diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 4b71a621c3..e2411ecfad 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -256,7 +256,7 @@ jobs:
with:
path: |
~/yt-dlp-build-venv
- key: cache-reqs-${{ github.job }}
+ key: cache-reqs-${{ github.job }}-${{ github.ref }}
- name: Install Requirements
run: |
@@ -331,19 +331,16 @@ jobs:
if: steps.restore-cache.outputs.cache-hit == 'true'
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- cache_key: cache-reqs-${{ github.job }}
- repository: ${{ github.repository }}
- branch: ${{ github.ref }}
+ cache_key: cache-reqs-${{ github.job }}-${{ github.ref }}
run: |
- gh extension install actions/gh-actions-cache
- gh actions-cache delete "${cache_key}" -R "${repository}" -B "${branch}" --confirm
+ gh cache delete "${cache_key}"
- name: Cache requirements
uses: actions/cache/save@v4
with:
path: |
~/yt-dlp-build-venv
- key: cache-reqs-${{ github.job }}
+ key: cache-reqs-${{ github.job }}-${{ github.ref }}
macos_legacy:
needs: process
diff --git a/.gitignore b/.gitignore
index 8fcd0de641..40bb34d2aa 100644
--- a/.gitignore
+++ b/.gitignore
@@ -105,6 +105,8 @@ README.txt
*.zsh
*.spec
test/testdata/sigs/player-*.js
+test/testdata/thumbnails/empty.webp
+test/testdata/thumbnails/foo\ %d\ bar/foo_%d.*
# Binary
/youtube-dl
diff --git a/Makefile b/Makefile
index 6c72ead1ef..273cb3cc0b 100644
--- a/Makefile
+++ b/Makefile
@@ -18,10 +18,11 @@ pypi-files: AUTHORS Changelog.md LICENSE README.md README.txt supportedsites \
tar pypi-files lazy-extractors install uninstall
clean-test:
- rm -rf test/testdata/sigs/player-*.js tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
+ rm -rf tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
*.frag.aria2 *.frag.urls *.info.json *.live_chat.json *.meta *.part* *.tmp *.temp *.unknown_video *.ytdl \
*.3gp *.ape *.ass *.avi *.desktop *.f4v *.flac *.flv *.gif *.jpeg *.jpg *.lrc *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 *.mp4 \
- *.mpg *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.ssa *.swf *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
+ *.mpg *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.ssa *.swf *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp \
+ test/testdata/sigs/player-*.js test/testdata/thumbnails/empty.webp "test/testdata/thumbnails/foo %d bar/foo_%d."*
clean-dist:
rm -rf yt-dlp.1.temp.md yt-dlp.1 README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz completions/ \
yt_dlp/extractor/lazy_extractors.py *.spec CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe yt_dlp.egg-info/ AUTHORS
diff --git a/bundle/docker/static/entrypoint.sh b/bundle/docker/static/entrypoint.sh
index 2202759742..8049e68205 100755
--- a/bundle/docker/static/entrypoint.sh
+++ b/bundle/docker/static/entrypoint.sh
@@ -2,6 +2,7 @@
set -e
source ~/.local/share/pipx/venvs/pyinstaller/bin/activate
+python -m devscripts.install_deps -o --include build
python -m devscripts.install_deps --include secretstorage --include curl-cffi
python -m devscripts.make_lazy_extractors
python devscripts/update-version.py -c "${channel}" -r "${origin}" "${version}"
diff --git a/bundle/pyinstaller.py b/bundle/pyinstaller.py
index 4184c4bc9f..c2f6511210 100755
--- a/bundle/pyinstaller.py
+++ b/bundle/pyinstaller.py
@@ -36,6 +36,9 @@ def main():
f'--name={name}',
'--icon=devscripts/logo.ico',
'--upx-exclude=vcruntime140.dll',
+ # Ref: https://github.com/yt-dlp/yt-dlp/issues/13311
+ # https://github.com/pyinstaller/pyinstaller/issues/9149
+ '--exclude-module=pkg_resources',
'--noconfirm',
'--additional-hooks-dir=yt_dlp/__pyinstaller',
*opts,
diff --git a/pyproject.toml b/pyproject.toml
index 7accaeeb9e..3775251e10 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -65,7 +65,7 @@ build = [
"build",
"hatchling",
"pip",
- "setuptools>=71.0.2", # 71.0.0 broke pyinstaller
+ "setuptools>=71.0.2,<81", # See https://github.com/pyinstaller/pyinstaller/issues/9149
"wheel",
]
dev = [
diff --git a/test/test_postprocessors.py b/test/test_postprocessors.py
index 603f85c654..ecc73e39eb 100644
--- a/test/test_postprocessors.py
+++ b/test/test_postprocessors.py
@@ -8,6 +8,8 @@ import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+import subprocess
+
from yt_dlp import YoutubeDL
from yt_dlp.utils import shell_quote
from yt_dlp.postprocessor import (
@@ -47,7 +49,18 @@ class TestConvertThumbnail(unittest.TestCase):
print('Skipping: ffmpeg not found')
return
- file = 'test/testdata/thumbnails/foo %d bar/foo_%d.{}'
+ test_data_dir = 'test/testdata/thumbnails'
+ generated_file = f'{test_data_dir}/empty.webp'
+
+ subprocess.check_call([
+ pp.executable, '-y', '-f', 'lavfi', '-i', 'color=c=black:s=320x320',
+ '-c:v', 'libwebp', '-pix_fmt', 'yuv420p', '-vframes', '1', generated_file,
+ ], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
+
+ file = test_data_dir + '/foo %d bar/foo_%d.{}'
+ initial_file = file.format('webp')
+ os.replace(generated_file, initial_file)
+
tests = (('webp', 'png'), ('png', 'jpg'))
for inp, out in tests:
@@ -55,11 +68,13 @@ class TestConvertThumbnail(unittest.TestCase):
if os.path.exists(out_file):
os.remove(out_file)
pp.convert_thumbnail(file.format(inp), out)
- assert os.path.exists(out_file)
+ self.assertTrue(os.path.exists(out_file))
for _, out in tests:
os.remove(file.format(out))
+ os.remove(initial_file)
+
class TestExec(unittest.TestCase):
def test_parse_cmd(self):
@@ -610,3 +625,7 @@ outpoint 10.000000
self.assertEqual(
r"'special '\'' characters '\'' galore'\'\'\'",
self._pp._quote_for_ffmpeg("special ' characters ' galore'''"))
+
+
+if __name__ == '__main__':
+ unittest.main()
diff --git a/test/testdata/thumbnails/foo %d bar/foo_%d.webp b/test/testdata/thumbnails/foo %d bar/foo_%d.webp
deleted file mode 100644
index d64d0839f0..0000000000
Binary files a/test/testdata/thumbnails/foo %d bar/foo_%d.webp and /dev/null differ
diff --git a/test/testdata/thumbnails/foo %d bar/placeholder b/test/testdata/thumbnails/foo %d bar/placeholder
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index 14a0068934..b0c52e0fcf 100644
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -300,7 +300,6 @@ from .brainpop import (
BrainPOPIlIE,
BrainPOPJrIE,
)
-from .bravotv import BravoTVIE
from .breitbart import BreitBartIE
from .brightcove import (
BrightcoveLegacyIE,
@@ -1262,6 +1261,7 @@ from .nba import (
)
from .nbc import (
NBCIE,
+ BravoTVIE,
NBCNewsIE,
NBCOlympicsIE,
NBCOlympicsStreamIE,
@@ -1269,6 +1269,7 @@ from .nbc import (
NBCSportsStreamIE,
NBCSportsVPlayerIE,
NBCStationsIE,
+ SyfyIE,
)
from .ndr import (
NDRIE,
@@ -2022,7 +2023,6 @@ from .svt import (
SVTSeriesIE,
)
from .swearnet import SwearnetEpisodeIE
-from .syfy import SyfyIE
from .syvdk import SYVDKIE
from .sztvhu import SztvHuIE
from .tagesschau import TagesschauIE
@@ -2147,6 +2147,7 @@ from .toggle import (
from .toggo import ToggoIE
from .tonline import TOnlineIE
from .toongoggles import ToonGogglesIE
+from .toutiao import ToutiaoIE
from .toutv import TouTvIE
from .toypics import (
ToypicsIE,
diff --git a/yt_dlp/extractor/adobepass.py b/yt_dlp/extractor/adobepass.py
index f1b8779271..91c40b32ef 100644
--- a/yt_dlp/extractor/adobepass.py
+++ b/yt_dlp/extractor/adobepass.py
@@ -3,6 +3,7 @@ import json
import re
import time
import urllib.parse
+import uuid
import xml.etree.ElementTree as etree
from .common import InfoExtractor
@@ -10,6 +11,7 @@ from ..networking.exceptions import HTTPError
from ..utils import (
NO_DEFAULT,
ExtractorError,
+ parse_qs,
unescapeHTML,
unified_timestamp,
urlencode_postdata,
@@ -45,6 +47,8 @@ MSO_INFO = {
'name': 'Comcast XFINITY',
'username_field': 'user',
'password_field': 'passwd',
+ 'login_hostname': 'login.xfinity.com',
+ 'needs_newer_ua': True,
},
'TWC': {
'name': 'Time Warner Cable | Spectrum',
@@ -74,6 +78,12 @@ MSO_INFO = {
'name': 'Verizon FiOS',
'username_field': 'IDToken1',
'password_field': 'IDToken2',
+ 'login_hostname': 'ssoauth.verizon.com',
+ },
+ 'Fubo': {
+ 'name': 'Fubo',
+ 'username_field': 'username',
