mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2025-12-15 20:48:58 +00:00
[ie/mtv] Overhaul extractors (#14052)
Adds SouthParkComBrIE and SouthParkCoUkIE Removes these extractors: - CMTIE: migrated to Paramount+ - ComedyCentralTVIE: migrated to Paramount+ - MTVDEIE: migrated to Paramount+ - MTVItaliaIE: migrated to Paramount+ - MTVItaliaProgrammaIE: migrated to Paramount+ - MTVJapanIE: migrated to JP Services - MTVServicesEmbeddedIE: dead domain - MTVVideoIE: migrated to Paramount+ - NickBrIE: redirects to landing page w/o any videos - NickDeIE: redirects to landing page w/o any videos - NickRuIE: redirects to landing page w/o any videos - BellatorIE: migrated to PFL - ParamountNetworkIE: migrated to Paramount+ - SouthParkNlIE: site no longer exists - TVLandIE: migrated to Paramount+ Closes #169, Closes #1711, Closes #1712, Closes #2621, Closes #3167, Closes #3893, Closes #4552, Closes #4702, Closes #4928, Closes #5249, Closes #6156, Closes #8722, Closes #9896, Closes #10168, Closes #12765, Closes #13446, Closes #14009 Authored by: bashonly, doe1080, Randalix, seproDev Co-authored-by: doe1080 <98906116+doe1080@users.noreply.github.com> Co-authored-by: Randalix <23729538+Randalix@users.noreply.github.com> Co-authored-by: sepro <sepro@sepr0.com>
This commit is contained in:
bashonly
@@ -1,652 +1,268 @@
|
||||
import re
|
||||
import xml.etree.ElementTree
|
||||
import base64
|
||||
import json
|
||||
import time
|
||||
import urllib.parse
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..networking import HEADRequest, Request
|
||||
from ..networking.exceptions import HTTPError
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
RegexNotFoundError,
|
||||
find_xpath_attr,
|
||||
fix_xml_ampersands,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
join_nonempty,
|
||||
strip_or_none,
|
||||
timeconvert,
|
||||
try_get,
|
||||
unescapeHTML,
|
||||
js_to_json,
|
||||
jwt_decode_hs256,
|
||||
parse_iso8601,
|
||||
parse_qs,
|
||||
update_url,
|
||||
update_url_query,
|
||||
url_basename,
|
||||
xpath_text,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import require, traverse_obj
|
||||
|
||||
|
||||
def _media_xml_tag(tag):
|
||||
return f'{{http://search.yahoo.com/mrss/}}{tag}'
|
||||
|
||||
|
||||
class MTVServicesInfoExtractor(InfoExtractor):
|
||||
_MOBILE_TEMPLATE = None
|
||||
_LANG = None
|
||||
class MTVServicesBaseIE(InfoExtractor):
|
||||
_GEO_BYPASS = False
|
||||
_GEO_COUNTRIES = ['US']
|
||||
_CACHE_SECTION = 'mtvservices'
|
||||
_ACCESS_TOKEN_KEY = 'access'
|
||||
_REFRESH_TOKEN_KEY = 'refresh'
|
||||
_MEDIA_TOKEN_KEY = 'media'
|
||||
_token_cache = {}
|
||||
|
||||
@staticmethod
|
||||
def _id_from_uri(uri):
|
||||
return uri.split(':')[-1]
|
||||
def _jwt_is_expired(token):
|
||||
return jwt_decode_hs256(token)['exp'] - time.time() < 120
|
||||
|
||||
@staticmethod
|
||||
def _remove_template_parameter(url):
|
||||
# Remove the templates, like &device={device}
|
||||
return re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', url)
|
||||
def _get_auth_suite_data(config):
|
||||
return traverse_obj(config, {
|
||||
'clientId': ('clientId', {str}),
|
||||
'countryCode': ('countryCode', {str}),
|
||||
})
|
||||
|
||||
def _get_feed_url(self, uri, url=None):
|
||||
return self._FEED_URL
|
||||
|
||||
def _get_thumbnail_url(self, uri, itemdoc):
|
||||
search_path = '{}/{}'.format(_media_xml_tag('group'), _media_xml_tag('thumbnail'))
|
||||
thumb_node = itemdoc.find(search_path)
|
||||
if thumb_node is None:
|
||||
return None
|
||||
return thumb_node.get('url') or thumb_node.text or None
|
||||
|
||||
def _extract_mobile_video_formats(self, mtvn_id):
|
||||
webpage_url = self._MOBILE_TEMPLATE % mtvn_id
|
||||
req = Request(webpage_url)
|
||||
# Otherwise we get a webpage that would execute some javascript
|
||||
req.headers['User-Agent'] = 'curl/7'
|
||||
webpage = self._download_webpage(req, mtvn_id,
|
||||
'Downloading mobile page')
|
||||
metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url'))
|
||||
req = HEADRequest(metrics_url)
|
||||
response = self._request_webpage(req, mtvn_id, 'Resolving url')
|
||||
url = response.url
|
||||
# Transform the url to get the best quality:
|
||||
url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, count=1)
|
||||
return [{'url': url, 'ext': 'mp4'}]
|
||||
|
||||
def _extract_video_formats(self, mdoc, mtvn_id, video_id):
|
||||
