[extractor/nebula] Remove broken cookie support (#5979)

Authored by: hheimbuerger
Closes #4002
This commit is contained in:
Henrik Heimbuerger 2023-02-17 09:32:55 +01:00 committed by GitHub
parent c61cf091a5
commit d50ea3ce5a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23

View file

@ -1,11 +1,9 @@
import itertools import itertools
import json import json
import time
import urllib.error import urllib.error
import urllib.parse
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ExtractorError, parse_iso8601, try_get from ..utils import ExtractorError, parse_iso8601
_BASE_URL_RE = r'https?://(?:www\.)?(?:watchnebula\.com|nebula\.app|nebula\.tv)' _BASE_URL_RE = r'https?://(?:www\.)?(?:watchnebula\.com|nebula\.app|nebula\.tv)'
@ -15,11 +13,10 @@ class NebulaBaseIE(InfoExtractor):
_nebula_api_token = None _nebula_api_token = None
_nebula_bearer_token = None _nebula_bearer_token = None
_zype_access_token = None
def _perform_nebula_auth(self, username, password): def _perform_nebula_auth(self, username, password):
if not username or not password: if not username or not password:
self.raise_login_required() self.raise_login_required(method='password')
data = json.dumps({'email': username, 'password': password}).encode('utf8') data = json.dumps({'email': username, 'password': password}).encode('utf8')
response = self._download_json( response = self._download_json(
@ -33,38 +30,10 @@ class NebulaBaseIE(InfoExtractor):
note='Logging in to Nebula with supplied credentials', note='Logging in to Nebula with supplied credentials',
errnote='Authentication failed or rejected') errnote='Authentication failed or rejected')
if not response or not response.get('key'): if not response or not response.get('key'):
self.raise_login_required() self.raise_login_required(method='password')
# save nebula token as cookie
self._set_cookie(
'nebula.app', 'nebula-auth',
urllib.parse.quote(
json.dumps({
"apiToken": response["key"],
"isLoggingIn": False,
"isLoggingOut": False,
}, separators=(",", ":"))),
expire_time=int(time.time()) + 86400 * 365,
)
return response['key'] return response['key']
def _retrieve_nebula_api_token(self, username=None, password=None):
"""
Check cookie jar for valid token. Try to authenticate using credentials if no valid token
can be found in the cookie jar.
"""
nebula_cookies = self._get_cookies('https://nebula.app')
nebula_cookie = nebula_cookies.get('nebula-auth')
if nebula_cookie:
self.to_screen('Authenticating to Nebula with token from cookie jar')
nebula_cookie_value = urllib.parse.unquote(nebula_cookie.value)
nebula_api_token = self._parse_json(nebula_cookie_value, None).get('apiToken')
if nebula_api_token:
return nebula_api_token
return self._perform_nebula_auth(username, password)
def _call_nebula_api(self, url, video_id=None, method='GET', auth_type='api', note=''): def _call_nebula_api(self, url, video_id=None, method='GET', auth_type='api', note=''):
assert method in ('GET', 'POST',) assert method in ('GET', 'POST',)
assert auth_type in ('api', 'bearer',) assert auth_type in ('api', 'bearer',)
@ -95,35 +64,24 @@ class NebulaBaseIE(InfoExtractor):
note='Authorizing to Nebula') note='Authorizing to Nebula')
return response['token'] return response['token']
def _fetch_zype_access_token(self): def _fetch_video_formats(self, slug):
""" stream_info = self._call_nebula_api(f'https://content.watchnebula.com/video/{slug}/stream/',
Get a Zype access token, which is required to access video streams -- in our case: to video_id=slug,
generate video URLs. auth_type='bearer',
""" note='Fetching video stream info')
user_object = self._call_nebula_api('https://api.watchnebula.com/api/v1/auth/user/', note='Retrieving Zype access token') manifest_url = stream_info['manifest']
return self._extract_m3u8_formats_and_subtitles(manifest_url, slug)
access_token = try_get(user_object, lambda x: x['zype_auth_info']['access_token'], str)
if not access_token:
if try_get(user_object, lambda x: x['is_subscribed'], bool):
