Merge branch 'yt-dlp:master' into pr/2475

This commit is contained in:
bashonly 2024-07-24 23:02:46 -05:00
commit cb02b582a8
No known key found for this signature in database
GPG key ID: 783F096F253D15B0
28 changed files with 746 additions and 618 deletions

View file

@ -650,3 +650,6 @@ DinhHuy2010
exterrestris exterrestris
harbhim harbhim
LeSuisse LeSuisse
DunnesH
iancmy
mokrueger

View file

@ -4,6 +4,54 @@ # Changelog
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
--> -->
### 2024.07.25
#### Extractor changes
- **abematv**: [Adapt key retrieval to request handler framework](https://github.com/yt-dlp/yt-dlp/commit/a3bab4752a2b3d56e5a59b4e0411bb8f695c010b) ([#10491](https://github.com/yt-dlp/yt-dlp/issues/10491)) by [bashonly](https://github.com/bashonly)
- **facebook**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/1a34a802f44a1dab8f642c79c3cc810e21541d3b) ([#10531](https://github.com/yt-dlp/yt-dlp/issues/10531)) by [bashonly](https://github.com/bashonly)
- **mlbtv**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/f0993391e6052ec8f7aacc286609564f226943b9) ([#10515](https://github.com/yt-dlp/yt-dlp/issues/10515)) by [bashonly](https://github.com/bashonly)
- **tiktok**: [Fix and deprioritize JSON subtitles](https://github.com/yt-dlp/yt-dlp/commit/2f97779f335ac069ecccd9c7bf81abf4a83cfe7a) ([#10516](https://github.com/yt-dlp/yt-dlp/issues/10516)) by [bashonly](https://github.com/bashonly)
- **vimeo**: [Fix chapters extraction](https://github.com/yt-dlp/yt-dlp/commit/a0a1bc3d8d8e3bb9a48a06e835815a0460e90e77) ([#10544](https://github.com/yt-dlp/yt-dlp/issues/10544)) by [bashonly](https://github.com/bashonly)
- **youtube**: [Fix `n` function name extraction for player `3400486c`](https://github.com/yt-dlp/yt-dlp/commit/713b4cd18f00556771af8cfdd9cea6cc1a09e948) ([#10542](https://github.com/yt-dlp/yt-dlp/issues/10542)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **build**: [Pin `setuptools` version](https://github.com/yt-dlp/yt-dlp/commit/e046db8a116b1c320d4785daadd48ea0b22a3987) ([#10493](https://github.com/yt-dlp/yt-dlp/issues/10493)) by [bashonly](https://github.com/bashonly)
### 2024.07.16
#### Core changes
- [Fix `noprogress` if `test=True` with `--quiet` and `--verbose`](https://github.com/yt-dlp/yt-dlp/commit/66ce3d76d87af3f81cc9dfec4be4704016cb1cdb) ([#10454](https://github.com/yt-dlp/yt-dlp/issues/10454)) by [Grub4K](https://github.com/Grub4K)
- [Support `auto-tty` and `no_color-tty` for `--color`](https://github.com/yt-dlp/yt-dlp/commit/d9cbced493cae2008508d94a2db5dd98be7c01fc) ([#10453](https://github.com/yt-dlp/yt-dlp/issues/10453)) by [Grub4K](https://github.com/Grub4K)
- **update**: [Fix network error handling](https://github.com/yt-dlp/yt-dlp/commit/ed1b9ed93dd90d2cc960c0d8eaa9d919db224203) ([#10486](https://github.com/yt-dlp/yt-dlp/issues/10486)) by [bashonly](https://github.com/bashonly)
- **utils**: `parse_codecs`: [Fix parsing of mixed case codec strings](https://github.com/yt-dlp/yt-dlp/commit/cc0070f6496e501d77352bad475fb02d6a86846a) by [bashonly](https://github.com/bashonly)
#### Extractor changes
- **adn**: [Adjust for .com domain change](https://github.com/yt-dlp/yt-dlp/commit/959b7a379b8e5da059d110a63339c964b6265736) ([#10399](https://github.com/yt-dlp/yt-dlp/issues/10399)) by [infanf](https://github.com/infanf)
- **afreecatv**: [Fix login and use `legacy_ssl`](https://github.com/yt-dlp/yt-dlp/commit/4cd41469243624d90b7a2009b95cbe0609343efe) ([#10440](https://github.com/yt-dlp/yt-dlp/issues/10440)) by [bashonly](https://github.com/bashonly)
- **box**: [Support enterprise URLs](https://github.com/yt-dlp/yt-dlp/commit/705f5b84dec75cc7af97f42fd1530e8062735970) ([#10419](https://github.com/yt-dlp/yt-dlp/issues/10419)) by [seproDev](https://github.com/seproDev)
- **digitalconcerthall**: [Extract HEVC and FLAC formats](https://github.com/yt-dlp/yt-dlp/commit/e62fa6b0e0186f8c5666c2c5ab64cf191abdafc1) ([#10470](https://github.com/yt-dlp/yt-dlp/issues/10470)) by [bashonly](https://github.com/bashonly)
- **dplay**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/39e6c4cb44b9292e89ac0afec3cd0afc2ae8775f) ([#10471](https://github.com/yt-dlp/yt-dlp/issues/10471)) by [bashonly](https://github.com/bashonly)
- **epidemicsound**: [Support sound effects URLs](https://github.com/yt-dlp/yt-dlp/commit/8531d2b03bac9cc746f2ee8098aaf8f115505f5b) ([#10436](https://github.com/yt-dlp/yt-dlp/issues/10436)) by [iancmy](https://github.com/iancmy)
- **generic**: [Fix direct video link extensions](https://github.com/yt-dlp/yt-dlp/commit/b9afb99e7c34d0eb15ddc6689cd7d20eebfda68e) ([#10468](https://github.com/yt-dlp/yt-dlp/issues/10468)) by [bashonly](https://github.com/bashonly)
- **picarto**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/bacd18b7df08b4995644fd12cee1f8c8e8636bc7) ([#10414](https://github.com/yt-dlp/yt-dlp/issues/10414)) by [Frankgoji](https://github.com/Frankgoji)
- **soundcloud**: permalink, user: [Extract tracks only](https://github.com/yt-dlp/yt-dlp/commit/22870b81bad97dfa6307a7add44753b2dffc76a9) ([#10463](https://github.com/yt-dlp/yt-dlp/issues/10463)) by [DunnesH](https://github.com/DunnesH)
- **tiktok**: live: [Fix room ID extraction](https://github.com/yt-dlp/yt-dlp/commit/d2189d3d36987ebeac426fd70a60a5fe86325a2b) ([#10408](https://github.com/yt-dlp/yt-dlp/issues/10408)) by [mokrueger](https://github.com/mokrueger)
- **tv5monde**: [Support browser impersonation](https://github.com/yt-dlp/yt-dlp/commit/9b95a6765a5f6325af99c4aca961587f0c426e8c) ([#10417](https://github.com/yt-dlp/yt-dlp/issues/10417)) by [bashonly](https://github.com/bashonly) (With fixes in [cc1a309](https://github.com/yt-dlp/yt-dlp/commit/cc1a3098c00995c6aebc2a16bd1050a66bad64db))
- **youtube**
- [Avoid poToken experiment player responses](https://github.com/yt-dlp/yt-dlp/commit/8b8b442cb005a8d85315f301615f83fb736b967a) ([#10456](https://github.com/yt-dlp/yt-dlp/issues/10456)) by [seproDev](https://github.com/seproDev) (With fixes in [16da8ef](https://github.com/yt-dlp/yt-dlp/commit/16da8ef9937ff76632dfef02e5062c5ba99c8ea2))
- [Invalidate nsig cache from < 2024.07.09](https://github.com/yt-dlp/yt-dlp/commit/04e17ba20a139f1b3e30ec4bafa3fba26888f0b3) ([#10401](https://github.com/yt-dlp/yt-dlp/issues/10401)) by [bashonly](https://github.com/bashonly)
- [Reduce android client priority](https://github.com/yt-dlp/yt-dlp/commit/b85eef0a615a01304f88a3847309c667e09a20df) ([#10467](https://github.com/yt-dlp/yt-dlp/issues/10467)) by [seproDev](https://github.com/seproDev)
#### Networking changes
- [Add `legacy_ssl` request extension](https://github.com/yt-dlp/yt-dlp/commit/150ecc45d9cacc919550c13b04fd998ac5103a6b) ([#10448](https://github.com/yt-dlp/yt-dlp/issues/10448)) by [coletdjnz](https://github.com/coletdjnz)
- **Request Handler**: curl_cffi: [Support `curl_cffi` 0.7.X](https://github.com/yt-dlp/yt-dlp/commit/42bfca00a6b460fc053514cdd7ac6f5b5daddf0c) by [coletdjnz](https://github.com/coletdjnz)
#### Misc. changes
- **build**
- [Include `curl_cffi` in `yt-dlp_linux`](https://github.com/yt-dlp/yt-dlp/commit/4521f30d1479315cd5c3bf4abdad19391952df98) by [bashonly](https://github.com/bashonly)
- [Pin `curl-cffi` to 0.5.10 for Windows](https://github.com/yt-dlp/yt-dlp/commit/ac30941ae682f71eab010877c9a977736a61d3cf) by [bashonly](https://github.com/bashonly)
- **cleanup**: Miscellaneous: [89a161e](https://github.com/yt-dlp/yt-dlp/commit/89a161e8c62569a662deda1c948664152efcb6b4) by [bashonly](https://github.com/bashonly)
### 2024.07.09 ### 2024.07.09
#### Core changes #### Core changes

View file

@ -368,7 +368,9 @@ ## General Options:
stderr) to apply the setting to. Can be one stderr) to apply the setting to. Can be one
of "always", "auto" (default), "never", or of "always", "auto" (default), "never", or
"no_color" (use non color terminal "no_color" (use non color terminal
sequences). Can be used multiple times sequences). Use "auto-tty" or "no_color-tty"
to decide based on terminal support only.
Can be used multiple times
--compat-options OPTS Options that can help keep compatibility --compat-options OPTS Options that can help keep compatibility
with youtube-dl or youtube-dlc with youtube-dl or youtube-dlc
configurations by reverting some of the configurations by reverting some of the
@ -1859,6 +1861,9 @@ #### orfon (orf:on)
#### bilibili #### bilibili
* `prefer_multi_flv`: Prefer extracting flv formats over mp4 for older videos that still provide legacy formats * `prefer_multi_flv`: Prefer extracting flv formats over mp4 for older videos that still provide legacy formats
#### digitalconcerthall
* `prefer_combined_hls`: Prefer extracting combined/pre-merged video and audio HLS formats. This will exclude 4K/HEVC video and lossless/FLAC audio formats, which are only available as split video/audio HLS formats
**Note**: These options may be changed/removed in the future without concern for backward compatibility **Note**: These options may be changed/removed in the future without concern for backward compatibility
<!-- MANPAGE: MOVE "INSTALLATION" SECTION HERE --> <!-- MANPAGE: MOVE "INSTALLATION" SECTION HERE -->

View file

@ -9,6 +9,7 @@ maintainers = [
{name = "Grub4K", email = "contact@grub4k.xyz"}, {name = "Grub4K", email = "contact@grub4k.xyz"},
{name = "bashonly", email = "bashonly@protonmail.com"}, {name = "bashonly", email = "bashonly@protonmail.com"},
{name = "coletdjnz", email = "coletdjnz@protonmail.com"}, {name = "coletdjnz", email = "coletdjnz@protonmail.com"},
{name = "sepro", email = "sepro@sepr0.com"},
] ]
description = "A feature-rich command-line audio/video downloader" description = "A feature-rich command-line audio/video downloader"
readme = "README.md" readme = "README.md"
@ -65,7 +66,7 @@ build = [
"build", "build",
"hatchling", "hatchling",
"pip", "pip",
"setuptools", "setuptools>=71.0.2", # 71.0.0 broke pyinstaller
"wheel", "wheel",
] ]
dev = [ dev = [

