Compare commits

...

17 Commits

Author SHA1 Message Date
Mozi
551f3d09d0
Merge 98e034ff8c into 6365e92589 2024-11-16 20:03:47 +01:00
sepro
6365e92589
[ie/bandlab] Add extractors (#11535)
Closes #7750
Authored by: seproDev
2024-11-16 17:56:43 +01:00
Alessandro Campolo
70c55cb08f
[ie/RadioRadicale] Add extractor (#5607)
Authored by: a13ssandr0, pzhlkj6612

Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>
2024-11-16 13:56:15 +01:00
Mozi
98e034ff8c comment about DRM 2024-10-31 01:23:23 +00:00
Mozi
971bf92c06 code style 2024-10-31 01:12:57 +00:00
Mozi
aa512f8b45 merge 'master' 2024-10-31 01:09:27 +00:00
Mozi
81075d168e fix typo; compat code 2024-10-31 01:06:31 +00:00
Mozi
77debf548f FifaContent: no positive redirection detection 2024-10-30 17:42:19 +00:00
Mozi
7f94f2fceb merge 'master' 2024-10-30 17:37:36 +00:00
Mozi
5f6a442047 Rewrite code; DRM content is being only matching 2024-10-30 17:37:09 +00:00
Mozi
76111ea625 merge 'master' 2024-10-28 00:32:14 +00:00
Mozi
ac5c846921 fix usage of self._merge_subtitles 2024-10-28 00:31:56 +00:00
Mozi
3585397c7f add fatal to _call_api 2024-10-18 16:11:54 +00:00
Mozi
dcc4a1672b merge 'master' 2024-10-18 16:03:20 +00:00
Mozi
bb98db29a1 simplify _call_api 2024-10-18 16:03:03 +00:00
Mozi
4e649c6a28 use "getter" in playlist_from_matches() 2024-10-13 10:26:00 +00:00
Mozi
a29bfa3b0c [ie/Fifa] Add extractors 2024-09-30 17:14:06 +00:00
4 changed files with 873 additions and 64 deletions

View File

@ -208,6 +208,10 @@ from .bandcamp import (
BandcampUserIE,
BandcampWeeklyIE,
)
from .bandlab import (
BandlabIE,
BandlabPlaylistIE,
)
from .bannedvideo import BannedVideoIE
from .bbc import (
BBCIE,
@ -642,7 +646,11 @@ from .fc2 import (
FC2LiveIE,
)
from .fczenit import FczenitIE
from .fifa import FifaIE
from .fifa import (
FifaArticleIE,
FifaContentIE,
FifaPlayerIE,
)
from .filmon import (
FilmOnChannelIE,
FilmOnIE,
@ -1649,6 +1657,7 @@ from .radiokapital import (
RadioKapitalIE,
RadioKapitalShowIE,
)
from .radioradicale import RadioRadicaleIE
from .radiozet import RadioZetPodcastIE
from .radlive import (
RadLiveChannelIE,

438
yt_dlp/extractor/bandlab.py Normal file
View File

@ -0,0 +1,438 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
format_field,
int_or_none,
parse_iso8601,
parse_qs,
truncate_string,
url_or_none,
)
from ..utils.traversal import traverse_obj, value
class BandlabBaseIE(InfoExtractor):
def _call_api(self, endpoint, asset_id, **kwargs):
headers = kwargs.pop('headers', None) or {}
return self._download_json(
f'https://www.bandlab.com/api/v1.3/{endpoint}/{asset_id}',
asset_id, headers={
'accept': 'application/json',
'referer': 'https://www.bandlab.com/',
'x-client-id': 'BandLab-Web',
'x-client-version': '10.1.124',
**headers,
}, **kwargs)
def _parse_revision(self, revision_data, url=None):
return {
'vcodec': 'none',
'media_type': 'revision',
'extractor_key': BandlabIE.ie_key(),
'extractor': BandlabIE.IE_NAME,
**traverse_obj(revision_data, {
'webpage_url': (
'id', ({value(url)}, {format_field(template='https://www.bandlab.com/revision/%s')}), filter, any),
'id': (('revisionId', 'id'), {str}, any),
'title': ('song', 'name', {str}),
'track': ('song', 'name', {str}),
'url': ('mixdown', 'file', {url_or_none}),
'thumbnail': ('song', 'picture', 'url', {url_or_none}),
'description': ('description', {str}),
'uploader': ('creator', 'name', {str}),
'uploader_id': ('creator', 'username', {str}),
'timestamp': ('createdOn', {parse_iso8601}),
'duration': ('mixdown', 'duration', {float_or_none}),
'view_count': ('counters', 'plays', {int_or_none}),
'like_count': ('counters', 'likes', {int_or_none}),
'comment_count': ('counters', 'comments', {int_or_none}),
'genres': ('genres', ..., 'name', {str}),
}),
}
def _parse_track(self, track_data, url=None):
return {
'vcodec': 'none',
'media_type': 'track',
'extractor_key': BandlabIE.ie_key(),
'extractor': BandlabIE.IE_NAME,
**traverse_obj(track_data, {
'webpage_url': (
'id', ({value(url)}, {format_field(template='https://www.bandlab.com/post/%s')}), filter, any),
'id': (('revisionId', 'id'), {str}, any),
'url': ('track', 'sample', 'audioUrl', {url_or_none}),
'title': ('track', 'name', {str}),
'track': ('track', 'name', {str}),
'description': ('caption', {str}),