# TODO: Reimplement the same Zype token polling the Nebula frontend implements
# see https://github.com/ytdl-org/youtube-dl/pull/24805#issuecomment-749231532
raise ExtractorError(
'Unable to extract Zype access token from Nebula API authentication endpoint. '
'Open an arbitrary video in a browser with this account to generate a token',
expected=True)
raise ExtractorError('Unable to extract Zype access token from Nebula API authentication endpoint')
return access_token
def _build_video_info(self, episode): def _build_video_info(self, episode):
zype_id = episode['zype_id'] fmts, subs = self._fetch_video_formats(episode['slug'])
zype_video_url = f'https://player.zype.com/embed/{zype_id}.html?access_token={self._zype_access_token}'
channel_slug = episode['channel_slug'] channel_slug = episode['channel_slug']
channel_title = episode['channel_title']
return { return {
'id': episode['zype_id'], 'id': episode['zype_id'],
'display_id': episode['slug'], 'display_id': episode['slug'],
'_type': 'url_transparent', 'formats': fmts,
'ie_key': 'Zype', 'subtitles': subs,
'url': zype_video_url, 'webpage_url': f'https://nebula.tv/{episode["slug"]}',
'title': episode['title'], 'title': episode['title'],
'description': episode['description'], 'description': episode['description'],
'timestamp': parse_iso8601(episode['published_at']), 'timestamp': parse_iso8601(episode['published_at']),
@ -133,27 +91,26 @@ class NebulaBaseIE(InfoExtractor):
'height': key, 'height': key,
} for key, tn in episode['assets']['thumbnail'].items()], } for key, tn in episode['assets']['thumbnail'].items()],
'duration': episode['duration'], 'duration': episode['duration'],
'channel': episode['channel_title'], 'channel': channel_title,
'channel_id': channel_slug, 'channel_id': channel_slug,
'channel_url': f'https://nebula.app/{channel_slug}', 'channel_url': f'https://nebula.tv/{channel_slug}',
'uploader': episode['channel_title'], 'uploader': channel_title,
'uploader_id': channel_slug, 'uploader_id': channel_slug,
'uploader_url': f'https://nebula.app/{channel_slug}', 'uploader_url': f'https://nebula.tv/{channel_slug}',
'series': episode['channel_title'], 'series': channel_title,
'creator': episode['channel_title'], 'creator': channel_title,
} }
def _perform_login(self, username=None, password=None): def _perform_login(self, username=None, password=None):
self._nebula_api_token = self._retrieve_nebula_api_token(username, password) self._nebula_api_token = self._perform_nebula_auth(username, password)
self._nebula_bearer_token = self._fetch_nebula_bearer_token() self._nebula_bearer_token = self._fetch_nebula_bearer_token()
self._zype_access_token = self._fetch_zype_access_token()
class NebulaIE(NebulaBaseIE): class NebulaIE(NebulaBaseIE):
_VALID_URL = rf'{_BASE_URL_RE}/videos/(?P<id>[-\w]+)' _VALID_URL = rf'{_BASE_URL_RE}/videos/(?P<id>[-\w]+)'
_TESTS = [ _TESTS = [
{ {
'url': 'https://nebula.app/videos/that-time-disney-remade-beauty-and-the-beast', 'url': 'https://nebula.tv/videos/that-time-disney-remade-beauty-and-the-beast',
'md5': '14944cfee8c7beeea106320c47560efc', 'md5': '14944cfee8c7beeea106320c47560efc',
'info_dict': { 'info_dict': {
'id': '5c271b40b13fd613090034fd', 'id': '5c271b40b13fd613090034fd',
@ -167,19 +124,17 @@ class NebulaIE(NebulaBaseIE):
'uploader': 'Lindsay Ellis', 'uploader': 'Lindsay Ellis',
'uploader_id': 'lindsayellis', 'uploader_id': 'lindsayellis',
'timestamp': 1533009600, 'timestamp': 1533009600,
'uploader_url': 'https://nebula.app/lindsayellis', 'uploader_url': 'https://nebula.tv/lindsayellis',
'series': 'Lindsay Ellis', 'series': 'Lindsay Ellis',
'average_rating': int,
'display_id': 'that-time-disney-remade-beauty-and-the-beast', 'display_id': 'that-time-disney-remade-beauty-and-the-beast',
'channel_url': 'https://nebula.app/lindsayellis', 'channel_url': 'https://nebula.tv/lindsayellis',
'creator': 'Lindsay Ellis', 'creator': 'Lindsay Ellis',
'duration': 2212, 'duration': 2212,
'view_count': int,
'thumbnail': r're:https://\w+\.cloudfront\.net/[\w-]+\.jpeg?.*', 'thumbnail': r're:https://\w+\.cloudfront\.net/[\w-]+\.jpeg?.*',
}, },
}, },
{ {
