Sample Code - http://www.delvenetworks.com/sample-code/playerCode-demo.html',
},
'playlist_mincount': 3,
}, {
'only_matching': True,
}]
_PLAYLIST_SERVICE_PATH = 'channel'
- _API_PATH = 'channels'
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
channel_id = self._match_id(url)
+ source_url = smuggled_data.get('source_url')
- pc, mobile, medias = self._extract(
+ pc, mobile = self._extract(
channel_id, 'getPlaylistByChannelId',
'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1',
- 'media', smuggled_data.get('source_url'))
+ source_url)
entries = [
- self._extract_info_helper(pc, mobile, i, medias['media_list'][i])
- for i in range(len(medias['media_list']))]
+ self._extract_info(pc, mobile, i, source_url)
+ for i in range(len(pc['playlistItems']))]
- return self.playlist_result(entries, channel_id, pc['title'])
+ return self.playlist_result(
+ entries, channel_id, pc.get('title'), mobile.get('description'))
class LimelightChannelListIE(LimelightBaseIE):
def _real_extract(self, url):
channel_list_id = self._match_id(url)
- channel_list = self._call_playlist_service(channel_list_id, 'getMobileChannelListById')
+ channel_list = self._call_playlist_service(
+ channel_list_id, 'getMobileChannelListById')
entries = [
self.url_result('limelight:channel:%s' % channel['id'], 'LimelightChannel')
for channel in channel_list['channelList']]
- return self.playlist_result(entries, channel_list_id, channel_list['title'])
+ return self.playlist_result(
+ entries, channel_list_id, channel_list['title'])
from ..compat import (
compat_b64decode,
compat_HTTPError,
- compat_str,
)
from ..utils import (
ExtractorError,
'sso': 'true',
})
- login_state_url = compat_str(urlh.geturl())
+ login_state_url = urlh.geturl()
try:
login_page = self._download_webpage(
})
access_token = self._search_regex(
- r'access_token=([^=&]+)', compat_str(urlh.geturl()),
+ r'access_token=([^=&]+)', urlh.geturl(),
'access token')
self._download_webpage(
from .theplatform import ThePlatformBaseIE
from ..compat import (
compat_parse_qs,
- compat_str,
compat_urllib_parse_urlparse,
)
from ..utils import (
continue
urlh = ie._request_webpage(
embed_url, video_id, note='Following embed URL redirect')
- embed_url = compat_str(urlh.geturl())
+ embed_url = urlh.geturl()
program_guid = _program_guid(_qs(embed_url))
if program_guid:
entries.append(embed_url)
query = mobj.group('query')
webpage, urlh = self._download_webpage_handle(url, resource_id) # XXX: add UrlReferrer?
- redirect_url = compat_str(urlh.geturl())
+ redirect_url = urlh.geturl()
# XXX: might have also extracted UrlReferrer and QueryString from the html
service_path = compat_urlparse.urljoin(redirect_url, self._html_search_regex(
from ..utils import (
determine_ext,
int_or_none,
+ merge_dicts,
parse_iso8601,
qualities,
try_get,
def _extract_embed(self, webpage, display_id):
embed_url = self._html_search_meta(
- 'embedURL', webpage, 'embed URL', fatal=True)
+ 'embedURL', webpage, 'embed URL',
+ default=None) or self._search_regex(
+ r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+ 'embed URL', group='url')
description = self._search_regex(
r'<p[^>]+itemprop="description">([^<]+)</p>',
webpage, 'description', default=None) or self._og_search_description(webpage)
timestamp = parse_iso8601(
self._search_regex(
r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"',
- webpage, 'upload date', fatal=False))
- return {
+ webpage, 'upload date', default=None))
+ info = self._search_json_ld(webpage, display_id, default={})
+ return merge_dicts({
'_type': 'url_transparent',
'url': embed_url,
'display_id': display_id,
'description': description,
'timestamp': timestamp,
- }
+ }, info)
class NJoyIE(NDRBaseIE):
class NhkVodIE(InfoExtractor):
- _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[a-z]+-\d{8}-\d+)'
+ _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[^/]+?-\d{8}-\d+)'
# Content available only for a limited period of time. Visit
# https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
_TESTS = [{
}, {
'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/',
'only_matching': True,
+ }, {
+ 'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/j_art-20150903-1/',
+ 'only_matching': True,
}]
- _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7/episode/%s/%s/all%s.json'
+ _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7a/episode/%s/%s/all%s.json'
def _real_extract(self, url):
lang, m_type, episode_id = re.match(self._VALID_URL, url).groups()
audio = episode['audio']
audio_path = audio['audio']
info['formats'] = self._extract_m3u8_formats(
- 'https://nhks-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
- episode_id, 'm4a', m3u8_id='hls', fatal=False)
- for proto in ('rtmpt', 'rtmp'):
- info['formats'].append({
- 'ext': 'flv',
- 'format_id': proto,
- 'url': '%s://flv.nhk.or.jp/ondemand/mp4:flv%s' % (proto, audio_path),
- 'vcodec': 'none',
- })
+ 'https://nhkworld-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
+ episode_id, 'm4a', entry_protocol='m3u8_native',
+ m3u8_id='hls', fatal=False)
for f in info['formats']:
f['language'] = lang
return info
_VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1',
- 'md5': 'b3834f6de5401baabf31ed57456463f7',
+ 'md5': 'ee009bafcc794541570edd44b71cbea3',
'info_dict': {
'id': '8o0n0r',
'ext': 'mp4',
formats = []
for format_id, format_list in bitrates.items():
if not isinstance(format_list, list):
- continue
+ format_list = [format_list]
for format_url in format_list:
format_url = url_or_none(format_url)
if not format_url:
continue
+ if format_id == 'hls':
+ formats.extend(self._extract_m3u8_formats(
+ format_url, video_id, ext='mp4',
+ entry_protocol='m3u8_native', m3u8_id='hls',
+ fatal=False))
+ continue
f = {
'url': format_url,
}
_VALID_URL = r'https?://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)'
_TESTS = [{
'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260',
- 'md5': '1dd7b9d5ea27bc361f110cd855a19bd3',
+ 'md5': '249baab7d0104e186e78b0899c7d5f28',
'info_dict': {
'id': '1757139',
'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci',
'params': {
# rtmp download
'skip_download': True,
- }
+ },
+ 'skip': 'gone',
}, {
# media.cms.nova.cz embed
'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil',
'skip_download': True,
},
'add_ie': [NovaEmbedIE.ie_key()],
+ 'skip': 'CHYBA 404: STRÁNKA NENALEZENA',
}, {
'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html',
'only_matching': True,
webpage = self._download_webpage(url, display_id)
+ description = clean_html(self._og_search_description(webpage, default=None))
+ if site == 'novaplus':
+ upload_date = unified_strdate(self._search_regex(
+ r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None))
+ elif site == 'fanda':
+ upload_date = unified_strdate(self._search_regex(
+ r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None))
+ else:
+ upload_date = None
+
# novaplus
embed_id = self._search_regex(
r'<iframe[^>]+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)',
webpage, 'embed url', default=None)
if embed_id:
- return self.url_result(
- 'https://media.cms.nova.cz/embed/%s' % embed_id,
- ie=NovaEmbedIE.ie_key(), video_id=embed_id)
+ return {
+ '_type': 'url_transparent',
+ 'url': 'https://media.cms.nova.cz/embed/%s' % embed_id,
+ 'ie_key': NovaEmbedIE.ie_key(),
+ 'id': embed_id,
+ 'description': description,
+ 'upload_date': upload_date
+ }
video_id = self._search_regex(
[r"(?:media|video_id)\s*:\s*'(\d+)'",
self._sort_formats(formats)
title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage)
- description = clean_html(self._og_search_description(webpage, default=None))
thumbnail = config.get('poster')
- if site == 'novaplus':
- upload_date = unified_strdate(self._search_regex(
- r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None))
- elif site == 'fanda':
- upload_date = unified_strdate(self._search_regex(
- r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None))
- else:
- upload_date = None
-
return {
'id': video_id,
'display_id': display_id,
from ..utils import (
int_or_none,
qualities,
+ url_or_none,
)
},
}],
'expected_warnings': ['Failed to download m3u8 information'],
+ }, {
+ # multimedia, no formats, stream
+ 'url': 'https://www.npr.org/2020/02/14/805476846/laura-stevenson-tiny-desk-concert',
+ 'only_matching': True,
}]
def _real_extract(self, url):
'format_id': format_id,
'quality': quality(format_id),
})
+ for stream_id, stream_entry in media.get('stream', {}).items():
+ if not isinstance(stream_entry, dict):
+ continue
+ if stream_id != 'hlsUrl':
+ continue
+ stream_url = url_or_none(stream_entry.get('$text'))
+ if not stream_url:
+ continue
+ formats.extend(self._extract_m3u8_formats(
+ stream_url, stream_id, 'mp4', 'm3u8_native',
+ m3u8_id='hls', fatal=False))
self._sort_formats(formats)
entries.append({
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
'filesize': get_file_size(video.get('file_size') or video.get('fileSize')),
- 'tbr': int_or_none(video.get('bitrate'), 1000),
+ 'tbr': int_or_none(video.get('bitrate'), 1000) or None,
'ext': ext,
})
- self._sort_formats(formats)
+ self._sort_formats(formats, ('height', 'width', 'filesize', 'tbr', 'fps', 'format_id'))
thumbnails = []
for image in video_data.get('images', []):
from ..utils import (
int_or_none,
parse_resolution,
+ str_or_none,
try_get,
unified_timestamp,
url_or_none,
peertube\.cpy\.re
)'''
_UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}'
+ _API_BASE = 'https://%s/api/v1/videos/%s/%s'
_VALID_URL = r'''(?x)
(?:
peertube:(?P<host>[^:]+):|
(?P<id>%s)
''' % (_INSTANCES_RE, _UUID_RE)
_TESTS = [{
- 'url': 'https://peertube.cpy.re/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c',
- 'md5': '80f24ff364cc9d333529506a263e7feb',
+ 'url': 'https://framatube.org/videos/watch/9c9de5e8-0a1e-484a-b099-e80766180a6d',
+ 'md5': '9bed8c0137913e17b86334e5885aacff',
'info_dict': {
- 'id': '2790feb0-8120-4e63-9af3-c943c69f5e6c',
+ 'id': '9c9de5e8-0a1e-484a-b099-e80766180a6d',
'ext': 'mp4',
- 'title': 'wow',
- 'description': 'wow such video, so gif',
+ 'title': 'What is PeerTube?',
+ 'description': 'md5:3fefb8dde2b189186ce0719fda6f7b10',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
- 'timestamp': 1519297480,
- 'upload_date': '20180222',
- 'uploader': 'Luclu7',
- 'uploader_id': '7fc42640-efdb-4505-a45d-a15b1a5496f1',
- 'uploder_url': 'https://peertube.nsa.ovh/accounts/luclu7',
- 'license': 'Unknown',
- 'duration': 3,
+ 'timestamp': 1538391166,
+ 'upload_date': '20181001',
+ 'uploader': 'Framasoft',