'thumbnail': ('track', 'picture', ('original', 'url'), {url_or_none}, any),
'view_count': ('counters', 'plays', {int_or_none}),
'like_count': ('counters', 'likes', {int_or_none}),
'comment_count': ('counters', 'comments', {int_or_none}),
'duration': ('track', 'sample', 'duration', {float_or_none}),
'uploader': ('creator', 'name', {str}),
'uploader_id': ('creator', 'username', {str}),
'timestamp': ('createdOn', {parse_iso8601}),
}),
}
def _parse_video(self, video_data, url=None):
return {
'media_type': 'video',
'extractor_key': BandlabIE.ie_key(),
'extractor': BandlabIE.IE_NAME,
**traverse_obj(video_data, {
'id': ('id', {str}),
'webpage_url': (
'id', ({value(url)}, {format_field(template='https://www.bandlab.com/post/%s')}), filter, any),
'url': ('video', 'url', {url_or_none}),
'title': ('caption', {lambda x: x.replace('\n', ' ')}, {truncate_string(left=50)}),
'description': ('caption', {str}),
'thumbnail': ('video', 'picture', 'url', {url_or_none}),
'view_count': ('video', 'counters', 'plays', {int_or_none}),
'like_count': ('video', 'counters', 'likes', {int_or_none}),
'comment_count': ('counters', 'comments', {int_or_none}),
'duration': ('video', 'duration', {float_or_none}),
'uploader': ('creator', 'name', {str}),
'uploader_id': ('creator', 'username', {str}),
}),
}
class BandlabIE(BandlabBaseIE):
_VALID_URL = [
r'https?://(?:www\.)?bandlab.com/(?P<url_type>track|post|revision)/(?P<id>[\da-f_-]+)',
r'https?://(?:www\.)?bandlab.com/(?P<url_type>embed)/\?(?:[^#]*&)?id=(?P<id>[\da-f-]+)',
]
_EMBED_REGEX = [rf'<iframe[^>]+src=[\'"](?P<url>{_VALID_URL[1]})[\'"]']
_TESTS = [{
'url': 'https://www.bandlab.com/track/04b37e88dba24967b9dac8eb8567ff39_07d7f906fc96ee11b75e000d3a428fff',
'md5': '46f7b43367dd268bbcf0bbe466753b2c',
'info_dict': {
'id': '02d7f906-fc96-ee11-b75e-000d3a428fff',
'ext': 'm4a',
'uploader_id': 'ender_milze',
'track': 'sweet black',
'description': 'composed by juanjn3737',
'timestamp': 1702171963,
'view_count': int,
'like_count': int,
'duration': 54.629999999999995,
'title': 'sweet black',
'upload_date': '20231210',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/fa082beb-b856-4730-9170-a57e4e32cc2c/',
'genres': ['Lofi'],
'uploader': 'ender milze',
'comment_count': int,
'media_type': 'revision',
},
}, {
# Same track as above but post URL
'url': 'https://www.bandlab.com/post/07d7f906-fc96-ee11-b75e-000d3a428fff',
'md5': '46f7b43367dd268bbcf0bbe466753b2c',
'info_dict': {
'id': '02d7f906-fc96-ee11-b75e-000d3a428fff',
'ext': 'm4a',
'uploader_id': 'ender_milze',
'track': 'sweet black',
'description': 'composed by juanjn3737',
'timestamp': 1702171973,
'view_count': int,
'like_count': int,
'duration': 54.629999999999995,
'title': 'sweet black',
'upload_date': '20231210',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/fa082beb-b856-4730-9170-a57e4e32cc2c/',
'genres': ['Lofi'],
'uploader': 'ender milze',
'comment_count': int,
'media_type': 'revision',
},
}, {
# SharedKey Example
'url': 'https://www.bandlab.com/track/048916c2-c6da-ee11-85f9-6045bd2e11f9?sharedKey=0NNWX8qYAEmI38lWAzCNDA',
'md5': '15174b57c44440e2a2008be9cae00250',
'info_dict': {
'id': '038916c2-c6da-ee11-85f9-6045bd2e11f9',
'ext': 'm4a',
'comment_count': int,
'genres': ['Other'],
'uploader_id': 'user8353034818103753',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/51b18363-da23-4b9b-a29c-2933a3e561ca/',
'timestamp': 1709625771,
'track': 'PodcastMaerchen4b',
'duration': 468.14,
'view_count': int,
'description': 'Podcast: Neues aus der Märchenwelt',
'like_count': int,
'upload_date': '20240305',
'uploader': 'Erna Wageneder',
'title': 'PodcastMaerchen4b',
'media_type': 'revision',
},
}, {
# Different Revision selected
'url': 'https://www.bandlab.com/track/130343fc-148b-ea11-96d2-0003ffd1fc09?revId=110343fc-148b-ea11-96d2-0003ffd1fc09',
'md5': '74e055ef9325d63f37088772fbfe4454',
'info_dict': {
'id': '110343fc-148b-ea11-96d2-0003ffd1fc09',
'ext': 'm4a',
'timestamp': 1588273294,
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/users/b612e533-e4f7-4542-9f50-3fcfd8dd822c/',
'description': 'Final Revision.',
'title': 'Replay ( Instrumental)',
'uploader': 'David R Sparks',
'uploader_id': 'davesnothome69',
'view_count': int,
'comment_count': int,