if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4|copyright_error\.flv(?:\?geo\b.+?)?)$', mdoc.find('.//src').text) is not None:
|
||||
if mtvn_id is not None and self._MOBILE_TEMPLATE is not None:
|
||||
self.to_screen('The normal version is not available from your '
|
||||
'country, trying with the mobile version')
|
||||
return self._extract_mobile_video_formats(mtvn_id)
|
||||
raise ExtractorError('This video is not available from your country.',
|
||||
expected=True)
|
||||
|
||||
formats = []
|
||||
for rendition in mdoc.findall('.//rendition'):
|
||||
if rendition.get('method') == 'hls':
|
||||
hls_url = rendition.find('./src').text
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
hls_url, video_id, ext='mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
else:
|
||||
# fms
|
||||
try:
|
||||
_, _, ext = rendition.attrib['type'].partition('/')
|
||||
rtmp_video_url = rendition.find('./src').text
|
||||
if 'error_not_available.swf' in rtmp_video_url:
|
||||
raise ExtractorError(
|
||||
f'{self.IE_NAME} said: video is not available',
|
||||
expected=True)
|
||||
if rtmp_video_url.endswith('siteunavail.png'):
|
||||
continue
|
||||
formats.extend([{
|
||||
'ext': 'flv' if rtmp_video_url.startswith('rtmp') else ext,
|
||||
'url': rtmp_video_url,
|
||||
'format_id': join_nonempty(
|
||||
'rtmp' if rtmp_video_url.startswith('rtmp') else None,
|
||||
rendition.get('bitrate')),
|
||||
'width': int(rendition.get('width')),
|
||||
'height': int(rendition.get('height')),
|
||||
}])
|
||||
except (KeyError, TypeError):
|
||||
raise ExtractorError('Invalid rendition field.')
|
||||
return formats
|
||||
|
||||
def _extract_subtitles(self, mdoc, mtvn_id):
|
||||
subtitles = {}
|
||||
for transcript in mdoc.findall('.//transcript'):
|
||||
if transcript.get('kind') != 'captions':
|
||||
continue
|
||||
lang = transcript.get('srclang')
|
||||
for typographic in transcript.findall('./typographic'):
|
||||
sub_src = typographic.get('src')
|
||||
if not sub_src:
|
||||
continue
|
||||
ext = typographic.get('format')
|
||||
if ext == 'cea-608':
|
||||
ext = 'scc'
|
||||
subtitles.setdefault(lang, []).append({
|
||||
'url': str(sub_src),
|
||||
'ext': ext,
|
||||
})
|
||||
return subtitles
|
||||
|
||||
def _get_video_info(self, itemdoc, use_hls=True):
|
||||
uri = itemdoc.find('guid').text
|
||||
video_id = self._id_from_uri(uri)
|
||||
self.report_extraction(video_id)
|
||||
content_el = itemdoc.find('{}/{}'.format(_media_xml_tag('group'), _media_xml_tag('content')))
|
||||
mediagen_url = self._remove_template_parameter(content_el.attrib['url'])
|
||||
mediagen_url = mediagen_url.replace('device={device}', '')
|
||||
if 'acceptMethods' not in mediagen_url:
|
||||
mediagen_url += '&' if '?' in mediagen_url else '?'
|
||||
mediagen_url += 'acceptMethods='
|
||||
mediagen_url += 'hls' if use_hls else 'fms'
|
||||
|
||||
mediagen_doc = self._download_xml(
|
||||
mediagen_url, video_id, 'Downloading video urls', fatal=False)
|
||||
|
||||
if not isinstance(mediagen_doc, xml.etree.ElementTree.Element):
|
||||
return None
|
||||
|
||||
item = mediagen_doc.find('./video/item')
|
||||
if item is not None and item.get('type') == 'text':
|
||||
message = f'{self.IE_NAME} returned error: '
|
||||
if item.get('code') is not None:
|
||||
message += '{} - '.format(item.get('code'))
|
||||
message += item.text
|
||||
raise ExtractorError(message, expected=True)
|
||||
|
||||
description = strip_or_none(xpath_text(itemdoc, 'description'))
|
||||
|
||||
timestamp = timeconvert(xpath_text(itemdoc, 'pubDate'))
|
||||
|
||||
title_el = None
|
||||
if title_el is None:
|
||||
title_el = find_xpath_attr(
|
||||
itemdoc, './/{http://search.yahoo.com/mrss/}category',
|
||||
'scheme', 'urn:mtvn:video_title')
|
||||
if title_el is None:
|
||||
title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
|
||||
if title_el is None:
|
||||
title_el = itemdoc.find('.//title')
|
||||
if title_el.text is None:
|
||||
title_el = None
|
||||
|
||||
title = title_el.text
|
||||
if title is None:
|
||||
raise ExtractorError('Could not find video title')
|
||||
title = title.strip()
|
||||
|
||||
series = find_xpath_attr(
|
||||
itemdoc, './/{http://search.yahoo.com/mrss/}category',
|
||||
'scheme', 'urn:mtvn:franchise')
|
||||
season = find_xpath_attr(
|
||||
itemdoc, './/{http://search.yahoo.com/mrss/}category',
|
||||
'scheme', 'urn:mtvn:seasonN')
|
||||
episode = find_xpath_attr(
|
||||
itemdoc, './/{http://search.yahoo.com/mrss/}category',
|
||||