+ 'uploader_id': '3',
+ 'uploader_url': 'https://framatube.org/accounts/framasoft',
+ 'channel': 'Les vidéos de Framasoft',
+ 'channel_id': '2',
+ 'channel_url': 'https://framatube.org/video-channels/bf54d359-cfad-4935-9d45-9d6be93f63e8',
+ 'language': 'en',
+ 'license': 'Attribution - Share Alike',
+ 'duration': 113,
'view_count': int,
'like_count': int,
'dislike_count': int,
- 'tags': list,
- 'categories': list,
+ 'tags': ['framasoft', 'peertube'],
+ 'categories': ['Science & Technology'],
}
}, {
'url': 'https://peertube.tamanoir.foucry.net/videos/watch/0b04f13d-1e18-4f1d-814e-4979aa7c9c44',
entries = [peertube_url]
return entries
+ def _call_api(self, host, video_id, path, note=None, errnote=None, fatal=True):
+ return self._download_json(
+ self._API_BASE % (host, video_id, path), video_id,
+ note=note, errnote=errnote, fatal=fatal)
+
+ def _get_subtitles(self, host, video_id):
+ captions = self._call_api(
+ host, video_id, 'captions', note='Downloading captions JSON',
+ fatal=False)
+ if not isinstance(captions, dict):
+ return
+ data = captions.get('data')
+ if not isinstance(data, list):
+ return
+ subtitles = {}
+ for e in data:
+ language_id = try_get(e, lambda x: x['language']['id'], compat_str)
+ caption_url = urljoin('https://%s' % host, e.get('captionPath'))
+ if not caption_url:
+ continue
+ subtitles.setdefault(language_id or 'en', []).append({
+ 'url': caption_url,
+ })
+ return subtitles
+
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host') or mobj.group('host_2')
video_id = mobj.group('id')
- video = self._download_json(
- 'https://%s/api/v1/videos/%s' % (host, video_id), video_id)
+ video = self._call_api(
+ host, video_id, '', note='Downloading video JSON')
title = video['name']
formats.append(f)
self._sort_formats(formats)
- def account_data(field):
- return try_get(video, lambda x: x['account'][field], compat_str)
+ full_description = self._call_api(
+ host, video_id, 'description', note='Downloading description JSON',
+ fatal=False)
+
+ description = None
+ if isinstance(full_description, dict):
+ description = str_or_none(full_description.get('description'))
+ if not description:
+ description = video.get('description')
+
+ subtitles = self.extract_subtitles(host, video_id)
+
+ def data(section, field, type_):
+ return try_get(video, lambda x: x[section][field], type_)
+
+ def account_data(field, type_):
+ return data('account', field, type_)
+
+ def channel_data(field, type_):
+ return data('channel', field, type_)
- category = try_get(video, lambda x: x['category']['label'], compat_str)
+ category = data('category', 'label', compat_str)
categories = [category] if category else None
nsfw = video.get('nsfw')
return {
'id': video_id,
'title': title,
- 'description': video.get('description'),
+ 'description': description,
'thumbnail': urljoin(url, video.get('thumbnailPath')),
'timestamp': unified_timestamp(video.get('publishedAt')),
- 'uploader': account_data('displayName'),
- 'uploader_id': account_data('uuid'),
- 'uploder_url': account_data('url'),
- 'license': try_get(
- video, lambda x: x['licence']['label'], compat_str),
+ 'uploader': account_data('displayName', compat_str),
+ 'uploader_id': str_or_none(account_data('id', int)),
+ 'uploader_url': url_or_none(account_data('url', compat_str)),
+ 'channel': channel_data('displayName', compat_str),
+ 'channel_id': str_or_none(channel_data('id', int)),
+ 'channel_url': url_or_none(channel_data('url', compat_str)),
+ 'language': data('language', 'id', compat_str),
+ 'license': data('licence', 'label', compat_str),
'duration': int_or_none(video.get('duration')),
'view_count': int_or_none(video.get('views')),
'like_count': int_or_none(video.get('likes')),
'tags': try_get(video, lambda x: x['tags'], list),
'categories': categories,
'formats': formats,
+ 'subtitles': subtitles
}
headers={'Referer': self._LOGIN_URL})
# login succeeded
- if 'platzi.com/login' not in compat_str(urlh.geturl()):
+ if 'platzi.com/login' not in urlh.geturl():
return
login_error = self._webpage_read_content(
'ext': 'mp4',
'title': 'The Ol’ Raise and Switch!',
'description': 'md5:7db77f7107f98ba88401d3adc80ff7af',
- 'timestamp': 1511824728,
- 'upload_date': '20171127',
},
'add_id': ['LimelightMedia'],
}, {
# no data-video-title
- 'url': 'https://www.pokemon.com/us/pokemon-episodes/pokemon-movies/pokemon-the-rise-of-darkrai-2008',
+ 'url': 'https://www.pokemon.com/fr/episodes-pokemon/films-pokemon/pokemon-lascension-de-darkrai-2008',
'info_dict': {
- 'id': '99f3bae270bf4e5097274817239ce9c8',
+ 'id': 'dfbaf830d7e54e179837c50c0c6cc0e1',
'ext': 'mp4',
- 'title': 'Pokémon: The Rise of Darkrai',
- 'description': 'md5:ea8fbbf942e1e497d54b19025dd57d9d',
- 'timestamp': 1417778347,
- 'upload_date': '20141205',
+ 'title': "Pokémon : L'ascension de Darkrai",
+ 'description': 'md5:d1dbc9e206070c3e14a06ff557659fb5',
},
'add_id': ['LimelightMedia'],
'params': {
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+ compat_b64decode,
+ compat_chr,
+)
+from ..utils import int_or_none
+
+
+class PopcorntimesIE(InfoExtractor):
+ _VALID_URL = r'https?://popcorntimes\.tv/[^/]+/m/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)'
+ _TEST = {
+ 'url': 'https://popcorntimes.tv/de/m/A1XCFvz/haensel-und-gretel-opera-fantasy',
+ 'md5': '93f210991ad94ba8c3485950a2453257',
+ 'info_dict': {
+ 'id': 'A1XCFvz',
+ 'display_id': 'haensel-und-gretel-opera-fantasy',
+ 'ext': 'mp4',
+ 'title': 'Hänsel und Gretel',
+ 'description': 'md5:1b8146791726342e7b22ce8125cf6945',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ 'creator': 'John Paul',
+ 'release_date': '19541009',
+ 'duration': 4260,
+ 'tbr': 5380,
+ 'width': 720,
+ 'height': 540,
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id, display_id = mobj.group('id', 'display_id')
+
+ webpage = self._download_webpage(url, display_id)
+
+ title = self._search_regex(
+ r'<h1>([^<]+)', webpage, 'title',
+ default=None) or self._html_search_meta(
+ 'ya:ovs:original_name', webpage, 'title', fatal=True)
+
+ loc = self._search_regex(
+ r'PCTMLOC\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'loc',
+ group='value')
+
+ loc_b64 = ''
+ for c in loc:
+ c_ord = ord(c)
+ if ord('a') <= c_ord <= ord('z') or ord('A') <= c_ord <= ord('Z'):
+ upper = ord('Z') if c_ord <= ord('Z') else ord('z')
+ c_ord += 13
+ if upper < c_ord:
+ c_ord -= 26
+ loc_b64 += compat_chr(c_ord)
+
+ video_url = compat_b64decode(loc_b64).decode('utf-8')
+
+ description = self._html_search_regex(
+ r'(?s)<div[^>]+class=["\']pt-movie-desc[^>]+>(.+?)</div>', webpage,
+ 'description', fatal=False)
+
+ thumbnail = self._search_regex(
+ r'<img[^>]+class=["\']video-preview[^>]+\bsrc=(["\'])(?P<value>(?:(?!\1).)+)\1',
+ webpage, 'thumbnail', default=None,
+ group='value') or self._og_search_thumbnail(webpage)
+
+ creator = self._html_search_meta(
+ 'video:director', webpage, 'creator', default=None)
+
+ release_date = self._html_search_meta(
+ 'video:release_date', webpage, default=None)
+ if release_date:
+ release_date = release_date.replace('-', '')
+
+ def int_meta(name):
+ return int_or_none(self._html_search_meta(
+ name, webpage, default=None))
+
+ return {
+ 'id': video_id,
+ 'display_id': display_id,
+ 'url': video_url,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'creator': creator,
+ 'release_date': release_date,
+ 'duration': int_meta('video:duration'),
+ 'tbr': int_meta('ya:ovs:bitrate'),
+ 'width': int_meta('og:video:width'),
+ 'height': int_meta('og:video:height'),
+ 'http_headers': {
+ 'Referer': url,
+ },
+ }
ExtractorError,
int_or_none,
js_to_json,
+ merge_dicts,
urljoin,
)
'view_count': int,
'like_count': int,
'age_limit': 18,
- }
+ },
+ 'skip': 'HTTP Error 404: Not Found',
}, {
- # removed video
'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
- 'md5': '956b8ca569f7f4d8ec563e2c41598441',
+ 'md5': '1b7b3a40b9d65a8e5b25f7ab9ee6d6de',
'info_dict': {
'id': '1962',
'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
'ext': 'mp4',
- 'title': 'Sierra loves doing laundry',
+ 'title': 'md5:98c6f8b2d9c229d0f0fde47f61a1a759',
'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
'thumbnail': r're:^https?://.*\.jpg',
'view_count': int,
'like_count': int,
'age_limit': 18,
},
- 'skip': 'Not available anymore',
}]
def _real_extract(self, url):
r"(?s)sources'?\s*[:=]\s*(\{.+?\})",
webpage, 'sources', default='{}')), video_id)
+ info = {}
if not sources:
+ entries = self._parse_html5_media_entries(url, webpage, video_id)
+ if entries:
+ info = entries[0]
+
+ if not sources and not info:
message = self._html_search_regex(
r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1',
webpage, 'error message', group='value')
'format_id': format_id,
'height': height,
})
- self._sort_formats(formats)
+ if formats:
+ info['formats'] = formats
+ self._sort_formats(info['formats'])
description = self._html_search_regex(
- r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1',
- webpage, 'description', fatal=False, group='value')
+ (r'(?s)<section[^>]+class=["\']video-description[^>]+>(?P<value>.+?)</section>',
+ r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1'),
+ webpage, 'description', fatal=False,
+ group='value') or self._html_search_meta(
+ 'description', webpage, default=None) or self._og_search_description(webpage)
view_count = int_or_none(self._html_search_regex(
r'(\d+) views\s*<', webpage, 'view count', fatal=False))
thumbnail = self._search_regex(
r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
- 'thumbnail', fatal=False, group='url')
+ 'thumbnail', default=None, group='url')
like_count = int_or_none(self._search_regex(
- (r'(\d+)\s*</11[^>]+>(?: |\s)*\blikes',
+ (r'(\d+)</span>\s*likes',
+ r'(\d+)\s*</11[^>]+>(?: |\s)*\blikes',
r'class=["\']save-count["\'][^>]*>\s*(\d+)'),
webpage, 'like count', fatal=False))
- return {
+ return merge_dicts(info, {
'id': video_id,
'display_id': display_id,
'title': title,
'like_count': like_count,
'formats': formats,
'age_limit': 18,
- }
+ })
_VALID_URL = r'''(?x)
https?://
(?:
- (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
+ (?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
(?:www\.)?thumbzilla\.com/video/
)
(?P<id>[\da-z]+)
}, {
'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82',
+ 'only_matching': True,
}]
@staticmethod
host = mobj.group('host') or 'pornhub.com'
video_id = mobj.group('id')
+ if 'premium' in host:
+ if not self._downloader.params.get('cookiefile'):
+ raise ExtractorError(
+ 'PornHub Premium requires authentication.'