'track': 'Replay ( Instrumental)',
'genres': ['Rock'],
'upload_date': '20200430',
'like_count': int,
'duration': 279.43,
'media_type': 'revision',
},
}, {
# Video
'url': 'https://www.bandlab.com/post/5cdf9036-3857-ef11-991a-6045bd36e0d9',
'md5': '8caa2ef28e86c1dacf167293cfdbeba9',
'info_dict': {
'id': '5cdf9036-3857-ef11-991a-6045bd36e0d9',
'ext': 'mp4',
'duration': 44.705,
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/videos/67c6cef1-cef6-40d3-831e-a55bc1dcb972/',
'comment_count': int,
'title': 'backing vocals',
'uploader_id': 'marliashya',
'uploader': 'auraa',
'like_count': int,
'description': 'backing vocals',
'media_type': 'video',
},
}, {
# Embed Example
'url': 'https://www.bandlab.com/embed/?blur=false&id=014de0a4-7d82-ea11-a94c-0003ffd19c0f',
'md5': 'a4ad05cb68c54faaed9b0a8453a8cf4a',
'info_dict': {
'id': '014de0a4-7d82-ea11-a94c-0003ffd19c0f',
'ext': 'm4a',
'comment_count': int,
'genres': ['Electronic'],
'uploader': 'Charlie Henson',
'timestamp': 1587328674,
'upload_date': '20200419',
'view_count': int,
'track': 'Positronic Meltdown',
'duration': 318.55,
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/87165bc3-5439-496e-b1f7-a9f13b541ff2/',
'description': 'Checkout my tracks at AOMX http://aomxsounds.com/',
'uploader_id': 'microfreaks',
'title': 'Positronic Meltdown',
'like_count': int,
'media_type': 'revision',
},
}, {
# Track without revisions available
'url': 'https://www.bandlab.com/track/55767ac51789ea11a94c0003ffd1fc09_2f007b0a37b94ec7a69bc25ae15108a5',
'md5': 'f05d68a3769952c2d9257c473e14c15f',
'info_dict': {
'id': '55767ac51789ea11a94c0003ffd1fc09_2f007b0a37b94ec7a69bc25ae15108a5',
'ext': 'm4a',
'track': 'insame',
'like_count': int,
'duration': 84.03,
'title': 'insame',
'view_count': int,
'comment_count': int,
'uploader': 'Sorakime',
'uploader_id': 'sorakime',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/users/572a351a-0f3a-4c6a-ac39-1a5defdeeb1c/',
'timestamp': 1691162128,
'upload_date': '20230804',
'media_type': 'track',
},
}, {
'url': 'https://www.bandlab.com/revision/014de0a4-7d82-ea11-a94c-0003ffd19c0f',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://phantomluigi.github.io/',
'info_dict': {
'id': 'e14223c3-7871-ef11-bdfd-000d3a980db3',
'ext': 'm4a',
'view_count': int,
'upload_date': '20240913',
'uploader_id': 'phantommusicofficial',
'timestamp': 1726194897,
'uploader': 'Phantom',
'comment_count': int,
'genres': ['Progresive Rock'],
'description': 'md5:a38cd668f7a2843295ef284114f18429',
'duration': 225.23,
'like_count': int,
'title': 'Vermilion Pt. 2 (Cover)',
'track': 'Vermilion Pt. 2 (Cover)',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/62b10750-7aef-4f42-ad08-1af52f577e97/',
'media_type': 'revision',
},
}]
def _real_extract(self, url):
display_id, url_type = self._match_valid_url(url).group('id', 'url_type')
qs = parse_qs(url)
revision_id = traverse_obj(qs, (('revId', 'id'), 0, any))
if url_type == 'revision':
revision_id = display_id
revision_data = None
if not revision_id:
post_data = self._call_api(
'posts', display_id, note='Downloading post data',
query=traverse_obj(qs, {'sharedKey': ('sharedKey', 0)}))
revision_id = traverse_obj(post_data, (('revisionId', ('revision', 'id')), {str}, any))
revision_data = traverse_obj(post_data, ('revision', {dict}))
if not revision_data and not revision_id:
post_type = post_data.get('type')
if post_type == 'Video':
return self._parse_video(post_data, url=url)
if post_type == 'Track':
return self._parse_track(post_data, url=url)
raise ExtractorError(f'Could not extract data for post type {post_type!r}')
if not revision_data:
revision_data = self._call_api(
'revisions', revision_id, note='Downloading revision data', query={'edit': 'false'})
return self._parse_revision(revision_data, url=url)
class BandlabPlaylistIE(BandlabBaseIE):
_VALID_URL = [
r'https?://(?:www\.)?bandlab.com/(?:[\w]+/)?(?P<type>albums|collections)/(?P<id>[\da-f-]+)',
r'https?://(?:www\.)?bandlab.com/(?P<type>embed)/collection/\?(?:[^#]*&)?id=(?P<id>[\da-f-]+)',
]
_EMBED_REGEX = [rf'<iframe[^>]+src=[\'"](?P<url>{_VALID_URL[1]})[\'"]']
_TESTS = [{
'url': 'https://www.bandlab.com/davesnothome69/albums/89b79ea6-de42-ed11-b495-00224845aac7',
'info_dict': {