+ 'password_field': 'password',
},
'Cablevision': {
'name': 'Optimum/Cablevision',
@@ -1338,6 +1348,7 @@ MSO_INFO = {
'name': 'Sling TV',
'username_field': 'username',
'password_field': 'password',
+ 'login_hostname': 'identity.sling.com',
},
'Suddenlink': {
'name': 'Suddenlink',
@@ -1355,7 +1366,6 @@ MSO_INFO = {
class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
_SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s'
_USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
- _MODERN_USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; rv:131.0) Gecko/20100101 Firefox/131.0'
_MVPD_CACHE = 'ap-mvpd'
_DOWNLOADING_LOGIN_PAGE = 'Downloading Provider Login Page'
@@ -1367,6 +1377,14 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
return super()._download_webpage_handle(
*args, **kwargs)
+ @staticmethod
+ def _get_mso_headers(mso_info):
+ # yt-dlp's default user-agent is usually too old for some MSO's like Comcast_SSO
+ # See: https://github.com/yt-dlp/yt-dlp/issues/10848
+ return {
+ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:131.0) Gecko/20100101 Firefox/131.0',
+ } if mso_info.get('needs_newer_ua') else {}
+
@staticmethod
def _get_mvpd_resource(provider_id, title, guid, rating):
channel = etree.Element('channel')
@@ -1382,7 +1400,13 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
resource_rating.text = rating
return '' + etree.tostring(channel).decode() + ''
- def _extract_mvpd_auth(self, url, video_id, requestor_id, resource):
+ def _extract_mvpd_auth(self, url, video_id, requestor_id, resource, software_statement):
+ mso_id = self.get_param('ap_mso')
+ if mso_id:
+ mso_info = MSO_INFO[mso_id]
+ else:
+ mso_info = {}
+
def xml_text(xml_str, tag):
return self._search_regex(
f'<{tag}>(.+?)', xml_str, tag)
@@ -1391,15 +1415,27 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
token_expires = unified_timestamp(re.sub(r'[_ ]GMT', '', xml_text(token, date_ele)))
return token_expires and token_expires <= int(time.time())
- def post_form(form_page_res, note, data={}):
+ def post_form(form_page_res, note, data={}, validate_url=False):
form_page, urlh = form_page_res
post_url = self._html_search_regex(r']+action=(["\'])(?P.+?)\1', form_page, 'post url', group='url')
if not re.match(r'https?://', post_url):
post_url = urllib.parse.urljoin(urlh.url, post_url)
+ if validate_url:
+ # This request is submitting credentials so we should validate it when possible
+ url_parsed = urllib.parse.urlparse(post_url)
+ expected_hostname = mso_info.get('login_hostname')
+ if expected_hostname and expected_hostname != url_parsed.hostname:
+ raise ExtractorError(
+ f'Unexpected login URL hostname; expected "{expected_hostname}" but got '
+ f'"{url_parsed.hostname}". Aborting before submitting credentials')
+ if url_parsed.scheme != 'https':
+ self.write_debug('Upgrading login URL scheme to https')
+ post_url = urllib.parse.urlunparse(url_parsed._replace(scheme='https'))
form_data = self._hidden_inputs(form_page)
form_data.update(data)
return self._download_webpage_handle(
post_url, video_id, note, data=urlencode_postdata(form_data), headers={
+ **self._get_mso_headers(mso_info),
'Content-Type': 'application/x-www-form-urlencoded',
})
@@ -1432,40 +1468,72 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
}
guid = xml_text(resource, 'guid') if '<' in resource else resource
- count = 0
- while count < 2:
+ for _ in range(2):
requestor_info = self.cache.load(self._MVPD_CACHE, requestor_id) or {}
authn_token = requestor_info.get('authn_token')
if authn_token and is_expired(authn_token, 'simpleTokenExpires'):
authn_token = None
if not authn_token:
- mso_id = self.get_param('ap_mso')
- if mso_id:
- username, password = self._get_login_info('ap_username', 'ap_password', mso_id)
- if not username or not password:
- raise_mvpd_required()
- mso_info = MSO_INFO[mso_id]
-
- provider_redirect_page_res = self._download_webpage_handle(
- self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
- 'Downloading Provider Redirect Page', query={
- 'noflash': 'true',
- 'mso_id': mso_id,
- 'requestor_id': requestor_id,
- 'no_iframe': 'false',
- 'domain_name': 'adobe.com',
- 'redirect_url': url,
- }, headers={
- # yt-dlp's default user-agent is usually too old for Comcast_SSO
- # See: https://github.com/yt-dlp/yt-dlp/issues/10848
- 'User-Agent': self._MODERN_USER_AGENT,
- } if mso_id == 'Comcast_SSO' else None)
- elif not self._cookies_passed:
+ if not mso_id:
+ raise_mvpd_required()
+ username, password = self._get_login_info('ap_username', 'ap_password', mso_id)
+ if not username or not password:
raise_mvpd_required()
- if not mso_id:
- pass
- elif mso_id == 'Comcast_SSO':
+ device_info, urlh = self._download_json_handle(
+ 'https://sp.auth.adobe.com/indiv/devices',
+ video_id, 'Registering device with Adobe',
+ data=json.dumps({'fingerprint': uuid.uuid4().hex}).encode(),
+ headers={'Content-Type': 'application/json; charset=UTF-8'})
+
+ device_id = device_info['deviceId']
+ mvpd_headers['pass_sfp'] = urlh.get_header('pass_sfp')
+ mvpd_headers['Ap_21'] = device_id
+
+ registration = self._download_json(
+ 'https://sp.auth.adobe.com/o/client/register',
+ video_id, 'Registering client with Adobe',
+ data=json.dumps({'software_statement': software_statement}).encode(),
+ headers={'Content-Type': 'application/json; charset=UTF-8'})
+
+ access_token = self._download_json(
+ 'https://sp.auth.adobe.com/o/client/token', video_id,
+ 'Obtaining access token', data=urlencode_postdata({
+ 'grant_type': 'client_credentials',
+ 'client_id': registration['client_id'],
+ 'client_secret': registration['client_secret'],
+ }),
+ headers={
+ 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+ })['access_token']
+ mvpd_headers['Authorization'] = f'Bearer {access_token}'
+
+ reg_code = self._download_json(
+ f'https://sp.auth.adobe.com/reggie/v1/{requestor_id}/regcode',
+ video_id, 'Obtaining registration code',
+ data=urlencode_postdata({
+ 'requestor': requestor_id,
+ 'deviceId': device_id,
+ 'format': 'json',
+ }),
+ headers={
+ 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+ 'Authorization': f'Bearer {access_token}',
+ })['code']
+
+ provider_redirect_page_res = self._download_webpage_handle(
+ self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
+ 'Downloading Provider Redirect Page', query={
+ 'noflash': 'true',
+ 'mso_id': mso_id,
+ 'requestor_id': requestor_id,
+ 'no_iframe': 'false',
+ 'domain_name': 'adobe.com',
+ 'redirect_url': url,
+ 'reg_code': reg_code,
+ }, headers=self._get_mso_headers(mso_info))
+
+ if mso_id == 'Comcast_SSO':
# Comcast page flow varies by video site and whether you
# are on Comcast's network.
provider_redirect_page, urlh = provider_redirect_page_res
@@ -1489,8 +1557,8 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
oauth_redirect_url = extract_redirect_url(
provider_redirect_page, fatal=True)
provider_login_page_res = self._download_webpage_handle(
- oauth_redirect_url, video_id,
- self._DOWNLOADING_LOGIN_PAGE)
+ oauth_redirect_url, video_id, self._DOWNLOADING_LOGIN_PAGE,
+ headers=self._get_mso_headers(mso_info))
else:
provider_login_page_res = post_form(
provider_redirect_page_res,
@@ -1500,7 +1568,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
- })
+ }, validate_url=True)
mvpd_confirm_page, urlh = mvpd_confirm_page_res
if '' in mvpd_confirm_page:
post_form(mvpd_confirm_page_res, 'Confirming Login')
@@ -1539,7 +1607,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
provider_redirect_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
- })
+ }, validate_url=True)
saml_login_page, urlh = saml_login_page_res
if 'Please try again.' in saml_login_page:
raise ExtractorError(
@@ -1560,7 +1628,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
[saml_login_page, saml_redirect_url], 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
- })
+ }, validate_url=True)
if 'Please try again.' in saml_login_page:
raise ExtractorError(
'Failed to login, incorrect User ID or Password.')