View file

@ -354,7 +354,6 @@ # Supported sites
- **DigitallySpeaking** - **DigitallySpeaking**
- **Digiteka** - **Digiteka**
- **DiscogsReleasePlaylist** - **DiscogsReleasePlaylist**
- **Discovery**
- **DiscoveryLife** - **DiscoveryLife**
- **DiscoveryNetworksDe** - **DiscoveryNetworksDe**
- **DiscoveryPlus** - **DiscoveryPlus**
@ -363,7 +362,6 @@ # Supported sites
- **DiscoveryPlusItaly** - **DiscoveryPlusItaly**
- **DiscoveryPlusItalyShow** - **DiscoveryPlusItalyShow**
- **Disney** - **Disney**
- **DIYNetwork**
- **dlf** - **dlf**
- **dlf:corpus**: DLF Multi-feed Archives - **dlf:corpus**: DLF Multi-feed Archives
- **dlive:stream** - **dlive:stream**
@ -516,7 +514,6 @@ # Supported sites
- **GlattvisionTVLive**: [*glattvisiontv*](## "netrc machine") - **GlattvisionTVLive**: [*glattvisiontv*](## "netrc machine")
- **GlattvisionTVRecordings**: [*glattvisiontv*](## "netrc machine") - **GlattvisionTVRecordings**: [*glattvisiontv*](## "netrc machine")
- **Glide**: Glide mobile video messages (glide.me) - **Glide**: Glide mobile video messages (glide.me)
- **GlobalCyclingNetworkPlus**
- **GlobalPlayerAudio** - **GlobalPlayerAudio**
- **GlobalPlayerAudioEpisode** - **GlobalPlayerAudioEpisode**
- **GlobalPlayerLive** - **GlobalPlayerLive**
@ -820,8 +817,6 @@ # Supported sites
- **MotherlessGroup** - **MotherlessGroup**
- **MotherlessUploader** - **MotherlessUploader**
- **Motorsport**: motorsport.com (**Currently broken**) - **Motorsport**: motorsport.com (**Currently broken**)
- **MotorTrend**
- **MotorTrendOnDemand**
- **MovieFap** - **MovieFap**
- **Moviepilot** - **Moviepilot**
- **MoviewPlay** - **MoviewPlay**

View file

@ -929,6 +929,11 @@ def test_parse_codecs(self):
'acodec': 'none', 'acodec': 'none',
'dynamic_range': 'DV', 'dynamic_range': 'DV',
}) })
self.assertEqual(parse_codecs('fLaC'), {
'vcodec': 'none',
'acodec': 'flac',
'dynamic_range': None,
})
self.assertEqual(parse_codecs('theora, vorbis'), { self.assertEqual(parse_codecs('theora, vorbis'), {
'vcodec': 'theora', 'vcodec': 'theora',
'acodec': 'vorbis', 'acodec': 'vorbis',

View file

@ -171,6 +171,10 @@
'https://www.youtube.com/s/player/b22ef6e7/player_ias.vflset/en_US/base.js', 'https://www.youtube.com/s/player/b22ef6e7/player_ias.vflset/en_US/base.js',
'b6HcntHGkvBLk_FRf', 'kNPW6A7FyP2l8A', 'b6HcntHGkvBLk_FRf', 'kNPW6A7FyP2l8A',
), ),
(
'https://www.youtube.com/s/player/3400486c/player_ias.vflset/en_US/base.js',
'lL46g3XifCKUZn1Xfw', 'z767lhet6V2Skl',
),
] ]

View file

@ -452,7 +452,8 @@ class YoutubeDL:
Can also just be a single color policy, Can also just be a single color policy,
in which case it applies to all outputs. in which case it applies to all outputs.
Valid stream names are 'stdout' and 'stderr'. Valid stream names are 'stdout' and 'stderr'.
Valid color policies are one of 'always', 'auto', 'no_color' or 'never'. Valid color policies are one of 'always', 'auto',
'no_color', 'never', 'auto-tty' or 'no_color-tty'.
geo_bypass: Bypass geographic restriction via faking X-Forwarded-For geo_bypass: Bypass geographic restriction via faking X-Forwarded-For
HTTP header HTTP header
geo_bypass_country: geo_bypass_country:
@ -659,12 +660,15 @@ def __init__(self, params=None, auto_init=True):
self.params['color'] = 'no_color' self.params['color'] = 'no_color'
term_allow_color = os.getenv('TERM', '').lower() != 'dumb' term_allow_color = os.getenv('TERM', '').lower() != 'dumb'
no_color = bool(os.getenv('NO_COLOR')) base_no_color = bool(os.getenv('NO_COLOR'))
def process_color_policy(stream): def process_color_policy(stream):
stream_name = {sys.stdout: 'stdout', sys.stderr: 'stderr'}[stream] stream_name = {sys.stdout: 'stdout', sys.stderr: 'stderr'}[stream]
policy = traverse_obj(self.params, ('color', (stream_name, None), {str}), get_all=False) policy = traverse_obj(self.params, ('color', (stream_name, None), {str}, any)) or 'auto'
if policy in ('auto', None): if policy in ('auto', 'auto-tty', 'no_color-tty'):
no_color = base_no_color
if policy.endswith('tty'):
no_color = policy.startswith('no_color')
if term_allow_color and supports_terminal_sequences(stream): if term_allow_color and supports_terminal_sequences(stream):
return 'no_color' if no_color else True return 'no_color' if no_color else True
return False return False
@ -3168,11 +3172,12 @@ def dl(self, name, info, subtitle=False, test=False):
if test: if test:
verbose = self.params.get('verbose') verbose = self.params.get('verbose')
quiet = self.params.get('quiet') or not verbose
params = { params = {
'test': True, 'test': True,
'quiet': self.params.get('quiet') or not verbose, 'quiet': quiet,
'verbose': verbose, 'verbose': verbose,
'noprogress': not verbose, 'noprogress': quiet,
'nopart': True, 'nopart': True,
'skip_unavailable_fragments': False, 'skip_unavailable_fragments': False,
'keep_fragments': False, 'keep_fragments': False,

View file

@ -468,7 +468,7 @@ def metadataparser_actions(f):
default_downloader = ed.get_basename() default_downloader = ed.get_basename()
for policy in opts.color.values(): for policy in opts.color.values():
if policy not in ('always', 'auto', 'no_color', 'never'): if policy not in ('always', 'auto', 'auto-tty', 'no_color', 'no_color-tty', 'never'):
raise ValueError(f'"{policy}" is not a valid color policy') raise ValueError(f'"{policy}" is not a valid color policy')
warnings, deprecation_warnings = [], [] warnings, deprecation_warnings = [], []

View file

@ -504,7 +504,6 @@
from .digitalconcerthall import DigitalConcertHallIE from .digitalconcerthall import DigitalConcertHallIE
from .digiteka import DigitekaIE from .digiteka import DigitekaIE
from .discogs import DiscogsReleasePlaylistIE from .discogs import DiscogsReleasePlaylistIE
from .discovery import DiscoveryIE
from .disney import DisneyIE from .disney import DisneyIE
from .dispeak import DigitallySpeakingIE from .dispeak import DigitallySpeakingIE
from .dlf import ( from .dlf import (
@ -532,16 +531,12 @@
DiscoveryPlusIndiaShowIE, DiscoveryPlusIndiaShowIE,
DiscoveryPlusItalyIE, DiscoveryPlusItalyIE,
DiscoveryPlusItalyShowIE, DiscoveryPlusItalyShowIE,
DIYNetworkIE,
DPlayIE, DPlayIE,
FoodNetworkIE, FoodNetworkIE,
GlobalCyclingNetworkPlusIE,
GoDiscoveryIE, GoDiscoveryIE,
HGTVDeIE, HGTVDeIE,
HGTVUsaIE, HGTVUsaIE,
InvestigationDiscoveryIE, InvestigationDiscoveryIE,
MotorTrendIE,
MotorTrendOnDemandIE,
ScienceChannelIE, ScienceChannelIE,
TravelChannelIE, TravelChannelIE,
) )

View file

@ -9,12 +9,12 @@
import struct import struct
import time import time
import urllib.parse import urllib.parse
import urllib.request
import urllib.response
import uuid import uuid
from .common import InfoExtractor from .common import InfoExtractor
from ..aes import aes_ecb_decrypt from ..aes import aes_ecb_decrypt
from ..networking import RequestHandler, Response
from ..networking.exceptions import TransportError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
OnDemandPagedList, OnDemandPagedList,
@ -26,37 +26,36 @@
traverse_obj, traverse_obj,
update_url_query, update_url_query,
) )
from ..utils.networking import clean_proxies
def add_opener(ydl, handler): # FIXME: Create proper API in .networking class AbemaLicenseRH(RequestHandler):
"""Add a handler for opening URLs, like _download_webpage""" _SUPPORTED_URL_SCHEMES = ('abematv-license',)
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426 _SUPPORTED_PROXY_SCHEMES = None
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605 _SUPPORTED_FEATURES = None
rh = ydl._request_director.handlers['Urllib'] RH_NAME = 'abematv_license'
if 'abematv-license' in rh._SUPPORTED_URL_SCHEMES:
return
headers = ydl.params['http_headers'].copy()
proxies = ydl.proxies.copy()
clean_proxies(proxies, headers)
opener = rh._get_instance(cookiejar=ydl.cookiejar, proxies=proxies)
assert isinstance(opener, urllib.request.OpenerDirector)
opener.add_handler(handler)
rh._SUPPORTED_URL_SCHEMES = (*rh._SUPPORTED_URL_SCHEMES, 'abematv-license')
_STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
_HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
class AbemaLicenseHandler(urllib.request.BaseHandler): def __init__(self, *, ie: 'AbemaTVIE', **kwargs):
handler_order = 499 super().__init__(**kwargs)
STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
def __init__(self, ie: 'AbemaTVIE'):
# the protocol that this should really handle is 'abematv-license://'
# abematv_license_open is just a placeholder for development purposes
# ref. https://github.com/python/cpython/blob/f4c03484da59049eb62a9bf7777b963e2267d187/Lib/urllib/request.py#L510
setattr(self, 'abematv-license_open', getattr(self, 'abematv_license_open', None))
self.ie = ie self.ie = ie
def _send(self, request):
url = request.url
ticket = urllib.parse.urlparse(url).netloc
try:
response_data = self._get_videokey_from_ticket(ticket)
except ExtractorError as e:
raise TransportError(cause=e.cause) from e
except (IndexError, KeyError, TypeError) as e:
raise TransportError(cause=repr(e)) from e
return Response(
io.BytesIO(response_data), url,
headers={'Content-Length': str(len(response_data))})
def _get_videokey_from_ticket(self, ticket): def _get_videokey_from_ticket(self, ticket):
to_show = self.ie.get_param('verbose', False) to_show = self.ie.get_param('verbose', False)
media_token = self.ie._get_media_token(to_show=to_show) media_token = self.ie._get_media_token(to_show=to_show)
@ -72,25 +71,17 @@ def _get_videokey_from_ticket(self, ticket):
'Content-Type': 'application/json', 'Content-Type': 'application/json',
}) })
res = decode_base_n(license_response['k'], table=self.STRTABLE) res = decode_base_n(license_response['k'], table=self._STRTABLE)
encvideokey = bytes_to_intlist(struct.pack('>QQ', res >> 64, res & 0xffffffffffffffff)) encvideokey = bytes_to_intlist(struct.pack('>QQ', res >> 64, res & 0xffffffffffffffff))
h = hmac.new( h = hmac.new(
binascii.unhexlify(self.HKEY), binascii.unhexlify(self._HKEY),
(license_response['cid'] + self.ie._DEVICE_ID).encode(), (license_response['cid'] + self.ie._DEVICE_ID).encode(),
digestmod=hashlib.sha256) digestmod=hashlib.sha256)
enckey = bytes_to_intlist(h.digest()) enckey = bytes_to_intlist(h.digest())
return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey)) return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey))
def abematv_license_open(self, url):
url = url.get_full_url() if isinstance(url, urllib.request.Request) else url
ticket = urllib.parse.urlparse(url).netloc
response_data = self._get_videokey_from_ticket(ticket)
return urllib.response.addinfourl(io.BytesIO(response_data), headers={
'Content-Length': str(len(response_data)),
}, url=url, code=200)
class AbemaTVBaseIE(InfoExtractor): class AbemaTVBaseIE(InfoExtractor):
_NETRC_MACHINE = 'abematv' _NETRC_MACHINE = 'abematv'
@ -139,7 +130,7 @@ def _get_device_token(self):
if self._USERTOKEN: if self._USERTOKEN:
return self._USERTOKEN return self._USERTOKEN
add_opener(self._downloader, AbemaLicenseHandler(self)) self._downloader._request_director.add_handler(AbemaLicenseRH(ie=self, logger=None))
username, _ = self._get_login_info() username, _ = self._get_login_info()
auth_cache = username and self.cache.load(self._NETRC_MACHINE, username, min_ver='2024.01.19') auth_cache = username and self.cache.load(self._NETRC_MACHINE, username, min_ver='2024.01.19')