'thumbnail': 'https://bl-prod-images.azureedge.net/v1.3/albums/69507ff3-579a-45be-afca-9e87eddec944/',
'release_date': '20221003',
'title': 'Remnants',
'album': 'Remnants',
'like_count': int,
'album_type': 'LP',
'description': 'A collection of some feel good, rock hits.',
'comment_count': int,
'view_count': int,
'id': '89b79ea6-de42-ed11-b495-00224845aac7',
'uploader': 'David R Sparks',
'uploader_id': 'davesnothome69',
},
'playlist_count': 10,
}, {
'url': 'https://www.bandlab.com/slytheband/collections/955102d4-1040-ef11-86c3-000d3a42581b',
'info_dict': {
'id': '955102d4-1040-ef11-86c3-000d3a42581b',
'timestamp': 1720762659,
'view_count': int,
'title': 'My Shit 🖤',
'uploader_id': 'slytheband',
'uploader': '𝓢𝓛𝓨',
'upload_date': '20240712',
'like_count': int,
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/collections/2c64ca12-b180-4b76-8587-7a8da76bddc8/',
},
'playlist_count': 15,
}, {
# Embeds can contain both albums and collections with the same URL pattern. This is an album
'url': 'https://www.bandlab.com/embed/collection/?id=12cc6f7f-951b-ee11-907c-00224844f303',
'info_dict': {
'id': '12cc6f7f-951b-ee11-907c-00224844f303',
'release_date': '20230706',
'description': 'This is a collection of songs I created when I had an Amiga computer.',
'view_count': int,
'title': 'Mark Salud The Amiga Collection',
'uploader_id': 'mssirmooth1962',
'comment_count': int,
'thumbnail': 'https://bl-prod-images.azureedge.net/v1.3/albums/d618bd7b-0537-40d5-bdd8-61b066e77d59/',
'like_count': int,
'uploader': 'Mark Salud',
'album': 'Mark Salud The Amiga Collection',
'album_type': 'LP',
},
'playlist_count': 24,
}, {
# Tracks without revision id
'url': 'https://www.bandlab.com/embed/collection/?id=e98aafb5-d932-ee11-b8f0-00224844c719',
'info_dict': {
'like_count': int,
'uploader_id': 'sorakime',
'comment_count': int,
'uploader': 'Sorakime',
'view_count': int,
'description': 'md5:4ec31c568a5f5a5a2b17572ea64c3825',
'release_date': '20230812',
'title': 'Art',
'album': 'Art',
'album_type': 'Album',
'id': 'e98aafb5-d932-ee11-b8f0-00224844c719',
'thumbnail': 'https://bl-prod-images.azureedge.net/v1.3/albums/20c890de-e94a-4422-828a-2da6377a13c8/',
},
'playlist_count': 13,
}, {
'url': 'https://www.bandlab.com/albums/89b79ea6-de42-ed11-b495-00224845aac7',
'only_matching': True,
}]
def _entries(self, album_data):
for post in traverse_obj(album_data, ('posts', lambda _, v: v['type'])):
post_type = post['type']
if post_type == 'Revision':
yield self._parse_revision(post.get('revision'))
elif post_type == 'Track':
yield self._parse_track(post)
elif post_type == 'Video':
yield self._parse_video(post)
else:
self.report_warning(f'Skipping unknown post type: "{post_type}"')
def _real_extract(self, url):
playlist_id, playlist_type = self._match_valid_url(url).group('id', 'type')
endpoints = {
'albums': ['albums'],
'collections': ['collections'],
'embed': ['collections', 'albums'],
}.get(playlist_type)
for endpoint in endpoints:
playlist_data = self._call_api(
endpoint, playlist_id, note=f'Downloading {endpoint[:-1]} data',
fatal=False, expected_status=404)
if not playlist_data.get('errorCode'):
playlist_type = endpoint
break
if error_code := playlist_data.get('errorCode'):
raise ExtractorError(f'Could not find playlist data. Error code: "{error_code}"')
return self.playlist_result(
self._entries(playlist_data), playlist_id,
**traverse_obj(playlist_data, {
'title': ('name', {str}),
'description': ('description', {str}),
'uploader': ('creator', 'name', {str}),
'uploader_id': ('creator', 'username', {str}),
'timestamp': ('createdOn', {parse_iso8601}),
'release_date': ('releaseDate', {lambda x: x.replace('-', '')}, filter),
'thumbnail': ('picture', ('original', 'url'), {url_or_none}, any),
'like_count': ('counters', 'likes', {int_or_none}),
'comment_count': ('counters', 'comments', {int_or_none}),
'view_count': ('counters', 'plays', {int_or_none}),
}),
**(traverse_obj(playlist_data, {
'album': ('name', {str}),
'album_type': ('type', {str}),
}) if playlist_type == 'albums' else {}))

View File

@ -1,75 +1,315 @@
import functools
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
determine_ext,
float_or_none,
int_or_none,
traverse_obj,
parse_iso8601,
strip_or_none,