+ ' You may want to use --cookies.',
+ expected=True)
+
self._set_cookie(host, 'age_verified', '1')
def dl_webpage(platform):
# http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
# on that anymore.
title = self._html_search_meta(
- 'twitter:title', webpage, default=None) or self._search_regex(
- (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
- r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
- r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'),
+ 'twitter:title', webpage, default=None) or self._html_search_regex(
+ (r'(?s)<h1[^>]+class=["\']title["\'][^>]*>(?P<title>.+?)</h1>',
+ r'<div[^>]+data-video-title=(["\'])(?P<title>(?:(?!\1).)+)\1',
+ r'shareTitle["\']\s*[=:]\s*(["\'])(?P<title>(?:(?!\1).)+)\1'),
webpage, 'title', group='title')
video_urls = []
class PornHubUserIE(PornHubPlaylistBaseIE):
- _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
+ _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
_TESTS = [{
'url': 'https://www.pornhub.com/model/zoe_ph',
'playlist_mincount': 118,
class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
- _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
+ _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
_TESTS = [{
'url': 'https://www.pornhub.com/model/zoe_ph/videos',
'only_matching': True,
class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
- _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
+ _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
_TESTS = [{
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
'info_dict': {
from ..compat import (
compat_parse_qs,
- compat_str,
compat_urlparse,
)
from ..utils import (
'Downloading login page')
def is_logged(urlh):
- return 'learning.oreilly.com/home/' in compat_str(urlh.geturl())
+ return 'learning.oreilly.com/home/' in urlh.geturl()
if is_logged(urlh):
self.LOGGED_IN = True
return
- redirect_url = compat_str(urlh.geturl())
+ redirect_url = urlh.geturl()
parsed_url = compat_urlparse.urlparse(redirect_url)
qs = compat_parse_qs(parsed_url.query)
next_uri = compat_urlparse.urljoin(
class ServusIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)/(?P<id>[aA]{2}-\w+|\d+-\d+)'
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:www\.)?
+ (?:
+ servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)|
+ servustv\.com/videos
+ )
+ /(?P<id>[aA]{2}-\w+|\d+-\d+)
+ '''
_TESTS = [{
- 'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/',
+ # new URL schema
+ 'url': 'https://www.servustv.com/videos/aa-1t6vbu5pw1w12/',
'md5': '3e1dd16775aa8d5cbef23628cfffc1f4',
'info_dict': {
'id': 'AA-1T6VBU5PW1W12',
'description': 'md5:1247204d85783afe3682644398ff2ec4',
'thumbnail': r're:^https?://.*\.jpg',
}
+ }, {
+ # old URL schema
+ 'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/',
+ 'only_matching': True,
}, {
'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/',
'only_matching': True,
unified_timestamp,
update_url_query,
url_or_none,
+ urlhandle_detect_ext,
)
'repost_count': int,
}
},
- # not streamable song, preview
+ # geo-restricted
{
'url': 'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep',
'info_dict': {
'uploader_id': '9615865',
'timestamp': 1337635207,
'upload_date': '20120521',
- 'duration': 30,
+ 'duration': 227.155,
'license': 'all-rights-reserved',
'view_count': int,
'like_count': int,
'comment_count': int,
'repost_count': int,
},
- 'params': {
- # rtmp
- 'skip_download': True,
- },
},
# private link
{
'skip_download': True,
},
},
- # not available via api.soundcloud.com/i1/tracks/id/streams
{
'url': 'https://soundcloud.com/giovannisarani/mezzo-valzer',
'md5': 'e22aecd2bc88e0e4e432d7dcc0a1abf7',
'ext': 'mp3',
'title': 'Mezzo Valzer',
'description': 'md5:4138d582f81866a530317bae316e8b61',
- 'uploader': 'Giovanni Sarani',
+ 'uploader': 'Micronie',
'uploader_id': '3352531',
'timestamp': 1551394171,
'upload_date': '20190228',
'comment_count': int,
'repost_count': int,
},
- 'expected_warnings': ['Unable to download JSON metadata'],
}
]
- _API_BASE = 'https://api.soundcloud.com/'
_API_V2_BASE = 'https://api-v2.soundcloud.com/'
_BASE_URL = 'https://soundcloud.com/'
_IMAGE_REPL_RE = r'-([0-9a-z]+)\.jpg'
def _resolv_url(cls, url):
return SoundcloudIE._API_V2_BASE + 'resolve?url=' + url
- def _extract_info_dict(self, info, full_title=None, secret_token=None, version=2):
+ def _extract_info_dict(self, info, full_title=None, secret_token=None):
track_id = compat_str(info['id'])
title = info['title']
- track_base_url = self._API_BASE + 'tracks/%s' % track_id
format_urls = set()
formats = []
query['secret_token'] = secret_token
if info.get('downloadable') and info.get('has_downloads_left'):
- format_url = update_url_query(
- info.get('download_url') or track_base_url + '/download', query)
- format_urls.add(format_url)
- if version == 2:
- v1_info = self._download_json(
- track_base_url, track_id, query=query, fatal=False) or {}
- else:
- v1_info = info
- formats.append({
- 'format_id': 'download',
- 'ext': v1_info.get('original_format') or 'mp3',
- 'filesize': int_or_none(v1_info.get('original_content_size')),
- 'url': format_url,
- 'preference': 10,
- })
+ download_url = update_url_query(
+ self._API_V2_BASE + 'tracks/' + track_id + '/download', query)
+ redirect_url = (self._download_json(download_url, track_id, fatal=False) or {}).get('redirectUri')
+ if redirect_url:
+ urlh = self._request_webpage(
+ HEADRequest(redirect_url), track_id, fatal=False)
+ if urlh:
+ format_url = urlh.geturl()
+ format_urls.add(format_url)
+ formats.append({
+ 'format_id': 'download',
+ 'ext': urlhandle_detect_ext(urlh) or 'mp3',
+ 'filesize': int_or_none(urlh.headers.get('Content-Length')),
+ 'url': format_url,
+ 'preference': 10,
+ })
def invalid_url(url):
return not url or url in format_urls
}, 'http' if protocol == 'progressive' else protocol,
t.get('snipped') or '/preview/' in format_url)
- if not formats:
- # Old API, does not work for some tracks (e.g.
- # https://soundcloud.com/giovannisarani/mezzo-valzer)
- # and might serve preview URLs (e.g.
- # http://www.soundcloud.com/snbrn/ele)
- format_dict = self._download_json(
- track_base_url + '/streams', track_id,
- 'Downloading track url', query=query, fatal=False) or {}
-
- for key, stream_url in format_dict.items():
- if invalid_url(stream_url):
- continue
- format_urls.add(stream_url)
- mobj = re.search(r'(http|hls)_([^_]+)_(\d+)_url', key)
- if mobj:
- protocol, ext, abr = mobj.groups()
- add_format({
- 'abr': abr,
- 'ext': ext,
- 'url': stream_url,
- }, protocol)
-
- if not formats:
- # We fallback to the stream_url in the original info, this
- # cannot be always used, sometimes it can give an HTTP 404 error
- urlh = self._request_webpage(
- HEADRequest(info.get('stream_url') or track_base_url + '/stream'),
- track_id, query=query, fatal=False)
- if urlh:
- stream_url = urlh.geturl()
- if not invalid_url(stream_url):
- add_format({'url': stream_url}, 'http')
-
for f in formats:
f['vcodec'] = 'none'
+ if not formats and info.get('policy') == 'BLOCK':
+ self.raise_geo_restricted()
self._sort_formats(formats)
user = info.get('user') or {}
resolve_title += '/%s' % token
info_json_url = self._resolv_url(self._BASE_URL + resolve_title)
- version = 2
info = self._download_json(
- info_json_url, full_title, 'Downloading info JSON', query=query, fatal=False)
- if not info:
- info = self._download_json(
- info_json_url.replace(self._API_V2_BASE, self._API_BASE),
- full_title, 'Downloading info JSON', query=query)
- version = 1
+ info_json_url, full_title, 'Downloading info JSON', query=query)
- return self._extract_info_dict(info, full_title, token, version)
+ return self._extract_info_dict(info, full_title, token)
class SoundcloudPlaylistBaseIE(SoundcloudIE):
- def _extract_track_entries(self, tracks, token=None):
+ def _extract_set(self, playlist, token=None):
+ playlist_id = compat_str(playlist['id'])
+ tracks = playlist.get('tracks') or []
+ if not all([t.get('permalink_url') for t in tracks]) and token:
+ tracks = self._download_json(
+ self._API_V2_BASE + 'tracks', playlist_id,
+ 'Downloading tracks', query={
+ 'ids': ','.join([compat_str(t['id']) for t in tracks]),
+ 'playlistId': playlist_id,
+ 'playlistSecretToken': token,
+ })
entries = []
for track in tracks:
track_id = str_or_none(track.get('id'))
url += '?secret_token=' + token
entries.append(self.url_result(
url, SoundcloudIE.ie_key(), track_id))
- return entries
+ return self.playlist_result(
+ entries, playlist_id,
+ playlist.get('title'),
+ playlist.get('description'))
class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
'info_dict': {
'id': '2284613',
'title': 'The Royal Concept EP',
+ 'description': 'md5:71d07087c7a449e8941a70a29e34671e',
},
'playlist_mincount': 5,
}, {
msgs = (compat_str(err['error_message']) for err in info['errors'])
raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs))
- entries = self._extract_track_entries(info['tracks'], token)
-
- return self.playlist_result(
- entries, str_or_none(info.get('id')), info.get('title'))
+ return self._extract_set(info, token)
-class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
+class SoundcloudPagedPlaylistBaseIE(SoundcloudIE):
def _extract_playlist(self, base_url, playlist_id, playlist_title):
COMMON_QUERY = {
'limit': 2000000000,
self._API_V2_BASE + 'playlists/' + playlist_id,
playlist_id, 'Downloading playlist', query=query)
- entries = self._extract_track_entries(data['tracks'], token)
-
- return self.playlist_result(
- entries, playlist_id, data.get('title'), data.get('description'))
+ return self._extract_set(data, token)
class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE):
class SportDeutschlandIE(InfoExtractor):
_VALID_URL = r'https?://sportdeutschland\.tv/(?P<sport>[^/?#]+)/(?P<id>[^?#/]+)(?:$|[?#])'
_TESTS = [{
- 'url': 'http://sportdeutschland.tv/badminton/live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen',
+ 'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0',
'info_dict': {
- 'id': 'live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen',
+ 'id': 're-live-deutsche-meisterschaften-2020-halbfinals',
'ext': 'mp4',
- 'title': 're:Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen',
- 'categories': ['Badminton'],
+ 'title': 're:Re-live: Deutsche Meisterschaften 2020.*Halbfinals',
+ 'categories': ['Badminton-Deutschland'],
'view_count': int,
- 'thumbnail': r're:^https?://.*\.jpg$',
- 'description': r're:Die Badminton-WM 2014 aus Kopenhagen bei Sportdeutschland\.TV',
+ 'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
'timestamp': int,
- 'upload_date': 're:^201408[23][0-9]$',
+ 'upload_date': '20200201',
+ 'description': 're:.*', # meaningless description for THIS video
},
- 'params': {
- 'skip_download': 'Live stream',
- },
- }, {
- 'url': 'http://sportdeutschland.tv/li-ning-badminton-wm-2014/lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs',
- 'info_dict': {
- 'id': 'lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs',
- 'ext': 'mp4',
- 'upload_date': '20140825',
- 'description': 'md5:60a20536b57cee7d9a4ec005e8687504',
- 'timestamp': 1408976060,
- 'duration': 2732,
- 'title': 'Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen: Herren Einzel, Wei Lee vs. Keun Lee',
- 'thumbnail': r're:^https?://.*\.jpg$',
- 'view_count': int,
- 'categories': ['Li-Ning Badminton WM 2014'],
-
- }
}]
def _real_extract(self, url):
video_id = mobj.group('id')
sport_id = mobj.group('sport')
- api_url = 'http://proxy.vidibusdynamic.net/sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % (
+ api_url = 'https://proxy.vidibusdynamic.net/ssl/backend.sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % (
sport_id, video_id)
req = sanitized_Request(api_url, headers={
'Accept': 'application/vnd.vidibus.v2.html+json',
import re
from .common import InfoExtractor
-from ..compat import (
- compat_parse_qs,
- compat_urllib_parse_urlparse,
-)
+from ..compat import compat_str
from ..utils import (
determine_ext,
dict_get,
int_or_none,
- orderedSet,
+ str_or_none,
strip_or_none,
try_get,
- urljoin,
- compat_str,
)
class SVTSeriesIE(SVTPlayBaseIE):
- _VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)'
+ _VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)(?:.+?\btab=(?P<season_slug>[^&#]+))?'