View file

@ -16,6 +16,7 @@
float_or_none, float_or_none,
int_or_none, int_or_none,
intlist_to_bytes, intlist_to_bytes,
join_nonempty,
long_to_bytes, long_to_bytes,
parse_iso8601, parse_iso8601,
pkcs1pad, pkcs1pad,
@ -48,9 +49,9 @@ class ADNBaseIE(InfoExtractor):
class ADNIE(ADNBaseIE): class ADNIE(ADNBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/[^/?#]+/(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.com/(?:(?P<lang>de)/)?video/[^/?#]+/(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir', 'url': 'https://animationdigitalnetwork.com/video/fruits-basket/9841-episode-1-a-ce-soir',
'md5': '1c9ef066ceb302c86f80c2b371615261', 'md5': '1c9ef066ceb302c86f80c2b371615261',
'info_dict': { 'info_dict': {
'id': '9841', 'id': '9841',
@ -70,10 +71,10 @@ class ADNIE(ADNBaseIE):
}, },
'skip': 'Only available in French and German speaking Europe', 'skip': 'Only available in French and German speaking Europe',
}, { }, {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites', 'url': 'http://animedigitalnetwork.com/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://animationdigitalnetwork.de/video/the-eminence-in-shadow/23550-folge-1', 'url': 'https://animationdigitalnetwork.com/de/video/the-eminence-in-shadow/23550-folge-1',
'md5': '5c5651bf5791fa6fcd7906012b9d94e8', 'md5': '5c5651bf5791fa6fcd7906012b9d94e8',
'info_dict': { 'info_dict': {
'id': '23550', 'id': '23550',
@ -217,7 +218,7 @@ def _real_extract(self, url):
links_data = self._download_json( links_data = self._download_json(
links_url, video_id, 'Downloading links JSON metadata', headers={ links_url, video_id, 'Downloading links JSON metadata', headers={
'X-Player-Token': authorization, 'X-Player-Token': authorization,
'X-Target-Distribution': lang, 'X-Target-Distribution': lang or 'fr',
**self._HEADERS, **self._HEADERS,
}, query={ }, query={
'freeWithAds': 'true', 'freeWithAds': 'true',
@ -298,9 +299,9 @@ def _real_extract(self, url):
class ADNSeasonIE(ADNBaseIE): class ADNSeasonIE(ADNBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/(?P<id>[^/?#]+)/?(?:$|[#?])' _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.com/(?:(?P<lang>de)/)?video/(?P<id>[^/?#]+)/?(?:$|[#?])'
_TESTS = [{ _TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/tokyo-mew-mew-new', 'url': 'https://animationdigitalnetwork.com/video/tokyo-mew-mew-new',
'playlist_count': 12, 'playlist_count': 12,
'info_dict': { 'info_dict': {
'id': '911', 'id': '911',
@ -318,7 +319,7 @@ def _real_extract(self, url):
episodes = self._download_json( episodes = self._download_json(
f'{self._API_BASE_URL}video/show/{show_id}', video_show_slug, f'{self._API_BASE_URL}video/show/{show_id}', video_show_slug,
'Downloading episode list', headers={ 'Downloading episode list', headers={
'X-Target-Distribution': lang, 'X-Target-Distribution': lang or 'fr',
**self._HEADERS, **self._HEADERS,
}, query={ }, query={
'order': 'asc', 'order': 'asc',
@ -327,8 +328,8 @@ def _real_extract(self, url):
def entries(): def entries():
for episode_id in traverse_obj(episodes, ('videos', ..., 'id', {str_or_none})): for episode_id in traverse_obj(episodes, ('videos', ..., 'id', {str_or_none})):
yield self.url_result( yield self.url_result(join_nonempty(
f'https://animationdigitalnetwork.{lang}/video/{video_show_slug}/{episode_id}', 'https://animationdigitalnetwork.com', lang, 'video',
ADNIE, episode_id) video_show_slug, episode_id, delim='/'), ADNIE, episode_id)
return self.playlist_result(entries(), show_id, show.get('title')) return self.playlist_result(entries(), show_id, show.get('title'))

View file

@ -1,6 +1,8 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
parse_codecs,
try_get, try_get,
url_or_none, url_or_none,
urlencode_postdata, urlencode_postdata,
@ -12,6 +14,7 @@ class DigitalConcertHallIE(InfoExtractor):
IE_DESC = 'DigitalConcertHall extractor' IE_DESC = 'DigitalConcertHall extractor'
_VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert|work)/(?P<id>[0-9]+)-?(?P<part>[0-9]+)?' _VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert|work)/(?P<id>[0-9]+)-?(?P<part>[0-9]+)?'
_OAUTH_URL = 'https://api.digitalconcerthall.com/v2/oauth2/token' _OAUTH_URL = 'https://api.digitalconcerthall.com/v2/oauth2/token'
_USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.5 Safari/605.1.15'
_ACCESS_TOKEN = None _ACCESS_TOKEN = None
_NETRC_MACHINE = 'digitalconcerthall' _NETRC_MACHINE = 'digitalconcerthall'
_TESTS = [{ _TESTS = [{
@ -68,33 +71,42 @@ class DigitalConcertHallIE(InfoExtractor):
}] }]
def _perform_login(self, username, password): def _perform_login(self, username, password):
token_response = self._download_json( login_token = self._download_json(
self._OAUTH_URL, self._OAUTH_URL,
None, 'Obtaining token', errnote='Unable to obtain token', data=urlencode_postdata({ None, 'Obtaining token', errnote='Unable to obtain token', data=urlencode_postdata({
'affiliate': 'none', 'affiliate': 'none',
'grant_type': 'device', 'grant_type': 'device',
'device_vendor': 'unknown', 'device_vendor': 'unknown',
# device_model 'Safari' gets split streams of 4K/HEVC video and lossless/FLAC audio
'device_model': 'unknown' if self._configuration_arg('prefer_combined_hls') else 'Safari',
'app_id': 'dch.webapp', 'app_id': 'dch.webapp',
'app_version': '1.0.0', 'app_distributor': 'berlinphil',
'app_version': '1.84.0',
'client_secret': '2ySLN+2Fwb', 'client_secret': '2ySLN+2Fwb',
}), headers={ }), headers={
'Content-Type': 'application/x-www-form-urlencoded', 'Accept': 'application/json',
}) 'Content-Type': 'application/x-www-form-urlencoded;charset=UTF-8',
self._ACCESS_TOKEN = token_response['access_token'] 'User-Agent': self._USER_AGENT,
})['access_token']
try: try:
self._download_json( login_response = self._download_json(
self._OAUTH_URL, self._OAUTH_URL,
None, note='Logging in', errnote='Unable to login', data=urlencode_postdata({ None, note='Logging in', errnote='Unable to login', data=urlencode_postdata({
'grant_type': 'password', 'grant_type': 'password',
'username': username, 'username': username,
'password': password, 'password': password,
}), headers={ }), headers={
'Content-Type': 'application/x-www-form-urlencoded', 'Accept': 'application/json',
'Content-Type': 'application/x-www-form-urlencoded;charset=UTF-8',
'Referer': 'https://www.digitalconcerthall.com', 'Referer': 'https://www.digitalconcerthall.com',
'Authorization': f'Bearer {self._ACCESS_TOKEN}', 'Authorization': f'Bearer {login_token}',
'User-Agent': self._USER_AGENT,
}) })
except ExtractorError: except ExtractorError as error:
self.raise_login_required(msg='Login info incorrect') if isinstance(error.cause, HTTPError) and error.cause.status == 401:
raise ExtractorError('Invalid username or password', expected=True)
raise
self._ACCESS_TOKEN = login_response['access_token']
def _real_initialize(self): def _real_initialize(self):
if not self._ACCESS_TOKEN: if not self._ACCESS_TOKEN:
@ -108,11 +120,15 @@ def _entries(self, items, language, type_, **kwargs):
'Accept': 'application/json', 'Accept': 'application/json',
'Authorization': f'Bearer {self._ACCESS_TOKEN}', 'Authorization': f'Bearer {self._ACCESS_TOKEN}',
'Accept-Language': language, 'Accept-Language': language,
'User-Agent': self._USER_AGENT,
}) })
formats = [] formats = []
for m3u8_url in traverse_obj(stream_info, ('channel', ..., 'stream', ..., 'url', {url_or_none})): for m3u8_url in traverse_obj(stream_info, ('channel', ..., 'stream', ..., 'url', {url_or_none})):
formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', fatal=False)) formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
for fmt in formats:
if fmt.get('format_note') and fmt.get('vcodec') == 'none':
fmt.update(parse_codecs(fmt['format_note']))
yield { yield {
'id': video_id, 'id': video_id,
@ -140,13 +156,15 @@ def _real_extract(self, url):
f'https://api.digitalconcerthall.com/v2/{api_type}/{video_id}', video_id, headers={ f'https://api.digitalconcerthall.com/v2/{api_type}/{video_id}', video_id, headers={
'Accept': 'application/json', 'Accept': 'application/json',
'Accept-Language': language, 'Accept-Language': language,
'User-Agent': self._USER_AGENT,
'Authorization': f'Bearer {self._ACCESS_TOKEN}',
}) })
album_artists = traverse_obj(vid_info, ('_links', 'artist', ..., 'name'))
videos = [vid_info] if type_ == 'film' else traverse_obj(vid_info, ('_embedded', ..., ...)) videos = [vid_info] if type_ == 'film' else traverse_obj(vid_info, ('_embedded', ..., ...))
if type_ == 'work': if type_ == 'work':
videos = [videos[int(part) - 1]] videos = [videos[int(part) - 1]]
album_artists = traverse_obj(vid_info, ('_links', 'artist', ..., 'name', {str}))
thumbnail = traverse_obj(vid_info, ( thumbnail = traverse_obj(vid_info, (
'image', ..., {self._proto_relative_url}, {url_or_none}, 'image', ..., {self._proto_relative_url}, {url_or_none},
{lambda x: x.format(width=0, height=0)}, any)) # NB: 0x0 is the original size {lambda x: x.format(width=0, height=0)}, any)) # NB: 0x0 is the original size

View file

@ -1,115 +0,0 @@
import random
import string
import urllib.parse
from .discoverygo import DiscoveryGoBaseIE
from ..networking.exceptions import HTTPError
from ..utils import ExtractorError
class DiscoveryIE(DiscoveryGoBaseIE):
_VALID_URL = r'''(?x)https?://
(?P<site>
go\.discovery|
www\.
(?:
investigationdiscovery|
discoverylife|
animalplanet|
ahctv|
destinationamerica|
sciencechannel|
tlc
)|
watch\.
(?:
hgtv|
foodnetwork|
travelchannel|
diynetwork|
cookingchanneltv|
motortrend
)
)\.com/tv-shows/(?P<show_slug>[^/]+)/(?:video|full-episode)s/(?P<id>[^./?#]+)'''
_TESTS = [{
'url': 'https://go.discovery.com/tv-shows/cash-cab/videos/riding-with-matthew-perry',
'info_dict': {
'id': '5a2f35ce6b66d17a5026e29e',
'ext': 'mp4',
'title': 'Riding with Matthew Perry',
'description': 'md5:a34333153e79bc4526019a5129e7f878',
'duration': 84,
},
'params': {
'skip_download': True, # requires ffmpeg
},
}, {
'url': 'https://www.investigationdiscovery.com/tv-shows/final-vision/full-episodes/final-vision',
'only_matching': True,
}, {
'url': 'https://go.discovery.com/tv-shows/alaskan-bush-people/videos/follow-your-own-road',
'only_matching': True,
}, {
# using `show_slug` is important to get the correct video data
'url': 'https://www.sciencechannel.com/tv-shows/mythbusters-on-science/full-episodes/christmas-special',
'only_matching': True,
}]
_GEO_COUNTRIES = ['US']
_GEO_BYPASS = False
_API_BASE_URL = 'https://api.discovery.com/v1/'
def _real_extract(self, url):
site, show_slug, display_id = self._match_valid_url(url).groups()
access_token = None
cookies = self._get_cookies(url)
# prefer Affiliate Auth Token over Anonymous Auth Token
auth_storage_cookie = cookies.get('eosAf') or cookies.get('eosAn')
if auth_storage_cookie and auth_storage_cookie.value:
auth_storage = self._parse_json(urllib.parse.unquote(
urllib.parse.unquote(auth_storage_cookie.value)),
display_id, fatal=False) or {}
access_token = auth_storage.get('a') or auth_storage.get('access_token')
if not access_token:
access_token = self._download_json(
f'https://{site}.com/anonymous', display_id,
'Downloading token JSON metadata', query={
'authRel': 'authorization',
'client_id': '3020a40c2356a645b4b4',
'nonce': ''.join(random.choices(string.ascii_letters, k=32)),
'redirectUri': 'https://www.discovery.com/',
})['access_token']
headers = self.geo_verification_headers()
headers['Authorization'] = 'Bearer ' + access_token
try:
video = self._download_json(
self._API_BASE_URL + 'content/videos',
display_id, 'Downloading content JSON metadata',
headers=headers, query={
'embed': 'show.name',
'fields': 'authenticated,description.detailed,duration,episodeNumber,id,name,parental.rating,season.number,show,tags',
'slug': display_id,
'show_slug': show_slug,
})[0]
video_id = video['id']
stream = self._download_json(
self._API_BASE_URL + 'streaming/video/' + video_id,
display_id, 'Downloading streaming JSON metadata', headers=headers)
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status in (401, 403):
e_description = self._parse_json(
e.cause.response.read().decode(), display_id)['description']
if 'resource not available for country' in e_description:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
if 'Authorized Networks' in e_description:
raise ExtractorError(
'This video is only available via cable service provider subscription that'
' is not currently supported. You may want to use --cookies.', expected=True)
raise ExtractorError(e_description)
raise
return self._extract_video_info(video, stream, display_id)