unified_timestamp,
update_url_query,
)
from ..utils.traversal import traverse_obj
class FifaIE(InfoExtractor):
_VALID_URL = r'https?://www\.fifa\.com/fifaplus/(?P<locale>\w{2})/watch/([^#?]+/)?(?P<id>\w+)'
class FifaBaseIE(InfoExtractor):
_HEADERS = {
'content-type': 'application/json; charset=UTF-8',
'x-chili-accept-language': 'en',
'x-chili-api-version': '1.1',
'x-chili-authenticated': 'false',
'x-chili-device-id': 'undefined',
'x-chili-device-profile': 'WEB',
'x-chili-device-store': 'CHILI',
'x-chili-user-country': 'US',
'x-chili-accept-stream-mode': 'multi/codec-compatibility;q=0.8, mono/strict;q=0.7',
'x-chili-avod-compatibility': 'free,free-ads',
'x-chili-manifest-properties': 'subtitles',
'x-chili-streaming-proto': 'https',
}
def _call_api(self, path, video_id, note=None, headers=None, query=None, data=None):
return self._download_json(
f'https://www.plus.fifa.com/{path}', video_id, note, headers={
**self._HEADERS,
**(headers or {}),
}, query=query, data=data)
def _real_initialize(self):
device_info = self._call_api(
'gatekeeper/api/v1/devices/', None, 'Getting device info',
data=json.dumps({
'appVersion': '2.6.93',
'displayName': None,
'model': 'Chrome',
'manufacturer': 'Google Inc.',
'osName': 'Windows',
'osVersion': '10',
'platform': 'Chrome',
'platformVersion': '129.0.0.0',
'architecture': 'unknown',
'profile': 'WEB',
'store': 'CHILI',
'screenWidth': '1920',
'screenHeight': '1080',
}).encode())
self._HEADERS['x-chili-device-id'] = device_info['id']
def _extract_video(self, video_info, video_id):
formats = []
subtitles = {}
for stream_type in [
'hls/cbcs+h265.sdr;q=0.9, hls/cbcs+h264;q=0.5, hls/clear+h264;q=0.4, mp4/;q=0.1',
'mpd/cenc+h264;q=0.9, mpd/clear+h264;q=0.7, mp4/;q=0.1',
]:
session_info = self._call_api(
'flux-capacitor/api/v1/streaming/session', video_id,
'Getting streaming session', headers={'x-chili-accept-stream': stream_type},
data=json.dumps({'videoAssetId': video_info['id'], 'autoPlay': False}).encode())
streams_info = self._call_api(
'flux-capacitor/api/v1/streaming/urls', video_id, 'Getting streaming urls',
headers={'x-chili-streaming-session': session_info['id']})
for playlist_url in traverse_obj(streams_info, (..., 'url')):
ext = determine_ext(playlist_url)
if ext == 'mpd':
fmts, subs = self._extract_mpd_formats_and_subtitles(playlist_url, video_id)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
elif ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(playlist_url, video_id, m3u8_id='hls')
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
else:
raise ExtractorError(f'Unknown playlist URL {playlist_url}', video_id=video_id)
self._remove_duplicate_formats(formats)
return {
'id': video_id,
'title': strip_or_none(video_info['title']),
'duration': float_or_none(video_info.get('duration'), scale=1000),
'formats': formats,
'subtitles': subtitles,
'age_limit': traverse_obj(video_info, ('parental', 'age', {int_or_none})),
'thumbnails': [{
'url': update_url_query(x, {'width': 1408}),
'width': 1408,
} for x in [video_info.get('posterUrl'), video_info.get('wideCoverUrl')] if x],
}
class FifaPlayerIE(FifaBaseIE):
_VALID_URL = r'https?://(www\.)?plus\.fifa\.com/(?:\w{2})/player/(?P<id>[\w-]+)/?\?(?:[^#]+&)?catalogId=(?P<catalog_id>[\w-]+)'
_TESTS = [{
'url': 'https://www.fifa.com/fifaplus/en/watch/7on10qPcnyLajDDU3ntg6y',
'url': 'https://www.plus.fifa.com/en/player/f67b9d46-38c3-4e38-bbf3-89cf14cbcc1a?catalogId=b9c32230-1426-46d0-8448-ca824ae48603&entryPoint=Slider',
'info_dict': {
'id': '7on10qPcnyLajDDU3ntg6y',
'title': 'Italy v France | Final | 2006 FIFA World Cup Germany™ | Full Match Replay',
'description': 'md5:f4520d0ee80529c8ba4134a7d692ff8b',
'id': 'f67b9d46-38c3-4e38-bbf3-89cf14cbcc1a',
'ext': 'mp4',
'categories': ['FIFA Tournaments'],
'thumbnail': 'https://digitalhub.fifa.com/transform/135e2656-3a51-407b-8810-6c34bec5b59b/FMR_2006_Italy_France_Final_Hero',
'duration': 8165,
'release_timestamp': 1152403200,
'release_date': '20060709',
'title': 'Trailer | HD Cutz',
'age_limit': 0,
'duration': 195.84,
'thumbnail': r're:https://cdn\.plus\.fifa\.com//images/public/cms/[/\w-]+\.jpg\?width=1408',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.fifa.com/fifaplus/pt/watch/1cg5r5Qt6Qt12ilkDgb1sV',