_TESTS = [{
'url': 'https://www.svtplay.se/rederiet',
'info_dict': {
- 'id': 'rederiet',
+ 'id': '14445680',
'title': 'Rederiet',
- 'description': 'md5:505d491a58f4fcf6eb418ecab947e69e',
+ 'description': 'md5:d9fdfff17f5d8f73468176ecd2836039',
},
'playlist_mincount': 318,
}, {
- 'url': 'https://www.svtplay.se/rederiet?tab=sasong2',
+ 'url': 'https://www.svtplay.se/rederiet?tab=season-2-14445680',
'info_dict': {
- 'id': 'rederiet-sasong2',
+ 'id': 'season-2-14445680',
'title': 'Rederiet - Säsong 2',
- 'description': 'md5:505d491a58f4fcf6eb418ecab947e69e',
+ 'description': 'md5:d9fdfff17f5d8f73468176ecd2836039',
},
- 'playlist_count': 12,
+ 'playlist_mincount': 12,
}]
@classmethod
return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTSeriesIE, cls).suitable(url)
def _real_extract(self, url):
- series_id = self._match_id(url)
-
- qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
- season_slug = qs.get('tab', [None])[0]
-
- if season_slug:
- series_id += '-%s' % season_slug
-
- webpage = self._download_webpage(
- url, series_id, 'Downloading series page')
-
- root = self._parse_json(
- self._search_regex(
- self._SVTPLAY_RE, webpage, 'content', group='json'),
- series_id)
+ series_slug, season_id = re.match(self._VALID_URL, url).groups()
+
+ series = self._download_json(
+ 'https://api.svt.se/contento/graphql', series_slug,
+ 'Downloading series page', query={
+ 'query': '''{
+ listablesBySlug(slugs: ["%s"]) {
+ associatedContent(include: [productionPeriod, season]) {
+ items {
+ item {
+ ... on Episode {
+ videoSvtId
+ }
+ }
+ }
+ id
+ name
+ }
+ id
+ longDescription
+ name
+ shortDescription
+ }
+}''' % series_slug,
+ })['data']['listablesBySlug'][0]
season_name = None
entries = []
- for season in root['relatedVideoContent']['relatedVideosAccordion']:
+ for season in series['associatedContent']:
if not isinstance(season, dict):
continue
- if season_slug:
- if season.get('slug') != season_slug:
+ if season_id:
+ if season.get('id') != season_id:
continue
season_name = season.get('name')
- videos = season.get('videos')
- if not isinstance(videos, list):
+ items = season.get('items')
+ if not isinstance(items, list):
continue
- for video in videos:
- content_url = video.get('contentUrl')
- if not content_url or not isinstance(content_url, compat_str):
+ for item in items:
+ video = item.get('item') or {}
+ content_id = video.get('videoSvtId')
+ if not content_id or not isinstance(content_id, compat_str):
continue
- entries.append(
- self.url_result(
- urljoin(url, content_url),
- ie=SVTPlayIE.ie_key(),
- video_title=video.get('title')
- ))
-
- metadata = root.get('metaData')
- if not isinstance(metadata, dict):
- metadata = {}
+ entries.append(self.url_result(
+ 'svt:' + content_id, SVTPlayIE.ie_key(), content_id))
- title = metadata.get('title')
- season_name = season_name or season_slug
+ title = series.get('name')
+ season_name = season_name or season_id
if title and season_name:
title = '%s - %s' % (title, season_name)
- elif season_slug:
- title = season_slug
+ elif season_id:
+ title = season_id
return self.playlist_result(
- entries, series_id, title, metadata.get('description'))
+ entries, season_id or series.get('id'), title,
+ dict_get(series, ('longDescription', 'shortDescription')))
class SVTPageIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?svt\.se/(?:[^/]+/)*(?P<id>[^/?&#]+)'
+ _VALID_URL = r'https?://(?:www\.)?svt\.se/(?P<path>(?:[^/]+/)*(?P<id>[^/?&#]+))'
_TESTS = [{
- 'url': 'https://www.svt.se/sport/oseedat/guide-sommartraningen-du-kan-gora-var-och-nar-du-vill',
+ 'url': 'https://www.svt.se/sport/ishockey/bakom-masken-lehners-kamp-mot-mental-ohalsa',
'info_dict': {
- 'id': 'guide-sommartraningen-du-kan-gora-var-och-nar-du-vill',
- 'title': 'GUIDE: Sommarträning du kan göra var och när du vill',
+ 'id': '25298267',
+ 'title': 'Bakom masken – Lehners kamp mot mental ohälsa',
},
- 'playlist_count': 7,
+ 'playlist_count': 4,
}, {
- 'url': 'https://www.svt.se/nyheter/inrikes/ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner',
+ 'url': 'https://www.svt.se/nyheter/utrikes/svenska-andrea-ar-en-mil-fran-branderna-i-kalifornien',
'info_dict': {
- 'id': 'ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner',
- 'title': 'Ebba Busch Thor har bara delvis rätt om ”no-go-zoner”',
+ 'id': '24243746',
+ 'title': 'Svenska Andrea redo att fly sitt hem i Kalifornien',
},
- 'playlist_count': 1,
+ 'playlist_count': 2,
}, {
# only programTitle
'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
'info_dict': {
- 'id': '2900353',
+ 'id': '8439V2K',
'ext': 'mp4',
'title': 'Stjärnorna skojar till det - under SVT-intervjun',
'duration': 27,
return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url)
def _real_extract(self, url):
- playlist_id = self._match_id(url)
+ path, display_id = re.match(self._VALID_URL, url).groups()
- webpage = self._download_webpage(url, playlist_id)
+ article = self._download_json(
+ 'https://api.svt.se/nss-api/page/' + path, display_id,
+ query={'q': 'articles'})['articles']['content'][0]
- entries = [
- self.url_result(
- 'svt:%s' % video_id, ie=SVTPlayIE.ie_key(), video_id=video_id)
- for video_id in orderedSet(re.findall(
- r'data-video-id=["\'](\d+)', webpage))]
+ entries = []
- title = strip_or_none(self._og_search_title(webpage, default=None))
+ def _process_content(content):
+ if content.get('_type') in ('VIDEOCLIP', 'VIDEOEPISODE'):
+ video_id = compat_str(content['image']['svtId'])
+ entries.append(self.url_result(
+ 'svt:' + video_id, SVTPlayIE.ie_key(), video_id))
- return self.playlist_result(entries, playlist_id, title)
+ for media in article.get('media', []):
+ _process_content(media)
+
+ for obj in article.get('structuredBody', []):
+ _process_content(obj.get('content') or {})
+
+ return self.playlist_result(
+ entries, str_or_none(article.get('id')),
+ strip_or_none(article.get('title')))
from .common import InfoExtractor
from .wistia import WistiaIE
-from ..compat import compat_str
from ..utils import (
clean_html,
ExtractorError,
+ int_or_none,
get_element_by_class,
+ strip_or_none,
urlencode_postdata,
urljoin,
)
_SITES = {
# Only notable ones here
- 'upskillcourses.com': 'upskill',
- 'academy.gns3.com': 'gns3',
+ 'v1.upskillcourses.com': 'upskill',
+ 'gns3.teachable.com': 'gns3',
'academyhacker.com': 'academyhacker',
'stackskills.com': 'stackskills',
'market.saleshacker.com': 'saleshacker',
self._logged_in = True
return
- login_url = compat_str(urlh.geturl())
+ login_url = urlh.geturl()
login_form = self._hidden_inputs(login_page)
''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
_TESTS = [{
- 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
+ 'url': 'https://gns3.teachable.com/courses/gns3-certified-associate/lectures/6842364',
'info_dict': {
- 'id': 'uzw6zw58or',
- 'ext': 'mp4',
- 'title': 'Welcome to the Course!',
- 'description': 'md5:65edb0affa582974de4625b9cdea1107',
- 'duration': 138.763,
- 'timestamp': 1479846621,
- 'upload_date': '20161122',
+ 'id': 'untlgzk1v7',
+ 'ext': 'bin',
+ 'title': 'Overview',
+ 'description': 'md5:071463ff08b86c208811130ea1c2464c',
+ 'duration': 736.4,
+ 'timestamp': 1542315762,
+ 'upload_date': '20181115',
+ 'chapter': 'Welcome',
+ 'chapter_number': 1,
},
'params': {
'skip_download': True,
},
}, {
- 'url': 'http://upskillcourses.com/courses/119763/lectures/1747100',
+ 'url': 'http://v1.upskillcourses.com/courses/119763/lectures/1747100',
'only_matching': True,
}, {
- 'url': 'https://academy.gns3.com/courses/423415/lectures/6885939',
+ 'url': 'https://gns3.teachable.com/courses/423415/lectures/6885939',
'only_matching': True,
}, {
- 'url': 'teachable:https://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
+ 'url': 'teachable:https://v1.upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
'only_matching': True,
}]
webpage = self._download_webpage(url, video_id)
- wistia_url = WistiaIE._extract_url(webpage)
- if not wistia_url:
+ wistia_urls = WistiaIE._extract_urls(webpage)
+ if not wistia_urls:
if any(re.search(p, webpage) for p in (
r'class=["\']lecture-contents-locked',
r'>\s*Lecture contents locked',
title = self._og_search_title(webpage, default=None)
- return {
+ chapter = None
+ chapter_number = None
+ section_item = self._search_regex(
+ r'(?s)(?P<li><li[^>]+\bdata-lecture-id=["\']%s[^>]+>.+?</li>)' % video_id,
+ webpage, 'section item', default=None, group='li')
+ if section_item:
+ chapter_number = int_or_none(self._search_regex(
+ r'data-ss-position=["\'](\d+)', section_item, 'section id',
+ default=None))
+ if chapter_number is not None:
+ sections = []
+ for s in re.findall(
+ r'(?s)<div[^>]+\bclass=["\']section-title[^>]+>(.+?)</div>', webpage):
+ section = strip_or_none(clean_html(s))
+ if not section:
+ sections = []
+ break
+ sections.append(section)
+ if chapter_number <= len(sections):
+ chapter = sections[chapter_number - 1]
+
+ entries = [{
'_type': 'url_transparent',
'url': wistia_url,
'ie_key': WistiaIE.ie_key(),
'title': title,
- }
+ 'chapter': chapter,
+ 'chapter_number': chapter_number,
+ } for wistia_url in wistia_urls]
+
+ return self.playlist_result(entries, video_id, title)
class TeachableCourseIE(TeachableBaseIE):
/(?:courses|p)/(?:enrolled/)?(?P<id>[^/?#&]+)
''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
_TESTS = [{
- 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/',
+ 'url': 'http://v1.upskillcourses.com/courses/essential-web-developer-course/',
'info_dict': {
'id': 'essential-web-developer-course',
'title': 'The Essential Web Developer Course (Free)',
},
'playlist_count': 192,
}, {
- 'url': 'http://upskillcourses.com/courses/119763/',
+ 'url': 'http://v1.upskillcourses.com/courses/119763/',
'only_matching': True,
}, {
- 'url': 'http://upskillcourses.com/courses/enrolled/119763',
+ 'url': 'http://v1.upskillcourses.com/courses/enrolled/119763',
'only_matching': True,
}, {
- 'url': 'https://academy.gns3.com/courses/enrolled/423415',
+ 'url': 'https://gns3.teachable.com/courses/enrolled/423415',
'only_matching': True,
}, {
'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini',
determine_ext,
int_or_none,
str_or_none,
+ try_get,
urljoin,
)
'info_dict': {
'id': '1876350223',
'title': 'Bacalao con kokotxas al pil-pil',
- 'description': 'md5:1382dacd32dd4592d478cbdca458e5bb',
+ 'description': 'md5:716caf5601e25c3c5ab6605b1ae71529',
},
'playlist': [{
'md5': 'adb28c37238b675dad0f042292f209a7',
'description': 'md5:2771356ff7bfad9179c5f5cd954f1477',
'duration': 50,
},
+ }, {
+ # video in opening's content
+ 'url': 'https://www.telecinco.es/vivalavida/fiorella-sobrina-edmundo-arrocet-entrevista_18_2907195140.html',
+ 'info_dict': {
+ 'id': '2907195140',
+ 'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"',
+ 'description': 'md5:73f340a7320143d37ab895375b2bf13a',
+ },
+ 'playlist': [{
+ 'md5': 'adb28c37238b675dad0f042292f209a7',
+ 'info_dict': {
+ 'id': 'TpI2EttSDAReWpJ1o0NVh2',
+ 'ext': 'mp4',
+ 'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"',
+ 'duration': 1015,
+ },