View file

@ -1,171 +0,0 @@
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
determine_ext,
extract_attributes,
int_or_none,
parse_age_limit,
remove_end,
unescapeHTML,
url_or_none,
)
class DiscoveryGoBaseIE(InfoExtractor):
_VALID_URL_TEMPLATE = r'''(?x)https?://(?:www\.)?(?:
discovery|
investigationdiscovery|
discoverylife|
animalplanet|
ahctv|
destinationamerica|
sciencechannel|
tlc|
velocitychannel
)go\.com/%s(?P<id>[^/?#&]+)'''
def _extract_video_info(self, video, stream, display_id):
title = video['name']
if not stream:
if video.get('authenticated') is True:
raise ExtractorError(
'This video is only available via cable service provider subscription that'
' is not currently supported. You may want to use --cookies.', expected=True)
else:
raise ExtractorError('Unable to find stream')
STREAM_URL_SUFFIX = 'streamUrl'
formats = []
for stream_kind in ('', 'hds'):
suffix = STREAM_URL_SUFFIX.capitalize() if stream_kind else STREAM_URL_SUFFIX
stream_url = stream.get(f'{stream_kind}{suffix}')
if not stream_url:
continue
if stream_kind == '':
formats.extend(self._extract_m3u8_formats(
stream_url, display_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
elif stream_kind == 'hds':
formats.extend(self._extract_f4m_formats(
stream_url, display_id, f4m_id=stream_kind, fatal=False))
video_id = video.get('id') or display_id
description = video.get('description', {}).get('detailed')
duration = int_or_none(video.get('duration'))
series = video.get('show', {}).get('name')
season_number = int_or_none(video.get('season', {}).get('number'))
episode_number = int_or_none(video.get('episodeNumber'))
tags = video.get('tags')
age_limit = parse_age_limit(video.get('parental', {}).get('rating'))
subtitles = {}
captions = stream.get('captions')
if isinstance(captions, list):
for caption in captions:
subtitle_url = url_or_none(caption.get('fileUrl'))
if not subtitle_url or not subtitle_url.startswith('http'):
continue
lang = caption.get('fileLang', 'en')
ext = determine_ext(subtitle_url)
subtitles.setdefault(lang, []).append({
'url': subtitle_url,
'ext': 'ttml' if ext == 'xml' else ext,
})
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'duration': duration,
'series': series,
'season_number': season_number,
'episode_number': episode_number,
'tags': tags,
'age_limit': age_limit,
'formats': formats,
'subtitles': subtitles,
}
class DiscoveryGoIE(DiscoveryGoBaseIE):
_VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % r'(?:[^/]+/)+'
_GEO_COUNTRIES = ['US']
_TEST = {
'url': 'https://www.discoverygo.com/bering-sea-gold/reaper-madness/',
'info_dict': {
'id': '58c167d86b66d12f2addeb01',
'ext': 'mp4',
'title': 'Reaper Madness',
'description': 'md5:09f2c625c99afb8946ed4fb7865f6e78',
'duration': 2519,
'series': 'Bering Sea Gold',
'season_number': 8,
'episode_number': 6,
'age_limit': 14,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
container = extract_attributes(
self._search_regex(
r'(<div[^>]+class=["\']video-player-container[^>]+>)',
webpage, 'video container'))
video = self._parse_json(
container.get('data-video') or container.get('data-json'),
display_id)
stream = video.get('stream')
return self._extract_video_info(video, stream, display_id)
class DiscoveryGoPlaylistIE(DiscoveryGoBaseIE):
_VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % ''
_TEST = {
'url': 'https://www.discoverygo.com/bering-sea-gold/',
'info_dict': {
'id': 'bering-sea-gold',
'title': 'Bering Sea Gold',
'description': 'md5:cc5c6489835949043c0cc3ad66c2fa0e',
},
'playlist_mincount': 6,
}
@classmethod
def suitable(cls, url):
return False if DiscoveryGoIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
entries = []
for mobj in re.finditer(r'data-json=(["\'])(?P<json>{.+?})\1', webpage):
data = self._parse_json(
mobj.group('json'), display_id,
transform_source=unescapeHTML, fatal=False)
if not isinstance(data, dict) or data.get('type') != 'episode':
continue
episode_url = data.get('socialUrl')
if not episode_url:
continue
entries.append(self.url_result(
episode_url, ie=DiscoveryGoIE.ie_key(),
video_id=data.get('id')))
return self.playlist_result(
entries, display_id,
remove_end(self._og_search_title(
webpage, fatal=False), ' | Discovery GO'),
self._og_search_description(webpage))