'url': 'https://nebula.app/videos/the-logistics-of-d-day-landing-craft-how-the-allies-got-ashore', 'url': 'https://nebula.tv/videos/the-logistics-of-d-day-landing-craft-how-the-allies-got-ashore',
'md5': 'd05739cf6c38c09322422f696b569c23', 'md5': 'd05739cf6c38c09322422f696b569c23',
'info_dict': { 'info_dict': {
'id': '5e7e78171aaf320001fbd6be', 'id': '5e7e78171aaf320001fbd6be',
@ -192,19 +147,17 @@ class NebulaIE(NebulaBaseIE):
'channel_id': 'realengineering', 'channel_id': 'realengineering',
'uploader': 'Real Engineering', 'uploader': 'Real Engineering',
'uploader_id': 'realengineering', 'uploader_id': 'realengineering',
'view_count': int,
'series': 'Real Engineering', 'series': 'Real Engineering',
'average_rating': int,
'display_id': 'the-logistics-of-d-day-landing-craft-how-the-allies-got-ashore', 'display_id': 'the-logistics-of-d-day-landing-craft-how-the-allies-got-ashore',
'creator': 'Real Engineering', 'creator': 'Real Engineering',
'duration': 841, 'duration': 841,
'channel_url': 'https://nebula.app/realengineering', 'channel_url': 'https://nebula.tv/realengineering',
'uploader_url': 'https://nebula.app/realengineering', 'uploader_url': 'https://nebula.tv/realengineering',
'thumbnail': r're:https://\w+\.cloudfront\.net/[\w-]+\.jpeg?.*', 'thumbnail': r're:https://\w+\.cloudfront\.net/[\w-]+\.jpeg?.*',
}, },
}, },
{ {
'url': 'https://nebula.app/videos/money-episode-1-the-draw', 'url': 'https://nebula.tv/videos/money-episode-1-the-draw',
'md5': 'ebe28a7ad822b9ee172387d860487868', 'md5': 'ebe28a7ad822b9ee172387d860487868',
'info_dict': { 'info_dict': {
'id': '5e779ebdd157bc0001d1c75a', 'id': '5e779ebdd157bc0001d1c75a',
@ -217,14 +170,12 @@ class NebulaIE(NebulaBaseIE):
'channel_id': 'tom-scott-presents-money', 'channel_id': 'tom-scott-presents-money',
'uploader': 'Tom Scott Presents: Money', 'uploader': 'Tom Scott Presents: Money',
'uploader_id': 'tom-scott-presents-money', 'uploader_id': 'tom-scott-presents-money',
'uploader_url': 'https://nebula.app/tom-scott-presents-money', 'uploader_url': 'https://nebula.tv/tom-scott-presents-money',
'duration': 825, 'duration': 825,
'channel_url': 'https://nebula.app/tom-scott-presents-money', 'channel_url': 'https://nebula.tv/tom-scott-presents-money',
'view_count': int,
'series': 'Tom Scott Presents: Money', 'series': 'Tom Scott Presents: Money',
'display_id': 'money-episode-1-the-draw', 'display_id': 'money-episode-1-the-draw',
'thumbnail': r're:https://\w+\.cloudfront\.net/[\w-]+\.jpeg?.*', 'thumbnail': r're:https://\w+\.cloudfront\.net/[\w-]+\.jpeg?.*',
'average_rating': int,
'creator': 'Tom Scott Presents: Money', 'creator': 'Tom Scott Presents: Money',
}, },
}, },
@ -251,7 +202,7 @@ class NebulaSubscriptionsIE(NebulaBaseIE):
_VALID_URL = rf'{_BASE_URL_RE}/myshows' _VALID_URL = rf'{_BASE_URL_RE}/myshows'
_TESTS = [ _TESTS = [
{ {
'url': 'https://nebula.app/myshows', 'url': 'https://nebula.tv/myshows',
'playlist_mincount': 1, 'playlist_mincount': 1,
'info_dict': { 'info_dict': {
'id': 'myshows', 'id': 'myshows',
@ -279,7 +230,7 @@ class NebulaChannelIE(NebulaBaseIE):
_VALID_URL = rf'{_BASE_URL_RE}/(?!myshows|videos/)(?P<id>[-\w]+)' _VALID_URL = rf'{_BASE_URL_RE}/(?!myshows|videos/)(?P<id>[-\w]+)'
_TESTS = [ _TESTS = [
{ {
'url': 'https://nebula.app/tom-scott-presents-money', 'url': 'https://nebula.tv/tom-scott-presents-money',
'info_dict': { 'info_dict': {
'id': 'tom-scott-presents-money', 'id': 'tom-scott-presents-money',
'title': 'Tom Scott Presents: Money', 'title': 'Tom Scott Presents: Money',
@ -287,13 +238,13 @@ class NebulaChannelIE(NebulaBaseIE):
}, },
'playlist_count': 5, 'playlist_count': 5,
}, { }, {
'url': 'https://nebula.app/lindsayellis', 'url': 'https://nebula.tv/lindsayellis',
'info_dict': { 'info_dict': {
'id': 'lindsayellis', 'id': 'lindsayellis',
'title': 'Lindsay Ellis', 'title': 'Lindsay Ellis',
'description': 'Enjoy these hottest of takes on Disney, Transformers, and Musicals.', 'description': 'Enjoy these hottest of takes on Disney, Transformers, and Musicals.',
}, },
'playlist_mincount': 100, 'playlist_mincount': 2,
}, },
] ]