+ }],
+ 'params': {
+ 'skip_download': True,
+ },
}, {
'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html',
'only_matching': True,
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
article = self._parse_json(self._search_regex(
- r'window\.\$REACTBASE_STATE\.article\s*=\s*({.+})',
+ r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=\s*({.+})',
webpage, 'article'), display_id)['article']
title = article.get('title')
- description = clean_html(article.get('leadParagraph'))
+ description = clean_html(article.get('leadParagraph')) or ''
if article.get('editorialType') != 'VID':
entries = []
- for p in article.get('body', []):
+ body = [article.get('opening')]
+ body.extend(try_get(article, lambda x: x['body'], list) or [])
+ for p in body:
+ if not isinstance(p, dict):
+ continue
content = p.get('content')
- if p.get('type') != 'video' or not content:
+ if not content:
+ continue
+ type_ = p.get('type')
+ if type_ == 'paragraph':
+ content_str = str_or_none(content)
+ if content_str:
+ description += content_str
continue
- entries.append(self._parse_content(content, url))
+ if type_ == 'video' and isinstance(content, dict):
+ entries.append(self._parse_content(content, url))
return self.playlist_result(
entries, str_or_none(article.get('id')), title, description)
content = article['opening']['content']
'ext': 'mp4',
'title': 'Un petit choc et puis repart!',
'description': 'md5:b04a7e6b3f74e32d7b294cffe8658374',
- 'upload_date': '20180222',
- 'timestamp': 1519326631,
},
'params': {
'skip_download': True,
_VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)'
_TEST = {
'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon',
- 'md5': '47c987d0515561114cf03d1226a9d4c7',
+ 'md5': 'cafbe4f47a8dae0ca0159937878100d6',
'info_dict': {
- 'id': '100463871',
+ 'id': '7da3d50e495c406b8fc0b997659cc075',
'ext': 'mp4',
'title': 'Video Game Hackathon',
'description': 'md5:558afeba217c6c8d96c60e5421795c07',
- 'upload_date': '20160212',
- 'timestamp': 1455310233,
}
}
from __future__ import unicode_literals
from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import try_get
class ThisOldHouseIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode)/(?P<id>[^/?#]+)'
+ _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode|(?:[^/]+/)?\d+)/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench',
- 'md5': '568acf9ca25a639f0c4ff905826b662f',
'info_dict': {
- 'id': '2REGtUDQ',
+ 'id': '5dcdddf673c3f956ef5db202',
'ext': 'mp4',
'title': 'How to Build a Storage Bench',
'description': 'In the workshop, Tom Silva and Kevin O\'Connor build a storage bench for an entryway.',
'timestamp': 1442548800,
'upload_date': '20150918',
- }
+ },
+ 'params': {
+ 'skip_download': True,
+ },
}, {
'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins',
'only_matching': True,
}, {
'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric',
'only_matching': True,
+ }, {
+ 'url': 'https://www.thisoldhouse.com/furniture/21017078/how-to-build-a-storage-bench',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.thisoldhouse.com/21113884/s41-e13-paradise-lost',
+ 'only_matching': True,
}]
+ _ZYPE_TMPL = 'https://player.zype.com/embed/%s.html?api_key=hsOk_yMSPYNrT22e9pu8hihLXjaZf0JW5jsOWv4ZqyHJFvkJn6rtToHl09tbbsbe'
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
- (r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1',
- r'id=(["\'])inline-video-player-(?P<id>(?:(?!\1).)+)\1'),
- webpage, 'video id', default=None, group='id')
- if not video_id:
- drupal_settings = self._parse_json(self._search_regex(
- r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
- webpage, 'drupal settings'), display_id)
- video_id = try_get(
- drupal_settings, lambda x: x['jwplatform']['video_id'],
- compat_str) or list(drupal_settings['comScore'])[0]
- return self.url_result('jwplatform:' + video_id, 'JWPlatform', video_id)
+ r'<iframe[^>]+src=[\'"](?:https?:)?//thisoldhouse\.chorus\.build/videos/zype/([0-9a-f]{24})',
+ webpage, 'video id')
+ return self.url_result(self._ZYPE_TMPL % video_id, 'Zype', video_id)
class ToggleIE(InfoExtractor):
IE_NAME = 'toggle'
- _VALID_URL = r'https?://video\.toggle\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P<id>[0-9]+)'
_TESTS = [{
- 'url': 'http://video.toggle.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
+ 'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
'info_dict': {
'id': '343115',
'ext': 'mp4',
}
}, {
'note': 'DRM-protected video',
- 'url': 'http://video.toggle.sg/en/movies/dug-s-special-mission/341413',
+ 'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413',
'info_dict': {
'id': '341413',
'ext': 'wvm',
}, {
# this also tests correct video id extraction
'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay',
- 'url': 'http://video.toggle.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
+ 'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
'info_dict': {
'id': '332861',
'ext': 'mp4',
'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
'only_matching': True,
}, {
- 'url': 'http://video.toggle.sg/zh/series/zero-calling-s2-hd/ep13/336367',
+ 'url': 'http://www.mewatch.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
'only_matching': True,
}, {
- 'url': 'http://video.toggle.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
+ 'url': 'http://www.mewatch.sg/zh/series/zero-calling-s2-hd/ep13/336367',
'only_matching': True,
}, {
- 'url': 'http://video.toggle.sg/en/movies/seven-days/321936',
+ 'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
'only_matching': True,
}, {
- 'url': 'https://video.toggle.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
+ 'url': 'http://www.mewatch.sg/en/movies/seven-days/321936',
'only_matching': True,
}, {
- 'url': 'http://video.toggle.sg/en/channels/eleven-plus/401585',
+ 'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585',
'only_matching': True,
}]
import re
from .common import InfoExtractor
-from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
webpage, urlh = self._download_webpage_handle(url, video_id)
- redirect_url = compat_str(urlh.geturl())
+ redirect_url = urlh.geturl()
if 'tumblr.com/safe-mode' in redirect_url or redirect_url.startswith('/safe-mode'):
raise ExtractorError(
'This Tumblr may contain sensitive media. '
video_id = self._match_id(url)
video = self._download_json(
- 'http://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id,
+ 'https://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id,
data=json.dumps({
'playlist_id': video_id,
'serienavn': '',
from .common import InfoExtractor
from ..utils import (
- clean_html,
determine_ext,
extract_attributes,
- get_element_by_class,
int_or_none,
parse_duration,
- parse_iso8601,
)
class TV5MondePlusIE(InfoExtractor):
IE_DESC = 'TV5MONDE+'
- _VALID_URL = r'https?://(?:www\.)?tv5mondeplus\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)'
- _TEST = {
- 'url': 'http://www.tv5mondeplus.com/toutes-les-videos/documentaire/tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants',
- 'md5': '12130fc199f020673138a83466542ec6',
+ _VALID_URL = r'https?://(?:www\.)?(?:tv5mondeplus|revoir\.tv5monde)\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)'
+ _TESTS = [{
+ # movie
+ 'url': 'https://revoir.tv5monde.com/toutes-les-videos/cinema/rendez-vous-a-atlit',
+ 'md5': '8cbde5ea7b296cf635073e27895e227f',
'info_dict': {
- 'id': 'tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants',
+ 'id': '822a4756-0712-7329-1859-a13ac7fd1407',
+ 'display_id': 'rendez-vous-a-atlit',
'ext': 'mp4',
- 'title': 'Tdah, mon amour - Enfants',
- 'description': 'md5:230e3aca23115afcf8006d1bece6df74',
- 'upload_date': '20170401',
- 'timestamp': 1491022860,
- }
- }
+ 'title': 'Rendez-vous à Atlit',
+ 'description': 'md5:2893a4c5e1dbac3eedff2d87956e4efb',
+ 'upload_date': '20200130',
+ },
+ }, {
+ # series episode
+ 'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/c-est-la-vie-ennemie-juree',
+ 'info_dict': {
+ 'id': '0df7007c-4900-3936-c601-87a13a93a068',
+ 'display_id': 'c-est-la-vie-ennemie-juree',
+ 'ext': 'mp4',
+ 'title': "C'est la vie - Ennemie jurée",
+ 'description': 'md5:dfb5c63087b6f35fe0cc0af4fe44287e',
+ 'upload_date': '20200130',
+ 'series': "C'est la vie",
+ 'episode': 'Ennemie jurée',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/neuf-jours-en-hiver-neuf-jours-en-hiver',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://revoir.tv5monde.com/toutes-les-videos/info-societe/le-journal-de-la-rts-edition-du-30-01-20-19h30',
+ 'only_matching': True,
+ }]
_GEO_BYPASS = False
def _real_extract(self, url):
if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage:
self.raise_geo_restricted(countries=['FR'])
- series = get_element_by_class('video-detail__title', webpage)
- title = episode = get_element_by_class(
- 'video-detail__subtitle', webpage) or series
- if series and series != title:
- title = '%s - %s' % (series, title)
+ title = episode = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
vpl_data = extract_attributes(self._search_regex(
r'(<[^>]+class="video_player_loader"[^>]+>)',
webpage, 'video player loader'))
})
self._sort_formats(formats)
+ description = self._html_search_regex(
+ r'(?s)<div[^>]+class=["\']episode-texte[^>]+>(.+?)</div>', webpage,
+ 'description', fatal=False)
+
+ series = self._html_search_regex(
+ r'<p[^>]+class=["\']episode-emission[^>]+>([^<]+)', webpage,
+ 'series', default=None)
+
+ if series and series != title:
+ title = '%s - %s' % (series, title)
+
+ upload_date = self._search_regex(
+ r'(?:date_publication|publish_date)["\']\s*:\s*["\'](\d{4}_\d{2}_\d{2})',
+ webpage, 'upload date', default=None)
+ if upload_date:
+ upload_date = upload_date.replace('_', '')
+
+ video_id = self._search_regex(
+ (r'data-guid=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
+ r'id_contenu["\']\s:\s*(\d+)'), webpage, 'video id',
+ default=display_id)
+
return {
- 'id': display_id,
+ 'id': video_id,
'display_id': display_id,
'title': title,
- 'description': clean_html(get_element_by_class('video-detail__description', webpage)),
+ 'description': description,
'thumbnail': vpl_data.get('data-image'),
'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)),
- 'timestamp': parse_iso8601(self._html_search_meta('uploadDate', webpage)),
+ 'upload_date': upload_date,
'formats': formats,
- 'episode': episode,
'series': series,
+ 'episode': episode,
}
class TVAIE(InfoExtractor):
- _VALID_URL = r'https?://videos\.tva\.ca/details/_(?P<id>\d+)'
- _TEST = {
+ _VALID_URL = r'https?://videos?\.tva\.ca/details/_(?P<id>\d+)'
+ _TESTS = [{
'url': 'https://videos.tva.ca/details/_5596811470001',
'info_dict': {
'id': '5596811470001',
# m3u8 download
'skip_download': True,
}
- }
+ }, {
+ 'url': 'https://video.tva.ca/details/_5596811470001',
+ 'only_matching': True,
+ }]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5481942443001/default_default/index.html?videoId=%s'
def _real_extract(self, url):
_VALID_URL = r'''(?x)
https?://
(?P<host>
- (?:(?:www|porno)\.)?24video\.