View file

@ -346,8 +346,16 @@ def _real_extract(self, url):
class DiscoveryPlusBaseIE(DPlayBaseIE): class DiscoveryPlusBaseIE(DPlayBaseIE):
"""Subclasses must set _PRODUCT, _DISCO_API_PARAMS"""
_DISCO_CLIENT_VER = '27.43.0'
def _update_disco_api_headers(self, headers, disco_base, display_id, realm): def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
headers['x-disco-client'] = f'WEB:UNKNOWN:{self._PRODUCT}:25.2.6' headers.update({
'x-disco-params': f'realm={realm},siteLookupKey={self._PRODUCT}',
'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:{self._DISCO_CLIENT_VER}',
'Authorization': self._get_auth(disco_base, display_id, realm),
})
def _download_video_playback_info(self, disco_base, video_id, headers): def _download_video_playback_info(self, disco_base, video_id, headers):
return self._download_json( return self._download_json(
@ -368,6 +376,26 @@ def _real_extract(self, url):
class GoDiscoveryIE(DiscoveryPlusBaseIE): class GoDiscoveryIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:go\.)?discovery\.com/video' + DPlayBaseIE._PATH_REGEX _VALID_URL = r'https?://(?:go\.)?discovery\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{ _TESTS = [{
'url': 'https://go.discovery.com/video/in-the-eye-of-the-storm-discovery-atve-us/trapped-in-a-twister',
'info_dict': {
'id': '5352642',
'display_id': 'in-the-eye-of-the-storm-discovery-atve-us/trapped-in-a-twister',
'ext': 'mp4',
'title': 'Trapped in a Twister',
'description': 'Twisters destroy Midwest towns, trapping spotters in the eye of the storm.',
'episode_number': 1,
'episode': 'Episode 1',
'season_number': 1,
'season': 'Season 1',
'series': 'In The Eye Of The Storm',
'duration': 2490.237,
'upload_date': '20240715',
'timestamp': 1721008800,
'tags': [],
'creators': ['Discovery'],
'thumbnail': 'https://us1-prod-images.disco-api.com/2024/07/10/5e39637d-cabf-3ab3-8e9a-f4e9d37bc036.jpeg',
},
}, {
'url': 'https://go.discovery.com/video/dirty-jobs-discovery-atve-us/rodbuster-galvanizer', 'url': 'https://go.discovery.com/video/dirty-jobs-discovery-atve-us/rodbuster-galvanizer',
'info_dict': { 'info_dict': {
'id': '4164906', 'id': '4164906',
@ -395,6 +423,26 @@ class GoDiscoveryIE(DiscoveryPlusBaseIE):
class TravelChannelIE(DiscoveryPlusBaseIE): class TravelChannelIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?travelchannel\.com/video' + DPlayBaseIE._PATH_REGEX _VALID_URL = r'https?://(?:watch\.)?travelchannel\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{ _TESTS = [{
'url': 'https://watch.travelchannel.com/video/the-dead-files-travel-channel/protect-the-children',
'info_dict': {
'id': '4710177',
'display_id': 'the-dead-files-travel-channel/protect-the-children',
'ext': 'mp4',
'title': 'Protect the Children',
'description': 'An evil presence threatens an Ohio woman\'s children and marriage.',
'season_number': 14,
'season': 'Season 14',
'episode_number': 10,
'episode': 'Episode 10',
'series': 'The Dead Files',
'duration': 2550.481,
'timestamp': 1664510400,
'upload_date': '20220930',
'tags': [],
'creators': ['Travel Channel'],
'thumbnail': 'https://us1-prod-images.disco-api.com/2022/03/17/5e45eace-de5d-343a-9293-f400a2aa77d5.jpeg',
},
}, {
'url': 'https://watch.travelchannel.com/video/ghost-adventures-travel-channel/ghost-train-of-ely', 'url': 'https://watch.travelchannel.com/video/ghost-adventures-travel-channel/ghost-train-of-ely',
'info_dict': { 'info_dict': {
'id': '2220256', 'id': '2220256',
@ -422,6 +470,26 @@ class TravelChannelIE(DiscoveryPlusBaseIE):
class CookingChannelIE(DiscoveryPlusBaseIE): class CookingChannelIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?cookingchanneltv\.com/video' + DPlayBaseIE._PATH_REGEX _VALID_URL = r'https?://(?:watch\.)?cookingchanneltv\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{ _TESTS = [{
'url': 'https://watch.cookingchanneltv.com/video/bobbys-triple-threat-food-network-atve-us/titans-vs-marcus-samuelsson',
'info_dict': {
'id': '5350005',
'ext': 'mp4',
'display_id': 'bobbys-triple-threat-food-network-atve-us/titans-vs-marcus-samuelsson',
'title': 'Titans vs Marcus Samuelsson',
'description': 'Marcus Samuelsson throws his legendary global tricks at the Titans.',
'episode_number': 1,
'episode': 'Episode 1',
'season_number': 3,
'season': 'Season 3',
'series': 'Bobby\'s Triple Threat',
'duration': 2520.851,
'upload_date': '20240710',
'timestamp': 1720573200,
'tags': [],
'creators': ['Food Network'],
'thumbnail': 'https://us1-prod-images.disco-api.com/2024/07/04/529cd095-27ec-35c5-84e9-90ebd3e5d2da.jpeg',
},
}, {
'url': 'https://watch.cookingchanneltv.com/video/carnival-eats-cooking-channel/the-postman-always-brings-rice-2348634', 'url': 'https://watch.cookingchanneltv.com/video/carnival-eats-cooking-channel/the-postman-always-brings-rice-2348634',
'info_dict': { 'info_dict': {
'id': '2348634', 'id': '2348634',
@ -449,6 +517,22 @@ class CookingChannelIE(DiscoveryPlusBaseIE):
class HGTVUsaIE(DiscoveryPlusBaseIE): class HGTVUsaIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?hgtv\.com/video' + DPlayBaseIE._PATH_REGEX _VALID_URL = r'https?://(?:watch\.)?hgtv\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{ _TESTS = [{
'url': 'https://watch.hgtv.com/video/flip-or-flop-the-final-flip-hgtv-atve-us/flip-or-flop-the-final-flip',
'info_dict': {
'id': '5025585',
'display_id': 'flip-or-flop-the-final-flip-hgtv-atve-us/flip-or-flop-the-final-flip',
'ext': 'mp4',
'title': 'Flip or Flop: The Final Flip',
'description': 'Tarek and Christina are going their separate ways after one last flip!',
'series': 'Flip or Flop: The Final Flip',
'duration': 2580.644,
'upload_date': '20231101',
'timestamp': 1698811200,
'tags': [],
'creators': ['HGTV'],
'thumbnail': 'https://us1-prod-images.disco-api.com/2022/11/27/455caa6c-1462-3f14-b63d-a026d7a5e6d3.jpeg',
},
}, {
'url': 'https://watch.hgtv.com/video/home-inspector-joe-hgtv-atve-us/this-mold-house', 'url': 'https://watch.hgtv.com/video/home-inspector-joe-hgtv-atve-us/this-mold-house',
'info_dict': { 'info_dict': {
'id': '4289736', 'id': '4289736',
@ -476,6 +560,26 @@ class HGTVUsaIE(DiscoveryPlusBaseIE):
class FoodNetworkIE(DiscoveryPlusBaseIE): class FoodNetworkIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?foodnetwork\.com/video' + DPlayBaseIE._PATH_REGEX _VALID_URL = r'https?://(?:watch\.)?foodnetwork\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{ _TESTS = [{
'url': 'https://watch.foodnetwork.com/video/guys-grocery-games-food-network/wild-in-the-aisles',
'info_dict': {
'id': '2152549',
'display_id': 'guys-grocery-games-food-network/wild-in-the-aisles',
'ext': 'mp4',
'title': 'Wild in the Aisles',
'description': 'The chefs make spaghetti and meatballs with "Out of Stock" ingredients.',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'Episode 1',
'series': 'Guy\'s Grocery Games',
'tags': [],
'creators': ['Food Network'],
'duration': 2520.651,
'upload_date': '20230623',
'timestamp': 1687492800,
'thumbnail': 'https://us1-prod-images.disco-api.com/2022/06/15/37fb5333-cad2-3dbb-af7c-c20ec77c89c6.jpeg',
},
}, {
'url': 'https://watch.foodnetwork.com/video/kids-baking-championship-food-network/float-like-a-butterfly', 'url': 'https://watch.foodnetwork.com/video/kids-baking-championship-food-network/float-like-a-butterfly',
'info_dict': { 'info_dict': {
'id': '4116449', 'id': '4116449',
@ -503,6 +607,26 @@ class FoodNetworkIE(DiscoveryPlusBaseIE):
class DestinationAmericaIE(DiscoveryPlusBaseIE): class DestinationAmericaIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?destinationamerica\.com/video' + DPlayBaseIE._PATH_REGEX _VALID_URL = r'https?://(?:www\.)?destinationamerica\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{ _TESTS = [{
'url': 'https://www.destinationamerica.com/video/bbq-pit-wars-destination-america/smoke-on-the-water',
'info_dict': {
'id': '2218409',
'display_id': 'bbq-pit-wars-destination-america/smoke-on-the-water',
'ext': 'mp4',
'title': 'Smoke on the Water',
'description': 'The pitmasters head to Georgia for the Smoke on the Water BBQ Festival.',
'season_number': 2,
'season': 'Season 2',
'episode_number': 1,
'episode': 'Episode 1',
'series': 'BBQ Pit Wars',
'tags': [],
'creators': ['Destination America'],
'duration': 2614.878,
'upload_date': '20230623',
'timestamp': 1687492800,
'thumbnail': 'https://us1-prod-images.disco-api.com/2020/05/11/c0f8e85d-9a10-3e6f-8e43-f6faafa81ba2.jpeg',
},
}, {
'url': 'https://www.destinationamerica.com/video/alaska-monsters-destination-america-atve-us/central-alaskas-bigfoot', 'url': 'https://www.destinationamerica.com/video/alaska-monsters-destination-america-atve-us/central-alaskas-bigfoot',
'info_dict': { 'info_dict': {
'id': '4210904', 'id': '4210904',
@ -530,6 +654,26 @@ class DestinationAmericaIE(DiscoveryPlusBaseIE):
class InvestigationDiscoveryIE(DiscoveryPlusBaseIE): class InvestigationDiscoveryIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?investigationdiscovery\.com/video' + DPlayBaseIE._PATH_REGEX _VALID_URL = r'https?://(?:www\.)?investigationdiscovery\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{ _TESTS = [{
'url': 'https://www.investigationdiscovery.com/video/deadly-influence-the-social-media-murders-investigation-discovery-atve-us/rip-bianca',
'info_dict': {
'id': '5341132',
'display_id': 'deadly-influence-the-social-media-murders-investigation-discovery-atve-us/rip-bianca',
'ext': 'mp4',
'title': 'RIP Bianca',
'description': 'A teenage influencer discovers an online world of threat, harm and danger.',
'season_number': 1,
'season': 'Season 1',
'episode_number': 3,
'episode': 'Episode 3',
'series': 'Deadly Influence: The Social Media Murders',
'creators': ['Investigation Discovery'],
'tags': [],
'duration': 2490.888,
'upload_date': '20240618',
'timestamp': 1718672400,
'thumbnail': 'https://us1-prod-images.disco-api.com/2024/06/15/b567c774-9e44-3c6c-b0ba-db860a73e812.jpeg',
},
}, {
'url': 'https://www.investigationdiscovery.com/video/unmasked-investigation-discovery/the-killer-clown', 'url': 'https://www.investigationdiscovery.com/video/unmasked-investigation-discovery/the-killer-clown',
'info_dict': { 'info_dict': {
'id': '2139409', 'id': '2139409',
@ -557,6 +701,26 @@ class InvestigationDiscoveryIE(DiscoveryPlusBaseIE):
class AmHistoryChannelIE(DiscoveryPlusBaseIE): class AmHistoryChannelIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?ahctv\.com/video' + DPlayBaseIE._PATH_REGEX _VALID_URL = r'https?://(?:www\.)?ahctv\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{ _TESTS = [{
'url': 'https://www.ahctv.com/video/blood-and-fury-americas-civil-war-ahc/battle-of-bull-run',
'info_dict': {
'id': '2139199',
'display_id': 'blood-and-fury-americas-civil-war-ahc/battle-of-bull-run',
'ext': 'mp4',
'title': 'Battle of Bull Run',
'description': 'Two untested armies clash in the first real battle of the Civil War.',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'Episode 1',
'series': 'Blood and Fury: America\'s Civil War',
'duration': 2612.509,
'upload_date': '20220923',
'timestamp': 1663905600,
'creators': ['AHC'],
'tags': [],
'thumbnail': 'https://us1-prod-images.disco-api.com/2020/05/11/4af61bd7-d705-3108-82c4-1a6e541e20fa.jpeg',
},
}, {
'url': 'https://www.ahctv.com/video/modern-sniper-ahc/army', 'url': 'https://www.ahctv.com/video/modern-sniper-ahc/army',
'info_dict': { 'info_dict': {
'id': '2309730', 'id': '2309730',
@ -584,6 +748,26 @@ class AmHistoryChannelIE(DiscoveryPlusBaseIE):
class ScienceChannelIE(DiscoveryPlusBaseIE): class ScienceChannelIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?sciencechannel\.com/video' + DPlayBaseIE._PATH_REGEX _VALID_URL = r'https?://(?:www\.)?sciencechannel\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{ _TESTS = [{
'url': 'https://www.sciencechannel.com/video/spaces-deepest-secrets-science-atve-us/mystery-of-the-dead-planets',
'info_dict': {
'id': '2347335',
'display_id': 'spaces-deepest-secrets-science-atve-us/mystery-of-the-dead-planets',
'ext': 'mp4',
'title': 'Mystery of the Dead Planets',
'description': 'Astronomers unmask the truly destructive nature of the cosmos.',
'season_number': 7,
'season': 'Season 7',
'episode_number': 1,
'episode': 'Episode 1',
'series': 'Space\'s Deepest Secrets',
'duration': 2524.989,
'upload_date': '20230128',
'timestamp': 1674882000,
'creators': ['Science'],
'tags': [],
'thumbnail': 'https://us1-prod-images.disco-api.com/2021/03/30/3796829d-aead-3f9a-bd8d-e49048b3cdca.jpeg',
},
}, {
'url': 'https://www.sciencechannel.com/video/strangest-things-science-atve-us/nazi-mystery-machine', 'url': 'https://www.sciencechannel.com/video/strangest-things-science-atve-us/nazi-mystery-machine',
'info_dict': { 'info_dict': {
'id': '2842849', 'id': '2842849',
@ -608,36 +792,29 @@ class ScienceChannelIE(DiscoveryPlusBaseIE):
} }
class DIYNetworkIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?diynetwork\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://watch.diynetwork.com/video/pool-kings-diy-network/bringing-beach-life-to-texas',
'info_dict': {
'id': '2309730',
'display_id': 'pool-kings-diy-network/bringing-beach-life-to-texas',
'ext': 'mp4',
'title': 'Bringing Beach Life to Texas',
'description': 'The Pool Kings give a family a day at the beach in their own backyard.',
'season_number': 10,
'episode_number': 2,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://watch.diynetwork.com/video/pool-kings-diy-network/bringing-beach-life-to-texas',
'only_matching': True,
}]
_PRODUCT = 'diy'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.watch.diynetwork.com',
'realm': 'go',
'country': 'us',
}
class DiscoveryLifeIE(DiscoveryPlusBaseIE): class DiscoveryLifeIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?discoverylife\.com/video' + DPlayBaseIE._PATH_REGEX _VALID_URL = r'https?://(?:www\.)?discoverylife\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{ _TESTS = [{
'url': 'https://www.discoverylife.com/video/er-files-discovery-life-atve-us/sweet-charity',
'info_dict': {
'id': '2347614',
'display_id': 'er-files-discovery-life-atve-us/sweet-charity',
'ext': 'mp4',
'title': 'Sweet Charity',
'description': 'The staff at Charity Hospital treat a serious foot infection.',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'Episode 1',
'series': 'ER Files',
'duration': 2364.261,
'upload_date': '20230721',
'timestamp': 1689912000,
'creators': ['Discovery Life'],
'tags': [],
'thumbnail': 'https://us1-prod-images.disco-api.com/2021/03/16/4b6f0124-360b-3546-b6a4-5552db886b86.jpeg',
},
}, {
'url': 'https://www.discoverylife.com/video/surviving-death-discovery-life-atve-us/bodily-trauma', 'url': 'https://www.discoverylife.com/video/surviving-death-discovery-life-atve-us/bodily-trauma',
'info_dict': { 'info_dict': {
'id': '2218238', 'id': '2218238',
@ -665,6 +842,26 @@ class DiscoveryLifeIE(DiscoveryPlusBaseIE):
class AnimalPlanetIE(DiscoveryPlusBaseIE): class AnimalPlanetIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?animalplanet\.com/video' + DPlayBaseIE._PATH_REGEX _VALID_URL = r'https?://(?:www\.)?animalplanet\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{ _TESTS = [{
'url': 'https://www.animalplanet.com/video/mysterious-creatures-with-forrest-galante-animal-planet-atve-us/the-demon-of-peru',
'info_dict': {
'id': '4650835',
'display_id': 'mysterious-creatures-with-forrest-galante-animal-planet-atve-us/the-demon-of-peru',
'ext': 'mp4',
'title': 'The Demon of Peru',
'description': 'In Peru, a farming village is being terrorized by a “man-like beast.”',
'season_number': 1,
'season': 'Season 1',
'episode_number': 4,
'episode': 'Episode 4',
'series': 'Mysterious Creatures with Forrest Galante',
'duration': 2490.488,
'upload_date': '20230111',
'timestamp': 1673413200,
'creators': ['Animal Planet'],
'tags': [],
'thumbnail': 'https://us1-prod-images.disco-api.com/2022/03/01/6dbaa833-9a2e-3fee-9381-c19eddf67c0c.jpeg',
},
}, {
'url': 'https://www.animalplanet.com/video/north-woods-law-animal-planet/squirrel-showdown', 'url': 'https://www.animalplanet.com/video/north-woods-law-animal-planet/squirrel-showdown',
'info_dict': { 'info_dict': {
'id': '3338923', 'id': '3338923',
@ -692,6 +889,26 @@ class AnimalPlanetIE(DiscoveryPlusBaseIE):
class TLCIE(DiscoveryPlusBaseIE): class TLCIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:go\.)?tlc\.com/video' + DPlayBaseIE._PATH_REGEX _VALID_URL = r'https?://(?:go\.)?tlc\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{ _TESTS = [{
'url': 'https://go.tlc.com/video/90-day-the-last-resort-tlc-atve-us/the-last-chance',
'info_dict': {
'id': '5186422',
'display_id': '90-day-the-last-resort-tlc-atve-us/the-last-chance',
'ext': 'mp4',
'title': 'The Last Chance',
'description': 'Infidelity shakes Kalani and Asuelu\'s world, and Angela threatens divorce.',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'Episode 1',
'series': '90 Day: The Last Resort',
'duration': 5123.91,
'upload_date': '20230815',
'timestamp': 1692061200,
'creators': ['TLC'],
'tags': [],
'thumbnail': 'https://us1-prod-images.disco-api.com/2023/08/08/0ee367e2-ac76-334d-bf23-dbf796696a24.jpeg',
},
}, {
'url': 'https://go.tlc.com/video/my-600-lb-life-tlc/melissas-story-part-1', 'url': 'https://go.tlc.com/video/my-600-lb-life-tlc/melissas-story-part-1',
'info_dict': { 'info_dict': {
'id': '2206540', 'id': '2206540',
@ -716,93 +933,8 @@ class TLCIE(DiscoveryPlusBaseIE):
} }
class MotorTrendIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?motortrend\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://watch.motortrend.com/video/car-issues-motortrend-atve-us/double-dakotas',
'info_dict': {
'id': '"4859182"',
'display_id': 'double-dakotas',
'ext': 'mp4',
'title': 'Double Dakotas',
'description': 'Tylers buy-one-get-one Dakota deal has the Wizard pulling double duty.',
'season_number': 2,
'episode_number': 3,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://watch.motortrend.com/video/car-issues-motortrend-atve-us/double-dakotas',
'only_matching': True,
}]
_PRODUCT = 'vel'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.watch.motortrend.com',
'realm': 'go',
'country': 'us',
}
class MotorTrendOnDemandIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?motortrend(?:ondemand\.com|\.com/plus)/detail' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.motortrendondemand.com/detail/wheelstanding-dump-truck-stubby-bobs-comeback/37699/784',
'info_dict': {
'id': '37699',
'display_id': 'wheelstanding-dump-truck-stubby-bobs-comeback/37699',
'ext': 'mp4',
'title': 'Wheelstanding Dump Truck! Stubby Bobs Comeback',
'description': 'md5:996915abe52a1c3dfc83aecea3cce8e7',
'season_number': 5,
'episode_number': 52,
'episode': 'Episode 52',
'season': 'Season 5',
'thumbnail': r're:^https?://.+\.jpe?g$',
'timestamp': 1388534401,
'duration': 1887.345,
'creator': 'Originals',
'series': 'Roadkill',
'upload_date': '20140101',
'tags': [],
},
}, {
'url': 'https://www.motortrend.com/plus/detail/roadworthy-rescues-teaser-trailer/4922860/',
'info_dict': {
'id': '4922860',
'ext': 'mp4',
'title': 'Roadworthy Rescues | Teaser Trailer',
'description': 'Derek Bieri helps Freiburger and Finnegan with their \'68 big-block Dart.',
'display_id': 'roadworthy-rescues-teaser-trailer/4922860',
'creator': 'Originals',
'series': 'Roadworthy Rescues',
'thumbnail': r're:^https?://.+\.jpe?g$',
'upload_date': '20220907',
'timestamp': 1662523200,
'duration': 1066.356,
'tags': [],
},
}, {
'url': 'https://www.motortrend.com/plus/detail/ugly-duckling/2450033/12439',
'only_matching': True,
}]
_PRODUCT = 'MTOD'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.motortrendondemand.com',
'realm': 'motortrend',
'country': 'us',
}
def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
headers.update({
'x-disco-params': f'realm={realm}',
'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:4.39.1-gi1',
'Authorization': self._get_auth(disco_base, display_id, realm),
})
class DiscoveryPlusIE(DiscoveryPlusBaseIE): class DiscoveryPlusIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:\w{2}/)?video' + DPlayBaseIE._PATH_REGEX _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:(?P<country>[a-z]{2})/)?video(?:/sport)?' + DPlayBaseIE._PATH_REGEX
_TESTS = [{ _TESTS = [{
'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family', 'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family',
'info_dict': { 'info_dict': {
@ -823,14 +955,42 @@ class DiscoveryPlusIE(DiscoveryPlusBaseIE):
}, { }, {
'url': 'https://discoveryplus.com/ca/video/bering-sea-gold-discovery-ca/goldslingers', 'url': 'https://discoveryplus.com/ca/video/bering-sea-gold-discovery-ca/goldslingers',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://www.discoveryplus.com/gb/video/sport/eurosport-1-british-eurosport-1-british-sport/6-hours-of-spa-review',
'only_matching': True,
}] }]
_PRODUCT = 'dplus_us' _PRODUCT = None
_DISCO_API_PARAMS = { _DISCO_API_PARAMS = None
def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
headers.update({
'x-disco-params': f'realm={realm},siteLookupKey={self._PRODUCT}',
'x-disco-client': f'WEB:UNKNOWN:dplus_us:{self._DISCO_CLIENT_VER}',
'Authorization': self._get_auth(disco_base, display_id, realm),
})
def _real_extract(self, url):
video_id, country = self._match_valid_url(url).group('id', 'country')
if not country:
country = 'us'
self._PRODUCT = f'dplus_{country}'
if country in ('br', 'ca', 'us'):
self._DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.discoveryplus.com', 'disco_host': 'us1-prod-direct.discoveryplus.com',
'realm': 'go', 'realm': 'go',
'country': 'us', 'country': country,
} }
else:
self._DISCO_API_PARAMS = {
'disco_host': 'eu1-prod-direct.discoveryplus.com',
'realm': 'dplay',
'country': country,
}
return self._get_disco_api_info(url, video_id, **self._DISCO_API_PARAMS)
class DiscoveryPlusIndiaIE(DiscoveryPlusBaseIE): class DiscoveryPlusIndiaIE(DiscoveryPlusBaseIE):
@ -993,7 +1153,7 @@ class DiscoveryPlusItalyIE(DiscoveryPlusBaseIE):
'only_matching': True, 'only_matching': True,
}] }]
_PRODUCT = 'dplus_us' _PRODUCT = 'dplus_it'
_DISCO_API_PARAMS = { _DISCO_API_PARAMS = {
'disco_host': 'eu1-prod-direct.discoveryplus.com', 'disco_host': 'eu1-prod-direct.discoveryplus.com',
'realm': 'dplay', 'realm': 'dplay',
@ -1002,8 +1162,8 @@ class DiscoveryPlusItalyIE(DiscoveryPlusBaseIE):
def _update_disco_api_headers(self, headers, disco_base, display_id, realm): def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
headers.update({ headers.update({
'x-disco-params': f'realm={realm}', 'x-disco-params': f'realm={realm},siteLookupKey={self._PRODUCT}',
'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:25.2.6', 'x-disco-client': f'WEB:UNKNOWN:dplus_us:{self._DISCO_CLIENT_VER}',
'Authorization': self._get_auth(disco_base, display_id, realm), 'Authorization': self._get_auth(disco_base, display_id, realm),
}) })
@ -1044,39 +1204,3 @@ class DiscoveryPlusIndiaShowIE(DiscoveryPlusShowBaseIE):
_SHOW_STR = 'show' _SHOW_STR = 'show'
_INDEX = 4 _INDEX = 4
_VIDEO_IE = DiscoveryPlusIndiaIE _VIDEO_IE = DiscoveryPlusIndiaIE
class GlobalCyclingNetworkPlusIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://plus\.globalcyclingnetwork\.com/watch/(?P<id>\d+)'
_TESTS = [{
'url': 'https://plus.globalcyclingnetwork.com/watch/1397691',
'info_dict': {
'id': '1397691',
'ext': 'mp4',
'title': 'The Athertons: Mountain Biking\'s Fastest Family',
'description': 'md5:75a81937fcd8b989eec6083a709cd837',
'thumbnail': 'https://us1-prod-images.disco-api.com/2021/03/04/eb9e3026-4849-3001-8281-9356466f0557.png',
'series': 'gcn',
'creator': 'Gcn',
'upload_date': '20210309',
'timestamp': 1615248000,
'duration': 2531.0,
'tags': [],
},
'skip': 'Subscription required',
'params': {'skip_download': 'm3u8'},
}]
_PRODUCT = 'web'
_DISCO_API_PARAMS = {
'disco_host': 'disco-api-prod.globalcyclingnetwork.com',
'realm': 'gcn',
'country': 'us',
}
def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
headers.update({
'x-disco-params': f'realm={realm}',
'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:27.3.2',
'Authorization': self._get_auth(disco_base, display_id, realm),
})