'scheme', 'urn:mtvn:episodeN')
|
||||
series = series.text if series is not None else None
|
||||
season = season.text if season is not None else None
|
||||
episode = episode.text if episode is not None else None
|
||||
if season and episode:
|
||||
# episode number includes season, so remove it
|
||||
episode = re.sub(rf'^{season}', '', episode)
|
||||
|
||||
# This a short id that's used in the webpage urls
|
||||
mtvn_id = None
|
||||
mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category',
|
||||
'scheme', 'urn:mtvn:id')
|
||||
if mtvn_id_node is not None:
|
||||
mtvn_id = mtvn_id_node.text
|
||||
|
||||
formats = self._extract_video_formats(mediagen_doc, mtvn_id, video_id)
|
||||
|
||||
# Some parts of complete video may be missing (e.g. missing Act 3 in
|
||||
# http://www.southpark.de/alle-episoden/s14e01-sexual-healing)
|
||||
if not formats:
|
||||
return None
|
||||
|
||||
return {
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'subtitles': self._extract_subtitles(mediagen_doc, mtvn_id),
|
||||
'id': video_id,
|
||||
'thumbnail': self._get_thumbnail_url(uri, itemdoc),
|
||||
'description': description,
|
||||
'duration': float_or_none(content_el.attrib.get('duration')),
|
||||
'timestamp': timestamp,
|
||||
'series': series,
|
||||
'season_number': int_or_none(season),
|
||||
'episode_number': int_or_none(episode),
|
||||
def _call_auth_api(self, path, config, display_id=None, note=None, data=None, headers=None, query=None):
|
||||
headers = {
|
||||
'Accept': 'application/json',
|
||||
'Client-Description': 'deviceName=Chrome Windows;deviceType=desktop;system=Windows NT 10.0',
|
||||
'Api-Version': '2025-07-09',
|
||||
**(headers or {}),
|
||||
}
|
||||
if data is not None:
|
||||
headers['Content-Type'] = 'application/json'
|
||||
if isinstance(data, dict):
|
||||
data = json.dumps(data, separators=(',', ':')).encode()
|
||||
|
||||
def _get_feed_query(self, uri):
|
||||
data = {'uri': uri}
|
||||
if self._LANG:
|
||||
data['lang'] = self._LANG
|
||||
return data
|
||||
return self._download_json(
|
||||
f'https://auth.mtvnservices.com/{path}', display_id,
|
||||
note=note or 'Calling authentication API', data=data,
|
||||
headers=headers, query={**self._get_auth_suite_data(config), **(query or {})})
|
||||
|
||||
def _get_videos_info(self, uri, use_hls=True, url=None):
|
||||
video_id = self._id_from_uri(uri)
|
||||
feed_url = self._get_feed_url(uri, url)
|
||||
info_url = update_url_query(feed_url, self._get_feed_query(uri))
|
||||
return self._get_videos_info_from_url(info_url, video_id, use_hls)
|
||||
def _get_fresh_access_token(self, config, display_id=None, force_refresh=False):
|
||||
resource_id = config['resourceId']
|
||||
# resource_id should already be in _token_cache since _get_media_token is the caller
|
||||
tokens = self._token_cache[resource_id]
|
||||
|
||||
def _get_videos_info_from_url(self, url, video_id, use_hls=True):
|
||||
idoc = self._download_xml(
|
||||
url, video_id,
|
||||
'Downloading info', transform_source=fix_xml_ampersands)
|
||||
access_token = tokens.get(self._ACCESS_TOKEN_KEY)
|
||||
if not force_refresh and access_token and not self._jwt_is_expired(access_token):
|
||||
return access_token
|
||||
|
||||
title = xpath_text(idoc, './channel/title')
|
||||
description = xpath_text(idoc, './channel/description')
|
||||
if self._REFRESH_TOKEN_KEY not in tokens:
|
||||
response = self._call_auth_api(
|
||||
'accessToken', config, display_id, 'Retrieving auth tokens', data=b'')
|
||||
else:
|
||||
response = self._call_auth_api(
|
||||
'accessToken/refresh', config, display_id, 'Refreshing auth tokens',
|
||||
data={'refreshToken': tokens[self._REFRESH_TOKEN_KEY]},
|
||||
headers={'Authorization': f'Bearer {access_token}'})
|
||||
|
||||
entries = []
|
||||
for item in idoc.findall('.//item'):
|
||||
info = self._get_video_info(item, use_hls)
|
||||
if info:
|
||||
entries.append(info)
|
||||
tokens[self._ACCESS_TOKEN_KEY] = response['applicationAccessToken']
|
||||
tokens[self._REFRESH_TOKEN_KEY] = response['deviceRefreshToken']
|
||||
self.cache.store(self._CACHE_SECTION, resource_id, tokens)
|
||||
|
||||
# TODO: should be multi-video
|
||||
return self.playlist_result(
|
||||
entries, playlist_title=title, playlist_description=description)
|
||||
return tokens[self._ACCESS_TOKEN_KEY]
|
||||
|
||||
def _extract_triforce_mgid(self, webpage, data_zone=None, video_id=None):
|
||||
triforce_feed = self._parse_json(self._search_regex(