@@ -1631,7 +1699,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
- })
+ }, validate_url=True)
provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.url)
@@ -1682,7 +1750,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
- })
+ }, validate_url=True)
provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.url)
@@ -1699,6 +1767,27 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
query=hidden_data)
post_form(mvpd_confirm_page_res, 'Confirming Login')
+ elif mso_id == 'Fubo':
+ _, urlh = provider_redirect_page_res
+
+ fubo_response = self._download_json(
+ 'https://api.fubo.tv/partners/tve/connect', video_id,
+ 'Authenticating with Fubo', 'Unable to authenticate with Fubo',
+ query=parse_qs(urlh.url), data=json.dumps({
+ 'username': username,
+ 'password': password,
+ }).encode(), headers={
+ 'Accept': 'application/json',
+ 'Content-Type': 'application/json',
+ })
+
+ self._request_webpage(
+ 'https://sp.auth.adobe.com/adobe-services/oauth2', video_id,
+ 'Authenticating with Adobe', 'Failed to authenticate with Adobe',
+ query={
+ 'code': fubo_response['code'],
+ 'state': fubo_response['state'],
+ })
else:
# Some providers (e.g. DIRECTV NOW) have another meta refresh
# based redirect that should be followed.
@@ -1717,7 +1806,8 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
}
if mso_id in ('Cablevision', 'AlticeOne'):
form_data['_eventId_proceed'] = ''
- mvpd_confirm_page_res = post_form(provider_login_page_res, 'Logging in', form_data)
+ mvpd_confirm_page_res = post_form(
+ provider_login_page_res, 'Logging in', form_data, validate_url=True)
if mso_id != 'Rogers':
post_form(mvpd_confirm_page_res, 'Confirming Login')
@@ -1727,6 +1817,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
'Retrieving Session', data=urlencode_postdata({
'_method': 'GET',
'requestor_id': requestor_id,
+ 'reg_code': reg_code,
}), headers=mvpd_headers)
except ExtractorError as e:
if not mso_id and isinstance(e.cause, HTTPError) and e.cause.status == 401:
@@ -1734,7 +1825,6 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
raise
if 'bravotv|oxygen)\.com/(?:[^/]+/)+(?P[^/?#]+)'
- _TESTS = [{
- 'url': 'https://www.bravotv.com/top-chef/season-16/episode-15/videos/the-top-chef-season-16-winner-is',
- 'info_dict': {
- 'id': '3923059',
- 'ext': 'mp4',
- 'title': 'The Top Chef Season 16 Winner Is...',
- 'description': 'Find out who takes the title of Top Chef!',
- 'upload_date': '20190314',
- 'timestamp': 1552591860,
- 'season_number': 16,
- 'episode_number': 15,
- 'series': 'Top Chef',
- 'episode': 'The Top Chef Season 16 Winner Is...',
- 'duration': 190.357,
- 'season': 'Season 16',
- 'thumbnail': r're:^https://.+\.jpg',
- },
- 'params': {'skip_download': 'm3u8'},
- }, {
- 'url': 'https://www.bravotv.com/top-chef/season-20/episode-1/london-calling',
- 'info_dict': {
- 'id': '9000234570',
- 'ext': 'mp4',
- 'title': 'London Calling',
- 'description': 'md5:5af95a8cbac1856bd10e7562f86bb759',
- 'upload_date': '20230310',
- 'timestamp': 1678410000,
- 'season_number': 20,
- 'episode_number': 1,
- 'series': 'Top Chef',
- 'episode': 'London Calling',
- 'duration': 3266.03,
- 'season': 'Season 20',
- 'chapters': 'count:7',
- 'thumbnail': r're:^https://.+\.jpg',
- 'age_limit': 14,
- },
- 'params': {'skip_download': 'm3u8'},
- 'skip': 'This video requires AdobePass MSO credentials',
- }, {
- 'url': 'https://www.oxygen.com/in-ice-cold-blood/season-1/closing-night',
- 'info_dict': {
- 'id': '3692045',
- 'ext': 'mp4',
- 'title': 'Closing Night',
- 'description': 'md5:3170065c5c2f19548d72a4cbc254af63',
- 'upload_date': '20180401',
- 'timestamp': 1522623600,
- 'season_number': 1,
- 'episode_number': 1,
- 'series': 'In Ice Cold Blood',
- 'episode': 'Closing Night',
- 'duration': 2629.051,
- 'season': 'Season 1',
- 'chapters': 'count:6',
- 'thumbnail': r're:^https://.+\.jpg',
- 'age_limit': 14,
- },
- 'params': {'skip_download': 'm3u8'},
- 'skip': 'This video requires AdobePass MSO credentials',
- }, {
- 'url': 'https://www.oxygen.com/in-ice-cold-blood/season-2/episode-16/videos/handling-the-horwitz-house-after-the-murder-season-2',
- 'info_dict': {
- 'id': '3974019',
- 'ext': 'mp4',
- 'title': '\'Handling The Horwitz House After The Murder (Season 2, Episode 16)',
- 'description': 'md5:f9d638dd6946a1c1c0533a9c6100eae5',
- 'upload_date': '20190617',
- 'timestamp': 1560790800,
- 'season_number': 2,
- 'episode_number': 16,
- 'series': 'In Ice Cold Blood',
- 'episode': '\'Handling The Horwitz House After The Murder (Season 2, Episode 16)',
- 'duration': 68.235,
- 'season': 'Season 2',
- 'thumbnail': r're:^https://.+\.jpg',
- 'age_limit': 14,
- },
- 'params': {'skip_download': 'm3u8'},
- }, {
- 'url': 'https://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
- 'only_matching': True,
- }]
-
- def _real_extract(self, url):
- site, display_id = self._match_valid_url(url).group('site', 'id')
- webpage = self._download_webpage(url, display_id)
- settings = self._search_json(
- r']+data-drupal-selector="drupal-settings-json"[^>]*>', webpage, 'settings', display_id)
- tve = extract_attributes(get_element_html_by_class('tve-video-deck-app', webpage) or '')
- query = {
- 'manifest': 'm3u',
- 'formats': 'm3u,mpeg4',
- }
-
- if tve:
- account_pid = tve.get('data-mpx-media-account-pid') or 'HNK2IC'
- account_id = tve['data-mpx-media-account-id']
- metadata = self._parse_json(
- tve.get('data-normalized-video', ''), display_id, fatal=False, transform_source=unescapeHTML)
- video_id = tve.get('data-guid') or metadata['guid']
- if tve.get('data-entitlement') == 'auth':
- auth = traverse_obj(settings, ('tve_adobe_auth', {dict})) or {}
- site = remove_end(site, 'tv')
- release_pid = tve['data-release-pid']
- resource = self._get_mvpd_resource(
- tve.get('data-adobe-pass-resource-id') or auth.get('adobePassResourceId') or site,
- tve['data-title'], release_pid, tve.get('data-rating'))
- query.update({
- 'switch': 'HLSServiceSecure',
- 'auth': self._extract_mvpd_auth(
- url, release_pid, auth.get('adobePassRequestorId') or site, resource),
- })
-
- else:
- ls_playlist = traverse_obj(settings, ('ls_playlist', ..., {dict}), get_all=False) or {}
- account_pid = ls_playlist.get('mpxMediaAccountPid') or 'PHSl-B'
- account_id = ls_playlist['mpxMediaAccountId']
- video_id = ls_playlist['defaultGuid']
- metadata = traverse_obj(
- ls_playlist, ('videos', lambda _, v: v['guid'] == video_id, {dict}), get_all=False)
-
- tp_url = f'https://link.theplatform.com/s/{account_pid}/media/guid/{account_id}/{video_id}'
- tp_metadata = self._download_json(
- update_url_query(tp_url, {'format': 'preview'}), video_id, fatal=False)
-
- chapters = traverse_obj(tp_metadata, ('chapters', ..., {
- 'start_time': ('startTime', {float_or_none(scale=1000)}),
- 'end_time': ('endTime', {float_or_none(scale=1000)}),