View file

@ -2,6 +2,7 @@
from ..utils import ( from ..utils import (
float_or_none, float_or_none,
int_or_none, int_or_none,
join_nonempty,
orderedSet, orderedSet,
parse_iso8601, parse_iso8601,
parse_qs, parse_qs,
@ -13,7 +14,7 @@
class EpidemicSoundIE(InfoExtractor): class EpidemicSoundIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?epidemicsound\.com/track/(?P<id>[0-9a-zA-Z]+)' _VALID_URL = r'https?://(?:www\.)?epidemicsound\.com/(?:(?P<sfx>sound-effects/tracks)|track)/(?P<id>[0-9a-zA-Z-]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://www.epidemicsound.com/track/yFfQVRpSPz/', 'url': 'https://www.epidemicsound.com/track/yFfQVRpSPz/',
'md5': 'd98ff2ddb49e8acab9716541cbc9dfac', 'md5': 'd98ff2ddb49e8acab9716541cbc9dfac',
@ -47,6 +48,20 @@ class EpidemicSoundIE(InfoExtractor):
'release_timestamp': 1700535606, 'release_timestamp': 1700535606,
'release_date': '20231121', 'release_date': '20231121',
}, },
}, {
'url': 'https://www.epidemicsound.com/sound-effects/tracks/2f02f54b-9faa-4daf-abac-1cfe9e9cef69/',
'md5': '35d7cf05bd8b614a84f0495a05de9388',
'info_dict': {
'id': '208931',
'ext': 'mp3',
'upload_date': '20240603',
'timestamp': 1717436529,
'categories': ['appliance'],
'display_id': '6b2NXLURPr',
'duration': 1.0,
'title': 'Oven, Grill, Door Open 01',
'thumbnail': 'https://cdn.epidemicsound.com/curation-assets/commercial-release-cover-images/default-sfx/3000x3000.jpg',
},
}] }]
@staticmethod @staticmethod
@ -77,8 +92,10 @@ def _epidemic_fmt_or_none(f):
return f return f
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id, is_sfx = self._match_valid_url(url).group('id', 'sfx')
json_data = self._download_json(f'https://www.epidemicsound.com/json/track/{video_id}', video_id) json_data = self._download_json(join_nonempty(
'https://www.epidemicsound.com/json/track',
is_sfx and 'kosmos-id', video_id, delim='/'), video_id)
thumbnails = traverse_obj(json_data, [('imageUrl', 'cover')]) thumbnails = traverse_obj(json_data, [('imageUrl', 'cover')])
thumb_base_url = traverse_obj(json_data, ('coverArt', 'baseUrl', {url_or_none})) thumb_base_url = traverse_obj(json_data, ('coverArt', 'baseUrl', {url_or_none}))

View file

@ -571,16 +571,21 @@ def process_formats(info):
# Formats larger than ~500MB will return error 403 unless chunk size is regulated # Formats larger than ~500MB will return error 403 unless chunk size is regulated
f.setdefault('downloader_options', {})['http_chunk_size'] = 250 << 20 f.setdefault('downloader_options', {})['http_chunk_size'] = 250 << 20
def extract_relay_data(_filter): def yield_all_relay_data(_filter):
return self._parse_json(self._search_regex( for relay_data in re.findall(rf'data-sjs>({{.*?{_filter}.*?}})</script>', webpage):
rf'data-sjs>({{.*?{_filter}.*?}})</script>', yield self._parse_json(relay_data, video_id, fatal=False) or {}
webpage, 'replay data', default='{}'), video_id, fatal=False) or {}
def extract_relay_prefetched_data(_filter): def extract_relay_data(_filter):
return traverse_obj(extract_relay_data(_filter), ( return next(filter(None, yield_all_relay_data(_filter)), {})
'require', (None, (..., ..., ..., '__bbox', 'require')),
def extract_relay_prefetched_data(_filter, target_keys=None):
path = 'data'
if target_keys is not None:
path = lambda k, v: k == 'data' and any(target in v for target in variadic(target_keys))
return traverse_obj(yield_all_relay_data(_filter), (
..., 'require', (None, (..., ..., ..., '__bbox', 'require')),
lambda _, v: any(key.startswith('RelayPrefetchedStreamCache') for key in v), lambda _, v: any(key.startswith('RelayPrefetchedStreamCache') for key in v),
..., ..., '__bbox', 'result', 'data', {dict}), get_all=False) or {} ..., ..., '__bbox', 'result', path, {dict}), get_all=False) or {}
if not video_data: if not video_data:
server_js_data = self._parse_json(self._search_regex([ server_js_data = self._parse_json(self._search_regex([
@ -591,7 +596,8 @@ def extract_relay_prefetched_data(_filter):
if not video_data: if not video_data:
data = extract_relay_prefetched_data( data = extract_relay_prefetched_data(
r'"(?:dash_manifest|playable_url(?:_quality_hd)?)') r'"(?:dash_manifest|playable_url(?:_quality_hd)?)',
target_keys=('video', 'event', 'nodes', 'node', 'mediaset'))
if data: if data:
entries = [] entries = []

View file

@ -43,6 +43,7 @@
xpath_text, xpath_text,
xpath_with_ns, xpath_with_ns,
) )
from ..utils._utils import _UnsafeExtensionError
class GenericIE(InfoExtractor): class GenericIE(InfoExtractor):
@ -2446,9 +2447,13 @@ def _real_extract(self, url):
if not is_html(first_bytes): if not is_html(first_bytes):
self.report_warning( self.report_warning(
'URL could be a direct video link, returning it as such.') 'URL could be a direct video link, returning it as such.')
ext = determine_ext(url)
if ext not in _UnsafeExtensionError.ALLOWED_EXTENSIONS:
ext = 'unknown_video'
info_dict.update({ info_dict.update({
'direct': True, 'direct': True,
'url': url, 'url': url,
'ext': ext,
}) })
return info_dict return info_dict