'url': 'https://www.plus.fifa.com/en/player/af65939f-bbce-4b8f-8462-5140af533c5f?catalogId=fac6685c-a900-4e78-b5cd-192af5131ffe&entryPoint=Slider',
'md5': '2c4f5c591448d372f6ba85b8f3be37df',
'info_dict': {
'id': '1cg5r5Qt6Qt12ilkDgb1sV',
'title': 'Brazil v Germany | Semi-finals | 2014 FIFA World Cup Brazil™ | Extended Highlights',
'description': 'md5:d908c74ee66322b804ae2e521b02a855',
'id': 'af65939f-bbce-4b8f-8462-5140af533c5f',
'ext': 'mp4',
'categories': ['FIFA Tournaments', 'Highlights'],
'thumbnail': 'https://digitalhub.fifa.com/transform/d8fe6f61-276d-4a73-a7fe-6878a35fd082/FIFAPLS_100EXTHL_2014BRAvGER_TMB',
'duration': 902,
'release_timestamp': 1404777600,
'release_date': '20140708',
'title': 'Trailer | Bravas de Juárez',
'age_limit': 0,
'duration': 73.984,
'thumbnail': r're:https://cdn\.plus\.fifa\.com//images/public/cms/[/\w-]+\.jpg\?width=1408',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.fifa.com/fifaplus/fr/watch/3C6gQH9C2DLwzNx7BMRQdp',
'info_dict': {
'id': '3C6gQH9C2DLwzNx7BMRQdp',
'title': 'Josimar goal against Northern Ireland | Classic Goals',
'description': 'md5:cbe7e7bb52f603c9f1fe9a4780fe983b',
'ext': 'mp4',
'categories': ['FIFA Tournaments', 'Goal'],
'duration': 28,
'thumbnail': 'https://digitalhub.fifa.com/transform/f9301391-f8d9-48b5-823e-c093ac5e3e11/CG_MEN_1986_JOSIMAR',
},
'params': {'skip_download': 'm3u8'},
'url': 'https://plus.fifa.com/en/player/eeebdd38-5d51-4891-8307-ab5dd62c2c32?catalogId=ed3b2dcb-6886-4b34-8ba7-c8800027f7dd',
'only_matching': True,
}]
def _real_extract(self, url):
video_id, locale = self._match_valid_url(url).group('id', 'locale')
webpage = self._download_webpage(url, video_id)
video_id, catalog_id = self._match_valid_url(url).group('id', 'catalog_id')
video_asset = self._call_api(
'flux-capacitor/api/v1/videoasset', video_id,
'Downloading video asset', query={'catalog': catalog_id})
video_info = traverse_obj(video_asset, (lambda _, v: v['id'] == video_id), get_all=False)
if not video_info:
raise ExtractorError('Unable to extract video info')
return self._extract_video(video_info, video_id)
preconnect_link = self._search_regex(
r'<link\b[^>]+\brel\s*=\s*"preconnect"[^>]+href\s*=\s*"([^"]+)"', webpage, 'Preconnect Link')
video_details = self._download_json(
f'{preconnect_link}/sections/videoDetails/{video_id}', video_id, 'Downloading Video Details', fatal=False)
class FifaContentIE(FifaBaseIE):
_VALID_URL = r'https?://(www\.)?plus\.fifa\.com/(?:\w{2})/content/(?P<display_id>[\w-]+)/(?P<id>[\w-]+)/?(?:[#?]|$)'
_TESTS = [{
# from https://www.fifa.com/fifaplus/en/watch/series/48PQFX2J4TiDJcxWOxUPho/2ka5yomq8MBvfxe205zdQ9/6H72309PLWXafBIavvPzPQ#ReadMore
'url': 'https://www.plus.fifa.com/en/content/kariobangi/6f3be63f-76d9-4290-9e60-fd62afa95ed7',
'info_dict': {
'id': '6f3be63f-76d9-4290-9e60-fd62afa95ed7',
'title': 'Kariobangi',
'description': 'md5:b57eb012db2b84d482adedda82faf1c8',
'display_id': 'kariobangi',
'thumbnails': 'count:2',
},
'playlist_count': 0,
}, {
# from https://www.fifa.com/fifaplus/en/watch/series/5Ja1dDLuudkFF95OVHcYBG/5epcWav73zMbjTJh2RxIOt/1NIHdDxPlYodbNobjS1iX5
'url': 'https://www.plus.fifa.com/en/content/hd-cutz/b9c32230-1426-46d0-8448-ca824ae48603',
'info_dict': {
'id': 'b9c32230-1426-46d0-8448-ca824ae48603',
'title': 'HD Cutz',
'description': 'md5:86dd1e6d9b4463b3ccc2063ab3180c44',
'display_id': 'hd-cutz',
'thumbnails': 'count:2',
},
'playlist': [{
'info_dict': {
'id': 'b9c32230-1426-46d0-8448-ca824ae48603',
'ext': 'mp4',
'title': 'Trailer | HD Cutz',
'age_limit': 0,
'duration': 195.840,
'thumbnail': r're:https://cdn\.plus\.fifa\.com//images/public/cms/[/\w-]+\.jpg\?width=1408',
},
}],
'params': {'skip_download': 'm3u8'},
}, {
# from https://www.fifa.com/fifaplus/en/watch/movie/2OFuZ9TGyPH6x7nZsgnVBN
'url': 'https://www.plus.fifa.com/en/content/bravas-de-juarez/fac6685c-a900-4e78-b5cd-192af5131ffe',
'info_dict': {
'id': 'fac6685c-a900-4e78-b5cd-192af5131ffe',
'title': 'Bravas de Juárez',
'description': 'md5:e48e0f56fb27ac334e616976e0e62362',
'display_id': 'bravas-de-juarez',
},
'playlist': [{
'info_dict': {
'id': 'fac6685c-a900-4e78-b5cd-192af5131ffe',
'ext': 'mp4',
'title': 'Trailer | Bravas de Juárez',
'age_limit': 0,
'duration': 73.984,