- }))
- # prune pointless single chapters that span the entire duration from short videos
- if len(chapters) == 1 and not traverse_obj(chapters, (0, 'end_time')):
- chapters = None
-
- m3u8_url = self._request_webpage(HEADRequest(
- update_url_query(f'{tp_url}/stream.m3u8', query)), video_id, 'Checking m3u8 URL').url
- if 'mpeg_cenc' in m3u8_url:
- self.report_drm(video_id)
- formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
-
- return {
- 'id': video_id,
- 'formats': formats,
- 'subtitles': subtitles,
- 'chapters': chapters,
- **merge_dicts(traverse_obj(tp_metadata, {
- 'title': 'title',
- 'description': 'description',
- 'duration': ('duration', {float_or_none(scale=1000)}),
- 'timestamp': ('pubDate', {float_or_none(scale=1000)}),
- 'season_number': (('pl1$seasonNumber', 'nbcu$seasonNumber'), {int_or_none}),
- 'episode_number': (('pl1$episodeNumber', 'nbcu$episodeNumber'), {int_or_none}),
- 'series': (('pl1$show', 'nbcu$show'), (None, ...), {str}),
- 'episode': (('title', 'pl1$episodeNumber', 'nbcu$episodeNumber'), {str_or_none}),
- 'age_limit': ('ratings', ..., 'rating', {parse_age_limit}),
- }, get_all=False), traverse_obj(metadata, {
- 'title': 'title',
- 'description': 'description',
- 'duration': ('durationInSeconds', {int_or_none}),
- 'timestamp': ('airDate', {unified_timestamp}),
- 'thumbnail': ('thumbnailUrl', {url_or_none}),
- 'season_number': ('seasonNumber', {int_or_none}),
- 'episode_number': ('episodeNumber', {int_or_none}),
- 'episode': 'episodeTitle',
- 'series': 'show',
- })),
- }
diff --git a/yt_dlp/extractor/brightcove.py b/yt_dlp/extractor/brightcove.py
index 3ada1fd5de..d4ac7a0c28 100644
--- a/yt_dlp/extractor/brightcove.py
+++ b/yt_dlp/extractor/brightcove.py
@@ -923,10 +923,18 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
errors = json_data.get('errors')
if errors and errors[0].get('error_subcode') == 'TVE_AUTH':
custom_fields = json_data['custom_fields']
+ missing_fields = ', '.join(
+ key for key in ('source_url', 'software_statement') if not smuggled_data.get(key))
+ if missing_fields:
+ raise ExtractorError(
+ f'Missing fields in smuggled data: {missing_fields}. '
+ f'This video can be only extracted from the webpage where it is embedded. '
+ f'Pass the URL of the embedding webpage instead of the Brightcove URL', expected=True)
tve_token = self._extract_mvpd_auth(
smuggled_data['source_url'], video_id,
custom_fields['bcadobepassrequestorid'],
- custom_fields['bcadobepassresourceid'])
+ custom_fields['bcadobepassresourceid'],
+ smuggled_data['software_statement'])
json_data = self._download_json(
api_url, video_id, headers={
'Accept': f'application/json;pk={policy_key}',
diff --git a/yt_dlp/extractor/espn.py b/yt_dlp/extractor/espn.py
index 37e74bc08e..ceba024bc3 100644
--- a/yt_dlp/extractor/espn.py
+++ b/yt_dlp/extractor/espn.py
@@ -329,6 +329,7 @@ class WatchESPNIE(AdobePassIE):
}]
_API_KEY = 'ZXNwbiZicm93c2VyJjEuMC4w.ptUt7QxsteaRruuPmGZFaJByOoqKvDP2a5YkInHrc7c'
+ _SOFTWARE_STATEMENT = 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIyZGJmZWM4My03OWE1LTQyNzEtYTVmZC04NTZjYTMxMjRjNjMiLCJuYmYiOjE1NDAyMTI3NjEsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTQwMjEyNzYxfQ.yaK3r4AI2uLVvsyN1GLzqzgzRlxMPtasSaiYYBV0wIstqih5tvjTmeoLmi8Xy9Kp_U7Md-bOffwiyK3srHkpUkhhwXLH2x6RPjmS1tPmhaG7-3LBcHTf2ySPvXhVf7cN4ngldawK4tdtLtsw6rF_JoZE2yaC6XbS2F51nXSFEDDnOQWIHEQRG3aYAj-38P2CLGf7g-Yfhbp5cKXeksHHQ90u3eOO4WH0EAjc9oO47h33U8KMEXxJbvjV5J8Va2G2fQSgLDZ013NBI3kQnE313qgqQh2feQILkyCENpB7g-TVBreAjOaH1fU471htSoGGYepcAXv-UDtpgitDiLy7CQ'
def _call_bamgrid_api(self, path, video_id, payload=None, headers={}):
if 'Authorization' not in headers:
@@ -405,8 +406,8 @@ class WatchESPNIE(AdobePassIE):
# TV Provider required
else:
- resource = self._get_mvpd_resource('ESPN', video_data['name'], video_id, None)
- auth = self._extract_mvpd_auth(url, video_id, 'ESPN', resource).encode()
+ resource = self._get_mvpd_resource('espn1', video_data['name'], video_id, None)
+ auth = self._extract_mvpd_auth(url, video_id, 'ESPN', resource, self._SOFTWARE_STATEMENT).encode()
asset = self._download_json(
f'https://watch.auth.api.espn.com/video/auth/media/{video_id}/asset?apikey=uiqlbgzdwuru14v627vdusswb',
diff --git a/yt_dlp/extractor/go.py b/yt_dlp/extractor/go.py
index 83c1979db8..4e138a828f 100644
--- a/yt_dlp/extractor/go.py
+++ b/yt_dlp/extractor/go.py
@@ -7,161 +7,157 @@ from ..utils import (
int_or_none,
join_nonempty,
parse_age_limit,
- remove_end,
- remove_start,
- traverse_obj,
- try_get,
unified_timestamp,
urlencode_postdata,
)
+from ..utils.traversal import traverse_obj
class GoIE(AdobePassIE):
_SITE_INFO = {
'abc': {
'brand': '001',
- 'requestor_id': 'ABC',
+ 'requestor_id': 'dtci',
+ 'provider_id': 'ABC',
+ 'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI4OTcwMjlkYS0yYjM1LTQyOWUtYWQ0NS02ZjZiZjVkZTdhOTUiLCJuYmYiOjE2MjAxNzM5NjksImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNjIwMTczOTY5fQ.SC69DVJWSL8sIe-vVUrP6xS_kzHKqwz9PdKYexs_y-f7Vin6mM-7S-W1TE_-K55O0pyf-TL4xYgvm6LIye8CckG-nZfVwNPV4huduov0jmIcxCQFeUwkHULG2IaA44wfBVUBdaHgkhPweZ2amjycO_IXtez-gBXOLbE3B7Gx9j_5ISCFtyVUblThKfoGyQv6KT6t8Vpmc4ZSKCCQp74KWFFypydb9ucego1taW_nQD06Cdf4yByLd6NaTBceMcIKbug9b9gxFm3XBgJ5q3z7KGo1Kr6XalAV5j4m-fQ91wczlTilX8FM4AljMupyRM9mA_aEADILQ4hS79q4SM0w6w',
},
'freeform': {
'brand': '002',
'requestor_id': 'ABCFamily',
- },
- 'watchdisneychannel': {
- 'brand': '004',
- 'resource_id': 'Disney',
- },
- 'watchdisneyjunior': {
- 'brand': '008',
- 'resource_id': 'DisneyJunior',
- },
- 'watchdisneyxd': {
- 'brand': '009',
- 'resource_id': 'DisneyXD',
+ 'provider_id': 'ABCFamily',
+ 'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJhZWM2MGYyNC0xYzRjLTQ1NzQtYjc0Zi03ZmM4N2E5YWMzMzgiLCJuYmYiOjE1ODc2NjU5MjMsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTg3NjY1OTIzfQ.flCn3dhvmvPnWmV0JV8Fm0YFyj07yPez9-n1GFEwVIm_S2wQVWbWyJhqsAyLZVFrhOMZYTqmPS3OHxGwTwXkEYn6PD7o_vIVG3oqi-Xn1m5jRt_Gazw5qEtpat6VE7bvKGSD3ZhcidOrsCk8NcYyq75u61NHDvSl81pcedJjVRVUpsqrEwmo0aVbA0C8PX3ri0mEbGvkMKvHn8E60xp-PSE-VK8SDT0plwPu_TwUszkZ6-_I8_2xcv_WBqcXFkAVg7Q-iNJXgQvmNsrpcrYuLvi6hEH4ZLtoDcXU6MhwTQAJTiHSo8x9aHX1_qFP09CzlNOFQbC2ZEJdP9SvA53SLQ',
},
'disneynow': {
- 'brand': '011',
+ 'brand': '011', # also: '004', '008', '009'
+ 'requestor_id': 'DisneyChannels',
+ 'provider_id': 'DisneyChannels',
+ 'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI1MzAzNTRiOS04NDNiLTRkNjAtYTQ3ZS0yNzk1MzlkOTIyNTciLCJuYmYiOjE1NTg5ODc0NDksImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTU4OTg3NDQ5fQ.Jud6YS6-J2h0h6po0oMheDym0qRTJQGj4kzacrz4DFuEwhcBkkykW6pF5pKuAUJy9HCZ40oDAHe2KcTlDJjCZF5tDaUEfdihakZ9cC_rG7MU-QoRne8qaB_dPDKwGuk-ZyWD8eV3zwTJmbGo8hDxYTEU81YNCxwhyc_BPDr5TYiubbmpP3_pTnXmSpuL58isJ2peSKWlX9BacuXtBY25c_QnPFKk-_EETm7IHkTpDazde1QfHWGu4s4yJpKGk8RVVujVG6h6ELlL-ZeYLilBm7iS7h1TYG1u7fJhyZRL7isaom6NvAzsvN3ngss1fLwt8decP8wzdFHrbYTdTjW8qw',