+ (?:(?:www|porno?)\.)?24video\.
(?:net|me|xxx|sexy?|tube|adult|site|vip)
)/
(?:
}, {
'url': 'https://www.24video.vip/video/view/1044982',
'only_matching': True,
+ }, {
+ 'url': 'https://porn.24video.net/video/2640421-vsya-takay',
+ 'only_matching': True,
}]
def _real_extract(self, url):
channel_id = self._match_id(url)
stream = self._call_api(
- 'kraken/streams/%s?stream_type=all' % channel_id, channel_id,
- 'Downloading stream JSON').get('stream')
+ 'kraken/streams/%s?stream_type=all' % channel_id.lower(),
+ channel_id, 'Downloading stream JSON').get('stream')
if not stream:
raise ExtractorError('%s is offline' % channel_id, expected=True)
from __future__ import unicode_literals
-import base64
+import json
import re
from .common import InfoExtractor
-from ..compat import compat_urllib_parse_unquote
+from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
- clean_html,
- determine_ext,
int_or_none,
- js_to_json,
parse_age_limit,
- parse_duration,
- try_get,
)
class ViewLiftBaseIE(InfoExtractor):
- _DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm)\.com|hoichoi\.tv'
+ _API_BASE = 'https://prod-api.viewlift.com/'
+ _DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm|failarmy|ftfnext|lnppass\.legapallacanestro|moviespree|app\.myoutdoortv|neoufitness|pflmma|theidentitytb)\.com|(?:hoichoi|app\.horseandcountry|kronon|marquee|supercrosslive)\.tv'
+ _SITE_MAP = {
+ 'ftfnext': 'lax',
+ 'funnyforfree': 'snagfilms',
+ 'hoichoi': 'hoichoitv',
+ 'kiddovid': 'snagfilms',
+ 'laxsportsnetwork': 'lax',
+ 'legapallacanestro': 'lnp',
+ 'marquee': 'marquee-tv',
+ 'monumentalsportsnetwork': 'monumental-network',
+ 'moviespree': 'bingeflix',
+ 'pflmma': 'pfl',
+ 'snagxtreme': 'snagfilms',
+ 'theidentitytb': 'tampabay',
+ 'vayafilm': 'snagfilms',
+ }
+ _TOKENS = {}
+
+ def _call_api(self, site, path, video_id, query):
+ token = self._TOKENS.get(site)
+ if not token:
+ token_query = {'site': site}
+ email, password = self._get_login_info(netrc_machine=site)
+ if email:
+ resp = self._download_json(
+ self._API_BASE + 'identity/signin', video_id,
+ 'Logging in', query=token_query, data=json.dumps({
+ 'email': email,
+ 'password': password,
+ }).encode())
+ else:
+ resp = self._download_json(
+ self._API_BASE + 'identity/anonymous-token', video_id,
+ 'Downloading authorization token', query=token_query)
+ self._TOKENS[site] = token = resp['authorizationToken']
+ return self._download_json(
+ self._API_BASE + path, video_id,
+ headers={'Authorization': token}, query=query)
class ViewLiftEmbedIE(ViewLiftBaseIE):
- _VALID_URL = r'https?://(?:(?:www|embed)\.)?(?:%s)/embed/player\?.*\bfilmId=(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' % ViewLiftBaseIE._DOMAINS_REGEX
+ IE_NAME = 'viewlift:embed'
+ _VALID_URL = r'https?://(?:(?:www|embed)\.)?(?P<domain>%s)/embed/player\?.*\bfilmId=(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' % ViewLiftBaseIE._DOMAINS_REGEX
_TESTS = [{
'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
'md5': '2924e9215c6eff7a55ed35b72276bd93',
'id': '74849a00-85a9-11e1-9660-123139220831',
'ext': 'mp4',
'title': '#whilewewatch',
+ 'description': 'md5:b542bef32a6f657dadd0df06e26fb0c8',
+ 'timestamp': 1334350096,
+ 'upload_date': '20120413',
}
}, {
# invalid labels, 360p is better that 480p
'id': '17ca0950-a74a-11e0-a92a-0026bb61d036',
'ext': 'mp4',
'title': 'Life in Limbo',
- }
+ },
+ 'skip': 'The video does not exist',
}, {
'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
'only_matching': True,
return mobj.group('url')
def _real_extract(self, url):
- video_id = self._match_id(url)
-
- webpage = self._download_webpage(url, video_id)
-
- if '>This film is not playable in your area.<' in webpage:
- raise ExtractorError(
- 'Film %s is not playable in your area.' % video_id, expected=True)
+ domain, film_id = re.match(self._VALID_URL, url).groups()
+ site = domain.split('.')[-2]
+ if site in self._SITE_MAP:
+ site = self._SITE_MAP[site]
+ try:
+ content_data = self._call_api(
+ site, 'entitlement/video/status', film_id, {
+ 'id': film_id
+ })['video']
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+ error_message = self._parse_json(e.cause.read().decode(), film_id).get('errorMessage')
+ if error_message == 'User does not have a valid subscription or has not purchased this content.':
+ self.raise_login_required()
+ raise ExtractorError(error_message, expected=True)
+ raise
+ gist = content_data['gist']
+ title = gist['title']
+ video_assets = content_data['streamingInfo']['videoAssets']
formats = []
- has_bitrate = False
- sources = self._parse_json(self._search_regex(
- r'(?s)sources:\s*(\[.+?\]),', webpage,
- 'sources', default='[]'), video_id, js_to_json)
- for source in sources:
- file_ = source.get('file')
- if not file_:
+ mpeg_video_assets = video_assets.get('mpeg') or []
+ for video_asset in mpeg_video_assets:
+ video_asset_url = video_asset.get('url')
+ if not video_asset:
continue
- type_ = source.get('type')
- ext = determine_ext(file_)
- format_id = source.get('label') or ext
- if all(v in ('m3u8', 'hls') for v in (type_, ext)):
- formats.extend(self._extract_m3u8_formats(
- file_, video_id, 'mp4', 'm3u8_native',
- m3u8_id='hls', fatal=False))
- else:
- bitrate = int_or_none(self._search_regex(
- [r'(\d+)kbps', r'_\d{1,2}x\d{1,2}_(\d{3,})\.%s' % ext],
- file_, 'bitrate', default=None))
- if not has_bitrate and bitrate:
- has_bitrate = True
- height = int_or_none(self._search_regex(
- r'^(\d+)[pP]$', format_id, 'height', default=None))
- formats.append({
- 'url': file_,
- 'format_id': 'http-%s%s' % (format_id, ('-%dk' % bitrate if bitrate else '')),
- 'tbr': bitrate,
- 'height': height,
- })
- if not formats:
- hls_url = self._parse_json(self._search_regex(
- r'filmInfo\.src\s*=\s*({.+?});',
- webpage, 'src'), video_id, js_to_json)['src']
- formats = self._extract_m3u8_formats(
- hls_url, video_id, 'mp4', 'm3u8_native',
- m3u8_id='hls', fatal=False)
- field_preference = None if has_bitrate else ('height', 'tbr', 'format_id')
- self._sort_formats(formats, field_preference)
-
- title = self._search_regex(
- [r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'],
- webpage, 'title')
-
- return {
- 'id': video_id,
+ bitrate = int_or_none(video_asset.get('bitrate'))
+ height = int_or_none(self._search_regex(
+ r'^_?(\d+)[pP]$', video_asset.get('renditionValue'),
+ 'height', default=None))
+ formats.append({
+ 'url': video_asset_url,
+ 'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''),
+ 'tbr': bitrate,
+ 'height': height,
+ 'vcodec': video_asset.get('codec'),
+ })
+
+ hls_url = video_assets.get('hls')
+ if hls_url:
+ formats.extend(self._extract_m3u8_formats(
+ hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+ self._sort_formats(formats, ('height', 'tbr', 'format_id'))
+
+ info = {
+ 'id': film_id,
'title': title,
+ 'description': gist.get('description'),
+ 'thumbnail': gist.get('videoImageUrl'),
+ 'duration': int_or_none(gist.get('runtime')),
+ 'age_limit': parse_age_limit(content_data.get('parentalRating')),
+ 'timestamp': int_or_none(gist.get('publishDate'), 1000),
'formats': formats,
}
+ for k in ('categories', 'tags'):
+ info[k] = [v['title'] for v in content_data.get(k, []) if v.get('title')]
+ return info
class ViewLiftIE(ViewLiftBaseIE):
- _VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?:/(?:films/title|show|(?:news/)?videos?))?/(?P<id>[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX
+ IE_NAME = 'viewlift'
+ _VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?P<path>(?:/(?:films/title|show|(?:news/)?videos?|watch))?/(?P<id>[^?#]+))' % ViewLiftBaseIE._DOMAINS_REGEX
_TESTS = [{
'url': 'http://www.snagfilms.com/films/title/lost_for_life',
'md5': '19844f897b35af219773fd63bdec2942',
'id': '00000148-7b53-de26-a9fb-fbf306f70020',
'display_id': 'augie_alone/s_2_ep_12_love',
'ext': 'mp4',
- 'title': 'Augie, Alone:S. 2 Ep. 12 - Love',
- 'description': 'md5:db2a5c72d994f16a780c1eb353a8f403',
+ 'title': 'S. 2 Ep. 12 - Love',
+ 'description': 'Augie finds love.',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 107,
+ 'upload_date': '20141012',
+ 'timestamp': 1413129540,
+ 'age_limit': 17,
},
'params': {
'skip_download': True,
# Was once Kaltura embed
'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15',
'only_matching': True,
+ }, {
+ 'url': 'https://www.marquee.tv/watch/sadlerswells-sacredmonsters',
+ 'only_matching': True,
}]
@classmethod
return False if ViewLiftEmbedIE.suitable(url) else super(ViewLiftIE, cls).suitable(url)
def _real_extract(self, url):
- domain, display_id = re.match(self._VALID_URL, url).groups()
-
- webpage = self._download_webpage(url, display_id)
-
- if ">Sorry, the Film you're looking for is not available.<" in webpage:
- raise ExtractorError(
- 'Film %s is not available.' % display_id, expected=True)
-
- initial_store_state = self._search_regex(
- r"window\.initialStoreState\s*=.*?JSON\.parse\(unescape\(atob\('([^']+)'\)\)\)",
- webpage, 'Initial Store State', default=None)
- if initial_store_state:
- modules = self._parse_json(compat_urllib_parse_unquote(base64.b64decode(
- initial_store_state).decode()), display_id)['page']['data']['modules']
- content_data = next(m['contentData'][0] for m in modules if m.get('moduleType') == 'VideoDetailModule')
- gist = content_data['gist']
- film_id = gist['id']
- title = gist['title']
- video_assets = try_get(
- content_data, lambda x: x['streamingInfo']['videoAssets'], dict)
- if not video_assets:
- token = self._download_json(
- 'https://prod-api.viewlift.com/identity/anonymous-token',
- film_id, 'Downloading authorization token',
- query={'site': 'snagfilms'})['authorizationToken']
- video_assets = self._download_json(
- 'https://prod-api.viewlift.com/entitlement/video/status',
- film_id, headers={
- 'Authorization': token,
- 'Referer': url,
- }, query={
- 'id': film_id
- })['video']['streamingInfo']['videoAssets']
-
- formats = []
- mpeg_video_assets = video_assets.get('mpeg') or []
- for video_asset in mpeg_video_assets:
- video_asset_url = video_asset.get('url')
- if not video_asset:
- continue
- bitrate = int_or_none(video_asset.get('bitrate'))
- height = int_or_none(self._search_regex(
- r'^_?(\d+)[pP]$', video_asset.get('renditionValue'),
- 'height', default=None))
- formats.append({
- 'url': video_asset_url,
- 'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''),
- 'tbr': bitrate,
- 'height': height,
- 'vcodec': video_asset.get('codec'),
- })
-
- hls_url = video_assets.get('hls')
- if hls_url:
- formats.extend(self._extract_m3u8_formats(
- hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
- self._sort_formats(formats, ('height', 'tbr', 'format_id'))
-
- info = {
- 'id': film_id,
- 'display_id': display_id,
- 'title': title,
- 'description': gist.get('description'),
- 'thumbnail': gist.get('videoImageUrl'),
- 'duration': int_or_none(gist.get('runtime')),
- 'age_limit': parse_age_limit(content_data.get('parentalRating')),
- 'timestamp': int_or_none(gist.get('publishDate'), 1000),
- 'formats': formats,
- }
- for k in ('categories', 'tags'):
- info[k] = [v['title'] for v in content_data.get(k, []) if v.get('title')]
- return info
- else:
- film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id')
-
- snag = self._parse_json(
- self._search_regex(
- r'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag', default='[]'),
- display_id)
-
- for item in snag:
- if item.get('data', {}).get('film', {}).get('id') == film_id:
- data = item['data']['film']
- title = data['title']
- description = clean_html(data.get('synopsis'))
- thumbnail = data.get('image')
- duration = int_or_none(data.get('duration') or data.get('runtime'))
- categories = [
- category['title'] for category in data.get('categories', [])
- if category.get('title')]
- break
- else:
- title = self._html_search_regex(
- (r'itemprop="title">([^<]+)<',
- r'(?s)itemprop="title">(.+?)<div'), webpage, 'title')
- description = self._html_search_regex(
- r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
- webpage, 'description', default=None) or self._og_search_description(webpage)
- thumbnail = self._og_search_thumbnail(webpage)
- duration = parse_duration(self._search_regex(
- r'<span itemprop="duration" class="film-duration strong">([^<]+)<',
- webpage, 'duration', fatal=False))
- categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage)
-
- return {
- '_type': 'url_transparent',
- 'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id),
- 'id': film_id,
- 'display_id': display_id,
- 'title': title,
- 'description': description,
- 'thumbnail': thumbnail,
- 'duration': duration,
- 'categories': categories,
- 'ie_key': 'ViewLiftEmbed',
- }
+ domain, path, display_id = re.match(self._VALID_URL, url).groups()
+ site = domain.split('.')[-2]
+ if site in self._SITE_MAP:
+ site = self._SITE_MAP[site]
+ modules = self._call_api(
+ site, 'content/pages', display_id, {
+ 'includeContent': 'true',
+ 'moduleOffset': 1,
+ 'path': path,
+ 'site': site,
+ })['modules']
+ film_id = next(m['contentData'][0]['gist']['id'] for m in modules if m.get('moduleType') == 'VideoDetailModule')
+ return {
+ '_type': 'url_transparent',
+ 'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id),
+ 'id': film_id,
+ 'display_id': display_id,
+ 'ie_key': 'ViewLiftEmbed',
+ }
unified_timestamp,
unsmuggle_url,
urlencode_postdata,
+ urljoin,
unescapeHTML,
)
for tt in text_tracks:
subtitles[tt['lang']] = [{
'ext': 'vtt',
- 'url': 'https://vimeo.com' + tt['url'],
+ 'url': urljoin('https://vimeo.com', tt['url']),
}]
thumbnails = []
# Retrieve video webpage to extract further information
webpage, urlh = self._download_webpage_handle(
url, video_id, headers=headers)
- redirect_url = compat_str(urlh.geturl())
+ redirect_url = urlh.geturl()
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
errmsg = ee.cause.read()
return self._TITLE or self._html_search_regex(
self._TITLE_RE, webpage, 'list title', fatal=False)
- 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)
'Downloading page %s' % pagenum)
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
_BASE_URL_TEMPL = 'https://vimeo.com/%s'
-class VimeoAlbumIE(VimeoChannelIE):
+class VimeoAlbumIE(VimeoBaseInfoExtractor):
IE_NAME = 'vimeo:album'
_VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
_TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
def _real_extract(self, url):
album_id = self._match_id(url)
webpage = self._download_webpage(url, album_id)
- webpage = self._login_list_password(url, album_id, webpage)
- api_config = self._extract_vimeo_config(webpage, album_id)['api']
+ viewer = self._parse_json(self._search_regex(
+ r'bootstrap_data\s*=\s*({.+?})</script>',
+ 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},
+ query={'fields': 'description,name,privacy'})
+ hashed_pass = None
+ if try_get(album, lambda x: x['privacy']['view']) == 'password':
+ password = self._downloader.params.get('videopassword')
+ if not password:
+ raise ExtractorError(
+ 'This album is protected by a password, use the --video-password option',
+ expected=True)
+ self._set_vimeo_cookie('vuid', viewer['vuid'])
+ try:
+ hashed_pass = self._download_json(
+ 'https://vimeo.com/showcase/%s/auth' % album_id,
+ 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, compat_HTTPError) and e.cause.code == 401:
+ raise ExtractorError('Wrong password', expected=True)
+ raise
entries = OnDemandPagedList(functools.partial(
- self._fetch_page, album_id, api_config['jwt'],
- api_config.get('hashed_pass')), self._PAGE_SIZE)
- return self.playlist_result(entries, album_id, self._html_search_regex(
- r'<title>\s*(.+?)(?:\s+on Vimeo)?</title>', webpage, 'title', fatal=False))
+ self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
+ return self.playlist_result(
+ entries, album_id, album.get('name'), album.get('description'))
class VimeoGroupsIE(VimeoChannelIE):
# https://wistia.com/support/embed-and-share/video-on-your-website
@staticmethod
def _extract_url(webpage):
- match = re.search(
- r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage)
- if match:
- return unescapeHTML(match.group('url'))
+ urls = WistiaIE._extract_urls(webpage)
+ return urls[0] if urls else None
- match = re.search(
- r'''(?sx)
- <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
- <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2
- ''', webpage)
- if match:
- return 'wistia:%s' % match.group('id')
-
- match = re.search(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage)
- if match:
- return 'wistia:%s' % match.group('id')
+ @staticmethod
+ def _extract_urls(webpage):
+ urls = []
+ for match in re.finditer(
+ r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage):
+ urls.append(unescapeHTML(match.group('url')))
+ for match in re.finditer(
+ r'''(?sx)
+ <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2
+ ''', webpage):
+ urls.append('wistia:%s' % match.group('id'))
+ for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage):
+ urls.append('wistia:%s' % match.group('id'))
+ return urls
def _real_extract(self, url):
video_id = self._match_id(url)
display_id = mobj.group('display_id') or mobj.group('display_id_2')
desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
- webpage = self._download_webpage(desktop_url, video_id)
+ webpage, urlh = self._download_webpage_handle(desktop_url, video_id)
error = self._html_search_regex(
r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
'ext': determine_ext(format_url, 'mp4'),
'height': get_height(quality),
'filesize': filesize,
+ 'http_headers': {
+ 'Referer': urlh.geturl(),
+ },
})
self._sort_formats(formats)
'display_id': 'A-Super-Run-Part-1-YT',
'ext': 'flv',
'title': 'A Super Run - Part 1 (YT)',
- 'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93',
+ 'description': 'md5:4cc3af1aa1b0413289babc88f0d4f616',
'uploader': 'tshirtguy59',
'duration': 579,
'view_count': int,
'Cookie': 'age_verified=1; cookiesAccepted=1',
})
- sources = self._parse_json(self._search_regex(
- r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
- webpage, 'sources', group='sources'), video_id,
- transform_source=js_to_json)
+ title, thumbnail, duration = [None] * 3
+
+ config = self._parse_json(self._search_regex(
+ r'playerConf\s*=\s*({.+?})\s*,\s*\n', webpage, 'config',
+ default='{}'), video_id, transform_source=js_to_json, fatal=False)
+ if config:
+ config = config.get('mainRoll')
+ if isinstance(config, dict):
+ title = config.get('title')
+ thumbnail = config.get('poster')
+ duration = int_or_none(config.get('duration'))
+ sources = config.get('sources') or config.get('format')
+
+ if not isinstance(sources, dict):
+ sources = self._parse_json(self._search_regex(
+ r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
+ webpage, 'sources', group='sources'), video_id,
+ transform_source=js_to_json)
formats = []
for format_id, format_url in sources.items():
self._remove_duplicate_formats(formats)
self._sort_formats(formats)
- title = self._search_regex(
- (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
- webpage, 'title', group='title')
- description = self._search_regex(
+ if not title:
+ title = self._search_regex(
+ (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
+ webpage, 'title', group='title')
+ description = self._og_search_description(
+ webpage, default=None) or self._html_search_meta(
+ 'twitter:description', webpage, default=None) or self._search_regex(
r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
uploader = self._search_regex(
(r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
webpage, 'uploader', fatal=False)
- duration = parse_duration(self._search_regex(
- r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
- webpage, 'duration', fatal=False))
+ if not duration:
+ duration = parse_duration(self._search_regex(
+ r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
+ webpage, 'duration', fatal=False))
view_count = str_to_int(self._search_regex(
- r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>',
+ (r'["\']viewsCount["\'][^>]*>(\d+)\s+views',
+ r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>'),
webpage, 'view count', fatal=False))
comment_count = str_to_int(self._html_search_regex(
r'>Comments? \(([\d,\.]+)\)<',
'display_id': display_id,
'title': title,
'description': description,
+ 'thumbnail': thumbnail,
'uploader': uploader,
'duration': duration,
'view_count': view_count,
'id': 'greenshowers-4056496',
'age_limit': 18,
},
- 'playlist_mincount': 155,
+ 'playlist_mincount': 154,
}
def _real_extract(self, url):
encodings = self._parse_json(
self._search_regex(
- r'encodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings',
+ r'[Ee]ncodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings',
default='[]'),
video_id, fatal=False)
for encoding in encodings:
from ..utils import (
bool_or_none,
clean_html,
- dict_get,
error_to_compat_str,
extract_attributes,
ExtractorError,
'upload_date': '20120506',
'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
'alt_title': 'I Love It (feat. Charli XCX)',
- 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
+ 'description': 'md5:19a2f98d9032b9311e686ed039564f63',
'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
'iconic ep', 'iconic', 'love', 'it'],
'id': 'nfWlot6h_JM',
'ext': 'm4a',
'title': 'Taylor Swift - Shake It Off',
- 'description': 'md5:bec2185232c05479482cb5a9b82719bf',
+ 'description': 'md5:307195cd21ff7fa352270fe884570ef0',
'duration': 242,
'uploader': 'TaylorSwiftVEVO',
'uploader_id': 'TaylorSwiftVEVO',
'upload_date': '20140818',
- 'creator': 'Taylor Swift',
},
'params': {
'youtube_include_dash_manifest': True,
'upload_date': '20100430',
'uploader_id': 'deadmau5',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
- 'creator': 'deadmau5',
+ 'creator': 'Dada Life, deadmau5',
'description': 'md5:12c56784b8032162bb936a5f76d55360',
'uploader': 'deadmau5',
'title': 'Deadmau5 - Some Chords (HD)',
- 'alt_title': 'Some Chords',
+ 'alt_title': 'This Machine Kills Some Chords',
},
'expected_warnings': [
'DASH manifest missing',
'skip_download': True,
'youtube_include_dash_manifest': False,
},
+ 'skip': 'not actual anymore',
},
{
# Youtube Music Auto-generated description
'title': 'Voyeur Girl',
'description': 'md5:7ae382a65843d6df2685993e90a8628f',
'upload_date': '20190312',
- 'uploader': 'Various Artists - Topic',
- 'uploader_id': 'UCVWKBi1ELZn0QX2CBLSkiyw',