|
||||
r'triforceManifestFeed\s*=\s*({.+?})\s*;\s*\n', webpage,
|
||||
'triforce feed', default='{}'), video_id, fatal=False)
|
||||
def _get_media_token(self, video_config, config, display_id=None):
|
||||
resource_id = config['resourceId']
|
||||
if resource_id in self._token_cache:
|
||||
tokens = self._token_cache[resource_id]
|
||||
else:
|
||||
tokens = self._token_cache[resource_id] = self.cache.load(self._CACHE_SECTION, resource_id) or {}
|
||||
|
||||
data_zone = self._search_regex(
|
||||
r'data-zone=(["\'])(?P<zone>.+?_lc_promo.*?)\1', webpage,
|
||||
'data zone', default=data_zone, group='zone')
|
||||
media_token = tokens.get(self._MEDIA_TOKEN_KEY)
|
||||
if media_token and not self._jwt_is_expired(media_token):
|
||||
return media_token
|
||||
|
||||
feed_url = try_get(
|
||||
triforce_feed, lambda x: x['manifest']['zones'][data_zone]['feed'],
|
||||
str)
|
||||
if not feed_url:
|
||||
return
|
||||
access_token = self._get_fresh_access_token(config, display_id)
|
||||
if not jwt_decode_hs256(access_token).get('accessMethods'):
|
||||
# MTVServices uses a custom AdobePass oauth flow which is incompatible with AdobePassIE
|
||||
mso_id = self.get_param('ap_mso')
|
||||
if not mso_id:
|
||||
raise ExtractorError(
|
||||
'This video is only available for users of participating TV providers. '
|
||||
'Use --ap-mso to specify Adobe Pass Multiple-system operator Identifier and pass '
|
||||
'cookies from a browser session where you are signed-in to your provider.', expected=True)
|
||||
|
||||
feed = self._download_json(feed_url, video_id, fatal=False)
|
||||
if not feed:
|
||||
return
|
||||
auth_suite_data = json.dumps(
|
||||
self._get_auth_suite_data(config), separators=(',', ':')).encode()
|
||||
callback_url = update_url_query(config['callbackURL'], {
|
||||
'authSuiteData': urllib.parse.quote(base64.b64encode(auth_suite_data).decode()),
|
||||
'mvpdCode': mso_id,
|
||||
})
|
||||
auth_url = self._call_auth_api(
|
||||
f'mvpd/{mso_id}/login', config, display_id,
|
||||
'Retrieving provider authentication URL',
|
||||
query={'callbackUrl': callback_url},
|
||||
headers={'Authorization': f'Bearer {access_token}'})['authenticationUrl']
|
||||
res = self._download_webpage_handle(auth_url, display_id, 'Downloading provider auth page')
|
||||
# XXX: The following "provider-specific code" likely only works if mso_id == Comcast_SSO
|
||||
# BEGIN provider-specific code
|
||||
redirect_url = self._search_json(
|
||||
r'initInterstitialRedirect\(', res[0], 'redirect JSON',
|
||||
display_id, transform_source=js_to_json)['continue']
|
||||
urlh = self._request_webpage(redirect_url, display_id, 'Requesting provider redirect page')
|
||||
authorization_code = parse_qs(urlh.url)['authorizationCode'][-1]
|
||||
# END provider-specific code
|
||||
self._call_auth_api(
|
||||
f'access/mvpd/{mso_id}', config, display_id,
|
||||
'Submitting authorization code to MTVNServices',
|
||||
query={'authorizationCode': authorization_code}, data=b'',
|
||||
headers={'Authorization': f'Bearer {access_token}'})
|
||||
access_token = self._get_fresh_access_token(config, display_id, force_refresh=True)
|
||||
|
||||
return try_get(feed, lambda x: x['result']['data']['id'], str)
|
||||
tokens[self._MEDIA_TOKEN_KEY] = self._call_auth_api(
|
||||
'mediaToken', config, display_id, 'Fetching media token', data={
|
||||
'content': {('id' if k == 'videoId' else k): v for k, v in video_config.items()},
|
||||
'resourceId': resource_id,
|
||||
}, headers={'Authorization': f'Bearer {access_token}'})['mediaToken']
|
||||
|
||||
@staticmethod
|
||||
def _extract_child_with_type(parent, t):
|
||||
for c in parent['children']:
|
||||
if c.get('type') == t:
|
||||
return c
|
||||
self.cache.store(self._CACHE_SECTION, resource_id, tokens)
|
||||
return tokens[self._MEDIA_TOKEN_KEY]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
def _extract_mgid(self, webpage):
|
||||
try:
|
||||
# the url can be http://media.mtvnservices.com/fb/{mgid}.swf
|
||||
# or http://media.mtvnservices.com/{mgid}
|
||||
og_url = self._og_search_video_url(webpage)
|
||||
mgid = url_basename(og_url)
|
||||
if mgid.endswith('.swf'):
|
||||
mgid = mgid[:-4]
|
||||
except RegexNotFoundError:
|
||||
mgid = None
|
||||
data = self._download_json(
|
||||
update_url(url, query=None), display_id,
|
||||
query={'json': 'true'})
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, HTTPError) and e.cause.status == 404 and not self.suitable(e.cause.response.url):