View file

@ -1,16 +1,21 @@
import json
import re import re
import urllib.parse import time
import uuid import uuid
from .common import InfoExtractor from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import ( from ..utils import (
ExtractorError,
determine_ext, determine_ext,
int_or_none, int_or_none,
join_nonempty, join_nonempty,
jwt_decode_hs256,
parse_duration, parse_duration,
parse_iso8601, parse_iso8601,
try_get, try_get,
url_or_none, url_or_none,
urlencode_postdata,
) )
from ..utils.traversal import traverse_obj from ..utils.traversal import traverse_obj
@ -276,81 +281,213 @@ def _download_video_data(self, display_id):
class MLBTVIE(InfoExtractor): class MLBTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?mlb\.com/tv/g(?P<id>\d{6})' _VALID_URL = r'https?://(?:www\.)?mlb\.com/tv/g(?P<id>\d{6})'
_NETRC_MACHINE = 'mlb' _NETRC_MACHINE = 'mlb'
_TESTS = [{ _TESTS = [{
'url': 'https://www.mlb.com/tv/g661581/vee2eff5f-a7df-4c20-bdb4-7b926fa12638', 'url': 'https://www.mlb.com/tv/g661581/vee2eff5f-a7df-4c20-bdb4-7b926fa12638',
'info_dict': { 'info_dict': {
'id': '661581', 'id': '661581',
'ext': 'mp4', 'ext': 'mp4',
'title': '2022-07-02 - St. Louis Cardinals @ Philadelphia Phillies', 'title': '2022-07-02 - St. Louis Cardinals @ Philadelphia Phillies',
'release_date': '20220702',
'release_timestamp': 1656792300,
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
}] }]
_GRAPHQL_INIT_QUERY = '''\
mutation initSession($device: InitSessionInput!, $clientType: ClientType!, $experience: ExperienceTypeInput) {
initSession(device: $device, clientType: $clientType, experience: $experience) {
deviceId
sessionId
entitlements {
code
}
location {
countryCode
regionName
zipCode
latitude
longitude
}
clientExperience
features
}
}'''
_GRAPHQL_PLAYBACK_QUERY = '''\
mutation initPlaybackSession(
$adCapabilities: [AdExperienceType]
$mediaId: String!
$deviceId: String!
$sessionId: String!
$quality: PlaybackQuality
) {
initPlaybackSession(
adCapabilities: $adCapabilities
mediaId: $mediaId
deviceId: $deviceId
sessionId: $sessionId
quality: $quality
) {
playbackSessionId
playback {
url
token
expiration
cdn
}
}
}'''
_APP_VERSION = '7.8.2'
_device_id = None
_session_id = None
_access_token = None _access_token = None
_token_expiry = 0
@property
def _api_headers(self):
if (self._token_expiry - 120) <= time.time():
self.write_debug('Access token has expired; re-logging in')
self._perform_login(*self._get_login_info())
return {'Authorization': f'Bearer {self._access_token}'}
def _real_initialize(self): def _real_initialize(self):
if not self._access_token: if not self._access_token:
self.raise_login_required( self.raise_login_required(
'All videos are only available to registered users', method='password') 'All videos are only available to registered users', method='password')
def _set_device_id(self, username):
if not self._device_id:
self._device_id = self.cache.load(
self._NETRC_MACHINE, 'device_ids', default={}).get(username)
if self._device_id:
return
self._device_id = str(uuid.uuid4())
self.cache.store(self._NETRC_MACHINE, 'device_ids', {username: self._device_id})
def _perform_login(self, username, password): def _perform_login(self, username, password):
data = f'grant_type=password&username={urllib.parse.quote(username)}&password={urllib.parse.quote(password)}&scope=openid offline_access&client_id=0oa3e1nutA1HLzAKG356' try:
access_token = self._download_json(
'https://ids.mlb.com/oauth2/aus1m088yK07noBfh356/v1/token', None,
headers={
'User-Agent': 'okhttp/3.12.1',
'Content-Type': 'application/x-www-form-urlencoded',
}, data=data.encode())['access_token']
entitlement = self._download_webpage(
f'https://media-entitlement.mlb.com/api/v3/jwt?os=Android&appname=AtBat&did={uuid.uuid4()}', None,
headers={
'User-Agent': 'okhttp/3.12.1',
'Authorization': f'Bearer {access_token}',
})
data = f'grant_type=urn:ietf:params:oauth:grant-type:token-exchange&subject_token={entitlement}&subject_token_type=urn:ietf:params:oauth:token-type:jwt&platform=android-tv'
self._access_token = self._download_json( self._access_token = self._download_json(
'https://us.edge.bamgrid.com/token', None, 'https://ids.mlb.com/oauth2/aus1m088yK07noBfh356/v1/token', None,
headers={ 'Logging in', 'Unable to log in', headers={
'Accept': 'application/json', 'User-Agent': 'okhttp/3.12.1',
'Authorization': 'Bearer bWxidHYmYW5kcm9pZCYxLjAuMA.6LZMbH2r--rbXcgEabaDdIslpo4RyZrlVfWZhsAgXIk',
'Content-Type': 'application/x-www-form-urlencoded', 'Content-Type': 'application/x-www-form-urlencoded',
}, data=data.encode())['access_token'] }, data=urlencode_postdata({
'grant_type': 'password',
'username': username,
'password': password,
'scope': 'openid offline_access',
'client_id': '0oa3e1nutA1HLzAKG356',
}))['access_token']
except ExtractorError as error:
if isinstance(error.cause, HTTPError) and error.cause.status == 400:
raise ExtractorError('Invalid username or password', expected=True)
raise
self._token_expiry = traverse_obj(self._access_token, ({jwt_decode_hs256}, 'exp', {int})) or 0
self._set_device_id(username)
self._session_id = self._call_api({
'operationName': 'initSession',
'query': self._GRAPHQL_INIT_QUERY,
'variables': {
'device': {
'appVersion': self._APP_VERSION,
'deviceFamily': 'desktop',
'knownDeviceId': self._device_id,
'languagePreference': 'ENGLISH',
'manufacturer': '',
'model': '',
'os': '',
'osVersion': '',
},
'clientType': 'WEB',
},
}, None, 'session ID')['data']['initSession']['sessionId']
def _call_api(self, data, video_id, description='GraphQL JSON', fatal=True):
return self._download_json(
'https://media-gateway.mlb.com/graphql', video_id,
f'Downloading {description}', f'Unable to download {description}', fatal=fatal,
headers={
**self._api_headers,
'Accept': 'application/json',
'Content-Type': 'application/json',
'x-client-name': 'WEB',
'x-client-version': self._APP_VERSION,
}, data=json.dumps(data, separators=(',', ':')).encode())
def _extract_formats_and_subtitles(self, broadcast, video_id):
feed = traverse_obj(broadcast, ('homeAway', {str.title}))
medium = traverse_obj(broadcast, ('type', {str}))
language = traverse_obj(broadcast, ('language', {str.lower}))
format_id = join_nonempty(feed, medium, language)
response = self._call_api({
'operationName': 'initPlaybackSession',
'query': self._GRAPHQL_PLAYBACK_QUERY,
'variables': {
'adCapabilities': ['GOOGLE_STANDALONE_AD_PODS'],
'deviceId': self._device_id,
'mediaId': broadcast['mediaId'],
'quality': 'PLACEHOLDER',
'sessionId': self._session_id,
},
}, video_id, f'{format_id} broadcast JSON', fatal=False)
playback = traverse_obj(response, ('data', 'initPlaybackSession', 'playback', {dict}))
m3u8_url = traverse_obj(playback, ('url', {url_or_none}))
token = traverse_obj(playback, ('token', {str}))
if not (m3u8_url and token):
errors = '; '.join(traverse_obj(response, ('errors', ..., 'message', {str})))
if 'not entitled' in errors:
raise ExtractorError(errors, expected=True)
elif errors: # Only warn when 'blacked out' since radio formats are available
self.report_warning(f'API returned errors for {format_id}: {errors}')
else:
self.report_warning(f'No formats available for {format_id} broadcast; skipping')
return [], {}
cdn_headers = {'x-cdn-token': token}
fmts, subs = self._extract_m3u8_formats_and_subtitles(
m3u8_url.replace(f'/{token}/', '/'), video_id, 'mp4',
m3u8_id=format_id, fatal=False, headers=cdn_headers)
for fmt in fmts:
fmt['http_headers'] = cdn_headers
fmt.setdefault('format_note', join_nonempty(feed, medium, delim=' '))
fmt.setdefault('language', language)
if fmt.get('vcodec') == 'none' and fmt['language'] == 'en':
fmt['source_preference'] = 10
return fmts, subs
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
airings = self._download_json( metadata = traverse_obj(self._download_json(
f'https://search-api-mlbtv.mlb.com/svc/search/v2/graphql/persisted/query/core/Airings?variables=%7B%22partnerProgramIds%22%3A%5B%22{video_id}%22%5D%2C%22applyEsniMediaRightsLabels%22%3Atrue%7D', 'https://statsapi.mlb.com/api/v1/schedule', video_id, query={
video_id)['data']['Airings'] 'gamePk': video_id,
'hydrate': 'broadcasts(all),statusFlags',
}), ('dates', ..., 'games', lambda _, v: str(v['gamePk']) == video_id and v['broadcasts'], any))
broadcasts = traverse_obj(metadata, (
'broadcasts', lambda _, v: v['mediaId'] and v['mediaState']['mediaStateCode'] != 'MEDIA_OFF'))
formats, subtitles = [], {} formats, subtitles = [], {}
for airing in traverse_obj(airings, lambda _, v: v['playbackUrls'][0]['href']): for broadcast in broadcasts:
format_id = join_nonempty('feedType', 'feedLanguage', from_dict=airing) fmts, subs = self._extract_formats_and_subtitles(broadcast, video_id)
m3u8_url = traverse_obj(self._download_json( formats.extend(fmts)
airing['playbackUrls'][0]['href'].format(scenario='browser~csai'), video_id, self._merge_subtitles(subs, target=subtitles)
note=f'Downloading {format_id} stream info JSON',
errnote=f'Failed to download {format_id} stream info, skipping',
fatal=False, headers={
'Authorization': self._access_token,
'Accept': 'application/vnd.media-service+json; version=2',
}), ('stream', 'complete', {url_or_none}))
if not m3u8_url:
continue
f, s = self._extract_m3u8_formats_and_subtitles(
m3u8_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
formats.extend(f)
self._merge_subtitles(s, target=subtitles)
return { return {
'id': video_id, 'id': video_id,
'title': traverse_obj(airings, (..., 'titles', 0, 'episodeName'), get_all=False), 'title': join_nonempty(
'is_live': traverse_obj(airings, (..., 'mediaConfig', 'productType'), get_all=False) == 'LIVE', traverse_obj(metadata, ('officialDate', {str})),
traverse_obj(metadata, ('teams', ('away', 'home'), 'team', 'name', {str}, all, {' @ '.join})),
delim=' - '),
'is_live': traverse_obj(broadcasts, (..., 'mediaState', 'mediaStateCode', {str}, any)) == 'MEDIA_ON',
'release_timestamp': traverse_obj(metadata, ('gameDate', {parse_iso8601})),
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
'http_headers': {'Authorization': f'Bearer {self._access_token}'},
} }

View file

@ -871,7 +871,7 @@ class SoundcloudUserPermalinkIE(SoundcloudPagedPlaylistBaseIE):
'id': '30909869', 'id': '30909869',
'title': 'neilcic', 'title': 'neilcic',
}, },
'playlist_mincount': 23, 'playlist_mincount': 22,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -880,7 +880,7 @@ def _real_extract(self, url):
self._resolv_url(url), user_id, 'Downloading user info', headers=self._HEADERS) self._resolv_url(url), user_id, 'Downloading user info', headers=self._HEADERS)
return self._extract_playlist( return self._extract_playlist(
f'{self._API_V2_BASE}stream/users/{user["id"]}', str(user['id']), user.get('username')) f'{self._API_V2_BASE}users/{user["id"]}/tracks', str(user['id']), user.get('username'))
class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE): class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE):

View file

@ -23,7 +23,6 @@
mimetype2ext, mimetype2ext,
parse_qs, parse_qs,
qualities, qualities,
remove_start,
srt_subtitles_timecode, srt_subtitles_timecode,
str_or_none, str_or_none,
traverse_obj, traverse_obj,
@ -254,7 +253,16 @@ def _extract_web_data_and_status(self, url, video_id, fatal=True):
def _get_subtitles(self, aweme_detail, aweme_id, user_name): def _get_subtitles(self, aweme_detail, aweme_id, user_name):
# TODO: Extract text positioning info # TODO: Extract text positioning info
EXT_MAP = { # From lowest to highest preference
'creator_caption': 'json',
'srt': 'srt',
'webvtt': 'vtt',
}
preference = qualities(tuple(EXT_MAP.values()))
subtitles = {} subtitles = {}
# aweme/detail endpoint subs # aweme/detail endpoint subs
captions_info = traverse_obj( captions_info = traverse_obj(
aweme_detail, ('interaction_stickers', ..., 'auto_video_caption_info', 'auto_captions', ...), expected_type=dict) aweme_detail, ('interaction_stickers', ..., 'auto_video_caption_info', 'auto_captions', ...), expected_type=dict)
@ -278,8 +286,8 @@ def _get_subtitles(self, aweme_detail, aweme_id, user_name):
if not caption.get('url'): if not caption.get('url'):
continue continue
subtitles.setdefault(caption.get('lang') or 'en', []).append({ subtitles.setdefault(caption.get('lang') or 'en', []).append({
'ext': remove_start(caption.get('caption_format'), 'web'),
'url': caption['url'], 'url': caption['url'],
'ext': EXT_MAP.get(caption.get('Format')),
}) })
# webpage subs # webpage subs
if not subtitles: if not subtitles:
@ -288,9 +296,14 @@ def _get_subtitles(self, aweme_detail, aweme_id, user_name):
self._create_url(user_name, aweme_id), aweme_id, fatal=False) self._create_url(user_name, aweme_id), aweme_id, fatal=False)
for caption in traverse_obj(aweme_detail, ('video', 'subtitleInfos', lambda _, v: v['Url'])): for caption in traverse_obj(aweme_detail, ('video', 'subtitleInfos', lambda _, v: v['Url'])):
subtitles.setdefault(caption.get('LanguageCodeName') or 'en', []).append({ subtitles.setdefault(caption.get('LanguageCodeName') or 'en', []).append({
'ext': remove_start(caption.get('Format'), 'web'),
'url': caption['Url'], 'url': caption['Url'],
'ext': EXT_MAP.get(caption.get('Format')),
}) })
# Deprioritize creator_caption json since it can't be embedded or used by media players
for lang, subs_list in subtitles.items():
subtitles[lang] = sorted(subs_list, key=lambda x: preference(x['ext']))
return subtitles return subtitles
def _parse_url_key(self, url_key): def _parse_url_key(self, url_key):