+ 'uploader': 'Stephen - Topic',
+ 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
'artist': 'Stephen',
'track': 'Voyeur Girl',
'album': 'it\'s too much love to know my dear',
'id': '-hcAI0g-f5M',
'ext': 'mp4',
'title': 'Put It On Me',
- 'description': 'md5:93c55acc682ae7b0c668f2e34e1c069e',
+ 'description': 'md5:f6422397c07c4c907c6638e1fee380a5',
'upload_date': '20180426',
'uploader': 'Matt Maeson - Topic',
'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ',
def _extract_signature_function(self, video_id, player_url, example_sig):
id_m = re.match(
- r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
+ r'.*?[-.](?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
player_url)
if not id_m:
raise ExtractorError('Cannot identify player %r' % player_url)
def extract_view_count(v_info):
return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
- def extract_token(v_info):
- return dict_get(v_info, ('account_playback_token', 'accountPlaybackToken', 'token'))
-
def extract_player_response(player_response, video_id):
pl_response = str_or_none(player_response)
if not pl_response:
player_response = {}
# Get video info
+ video_info = {}
embed_webpage = None
if re.search(r'player-age-gate-content">', video_webpage) is not None:
age_gate = True
r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
})
video_info_url = proto + '://www.youtube.com/get_video_info?' + data
- video_info_webpage = self._download_webpage(
- video_info_url, video_id,
- note='Refetching age-gated info webpage',
- errnote='unable to download video info webpage')
- video_info = compat_parse_qs(video_info_webpage)
- pl_response = video_info.get('player_response', [None])[0]
- player_response = extract_player_response(pl_response, video_id)
- add_dash_mpd(video_info)
- view_count = extract_view_count(video_info)
+ try:
+ video_info_webpage = self._download_webpage(
+ video_info_url, video_id,
+ note='Refetching age-gated info webpage',
+ errnote='unable to download video info webpage')
+ except ExtractorError:
+ video_info_webpage = None
+ if video_info_webpage:
+ video_info = compat_parse_qs(video_info_webpage)
+ pl_response = video_info.get('player_response', [None])[0]
+ player_response = extract_player_response(pl_response, video_id)
+ add_dash_mpd(video_info)
+ view_count = extract_view_count(video_info)
else:
age_gate = False
- video_info = None
- sts = None
# Try looking directly into the video webpage
ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
if ytplayer_config:
args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
if args.get('livestream') == '1' or args.get('live_playback') == 1:
is_live = True
- sts = ytplayer_config.get('sts')
if not player_response:
player_response = extract_player_response(args.get('player_response'), video_id)
if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
add_dash_mpd_pr(player_response)
- # We also try looking in get_video_info since it may contain different dashmpd
- # URL that points to a DASH manifest with possibly different itag set (some itags
- # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
- # manifest pointed by get_video_info's dashmpd).
- # The general idea is to take a union of itags of both DASH manifests (for example
- # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093)
- self.report_video_info_webpage_download(video_id)
- for el in ('embedded', 'detailpage', 'vevo', ''):
- query = {
- 'video_id': video_id,
- 'ps': 'default',
- 'eurl': '',
- 'gl': 'US',
- 'hl': 'en',
- }
- if el:
- query['el'] = el
- if sts:
- query['sts'] = sts
- video_info_webpage = self._download_webpage(
- '%s://www.youtube.com/get_video_info' % proto,
- video_id, note=False,
- errnote='unable to download video info webpage',
- fatal=False, query=query)
- if not video_info_webpage:
- continue
- get_video_info = compat_parse_qs(video_info_webpage)
- if not player_response:
- pl_response = get_video_info.get('player_response', [None])[0]
- player_response = extract_player_response(pl_response, video_id)
- add_dash_mpd(get_video_info)
- if view_count is None:
- view_count = extract_view_count(get_video_info)
- if not video_info:
- video_info = get_video_info
- get_token = extract_token(get_video_info)
- if get_token:
- # Different get_video_info requests may report different results, e.g.
- # some may report video unavailability, but some may serve it without
- # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362,
- # the original webpage as well as el=info and el=embedded get_video_info
- # requests report video unavailability due to geo restriction while
- # el=detailpage succeeds and returns valid data). This is probably
- # due to YouTube measures against IP ranges of hosting providers.
- # Working around by preferring the first succeeded video_info containing
- # the token if no such video_info yet was found.
- token = extract_token(video_info)
- if not token:
- video_info = get_video_info
- break
def extract_unavailable_message():
messages = []
if messages:
return '\n'.join(messages)
- if not video_info:
+ if not video_info and not player_response:
unavailable_message = extract_unavailable_message()
if not unavailable_message:
unavailable_message = 'Unable to extract video data'
raise ExtractorError(
'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
+ if not isinstance(video_info, dict):
+ video_info = {}
+
video_details = try_get(
player_response, lambda x: x['videoDetails'], dict) or {}
else:
player_version = self._search_regex(
[r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
- r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
+ r'(?:www|player(?:_ias)?)[-.]([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
player_url,
'html5 player', fatal=False)
player_desc = 'html5 player %s' % player_version
f['stretched_ratio'] = ratio
if not formats:
- token = extract_token(video_info)
- if not token:
- if 'reason' in video_info:
- if 'The uploader has not made this video available in your country.' in video_info['reason']:
- regions_allowed = self._html_search_meta(
- 'regionsAllowed', video_webpage, default=None)
- countries = regions_allowed.split(',') if regions_allowed else None
- self.raise_geo_restricted(
- msg=video_info['reason'][0], countries=countries)
- reason = video_info['reason'][0]
- if 'Invalid parameters' in reason:
- unavailable_message = extract_unavailable_message()
- if unavailable_message:
- reason = unavailable_message
- raise ExtractorError(
- 'YouTube said: %s' % reason,
- expected=True, video_id=video_id)
- else:
- raise ExtractorError(
- '"token" parameter not in video info for unknown reason',
- video_id=video_id)
-
- if not formats and (video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos'])):
- raise ExtractorError('This video is DRM protected.', expected=True)
+ if 'reason' in video_info:
+ if 'The uploader has not made this video available in your country.' in video_info['reason']:
+ regions_allowed = self._html_search_meta(
+ 'regionsAllowed', video_webpage, default=None)
+ countries = regions_allowed.split(',') if regions_allowed else None
+ self.raise_geo_restricted(
+ msg=video_info['reason'][0], countries=countries)
+ reason = video_info['reason'][0]
+ if 'Invalid parameters' in reason:
+ unavailable_message = extract_unavailable_message()
+ if unavailable_message:
+ reason = unavailable_message
+ raise ExtractorError(
+ 'YouTube said: %s' % reason,
+ expected=True, video_id=video_id)
+ if video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos']):
+ raise ExtractorError('This video is DRM protected.', expected=True)
self._sort_formats(formats)
_VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})'
IE_NAME = 'youtube:playlist'
_TESTS = [{
- 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
+ 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
'info_dict': {
- 'title': 'ytdl test PL',
- 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
+ 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
+ 'uploader': 'Sergey M.',
+ 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
+ 'title': 'youtube-dl public playlist',
},
- 'playlist_count': 3,
+ 'playlist_count': 1,
}, {
- 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
+ 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
'info_dict': {
- 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
- 'title': 'YDL_Empty_List',
+ 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
+ 'uploader': 'Sergey M.',
+ 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
+ 'title': 'youtube-dl empty playlist',
},
'playlist_count': 0,
- 'skip': 'This playlist is private',
}, {
'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
'uploader': 'Christiaan008',
'uploader_id': 'ChRiStIaAn008',
},
- 'playlist_count': 95,
+ 'playlist_count': 96,
}, {
'note': 'issue #673',
'url': 'PLBB231211A4F62143',
'timestamp': 1359044972,
'upload_date': '20130124',
'view_count': int,
- 'comment_count': int,
},
},
{
'id': 'das-aktuelle-sportstudio',
'title': 'das aktuelle sportstudio | ZDF',
},
- 'playlist_count': 21,
+ 'playlist_mincount': 23,
}, {
'url': 'https://www.zdf.de/dokumentation/planet-e',
'info_dict': {
'id': 'planet-e',
'title': 'planet e.',
},
- 'playlist_count': 4,
+ 'playlist_mincount': 50,
}, {
'url': 'https://www.zdf.de/filme/taunuskrimi/',
'only_matching': True,
action='help',
help='Print this help text and exit')
general.add_option(
- '-v', '--version',
+ '--version',
action='version',
help='Print program version and exit')
general.add_option(
import sys
from zipimport import zipimporter
+from .compat import compat_realpath
from .utils import encode_compat_str
from .version import __version__
print_notes(to_screen, versions_info['versions'])
# sys.executable is set to the full pathname of the exe-file for py2exe
- filename = sys.executable if hasattr(sys, 'frozen') else sys.argv[0]
+ # though symlinks are not followed so that we need to do this manually
+ # with help of realpath
+ filename = compat_realpath(sys.executable if hasattr(sys, 'frozen') else sys.argv[0])
if not os.access(filename, os.W_OK):
to_screen('ERROR: no write permissions on %s' % filename)
class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
+ """
+ See [1] for cookie file format.
+
+ 1. https://curl.haxx.se/docs/http-cookies.html
+ """
_HTTPONLY_PREFIX = '#HttpOnly_'
def save(self, filename=None, ignore_discard=False, ignore_expires=False):
https_response = http_response
+class YoutubeDLRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
+ if sys.version_info[0] < 3:
+ def redirect_request(self, req, fp, code, msg, headers, newurl):
+ # On python 2 urlh.geturl() may sometimes return redirect URL
+ # as byte string instead of unicode. This workaround allows
+ # to force it always return unicode.
+ return compat_urllib_request.HTTPRedirectHandler.redirect_request(self, req, fp, code, msg, headers, compat_str(newurl))
+
+
def extract_timezone(date_str):
m = re.search(
r'^.{8,}?(?P<tz>Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)',
from __future__ import unicode_literals
-__version__ = '2020.01.24'
+__version__ = '2020.03.24'
Rapsys Git / youtubedl / commitdiff