'resource_id': 'Disney',
},
- 'fxnow.fxnetworks': {
- 'brand': '025',
+ 'fxnetworks': {
+ 'brand': '025', # also: '020'
'requestor_id': 'dtci',
+ 'provider_id': 'fx', # also 'fxx', 'fxm'
+ 'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIzYWRhYWZiNC02OTAxLTRlYzktOTdmNy1lYWZkZTJkODJkN2EiLCJuYmYiOjE1NjIwMjQwNzYsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTYyMDI0MDc2fQ.dhKMpZK50AObbZYrMiYPSfWtzXHUaeMP3jrIY4Cgfvh0GaEgk0Mns_zp78jypFeZgRtPVleQMQDNq2YEloRLcAGqP1aa6WVDglnK77ZWUm4IKai14Rwf3A6YBhSRoO2_lMmUGkuTf6gZY-kMIPqBYKqzTQiQl4HbniPFodIzFRiuI9QJVrkoyTGrJL4oqiX08PoFI3Z-TOti1Heu3EbFC-GveQHhlinYrzU7rbiAqLEz7FImtfBDsnXX1Y3uJDLYM3Bq4Oh0nrzTv1Fd62wNsCNErHHIbELidh1zZF0ujvt7ReuZUwAitm0UhEJ7OxNOUbEQWtae6pVNscvdvTFMpg',
+ },
+ 'nationalgeographic': {
+ 'brand': '026', # also '023'
+ 'requestor_id': 'dtci',
+ 'provider_id': 'ngc', # also 'ngw'
+ 'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIxMzE4YTM1Ni05Mjc4LTQ4NjEtYTFmNi1jMTIzMzg1ZWMzYzMiLCJuYmYiOjE1NjIwMjM4MjgsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTYyMDIzODI4fQ.Le-2OzF9-jrhJ7ZfWtLWk5iSHGVZoxeU1w0_fO--Heli0OwRZsRq2slSmx-oZTzxuWmAgDEiBkWSDcDK6sM25DrCLsdsJa3MBuZ-slBRtH8aq3HpNoqqLkU-vg6gRUEKMtwBUtwCu_9aKUCayYtndWv4b1DjVQeSrteOW5NNudWVYleAe0kxeNJQHo5If9SCzDudKVJktFUjhNks4QPOC_uONPkRRlL9D0fNvtOY-LRFckfcHhf5z9l1iZjeukV0YhdKnuw1wyiaWrQXBUDiBfbkCRd2DM-KnelqPxfiXCaTjGKDURRBO3pz33ebge3IFXSiU5vl4qHQ8xvunzGpFw',
},
}
- _VALID_URL = r'''(?x)
- https?://
- (?P
- (?:{}\.)?go|fxnow\.fxnetworks|
- (?:www\.)?(?:abc|freeform|disneynow)
- )\.com/
- (?:
- (?:[^/]+/)*(?P[Vv][Dd][Kk][Aa]\w+)|
- (?:[^/]+/)*(?P[^/?\#]+)
- )
- '''.format(r'\.|'.join(list(_SITE_INFO.keys())))
+ _URL_PATH_RE = r'(?:video|episode|movies-and-specials)/(?P[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
+ _VALID_URL = [
+ fr'https?://(?:www\.)?(?Pabc)\.com/{_URL_PATH_RE}',
+ fr'https?://(?:www\.)?(?Pfreeform)\.com/{_URL_PATH_RE}',
+ fr'https?://(?:www\.)?(?Pdisneynow)\.com/{_URL_PATH_RE}',
+ fr'https?://fxnow\.(?Pfxnetworks)\.com/{_URL_PATH_RE}',
+ fr'https?://(?:www\.)?(?Pnationalgeographic)\.com/tv/{_URL_PATH_RE}',
+ ]
_TESTS = [{
- 'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
+ 'url': 'https://abc.com/episode/4192c0e6-26e5-47a8-817b-ce8272b9e440/playlist/PL551127435',
'info_dict': {
- 'id': 'VDKA3807643',
+ 'id': 'VDKA10805898',
'ext': 'mp4',
- 'title': 'The Traitor in the White House',
- 'description': 'md5:05b009d2d145a1e85d25111bd37222e8',
- },
- 'params': {
- # m3u8 download
- 'skip_download': True,
- },
- 'skip': 'This content is no longer available.',
- }, {
- 'url': 'https://disneynow.com/shows/big-hero-6-the-series',
- 'info_dict': {
- 'title': 'Doraemon',
- 'id': 'SH55574025',
- },
- 'playlist_mincount': 51,
- }, {
- 'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood',
- 'info_dict': {
- 'id': 'VDKA3609139',
- 'title': 'This Guilty Blood',
- 'description': 'md5:f18e79ad1c613798d95fdabfe96cd292',
+ 'title': 'Switch the Flip',
+ 'description': 'To help get Brian’s life in order, Stewie and Brian swap bodies using a machine that Stewie invents.',
'age_limit': 14,
+ 'duration': 1297,
+ 'thumbnail': r're:https?://.+/.+\.jpg',
+ 'series': 'Family Guy',
+ 'season': 'Season 16',
+ 'season_number': 16,
+ 'episode': 'Episode 17',
+ 'episode_number': 17,
+ 'timestamp': 1746082800.0,
+ 'upload_date': '20250501',
+ },
+ 'params': {'skip_download': 'm3u8'},
+ 'skip': 'This video requires AdobePass MSO credentials',
+ }, {
+ 'url': 'https://disneynow.com/episode/21029660-ba06-4406-adb0-a9a78f6e265e/playlist/PL553044961',
+ 'info_dict': {
+ 'id': 'VDKA39546942',
+ 'ext': 'mp4',
+ 'title': 'Zero Friends Again',
+ 'description': 'Relationships fray under the pressures of a difficult journey.',
+ 'age_limit': 0,
+ 'duration': 1721,
+ 'thumbnail': r're:https?://.+/.+\.jpg',
+ 'series': 'Star Wars: Skeleton Crew',
+ 'season': 'Season 1',
+ 'season_number': 1,
+ 'episode': 'Episode 6',
+ 'episode_number': 6,
+ 'timestamp': 1746946800.0,
+ 'upload_date': '20250511',
+ },
+ 'params': {'skip_download': 'm3u8'},
+ 'skip': 'This video requires AdobePass MSO credentials',
+ }, {
+ 'url': 'https://fxnow.fxnetworks.com/episode/09f4fa6f-c293-469e-aebe-32c9ca5842a7/playlist/PL554408064',
+ 'info_dict': {
+ 'id': 'VDKA38112033',
+ 'ext': 'mp4',
+ 'title': 'The Return of Jerry',
+ 'description': 'The vampires’ long-lost fifth roommate returns. Written by Paul Simms; directed by Kyle Newacheck.',
+ 'age_limit': 17,
+ 'duration': 1493,
+ 'thumbnail': r're:https?://.+/.+\.jpg',
+ 'series': 'What We Do in the Shadows',
+ 'season': 'Season 6',
+ 'season_number': 6,
'episode': 'Episode 1',
- 'upload_date': '20170102',
- 'season': 'Season 2',
- 'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/abcf/Shadowhunters/video/201/ae5f75608d86bf88aa4f9f4aa76ab1b7/579x325-Q100_ae5f75608d86bf88aa4f9f4aa76ab1b7.jpg',
- 'duration': 2544,
- 'season_number': 2,
- 'series': 'Shadowhunters',
'episode_number': 1,
- 'timestamp': 1483387200,
- 'ext': 'mp4',
- },
- 'params': {
- 'geo_bypass_ip_block': '3.244.239.0/24',
- # m3u8 download
- 'skip_download': True,
+ 'timestamp': 1729573200.0,
+ 'upload_date': '20241022',
},
+ 'params': {'skip_download': 'm3u8'},
+ 'skip': 'This video requires AdobePass MSO credentials',
}, {
- 'url': 'https://abc.com/shows/the-rookie/episode-guide/season-04/12-the-knock',
+ 'url': 'https://www.freeform.com/episode/bda0eaf7-761a-4838-aa44-96f794000844/playlist/PL553044961',
'info_dict': {
- 'id': 'VDKA26050359',
- 'title': 'The Knock',
- 'description': 'md5:0c2947e3ada4c31f28296db7db14aa64',
- 'age_limit': 14,
+ 'id': 'VDKA39007340',
'ext': 'mp4',
- 'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/abc/TheRookie/video/412/daf830d06e83b11eaf5c0a299d993ae3/1556x876-Q75_daf830d06e83b11eaf5c0a299d993ae3.jpg',
- 'episode': 'Episode 12',
- 'season_number': 4,
- 'season': 'Season 4',
- 'timestamp': 1642975200,
- 'episode_number': 12,
- 'upload_date': '20220123',
- 'series': 'The Rookie',
- 'duration': 2572,
- },
- 'params': {
- 'geo_bypass_ip_block': '3.244.239.0/24',
- # m3u8 download
- 'skip_download': True,
+ 'title': 'Angel\'s Landing',
+ 'description': 'md5:91bf084e785c968fab16734df7313446',
+ 'age_limit': 14,
+ 'duration': 2523,
+ 'thumbnail': r're:https?://.+/.+\.jpg',
+ 'series': 'How I Escaped My Cult',
+ 'season': 'Season 1',
+ 'season_number': 1,
+ 'episode': 'Episode 2',
+ 'episode_number': 2,
+ 'timestamp': 1740038400.0,
+ 'upload_date': '20250220',
},
+ 'params': {'skip_download': 'm3u8'},
}, {
- 'url': 'https://fxnow.fxnetworks.com/shows/better-things/video/vdka12782841',
+ 'url': 'https://www.nationalgeographic.com/tv/episode/ca694661-1186-41ae-8089-82f64d69b16d/playlist/PL554408064',