'thumbnail': r're:https://cdn\.plus\.fifa\.com//images/public/cms/[/\w-]+\.jpg\?width=1408',
},
}],
}]
_WEBPAGE_TESTS = [{
# https://www.plus.fifa.com/en/content/le-moment-the-official-film-of-the-2019-fifa-womens-world-cup/68a89002-0182-4cc7-b858-e548de0fb9cc
'url': 'https://www.fifa.com/fifaplus/en/watch/movie/01ioUo8QHiajSisrvP3ES2',
'info_dict': {
'id': '68a89002-0182-4cc7-b858-e548de0fb9cc',
'title': 'Le Moment',
'description': 'md5:155f0c28ea9de733668d7eb1f7dbcb52',
'display_id': 'le-moment-the-official-film-of-the-2019-fifa-womens-world-cup',
},
'playlist_count': 0,
}, {
# https://www.plus.fifa.com/en/content/dreams-2018-fifa-world-cup-official-film/ebdce1da-ab82-4c0b-a7d3-b4fc71030339
'url': 'https://www.fifa.com/fifaplus/en/watch/movie/69GbI9lVcwhOeBvea5eKUB',
'info_dict': {
'id': 'ebdce1da-ab82-4c0b-a7d3-b4fc71030339',
'title': 'Dreams',
'description': 'md5:b795d218d5c2b88bff3c1569cb617acb',
'display_id': 'dreams-2018-fifa-world-cup-official-film',
},
'playlist_count': 0,
}]
preplay_parameters = self._download_json(
f'{preconnect_link}/videoPlayerData/{video_id}', video_id, 'Downloading Preplay Parameters')['preplayParameters']
def _entries(self, video_asset, video_id):
# trailers are non-DRM'd
for video_info in traverse_obj(video_asset, (lambda _, v: v['type'] == 'TRAILER', {dict})):
yield self._extract_video(video_info, video_id)
def _real_extract(self, url):
video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
video_content = self._call_api(
f'entertainment/api/v1/contents/{video_id}', video_id, 'Downloading video content')
video_asset = self._call_api(
'flux-capacitor/api/v1/videoasset', video_id,
'Downloading video asset', query={'catalog': video_id})
thumbnails = []
for key, width in [('coverUrl', 330), ('wideCoverUrl', 1408)]:
if thumbnail_url := video_content.get(key):
thumbnails.append({
'url': update_url_query(thumbnail_url, {'width': width}),
'width': width,
})
return self.playlist_result(
self._entries(video_asset, video_id), video_id,
strip_or_none(video_content['title']), strip_or_none(video_content.get('storyLine')),
display_id=display_id, thumbnails=thumbnails)
class FifaArticleIE(InfoExtractor):
_VALID_URL = r'https?://(www\.)?fifa\.com/(fifaplus/)?(?P<locale>\w{2})/articles/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://www.fifa.com/en/articles/foord-talks-2023-and-battling-kerr-for-the-wsl-title',
'info_dict': {
'id': 'foord-talks-2023-and-battling-kerr-for-the-wsl-title',
'title': 'Foord talks 2023 and battling Kerr for the WSL title',
'timestamp': 1651136400,
'upload_date': '20220428',
},
'playlist': [{
'info_dict': {
'id': '6B2xtOT2SDMB4JeF3i9n2y',
'ext': 'mp4',
'title': 'Foord & Kerr: Friends and rivals',
'description': 'md5:756e14e1814196948ec4d2a9663f7214',
'duration': 82,
'categories': ['News', 'Interview'],
'thumbnail': r're:https://digitalhub\.fifa\.com/transform/[^/]+/\w+',
},
}, {
'info_dict': {
'id': 'R2Y1vbwvggrlSr02Cfr99',
'ext': 'mp4',
'title': 'Foord: 2023 will be the best Women\'s World Cup yet',
'description': 'Matildas star Caitlin Foord looks ahead to the FIFA Women\'s World Cup Australia & New Zealand 2023™.',
'duration': 44,
'categories': ['News', 'Interview'],
'thumbnail': r're:https://digitalhub\.fifa\.com/transform/[^/]+/\w+',
},
}],
'params': {'skip_download': 'm3u8'},
}, {
# https://www.fifa.com/en/articles/stars-set-to-collide-in-uwcl-final
'url': 'https://www.fifa.com/fifaplus/en/articles/stars-set-to-collide-in-uwcl-final',
'only_matching': True,
}]
@functools.cached_property
def _preconnect_link(self):
return self._search_regex(
r'<link\b[^>]+\brel\s*=\s*"preconnect"[^>]+href\s*=\s*"([^"]+)"',
self._download_webpage('https://fifa.com/', None), 'Preconnect Link')
def _call_api(self, path, video_id, note=None, query=None, fatal=True):
return self._download_json(
f'{self._preconnect_link}/{path}', video_id, note, query=query, fatal=fatal)
def _entries(self, video_ids, article_id):
for video_id in video_ids:
video_details = self._call_api(
f'sections/videoDetails/{video_id}', article_id,
'Downloading Video Details', fatal=False)
preplay_parameters = self._call_api(
f'videoPlayerData/{video_id}', article_id,
'Downloading Preplay Parameters')['preplayParameters']