View file

@ -212,16 +212,6 @@ def _parse_config(self, config, video_id):
owner = video_data.get('owner') or {} owner = video_data.get('owner') or {}
video_uploader_url = owner.get('url') video_uploader_url = owner.get('url')
duration = int_or_none(video_data.get('duration'))
chapter_data = try_get(config, lambda x: x['embed']['chapters']) or []
chapters = [{
'title': current_chapter.get('title'),
'start_time': current_chapter.get('timecode'),
'end_time': next_chapter.get('timecode'),
} for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])]
if chapters and chapters[0]['start_time']: # Chapters may not start from 0
chapters[:0] = [{'title': '<Untitled>', 'start_time': 0, 'end_time': chapters[0]['start_time']}]
return { return {
'id': str_or_none(video_data.get('id')) or video_id, 'id': str_or_none(video_data.get('id')) or video_id,
'title': video_title, 'title': video_title,
@ -229,8 +219,12 @@ def _parse_config(self, config, video_id):
'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None, 'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
'uploader_url': video_uploader_url, 'uploader_url': video_uploader_url,
'thumbnails': thumbnails, 'thumbnails': thumbnails,
'duration': duration, 'duration': int_or_none(video_data.get('duration')),
'chapters': chapters or None, 'chapters': sorted(traverse_obj(config, (
'embed', 'chapters', lambda _, v: int(v['timecode']) is not None, {
'title': ('title', {str}),
'start_time': ('timecode', {int_or_none}),
})), key=lambda c: c['start_time']) or None,
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
'live_status': live_status, 'live_status': live_status,
@ -708,6 +702,39 @@ class VimeoIE(VimeoBaseInfoExtractor):
'skip_download': True, 'skip_download': True,
}, },
}, },
{
# chapters must be sorted, see: https://github.com/yt-dlp/yt-dlp/issues/5308
'url': 'https://player.vimeo.com/video/756714419',
'info_dict': {
'id': '756714419',
'ext': 'mp4',
'title': 'Dr Arielle Schwartz - Therapeutic yoga for optimum sleep',
'uploader': 'Alex Howard',
'uploader_id': 'user54729178',
'uploader_url': 'https://vimeo.com/user54729178',
'thumbnail': r're:https://i\.vimeocdn\.com/video/1520099929-[\da-f]+-d_1280',
'duration': 2636,
'chapters': [
{'start_time': 0, 'end_time': 10, 'title': '<Untitled Chapter 1>'},
{'start_time': 10, 'end_time': 106, 'title': 'Welcoming Dr Arielle Schwartz'},
{'start_time': 106, 'end_time': 305, 'title': 'What is therapeutic yoga?'},
{'start_time': 305, 'end_time': 594, 'title': 'Vagal toning practices'},
{'start_time': 594, 'end_time': 888, 'title': 'Trauma and difficulty letting go'},
{'start_time': 888, 'end_time': 1059, 'title': "Dr Schwartz' insomnia experience"},
{'start_time': 1059, 'end_time': 1471, 'title': 'A strategy for helping sleep issues'},
{'start_time': 1471, 'end_time': 1667, 'title': 'Yoga nidra'},
{'start_time': 1667, 'end_time': 2121, 'title': 'Wisdom in stillness'},
{'start_time': 2121, 'end_time': 2386, 'title': 'What helps us be more able to let go?'},
{'start_time': 2386, 'end_time': 2510, 'title': 'Practical tips to help ourselves'},
{'start_time': 2510, 'end_time': 2636, 'title': 'Where to find out more'},
],
},
'params': {
'http_headers': {'Referer': 'https://sleepsuperconference.com'},
'skip_download': 'm3u8',
},
'expected_warnings': ['Failed to parse XML: not well-formed'],
},
{ {
# user playlist alias -> https://vimeo.com/258705797 # user playlist alias -> https://vimeo.com/258705797
'url': 'https://vimeo.com/user26785108/newspiritualguide', 'url': 'https://vimeo.com/user26785108/newspiritualguide',

View file

@ -270,7 +270,7 @@ def build_innertube_clients():
THIRD_PARTY = { THIRD_PARTY = {
'embedUrl': 'https://www.youtube.com/', # Can be any valid URL 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
} }
BASE_CLIENTS = ('ios', 'android', 'web', 'tv', 'mweb') BASE_CLIENTS = ('ios', 'web', 'tv', 'mweb', 'android')
priority = qualities(BASE_CLIENTS[::-1]) priority = qualities(BASE_CLIENTS[::-1])
for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()): for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
@ -3131,7 +3131,14 @@ def _decrypt_nsig(self, s, video_id, player_url):
def _extract_n_function_name(self, jscode): def _extract_n_function_name(self, jscode):
funcname, idx = self._search_regex( funcname, idx = self._search_regex(
r'''(?x)(?:\.get\("n"\)\)&&\(b=|b=String\.fromCharCode\(110\),c=a\.get\(b\)\)&&\(c=) r'''(?x)
(?:
\.get\("n"\)\)&&\(b=|
(?:
b=String\.fromCharCode\(110\)|
([a-zA-Z0-9$.]+)&&\(b="nn"\[\+\1\]
),c=a\.get\(b\)\)&&\(c=
)
(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)''', (?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)''',
jscode, 'Initial JS player n function name', group=('nfunc', 'idx')) jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
if not idx: if not idx:
@ -3702,15 +3709,15 @@ def _invalid_player_response(self, pr, video_id):
return pr_id return pr_id
def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data): def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
initial_pr = None initial_pr = ignore_initial_response = None
if webpage: if webpage:
if 'web' in clients:
experiments = traverse_obj(master_ytcfg, ( experiments = traverse_obj(master_ytcfg, (
'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'serializedExperimentIds', {str}, {lambda x: x.split(',')}, ..., {str})) 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'serializedExperimentIds', {lambda x: x.split(',')}, ...))
if all(x in experiments for x in self._POTOKEN_EXPERIMENTS): if all(x in experiments for x in self._POTOKEN_EXPERIMENTS):
self.report_warning( self.report_warning(
'Webpage contains broken formats (poToken experiment detected). Ignoring initial player response') 'Webpage contains broken formats (poToken experiment detected). Ignoring initial player response')
master_ytcfg = self._get_default_ytcfg() ignore_initial_response = True
else:
initial_pr = self._search_json( initial_pr = self._search_json(
self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False) self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
@ -3740,8 +3747,10 @@ def append_client(*client_names):
skipped_clients = {} skipped_clients = {}
while clients: while clients:
client, base_client, variant = _split_innertube_client(clients.pop()) client, base_client, variant = _split_innertube_client(clients.pop())
player_ytcfg = master_ytcfg if client == 'web' else {} player_ytcfg = {}
if 'configs' not in self._configuration_arg('player_skip') and client != 'web': if client == 'web':
player_ytcfg = self._get_default_ytcfg() if ignore_initial_response else master_ytcfg
elif 'configs' not in self._configuration_arg('player_skip'):
player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage) player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
@ -3754,7 +3763,7 @@ def append_client(*client_names):
player_url = self._download_player_url(video_id) player_url = self._download_player_url(video_id)
tried_iframe_fallback = True tried_iframe_fallback = True
pr = initial_pr if client == 'web' and initial_pr else None pr = initial_pr if client == 'web' and not ignore_initial_response else None
for retry in self.RetryManager(fatal=False): for retry in self.RetryManager(fatal=False):
try: try:
pr = pr or self._extract_player_response( pr = pr or self._extract_player_response(
@ -3765,7 +3774,7 @@ def append_client(*client_names):
break break
experiments = traverse_obj(pr, ( experiments = traverse_obj(pr, (
'responseContext', 'serviceTrackingParams', lambda _, v: v['service'] == 'GFEEDBACK', 'responseContext', 'serviceTrackingParams', lambda _, v: v['service'] == 'GFEEDBACK',
'params', lambda _, v: v['key'] == 'e', 'value', {lambda x: x.split(',')}, ..., {str})) 'params', lambda _, v: v['key'] == 'e', 'value', {lambda x: x.split(',')}, ...))
if all(x in experiments for x in self._POTOKEN_EXPERIMENTS): if all(x in experiments for x in self._POTOKEN_EXPERIMENTS):
pr = None pr = None
retry.error = ExtractorError('API returned broken formats (poToken experiment detected)', expected=True) retry.error = ExtractorError('API returned broken formats (poToken experiment detected)', expected=True)

View file

@ -462,6 +462,7 @@ def _alias_callback(option, opt_str, value, parser, opts, nargs):
'the STREAM (stdout or stderr) to apply the setting to. ' 'the STREAM (stdout or stderr) to apply the setting to. '
'Can be one of "always", "auto" (default), "never", or ' 'Can be one of "always", "auto" (default), "never", or '
'"no_color" (use non color terminal sequences). ' '"no_color" (use non color terminal sequences). '
'Use "auto-tty" or "no_color-tty" to decide based on terminal support only. '
'Can be used multiple times')) 'Can be used multiple times'))
general.add_option( general.add_option(
'--compat-options', '--compat-options',

View file

@ -310,6 +310,7 @@ def _download_update_spec(self, source_tags):
if isinstance(error, HTTPError) and error.status == 404: if isinstance(error, HTTPError) and error.status == 404:
continue continue
self._report_network_error(f'fetch update spec: {error}') self._report_network_error(f'fetch update spec: {error}')
return None
self._report_error( self._report_error(
f'The requested tag {self.requested_tag} does not exist for {self.requested_repo}', True) f'The requested tag {self.requested_tag} does not exist for {self.requested_repo}', True)
@ -557,9 +558,10 @@ def _report_permission_error(self, file):
def _report_network_error(self, action, delim=';', tag=None): def _report_network_error(self, action, delim=';', tag=None):
if not tag: if not tag:
tag = self.requested_tag tag = self.requested_tag
path = tag if tag == 'latest' else f'tag/{tag}'
self._report_error( self._report_error(
f'Unable to {action}{delim} visit https://github.com/{self.requested_repo}/releases/' f'Unable to {action}{delim} visit '
+ tag if tag == 'latest' else f'tag/{tag}', True) f'https://github.com/{self.requested_repo}/releases/{path}', True)
# XXX: Everything below this line in this class is deprecated / for compat only # XXX: Everything below this line in this class is deprecated / for compat only
@property @property

View file

@ -2984,6 +2984,7 @@ def parse_codecs(codecs_str):
str.strip, codecs_str.strip().strip(',').split(',')))) str.strip, codecs_str.strip().strip(',').split(','))))
vcodec, acodec, scodec, hdr = None, None, None, None vcodec, acodec, scodec, hdr = None, None, None, None
for full_codec in split_codecs: for full_codec in split_codecs:
full_codec = re.sub(r'^([^.]+)', lambda m: m.group(1).lower(), full_codec)
parts = re.sub(r'0+(?=\d)', '', full_codec).split('.') parts = re.sub(r'0+(?=\d)', '', full_codec).split('.')
if parts[0] in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', if parts[0] in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2',
'h263', 'h264', 'mp4v', 'hvc1', 'av1', 'theora', 'dvh1', 'dvhe'): 'h263', 'h264', 'mp4v', 'hvc1', 'av1', 'theora', 'dvh1', 'dvhe'):
@ -5110,6 +5111,7 @@ class _UnsafeExtensionError(Exception):
'gif', 'gif',
'heic', 'heic',
'ico', 'ico',
'image',
'jng', 'jng',
'jpeg', 'jpeg',
'jxl', 'jxl',

View file

@ -1,8 +1,8 @@
# Autogenerated by devscripts/update-version.py # Autogenerated by devscripts/update-version.py
__version__ = '2024.07.09' __version__ = '2024.07.25'
RELEASE_GIT_HEAD = '7ead7332af69422cee931aec3faa277288e9e212' RELEASE_GIT_HEAD = 'f0993391e6052ec8f7aacc286609564f226943b9'
VARIANT = None VARIANT = None
@ -12,4 +12,4 @@
ORIGIN = 'yt-dlp/yt-dlp' ORIGIN = 'yt-dlp/yt-dlp'
_pkg_version = '2024.07.09' _pkg_version = '2024.07.25'