'info_dict': {
- 'id': 'VDKA12782841',
- 'title': 'First Look: Better Things - Season 2',
- 'description': 'md5:fa73584a95761c605d9d54904e35b407',
+ 'id': 'VDKA39492078',
'ext': 'mp4',
- 'age_limit': 14,
- 'upload_date': '20170825',
- 'duration': 161,
- 'series': 'Better Things',
- 'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/fx/BetterThings/video/12782841/b6b05e58264121cc2c98811318e6d507/1556x876-Q75_b6b05e58264121cc2c98811318e6d507.jpg',
- 'timestamp': 1503661074,
- },
- 'params': {
- 'geo_bypass_ip_block': '3.244.239.0/24',
- # m3u8 download
- 'skip_download': True,
+ 'title': 'Heart of the Emperors',
+ 'description': 'md5:4fc50a2878f030bb3a7eac9124dca677',
+ 'age_limit': 0,
+ 'duration': 2775,
+ 'thumbnail': r're:https?://.+/.+\.jpg',
+ 'series': 'Secrets of the Penguins',
+ 'season': 'Season 1',
+ 'season_number': 1,
+ 'episode': 'Episode 1',
+ 'episode_number': 1,
+ 'timestamp': 1745204400.0,
+ 'upload_date': '20250421',
},
+ 'params': {'skip_download': 'm3u8'},
}, {
- 'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
+ 'url': 'https://www.freeform.com/movies-and-specials/c38281fc-9f8f-47c7-8220-22394f9df2e1',
'only_matching': True,
}, {
- 'url': 'http://abc.go.com/shows/world-news-tonight/episode-guide/2017-02/17-021717-intense-stand-off-between-man-with-rifle-and-police-in-oakland',
- 'only_matching': True,
- }, {
- # brand 004
- 'url': 'http://disneynow.go.com/shows/big-hero-6-the-series/season-01/episode-10-mr-sparkles-loses-his-sparkle/vdka4637915',
- 'only_matching': True,
- }, {
- # brand 008
- 'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
- 'only_matching': True,
- }, {
- 'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
- 'only_matching': True,
- }, {
- 'url': 'https://www.freeform.com/shows/cruel-summer/episode-guide/season-01/01-happy-birthday-jeanette-turner',
+ 'url': 'https://abc.com/video/219a454a-172c-41bf-878a-d169e6bc0bdc/playlist/PL5523098420',
'only_matching': True,
}]
@@ -171,58 +167,29 @@ class GoIE(AdobePassIE):
f'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/{brand}/001/-1/{show_id}/-1/{video_id}/-1/-1.json',
display_id)['video']
+ def _extract_global_var(self, name, webpage, video_id):
+ return self._search_json(
+ fr'window\[["\']{re.escape(name)}["\']\]\s*=',
+ webpage, f'{name.strip("_")} JSON', video_id)
+
def _real_extract(self, url):
- mobj = self._match_valid_url(url)
- sub_domain = remove_start(remove_end(mobj.group('sub_domain') or '', '.go'), 'www.')
- video_id, display_id = mobj.group('id', 'display_id')
- site_info = self._SITE_INFO.get(sub_domain, {})
- brand = site_info.get('brand')
- if not video_id or not site_info:
- webpage = self._download_webpage(url, display_id or video_id)
- data = self._parse_json(
- self._search_regex(
- r'["\']__abc_com__["\']\s*\]\s*=\s*({.+?})\s*;', webpage,
- 'data', default='{}'),
- display_id or video_id, fatal=False)
- # https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot
- layout = try_get(data, lambda x: x['page']['content']['video']['layout'], dict)
- video_id = None
- if layout:
- video_id = try_get(
- layout,
- (lambda x: x['videoid'], lambda x: x['video']['id']),
- str)
- if not video_id:
- video_id = self._search_regex(
- (
- # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
- # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
- r'data-video-id=["\']*(VDKA\w+)',
- # page.analytics.videoIdCode
- r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\w+)',
- # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
- r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)',
- ), webpage, 'video id', default=video_id)
- if not site_info:
- brand = self._search_regex(
- (r'data-brand=\s*["\']\s*(\d+)',
- r'data-page-brand=\s*["\']\s*(\d+)'), webpage, 'brand',
- default='004')
- site_info = next(
- si for _, si in self._SITE_INFO.items()
- if si.get('brand') == brand)
- if not video_id:
- # show extraction works for Disney, DisneyJunior and DisneyXD
- # ABC and Freeform has different layout
- show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id')
- videos = self._extract_videos(brand, show_id=show_id)
- show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False)
- entries = []
- for video in videos:
- entries.append(self.url_result(
- video['url'], 'Go', video.get('id'), video.get('title')))
- entries.reverse()
- return self.playlist_result(entries, show_id, show_title)
+ site, display_id = self._match_valid_url(url).group('site', 'id')
+ webpage = self._download_webpage(url, display_id)
+ config = self._extract_global_var('__CONFIG__', webpage, display_id)
+ data = self._extract_global_var(config['globalVar'], webpage, display_id)
+ video_id = traverse_obj(data, (
+ 'page', 'content', 'video', 'layout', (('video', 'id'), 'videoid'), {str}, any))
+ if not video_id:
+ video_id = self._search_regex([
+ # data-track-video_id="VDKA39492078"
+ # data-track-video_id_code="vdka39492078"
+ # data-video-id="'VDKA3609139'"
+ r'data-(?:track-)?video[_-]id(?:_code)?=["\']*((?:vdka|VDKA)\d+)',
+ # page.analytics.videoIdCode
+ r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\d+)'], webpage, 'video ID')
+
+ site_info = self._SITE_INFO[site]
+ brand = site_info['brand']
video_data = self._extract_videos(brand, video_id)[0]
video_id = video_data['id']
title = video_data['title']
@@ -238,26 +205,31 @@ class GoIE(AdobePassIE):
if ext == 'm3u8':
video_type = video_data.get('type')
data = {
- 'video_id': video_data['id'],
+ 'video_id': video_id,
'video_type': video_type,
'brand': brand,
'device': '001',
+ 'app_name': 'webplayer-abc',
}
if video_data.get('accesslevel') == '1':
- requestor_id = site_info.get('requestor_id', 'DisneyChannels')
+ provider_id = site_info['provider_id']
+ software_statement = traverse_obj(data, ('app', 'config', (
+ ('features', 'auth', 'softwareStatement'),
+ ('tvAuth', 'SOFTWARE_STATEMENTS', 'PRODUCTION'),
+ ), {str}, any)) or site_info['software_statement']
resource = site_info.get('resource_id') or self._get_mvpd_resource(
- requestor_id, title, video_id, None)
+ provider_id, title, video_id, None)
auth = self._extract_mvpd_auth(
- url, video_id, requestor_id, resource)
+ url, video_id, site_info['requestor_id'], resource, software_statement)
data.update({
'token': auth,
'token_type': 'ap',
- 'adobe_requestor_id': requestor_id,
+ 'adobe_requestor_id': provider_id,
})
else:
self._initialize_geo_bypass({'countries': ['US']})
entitlement = self._download_json(
- 'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
+ 'https://prod.gatekeeper.us-abc.symphony.edgedatg.go.com/vp2/ws-secure/entitlement/2020/playmanifest_secure.json',
video_id, data=urlencode_postdata(data))
errors = entitlement.get('errors', {}).get('errors', [])
if errors:
@@ -267,7 +239,7 @@ class GoIE(AdobePassIE):