content_data = self._download_json(
'https://content.uplynk.com/preplay/{contentId}/multiple.json?{queryStr}&sig={signature}'.format(**preplay_parameters),
video_id, 'Downloading Content Data')
'https://content.uplynk.com/preplay/{contentId}/multiple.json?{queryStr}&sig={signature}'.format(
**preplay_parameters), article_id, 'Downloading Content Data')
formats, subtitles = self._extract_m3u8_formats_and_subtitles(content_data['playURL'], article_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(content_data['playURL'], video_id)
return {
yield {
'id': video_id,
'title': video_details.get('title'),
'description': video_details.get('description'),
@ -80,3 +320,20 @@ class FifaIE(InfoExtractor):
'formats': formats,
'subtitles': subtitles,
}
def _real_extract(self, url):
article_id, locale = self._match_valid_url(url).group('id', 'locale')
page_id = self._call_api(f'pages/en/articles/{article_id}', article_id)['pageId']
page_info = self._call_api(f'sections/article/{page_id}', article_id, query={'locale': locale})
video_ids = []
if hero_video_entry_id := page_info.get('heroVideoEntryId'):
video_ids.append(hero_video_entry_id)
video_ids.extend(traverse_obj(page_info, (
'richtext', 'content', lambda _, v: v['data']['target']['contentTypesCheckboxValue'] == 'Video',
'data', 'target', 'sys', 'id')))
return self.playlist_result(
self._entries(video_ids, article_id), article_id, page_info.get('articleTitle'),
timestamp=parse_iso8601(page_info.get('articlePublishedDate')))

View File

@ -0,0 +1,105 @@
from .common import InfoExtractor
from ..utils import url_or_none
from ..utils.traversal import traverse_obj
class RadioRadicaleIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?radioradicale\.it/scheda/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://www.radioradicale.it/scheda/471591',
'md5': 'eb0fbe43a601f1a361cbd00f3c45af4a',
'info_dict': {
'id': '471591',
'ext': 'mp4',
'title': 'md5:e8fbb8de57011a3255db0beca69af73d',
'description': 'md5:5e15a789a2fe4d67da8d1366996e89ef',
'location': 'Napoli',
'duration': 2852.0,
'timestamp': 1459987200,
'upload_date': '20160407',
'thumbnail': 'https://www.radioradicale.it/photo400/0/0/9/0/1/00901768.jpg',
},
}, {
'url': 'https://www.radioradicale.it/scheda/742783/parlamento-riunito-in-seduta-comune-11a-della-xix-legislatura',
'info_dict': {
'id': '742783',
'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
'description': '-) Votazione per l\'elezione di un giudice della Corte Costituzionale (nono scrutinio)',
'location': 'CAMERA',
'duration': 5868.0,
'timestamp': 1730246400,
'upload_date': '20241030',
},
'playlist': [{
'md5': 'aa48de55dcc45478e4cd200f299aab7d',
'info_dict': {
'id': '742783-0',
'ext': 'mp4',
'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
},
}, {
'md5': 'be915c189c70ad2920e5810f32260ff5',
'info_dict': {
'id': '742783-1',
'ext': 'mp4',
'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
},
}, {
'md5': 'f0ee4047342baf8ed3128a8417ac5e0a',
'info_dict': {
'id': '742783-2',
'ext': 'mp4',
'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
},
}],
}]
def _entries(self, videos_info, page_id):
for idx, video in enumerate(traverse_obj(
videos_info, ('playlist', lambda _, v: v['sources']))):
video_id = f'{page_id}-{idx}'
formats = []
subtitles = {}
for m3u8_url in traverse_obj(video, ('sources', ..., 'src', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
for sub in traverse_obj(video, ('subtitles', ..., lambda _, v: url_or_none(v['src']))):
self._merge_subtitles({sub.get('srclang') or 'und': [{
'url': sub['src'],
'name': sub.get('label'),
}]}, target=subtitles)
yield {
'id': video_id,
'title': video.get('title'),
'formats': formats,
'subtitles': subtitles,
}
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
videos_info = self._search_json(
r'jQuery\.extend\(Drupal\.settings\s*,',
webpage, 'videos_info', page_id)['RRscheda']
entries = list(self._entries(videos_info, page_id))
common_info = {
'id': page_id,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'location': videos_info.get('luogo'),
**self._search_json_ld(webpage, page_id),
}
if len(entries) == 1:
return {
**entries[0],
**common_info,
}
return self.playlist_result(entries, multi_video=True, **common_info)