|
||||
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
|
||||
raise
|
||||
|
||||
if mgid is None or ':' not in mgid:
|
||||
mgid = self._search_regex(
|
||||
[r'data-mgid="(.*?)"', r'swfobject\.embedSWF\(".*?(mgid:.*?)"'],
|
||||
webpage, 'mgid', default=None)
|
||||
flex_wrapper = traverse_obj(data, (
|
||||
'children', lambda _, v: v['type'] == 'MainContainer',
|
||||
(None, ('children', lambda _, v: v['type'] == 'AviaWrapper')),
|
||||
'children', lambda _, v: v['type'] == 'FlexWrapper', {dict}, any))
|
||||
video_detail = traverse_obj(flex_wrapper, (
|
||||
(None, ('children', lambda _, v: v['type'] == 'AuthSuiteWrapper')),
|
||||
'children', lambda _, v: v['type'] == 'Player',
|
||||
'props', 'videoDetail', {dict}, any))
|
||||
if not video_detail:
|
||||
video_detail = traverse_obj(data, (
|
||||
'children', ..., ('handleTVEAuthRedirection', None),
|
||||
'videoDetail', {dict}, any, {require('video detail')}))
|
||||
|
||||
if not mgid:
|
||||
sm4_embed = self._html_search_meta(
|
||||
'sm4:video:embed', webpage, 'sm4 embed', default='')
|
||||
mgid = self._search_regex(
|
||||
r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None)
|
||||
mgid = video_detail['mgid']
|
||||
video_id = mgid.rpartition(':')[2]
|
||||
service_url = traverse_obj(video_detail, ('videoServiceUrl', {url_or_none}, {update_url(query=None)}))
|
||||
if not service_url:
|
||||
raise ExtractorError('This content is no longer available', expected=True)
|
||||
|
||||
if not mgid:
|
||||
mgid = self._extract_triforce_mgid(webpage)
|
||||
headers = {}
|
||||
if video_detail.get('authRequired'):
|
||||
# The vast majority of provider-locked content has been moved to Paramount+
|
||||
# BetIE is the only extractor that is currently known to reach this code path
|
||||
video_config = traverse_obj(flex_wrapper, (
|
||||
'children', lambda _, v: v['type'] == 'AuthSuiteWrapper',
|
||||
'props', 'videoConfig', {dict}, any, {require('video config')}))
|
||||
config = traverse_obj(data, (
|
||||
'props', 'authSuiteConfig', {dict}, {require('auth suite config')}))
|
||||
headers['X-VIA-TVE-MEDIATOKEN'] = self._get_media_token(video_config, config, display_id)
|
||||
|
||||
if not mgid:
|
||||
data = self._parse_json(self._search_regex(
|
||||
r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None)
|
||||
main_container = self._extract_child_with_type(data, 'MainContainer')
|
||||
ab_testing = self._extract_child_with_type(main_container, 'ABTesting')
|
||||
video_player = self._extract_child_with_type(ab_testing or main_container, 'VideoPlayer')
|
||||
if video_player:
|
||||
mgid = try_get(video_player, lambda x: x['props']['media']['video']['config']['uri'])
|
||||
else:
|
||||
flex_wrapper = self._extract_child_with_type(ab_testing or main_container, 'FlexWrapper')
|
||||
auth_suite_wrapper = self._extract_child_with_type(flex_wrapper, 'AuthSuiteWrapper')
|
||||
player = self._extract_child_with_type(auth_suite_wrapper or flex_wrapper, 'Player')
|
||||
if player:
|
||||
mgid = try_get(player, lambda x: x['props']['videoDetail']['mgid'])
|
||||
stream_info = self._download_json(
|
||||
service_url, video_id, 'Downloading API JSON', 'Unable to download API JSON',
|
||||
query={'clientPlatform': 'desktop'}, headers=headers)['stitchedstream']
|
||||
|
||||
if not mgid:
|
||||
raise ExtractorError('Could not extract mgid')
|
||||
manifest_type = stream_info['manifesttype']
|
||||
if manifest_type == 'hls':
|
||||
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
|
||||
stream_info['source'], video_id, 'mp4', m3u8_id=manifest_type)
|
||||
elif manifest_type == 'dash':
|
||||
formats, subtitles = self._extract_mpd_formats_and_subtitles(
|
||||
stream_info['source'], video_id, mpd_id=manifest_type)
|
||||
else:
|
||||
self.raise_no_formats(f'Unsupported manifest type "{manifest_type}"')
|
||||
formats, subtitles = [], {}
|
||||
|
||||
return mgid
|
||||
|
||||
def _real_extract(self, url):
|
||||
title = url_basename(url)
|
||||
webpage = self._download_webpage(url, title)
|
||||
mgid = self._extract_mgid(webpage)
|
||||
return self._get_videos_info(mgid, url=url)
|
||||
return {
|
||||
**traverse_obj(video_detail, {
|
||||
'title': ('title', {str}),
|
||||
'channel': ('channel', 'name', {str}),
|
||||
'thumbnails': ('images', ..., {'url': ('url', {url_or_none})}),
|
||||
'description': (('fullDescription', 'description'), {str}, any),