error['message'], countries=['US'])
error_message = ', '.join([error['message'] for error in errors])
raise ExtractorError(f'{self.IE_NAME} said: {error_message}', expected=True)
- asset_url += '?' + entitlement['uplynkData']['sessionKey']
+ asset_url += '?' + entitlement['entitlement']['uplynkData']['sessionKey']
fmts, subs = self._extract_m3u8_formats_and_subtitles(
asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False)
formats.extend(fmts)
diff --git a/yt_dlp/extractor/nba.py b/yt_dlp/extractor/nba.py
index 91ae1d14c6..c87046d8ef 100644
--- a/yt_dlp/extractor/nba.py
+++ b/yt_dlp/extractor/nba.py
@@ -19,7 +19,8 @@ from ..utils import (
class NBACVPBaseIE(TurnerBaseIE):
def _extract_nba_cvp_info(self, path, video_id, fatal=False):
return self._extract_cvp_info(
- f'http://secure.nba.com/{path}', video_id, {
+ # XXX: The 3rd argument (None) needs to be the AdobePass software_statement
+ f'http://secure.nba.com/{path}', video_id, None, {
'default': {
'media_src': 'http://nba.cdn.turner.com/nba/big',
},
@@ -94,6 +95,7 @@ class NBAWatchBaseIE(NBACVPBaseIE):
class NBAWatchEmbedIE(NBAWatchBaseIE):
+ _WORKING = False
IE_NAME = 'nba:watch:embed'
_VALID_URL = NBAWatchBaseIE._VALID_URL_BASE + r'embed\?.*?\bid=(?P\d+)'
_TESTS = [{
@@ -115,6 +117,7 @@ class NBAWatchEmbedIE(NBAWatchBaseIE):
class NBAWatchIE(NBAWatchBaseIE):
+ _WORKING = False
IE_NAME = 'nba:watch'
_VALID_URL = NBAWatchBaseIE._VALID_URL_BASE + r'(?:nba/)?video/(?P.+?(?=/index\.html)|(?:[^/]+/)*[^/?#&]+)'
_TESTS = [{
@@ -167,6 +170,7 @@ class NBAWatchIE(NBAWatchBaseIE):
class NBAWatchCollectionIE(NBAWatchBaseIE):
+ _WORKING = False
IE_NAME = 'nba:watch:collection'
_VALID_URL = NBAWatchBaseIE._VALID_URL_BASE + r'list/collection/(?P[^/?#&]+)'
_TESTS = [{
@@ -336,6 +340,7 @@ class NBABaseIE(NBACVPBaseIE):
class NBAEmbedIE(NBABaseIE):
+ _WORKING = False
IE_NAME = 'nba:embed'
_VALID_URL = r'https?://secure\.nba\.com/assets/amp/include/video/(?:topI|i)frame\.html\?.*?\bcontentId=(?P[^?#&]+)'
_TESTS = [{
@@ -358,6 +363,7 @@ class NBAEmbedIE(NBABaseIE):
class NBAIE(NBABaseIE):
+ _WORKING = False
IE_NAME = 'nba'
_VALID_URL = NBABaseIE._VALID_URL_BASE + f'(?!{NBABaseIE._CHANNEL_PATH_REGEX})video/(?P(?:[^/]+/)*[^/?#&]+)'
_TESTS = [{
@@ -385,6 +391,7 @@ class NBAIE(NBABaseIE):
class NBAChannelIE(NBABaseIE):
+ _WORKING = False
IE_NAME = 'nba:channel'
_VALID_URL = NBABaseIE._VALID_URL_BASE + f'(?:{NBABaseIE._CHANNEL_PATH_REGEX})/(?P[^/?#&]+)'
_TESTS = [{
diff --git a/yt_dlp/extractor/nbc.py b/yt_dlp/extractor/nbc.py
index d9aded09ea..bd4862bde0 100644
--- a/yt_dlp/extractor/nbc.py
+++ b/yt_dlp/extractor/nbc.py
@@ -6,7 +6,7 @@ import xml.etree.ElementTree
from .adobepass import AdobePassIE
from .common import InfoExtractor
-from .theplatform import ThePlatformIE, default_ns
+from .theplatform import ThePlatformBaseIE, ThePlatformIE, default_ns
from ..networking import HEADRequest
from ..utils import (
ExtractorError,
@@ -14,26 +14,130 @@ from ..utils import (
UserNotLive,
clean_html,
determine_ext,
+ extract_attributes,
float_or_none,
+ get_element_html_by_class,
int_or_none,
join_nonempty,
+ make_archive_id,
mimetype2ext,
parse_age_limit,
parse_duration,
+ parse_iso8601,
remove_end,
- smuggle_url,
- traverse_obj,
try_get,
unescapeHTML,
unified_timestamp,
update_url_query,
url_basename,
+ url_or_none,
)
+from ..utils.traversal import require, traverse_obj
-class NBCIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
- _VALID_URL = r'https?(?P://(?:www\.)?nbc\.com/(?:classic-tv/)?[^/]+/video/[^/]+/(?P(?:NBCE|n)?\d+))'
+class NBCUniversalBaseIE(ThePlatformBaseIE):
+ _GEO_COUNTRIES = ['US']
+ _GEO_BYPASS = False
+ _M3U8_RE = r'https?://[^/?#]+/prod/[\w-]+/(?P[^?#]+/)cmaf/mpeg_(?:cbcs|cenc)\w*/master_cmaf\w*\.m3u8'
+ def _download_nbcu_smil_and_extract_m3u8_url(self, tp_path, video_id, query):
+ smil = self._download_xml(
+ f'https://link.theplatform.com/s/{tp_path}', video_id,
+ 'Downloading SMIL manifest', 'Failed to download SMIL manifest', query={
+ **query,
+ 'format': 'SMIL', # XXX: Do not confuse "format" with "formats"
+ 'manifest': 'm3u',
+ 'switch': 'HLSServiceSecure', # Or else we get broken mp4 http URLs instead of HLS
+ }, headers=self.geo_verification_headers())
+
+ ns = f'//{{{default_ns}}}'
+ if url := traverse_obj(smil, (f'{ns}video/@src', lambda _, v: determine_ext(v) == 'm3u8', any)):
+ return url
+
+ exc = traverse_obj(smil, (f'{ns}param', lambda _, v: v.get('name') == 'exception', '@value', any))
+ if exc == 'GeoLocationBlocked':
+ self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
+ raise ExtractorError(traverse_obj(smil, (f'{ns}ref/@abstract', ..., any)), expected=exc == 'Expired')
+
+ def _extract_nbcu_formats_and_subtitles(self, tp_path, video_id, query):
+ # formats='mpeg4' will return either a working m3u8 URL or an m3u8 template for non-DRM HLS
+ # formats='m3u+none,mpeg4' may return DRM HLS but w/the "folders" needed for non-DRM template
+ query['formats'] = 'm3u+none,mpeg4'
+ m3u8_url = self._download_nbcu_smil_and_extract_m3u8_url(tp_path, video_id, query)
+
+ if mobj := re.fullmatch(self._M3U8_RE, m3u8_url):
+ query['formats'] = 'mpeg4'
+ m3u8_tmpl = self._download_nbcu_smil_and_extract_m3u8_url(tp_path, video_id, query)
+ # Example: https://vod-lf-oneapp-prd.akamaized.net/prod/video/{folders}master_hls.m3u8
+ if '{folders}' in m3u8_tmpl:
+ self.write_debug('Found m3u8 URL template, formatting URL path')
+ m3u8_url = m3u8_tmpl.format(folders=mobj.group('folders'))
+
+ if '/mpeg_cenc' in m3u8_url or '/mpeg_cbcs' in m3u8_url:
+ self.report_drm(video_id)
+
+ return self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
+
+ def _extract_nbcu_video(self, url, display_id, old_ie_key=None):
+ webpage = self._download_webpage(url, display_id)
+ settings = self._search_json(
+ r']+data-drupal-selector="drupal-settings-json"[^>]*>',
+ webpage, 'settings', display_id)
+
+ query = {}
+ tve = extract_attributes(get_element_html_by_class('tve-video-deck-app', webpage) or '')
+ if tve:
+ account_pid = tve.get('data-mpx-media-account-pid') or tve['data-mpx-account-pid']
+ account_id = tve['data-mpx-media-account-id']
+ metadata = self._parse_json(
+ tve.get('data-normalized-video') or '', display_id, fatal=False, transform_source=unescapeHTML)
+ video_id = tve.get('data-guid') or metadata['guid']
+ if tve.get('data-entitlement') == 'auth':
+ auth = settings['tve_adobe_auth']
+ release_pid = tve['data-release-pid']
+ resource = self._get_mvpd_resource(
+ tve.get('data-adobe-pass-resource-id') or auth['adobePassResourceId'],
+ tve['data-title'], release_pid, tve.get('data-rating'))
+ query['auth'] = self._extract_mvpd_auth(
+ url, release_pid, auth['adobePassRequestorId'],
+ resource, auth['adobePassSoftwareStatement'])
+ else:
+ ls_playlist = traverse_obj(settings, (
+ 'ls_playlist', lambda _, v: v['defaultGuid'], any, {require('LS playlist')}))
+ video_id = ls_playlist['defaultGuid']
+ account_pid = ls_playlist.get('mpxMediaAccountPid') or ls_playlist['mpxAccountPid']
+ account_id = ls_playlist['mpxMediaAccountId']
+ metadata = traverse_obj(ls_playlist, ('videos', lambda _, v: v['guid'] == video_id, any)) or {}
+
+ tp_path = f'{account_pid}/media/guid/{account_id}/{video_id}'
+ formats, subtitles = self._extract_nbcu_formats_and_subtitles(tp_path, video_id, query)
+ tp_metadata = self._download_theplatform_metadata(tp_path, video_id, fatal=False)
+ parsed_info = self._parse_theplatform_metadata(tp_metadata)
+ self._merge_subtitles(parsed_info['subtitles'], target=subtitles)
+
+ return {
+ **parsed_info,
+ **traverse_obj(metadata, {
+ 'title': ('title', {str}),
+ 'description': ('description', {str}),
+ 'duration': ('durationInSeconds', {int_or_none}),
+ 'timestamp': ('airDate', {parse_iso8601}),
+ 'thumbnail': ('thumbnailUrl', {url_or_none}),
+ 'season_number': ('seasonNumber', {int_or_none}),
+ 'episode_number': ('episodeNumber', {int_or_none}),
+ 'episode': ('episodeTitle', {str}),
+ 'series': ('show', {str}),
+ }),
+ 'id': video_id,
+ 'display_id': display_id,
+ 'formats': formats,
+ 'subtitles': subtitles,
+ '_old_archive_ids': [make_archive_id(old_ie_key, video_id)] if old_ie_key else None,
+ }
+
+
+class NBCIE(NBCUniversalBaseIE):
+ _VALID_URL = r'https?(?P://(?:www\.)?nbc\.com/(?:classic-tv/)?[^/?#]+/video/[^/?#]+/(?P\w+))'
_TESTS = [
{
'url': 'http://www.nbc.com/the-tonight-show/video/jimmy-fallon-surprises-fans-at-ben-jerrys/2848237',
@@ -49,47 +153,20 @@ class NBCIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
'episode_number': 86,
'season': 'Season 2',
'season_number': 2,
- 'series': 'Tonight Show: Jimmy Fallon',
- 'duration': 237.0,
- 'chapters': 'count:1',
- 'tags': 'count:4',
+ 'series': 'Tonight',
+ 'duration': 236.504,
+ 'tags': 'count:2',
'thumbnail': r're:https?://.+\.jpg',
'categories': ['Series/The Tonight Show Starring Jimmy Fallon'],
'media_type': 'Full Episode',
+ 'age_limit': 14,
+ '_old_archive_ids': ['theplatform 2848237'],
},
'params': {
'skip_download': 'm3u8',
},
},
{
- 'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
- 'info_dict': {
- 'id': '2832821',
- 'ext': 'mp4',
- 'title': 'Star Wars Teaser',
- 'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
- 'timestamp': 1417852800,
- 'upload_date': '20141206',
- 'uploader': 'NBCU-COM',
- },
- 'skip': 'page not found',
- },
- {
- # HLS streams requires the 'hdnea3' cookie
- 'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
- 'info_dict': {
- 'id': '101528f5a9e8127b107e98c5e6ce4638',
- 'ext': 'mp4',
- 'title': 'Goliath',
- 'description': 'When an unknown soldier saves the life of the King\'s son in battle, he\'s thrust into the limelight and politics of the kingdom.',
- 'timestamp': 1237100400,
- 'upload_date': '20090315',
- 'uploader': 'NBCU-COM',
- },
- 'skip': 'page not found',
- },
- {
- # manifest url does not have extension
'url': 'https://www.nbc.com/the-golden-globe-awards/video/oprah-winfrey-receives-cecil-b-de-mille-award-at-the-2018-golden-globes/3646439',
'info_dict': {
'id': '3646439',
@@ -99,48 +176,47 @@ class NBCIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
'episode_number': 1,
'season': 'Season 75',
'season_number': 75,
- 'series': 'The Golden Globe Awards',
+ 'series': 'Golden Globes',
'description': 'Oprah Winfrey receives the Cecil B. de Mille Award at the 75th Annual Golden Globe Awards.',
'uploader': 'NBCU-COM',
'upload_date': '20180107',
'timestamp': 1515312000,
- 'duration': 570.0,
+ 'duration': 569.703,
'tags': 'count:8',
'thumbnail': r're:https?://.+\.jpg',
- 'chapters': 'count:1',
+ 'media_type': 'Highlight',
+ 'age_limit': 0,
+ 'categories': ['Series/The Golden Globe Awards'],
+ '_old_archive_ids': ['theplatform 3646439'],
},
'params': {
'skip_download': 'm3u8',
},
},
{
- # new video_id format
- 'url': 'https://www.nbc.com/quantum-leap/video/bens-first-leap-nbcs-quantum-leap/NBCE125189978',
+ # Needs to be extracted from webpage instead of GraphQL
+ 'url': 'https://www.nbc.com/paris2024/video/ali-truwit-found-purpose-pool-after-her-life-changed/para24_sww_alitruwittodayshow_240823',
'info_dict': {
- 'id': 'NBCE125189978',
+ 'id': 'para24_sww_alitruwittodayshow_240823',
'ext': 'mp4',
- 'title': 'Ben\'s First Leap | NBC\'s Quantum Leap',
- 'description': 'md5:a82762449b7ec4bb83291a7b355ebf8e',
- 'uploader': 'NBCU-COM',
- 'series': 'Quantum Leap',
- 'season': 'Season 1',
- 'season_number': 1,
- 'episode': 'Ben\'s First Leap | NBC\'s Quantum Leap',
- 'episode_number': 1,
- 'duration': 170.171,
- 'chapters': [],
- 'timestamp': 1663956155,
- 'upload_date': '20220923',
- 'tags': 'count:10',
- 'age_limit': 0,
+ 'title': 'Ali Truwit found purpose in the pool after her life changed',
+ 'description': 'md5:c16d7489e1516593de1cc5d3f39b9bdb',
+ 'uploader': 'NBCU-SPORTS',
+ 'duration': 311.077,
'thumbnail': r're:https?://.+\.jpg',
- 'categories': ['Series/Quantum Leap 2022'],
- 'media_type': 'Highlight',
+ 'episode': 'Ali Truwit found purpose in the pool after her life changed',
+ 'timestamp': 1724435902.0,
+ 'upload_date': '20240823',
+ '_old_archive_ids': ['theplatform para24_sww_alitruwittodayshow_240823'],
},
'params': {
'skip_download': 'm3u8',
},
},
+ {
+ 'url': 'https://www.nbc.com/quantum-leap/video/bens-first-leap-nbcs-quantum-leap/NBCE125189978',
+ 'only_matching': True,
+ },
{
'url': 'https://www.nbc.com/classic-tv/charles-in-charge/video/charles-in-charge-pilot/n3310',
'only_matching': True,
@@ -151,6 +227,7 @@ class NBCIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
'only_matching': True,
},
]
+ _SOFTWARE_STATEMENT = 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI1Yzg2YjdkYy04NDI3LTRjNDUtOGQwZi1iNDkzYmE3MmQwYjQiLCJuYmYiOjE1Nzg3MDM2MzEsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTc4NzAzNjMxfQ.QQKIsBhAjGQTMdAqRTqhcz2Cddr4Y2hEjnSiOeKKki4nLrkDOsjQMmqeTR0hSRarraxH54wBgLvsxI7LHwKMvr7G8QpynNAxylHlQD3yhN9tFhxt4KR5wW3as02B-W2TznK9bhNWPKIyHND95Uo2Mi6rEQoq8tM9O09WPWaanE5BX_-r6Llr6dPq5F0Lpx2QOn2xYRb1T4nFxdFTNoss8GBds8OvChTiKpXMLHegLTc1OS4H_1a8tO_37jDwSdJuZ8iTyRLV4kZ2cpL6OL5JPMObD4-HQiec_dfcYgMKPiIfP9ZqdXpec2SVaCLsWEk86ZYvD97hLIQrK5rrKd1y-A'
def _real_extract(self, url):
permalink, video_id = self._match_valid_url(url).groups()
@@ -196,62 +273,50 @@ class NBCIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
'userId': '0',
}),
})['data']['bonanzaPage']['metadata']
- query = {
- 'mbr': 'true',
- 'manifest': 'm3u',
- 'switch': 'HLSServiceSecure',
- }
+
+ if not video_data:
+ # Some videos are not available via GraphQL API
+ webpage = self._download_webpage(url, video_id)
+ video_data = self._search_json(
+ r'