|
||||
'series': ('parentEntity', 'title', {str}),
|
||||
'season_number': ('seasonNumber', {int_or_none}),
|
||||
'episode_number': ('episodeAiringOrder', {int_or_none}),
|
||||
'duration': ('duration', 'milliseconds', {float_or_none(scale=1000)}),
|
||||
'timestamp': ((
|
||||
('originalPublishDate', {parse_iso8601}),
|
||||
('publishDate', 'timestamp', {int_or_none})), any),
|
||||
'release_timestamp': ((
|
||||
('originalAirDate', {parse_iso8601}),
|
||||
('airDate', 'timestamp', {int_or_none})), any),
|
||||
}),
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
|
||||
class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
|
||||
IE_NAME = 'mtvservices:embedded'
|
||||
_VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)'
|
||||
_EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media\.mtvnservices\.com/embed/.+?)\1']
|
||||
|
||||
_TEST = {
|
||||
# From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/
|
||||
'url': 'http://media.mtvnservices.com/embed/mgid:uma:video:mtv.com:1043906/cp~vid%3D1043906%26uri%3Dmgid%3Auma%3Avideo%3Amtv.com%3A1043906',
|
||||
'md5': 'cb349b21a7897164cede95bd7bf3fbb9',
|
||||
'info_dict': {
|
||||
'id': '1043906',
|
||||
'ext': 'mp4',
|
||||
'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds',
|
||||
'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.',
|
||||
'timestamp': 1400126400,
|
||||
'upload_date': '20140515',
|
||||
},
|
||||
}
|
||||
|
||||
def _get_feed_url(self, uri, url=None):
|
||||
video_id = self._id_from_uri(uri)
|
||||
config = self._download_json(
|
||||
f'http://media.mtvnservices.com/pmt/e1/access/index.html?uri={uri}&configtype=edge', video_id)
|
||||
return self._remove_template_parameter(config['feedWithQueryParams'])
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = self._match_valid_url(url)
|
||||
mgid = mobj.group('mgid')
|
||||
return self._get_videos_info(mgid)
|
||||
|
||||
|
||||
class MTVIE(MTVServicesInfoExtractor):
|
||||
class MTVIE(MTVServicesBaseIE):
|
||||
IE_NAME = 'mtv'
|
||||
_VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)'
|
||||
_FEED_URL = 'http://www.mtv.com/feeds/mrss/'
|
||||
|
||||
_VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|episodes)/(?P<id>[\da-z]{6})'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.mtv.com/video-clips/vl8qof/unlocking-the-truth-trailer',
|
||||
'md5': '1edbcdf1e7628e414a8c5dcebca3d32b',
|
||||
'url': 'https://www.mtv.com/video-clips/syolsj',
|
||||
'info_dict': {
|
||||
'id': '5e14040d-18a4-47c4-a582-43ff602de88e',
|
||||
'id': '213ea7f8-bac7-4a43-8cd5-8d8cb8c8160f',
|
||||
'ext': 'mp4',
|
||||
'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer',
|
||||
'description': '"Unlocking the Truth" premieres August 17th at 11/10c.',
|
||||
'timestamp': 1468846800,
|
||||
'upload_date': '20160718',
|
||||
'display_id': 'syolsj',
|
||||
'title': 'The Challenge: Vets & New Threats',
|
||||
'description': 'md5:c4d2e90a5fff6463740fbf96b2bb6a41',
|
||||
'duration': 95.0,
|
||||
'thumbnail': r're:https://images\.paramount\.tech/uri/mgid:arc:imageassetref',
|
||||
'series': 'The Challenge',
|
||||
'season': 'Season 41',
|
||||
'season_number': 41,
|
||||
'episode': 'Episode 0',
|
||||
'episode_number': 0,
|
||||
'timestamp': 1753945200,
|
||||
'upload_date': '20250731',
|
||||
'release_timestamp': 1753945200,
|
||||
'release_date': '20250731',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'http://www.mtv.com/full-episodes/94tujl/unlocking-the-truth-gates-of-hell-season-1-ep-101',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.mtv.com/episodes/g8xu7q/teen-mom-2-breaking-the-wall-season-7-ep-713',
|
||||
'only_matching': True,
|
||||
'url': 'https://www.mtv.com/episodes/uzvigh',
|
||||
'info_dict': {
|
||||
'id': '364e8b9e-e415-11ef-b405-16fff45bc035',
|
||||
'ext': 'mp4',
|
||||
'display_id': 'uzvigh',
|
||||
'title': 'CT Tamburello and Johnny Bananas',
|
||||
'description': 'md5:364cea52001e9c13f92784e3365c6606',
|
||||
'channel': 'MTV',
|
||||
'duration': 1260.0,
|
||||
'thumbnail': r're:https://images\.paramount\.tech/uri/mgid:arc:imageassetref',
|
||||
'series': 'Ridiculousness',
|
||||
'season': 'Season 47',
|
||||
'season_number': 47,
|
||||
'episode': 'Episode 19',
|
||||
'episode_number': 19,
|
||||
'timestamp': 1753318800,
|
||||
'upload_date': '20250724',
|
||||
'release_timestamp': 1753318800,
|
||||
'release_date': '20250724',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}]
|
||||
|
||||
|
||||
class MTVJapanIE(MTVServicesInfoExtractor):
|
||||
IE_NAME = 'mtvjapan'
|
||||
_VALID_URL = r'https?://(?:www\.)?mtvjapan\.com/videos/(?P<id>[0-9a-z]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.mtvjapan.com/videos/prayht/fresh-info-cadillac-escalade',
|
||||
'info_dict': {
|
||||
'id': 'bc01da03-6fe5-4284-8880-f291f4e368f5',
|
||||
'ext': 'mp4',
|
||||
'title': '【Fresh Info】Cadillac ESCALADE Sport Edition',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
_GEO_COUNTRIES = ['JP']
|
||||
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
|
||||
|
||||
def _get_feed_query(self, uri):
|
||||
return {
|
||||
'arcEp': 'mtvjapan.com',
|
||||
'mgid': uri,
|
||||
}
|
||||
|
||||
|
||||
class MTVVideoIE(MTVServicesInfoExtractor):
|
||||
IE_NAME = 'mtv:video'
|
||||
_VALID_URL = r'''(?x)^https?://
|
||||
(?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$|
|
||||
m\.mtv\.com/videos/video\.rbml\?.*?id=(?P<mgid>[^&]+))'''
|
||||
|
||||
_FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/'
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
|
||||
'md5': '850f3f143316b1e71fa56a4edfd6e0f8',
|
||||
'info_dict': {
|
||||
'id': '853555',
|
||||
'ext': 'mp4',
|
||||
'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
|
||||
'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
|
||||
'timestamp': 1352610000,
|
||||
'upload_date': '20121111',
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
def _get_thumbnail_url(self, uri, itemdoc):
|
||||
return 'http://mtv.mtvnimages.com/uri/' + uri
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = self._match_valid_url(url)
|
||||
video_id = mobj.group('videoid')
|
||||
uri = mobj.groupdict().get('mgid')
|
||||
if uri is None:
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
# Some videos come from Vevo.com
|
||||
m_vevo = re.search(
|
||||
r'(?s)isVevoVideo = true;.*?vevoVideoId = "(.*?)";', webpage)
|
||||
if m_vevo:
|
||||
vevo_id = m_vevo.group(1)
|
||||
self.to_screen(f'Vevo video detected: {vevo_id}')
|
||||
return self.url_result(f'vevo:{vevo_id}', ie='Vevo')
|
||||
|
||||
uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, 'uri')
|
||||
return self._get_videos_info(uri)
|
||||
|
||||
|
||||
class MTVDEIE(MTVServicesInfoExtractor):
|
||||
_WORKING = False
|
||||
IE_NAME = 'mtv.de'
|
||||
_VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P<id>[0-9a-z]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.mtv.de/musik/videoclips/2gpnv7/Traum',
|
||||
'info_dict': {
|
||||
'id': 'd5d472bc-f5b7-11e5-bffd-a4badb20dab5',
|
||||
'ext': 'mp4',
|
||||
'title': 'Traum',
|
||||
'description': 'Traum',
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'Blocked at Travis CI',
|
||||
}, {
|
||||
# mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97)
|
||||
'url': 'http://www.mtv.de/folgen/6b1ylu/teen-mom-2-enthuellungen-S5-F1',
|
||||
'info_dict': {
|
||||
'id': '1e5a878b-31c5-11e7-a442-0e40cf2fc285',
|
||||
'ext': 'mp4',
|
||||
'title': 'Teen Mom 2',
|
||||
'description': 'md5:dc65e357ef7e1085ed53e9e9d83146a7',
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'Blocked at Travis CI',
|
||||
}, {
|
||||
'url': 'http://www.mtv.de/news/glolix/77491-mtv-movies-spotlight--pixels--teil-3',
|
||||
'info_dict': {
|
||||
'id': 'local_playlist-4e760566473c4c8c5344',
|
||||
'ext': 'mp4',
|
||||
'title': 'Article_mtv-movies-spotlight-pixels-teil-3_short-clips_part1',
|
||||
'description': 'MTV Movies Supercut',
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'Das Video kann zur Zeit nicht abgespielt werden.',
|
||||
}]
|
||||
_GEO_COUNTRIES = ['DE']
|
||||
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
|
||||
|
||||
def _get_feed_query(self, uri):
|
||||
return {
|
||||
'arcEp': 'mtv.de',
|
||||
'mgid': uri,
|
||||
}
|
||||
|
||||
|
||||
class MTVItaliaIE(MTVServicesInfoExtractor):
|
||||
IE_NAME = 'mtv.it'
|
||||
_VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:episodi|video|musica)/(?P<id>[0-9a-z]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.mtv.it/episodi/24bqab/mario-una-serie-di-maccio-capatonda-cavoli-amario-episodio-completo-S1-E1',
|
||||
'info_dict': {
|
||||
'id': '0f0fc78e-45fc-4cce-8f24-971c25477530',
|
||||
'ext': 'mp4',
|
||||
'title': 'Cavoli amario (episodio completo)',
|
||||
'description': 'md5:4962bccea8fed5b7c03b295ae1340660',
|
||||
'series': 'Mario - Una Serie Di Maccio Capatonda',
|
||||
'season_number': 1,
|
||||
'episode_number': 1,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
_GEO_COUNTRIES = ['IT']
|
||||
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
|
||||
|
||||
def _get_feed_query(self, uri):
|
||||
return {
|
||||
'arcEp': 'mtv.it',
|
||||
'mgid': uri,
|
||||
}
|
||||
|
||||
|
||||
class MTVItaliaProgrammaIE(MTVItaliaIE): # XXX: Do not subclass from concrete IE
|
||||
IE_NAME = 'mtv.it:programma'
|
||||
_VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:programmi|playlist)/(?P<id>[0-9a-z]+)'
|
||||
_TESTS = [{
|
||||
# program page: general
|
||||
'url': 'http://www.mtv.it/programmi/s2rppv/mario-una-serie-di-maccio-capatonda',
|
||||
'info_dict': {
|
||||
'id': 'a6f155bc-8220-4640-aa43-9b95f64ffa3d',
|
||||
'title': 'Mario - Una Serie Di Maccio Capatonda',
|
||||
'description': 'md5:72fbffe1f77ccf4e90757dd4e3216153',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# program page: specific season
|
||||
'url': 'http://www.mtv.it/programmi/d9ncjf/mario-una-serie-di-maccio-capatonda-S2',
|
||||
'info_dict': {
|
||||
'id': '4deeb5d8-f272-490c-bde2-ff8d261c6dd1',
|
||||
'title': 'Mario - Una Serie Di Maccio Capatonda - Stagione 2',
|
||||
},
|
||||
'playlist_count': 34,
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# playlist page + redirect
|
||||
'url': 'http://www.mtv.it/playlist/sexy-videos/ilctal',
|
||||
'info_dict': {
|
||||
'id': 'dee8f9ee-756d-493b-bf37-16d1d2783359',
|
||||
'title': 'Sexy Videos',
|
||||
},
|
||||
'playlist_mincount': 145,
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
_GEO_COUNTRIES = ['IT']
|
||||
_FEED_URL = 'http://www.mtv.it/feeds/triforce/manifest/v8'
|
||||
|
||||
def _get_entries(self, title, url):
|
||||
while True:
|
||||
pg = self._search_regex(r'/(\d+)$', url, 'entries', '1')
|
||||
entries = self._download_json(url, title, f'page {pg}')
|
||||
url = try_get(
|
||||
entries, lambda x: x['result']['nextPageURL'], str)
|
||||
entries = try_get(
|
||||
entries, (
|
||||
lambda x: x['result']['data']['items'],
|
||||
lambda x: x['result']['data']['seasons']),
|
||||
list)
|
||||
for entry in entries or []:
|
||||
if entry.get('canonicalURL'):
|
||||
yield self.url_result(entry['canonicalURL'])
|
||||
if not url:
|
||||
break
|
||||
|
||||
def _real_extract(self, url):
|
||||
query = {'url': url}
|
||||
info_url = update_url_query(self._FEED_URL, query)
|
||||
video_id = self._match_id(url)
|
||||
info = self._download_json(info_url, video_id).get('manifest')
|
||||
|
||||
redirect = try_get(
|
||||
info, lambda x: x['newLocation']['url'], str)
|
||||
if redirect:
|
||||
return self.url_result(redirect)
|
||||
|
||||
title = info.get('title')
|
||||
video_id = try_get(
|
||||
info, lambda x: x['reporting']['itemId'], str)
|
||||
parent_id = try_get(
|
||||
info, lambda x: x['reporting']['parentId'], str)
|
||||
|
||||
playlist_url = current_url = None
|
||||
for z in (info.get('zones') or {}).values():
|
||||
if z.get('moduleName') in ('INTL_M304', 'INTL_M209'):
|
||||
info_url = z.get('feed')
|
||||
if z.get('moduleName') in ('INTL_M308', 'INTL_M317'):
|
||||
playlist_url = playlist_url or z.get('feed')
|
||||
if z.get('moduleName') in ('INTL_M300',):
|
||||
current_url = current_url or z.get('feed')
|
||||
|
||||
if not info_url:
|
||||
raise ExtractorError('No info found')
|
||||
|
||||
if video_id == parent_id:
|
||||
video_id = self._search_regex(
|
||||
r'([^\/]+)/[^\/]+$', info_url, 'video_id')
|
||||
|
||||
info = self._download_json(info_url, video_id, 'Show infos')
|
||||
info = try_get(info, lambda x: x['result']['data'], dict)
|
||||
title = title or try_get(
|
||||
info, (
|
||||
lambda x: x['title'],
|
||||
lambda x: x['headline']),
|
||||
str)
|
||||
description = try_get(info, lambda x: x['content'], str)
|
||||
|
||||
if current_url:
|
||||
season = try_get(
|
||||
self._download_json(playlist_url, video_id, 'Seasons info'),
|
||||
lambda x: x['result']['data'], dict)
|
||||
current = try_get(
|
||||
season, lambda x: x['currentSeason'], str)
|
||||
seasons = try_get(
|
||||
season, lambda x: x['seasons'], list) or []
|
||||
|
||||
if current in [s.get('eTitle') for s in seasons]:
|
||||
playlist_url = current_url
|
||||
|
||||
title = re.sub(
|
||||
r'[-|]\s*(?:mtv\s*italia|programma|playlist)',
|
||||
'', title, flags=re.IGNORECASE).strip()
|
||||
|
||||
return self.playlist_result(
|
||||
self._get_entries(title, playlist_url),
|
||||
video_id, title, description)
|
||||
|
||||
Reference in New Issue
Block a user