mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-26 01:01:25 +01:00
Compare commits
10 Commits
2f00c09960
...
6dd679bd90
| Author | SHA1 | Date | |
|---|---|---|---|
|
6dd679bd90 | ||
|
|
6365e92589 | ||
|
|
70c55cb08f | ||
|
|
aef78fdfa8 | ||
|
|
9768d62bf8 | ||
|
|
e569c03196 | ||
|
|
2e9c00649c | ||
|
|
d1175cf7a3 | ||
|
|
5f600dc613 | ||
|
|
79795b9502 |
|
|
@ -208,6 +208,10 @@ from .bandcamp import (
|
|||
BandcampUserIE,
|
||||
BandcampWeeklyIE,
|
||||
)
|
||||
from .bandlab import (
|
||||
BandlabIE,
|
||||
BandlabPlaylistIE,
|
||||
)
|
||||
from .bannedvideo import BannedVideoIE
|
||||
from .bbc import (
|
||||
BBCIE,
|
||||
|
|
@ -1381,15 +1385,15 @@ from .nowness import (
|
|||
)
|
||||
from .noz import NozIE
|
||||
from .npo import (
|
||||
NPOIE,
|
||||
NPO3IE,
|
||||
NTRIE,
|
||||
VPROIE,
|
||||
WNLIE,
|
||||
AndereTijdenIE,
|
||||
HetKlokhuisIE,
|
||||
NPOLiveIE,
|
||||
NPORadioFragmentIE,
|
||||
NPORadioIE,
|
||||
NPOStartIE,
|
||||
SchoolTVIE,
|
||||
ZappIE,
|
||||
)
|
||||
from .npr import NprIE
|
||||
from .nrk import (
|
||||
|
|
@ -1649,6 +1653,7 @@ 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
438
yt_dlp/extractor/bandlab.py
Normal 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 {}))
|
||||
|
|
@ -1,606 +1,438 @@
|
|||
import random
|
||||
import json
|
||||
import re
|
||||
import urllib.parse
|
||||
|
||||
from yt_dlp.utils._utils import ExtractorError
|
||||
from yt_dlp.utils.traversal import traverse_obj
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
orderedSet,
|
||||
str_or_none,
|
||||
try_call,
|
||||
unified_timestamp,
|
||||
url_or_none,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class NPOIE(InfoExtractor):
|
||||
IE_NAME = 'npo'
|
||||
IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl'
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:
|
||||
npo:|
|
||||
https?://
|
||||
(?:www\.)?
|
||||
(?:
|
||||
npo\.nl/(?:[^/]+/)*|
|
||||
(?:ntr|npostart)\.nl/(?:[^/]+/){2,}|
|
||||
omroepwnl\.nl/video/fragment/[^/]+__|
|
||||
(?:zapp|npo3)\.nl/(?:[^/]+/){2,}
|
||||
)
|
||||
)
|
||||
(?P<id>[^/?#]+)
|
||||
'''
|
||||
class NPOBaseIE(InfoExtractor):
|
||||
def _extract_product_id_information(self, product_id):
|
||||
token = self._download_json(
|
||||
f'https://npo.nl/start/api/domain/player-token?productId={product_id}', product_id,
|
||||
'Downloading token')['token']
|
||||
return self._extract_info_from_token(product_id, token)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
|
||||
'md5': '4b3f9c429157ec4775f2c9cb7b911016',
|
||||
'info_dict': {
|
||||
'id': 'VPWON_1220719',
|
||||
'ext': 'm4v',
|
||||
'title': 'Nieuwsuur',
|
||||
'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
|
||||
'upload_date': '20140622',
|
||||
},
|
||||
'skip': 'Video was removed',
|
||||
}, {
|
||||
'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
|
||||
'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
|
||||
'info_dict': {
|
||||
'id': 'VARA_101191800',
|
||||
'ext': 'm4v',
|
||||
'title': 'De Mega Mike & Mega Thomas show: The best of.',
|
||||
'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
|
||||
'upload_date': '20090227',
|
||||
'duration': 2400,
|
||||
},
|
||||
'skip': 'Video was removed',
|
||||
}, {
|
||||
'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
|
||||
'md5': '1b279c0547f6b270e014c576415268c5',
|
||||
'info_dict': {
|
||||
'id': 'VPWON_1169289',
|
||||
'ext': 'mp4',
|
||||
'title': 'Zwart geld: de toekomst komt uit Afrika',
|
||||
'description': 'md5:dffaf3d628a9c36f78ca48d834246261',
|
||||
'upload_date': '20130225',
|
||||
'duration': 3000,
|
||||
'creator': 'NED2',
|
||||
'series': 'Tegenlicht',
|
||||
'timestamp': 1361822340,
|
||||
'thumbnail': 'https://images.npo.nl/tile/1280x720/142854.jpg',
|
||||
'episode': 'Zwart geld: de toekomst komt uit Afrika',
|
||||
'episode_number': 18,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
|
||||
'info_dict': {
|
||||
'id': 'WO_VPRO_043706',
|
||||
'ext': 'mp4',
|
||||
'title': 'De nieuwe mens - Deel 1',
|
||||
'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
|
||||
'duration': 4680,
|
||||
'episode': 'De nieuwe mens - Deel 1',
|
||||
'thumbnail': 'https://images.npo.nl/tile/1280x720/6289.jpg',
|
||||
'timestamp': 1279716057,
|
||||
'series': 'De nieuwe mens - Deel 1',
|
||||
'upload_date': '20100721',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# non asf in streams
|
||||
'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
|
||||
'info_dict': {
|
||||
'id': 'WO_NOS_762771',
|
||||
'ext': 'mp4',
|
||||
'title': 'Hoe gaat Europa verder na Parijs?',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'Video was removed',
|
||||
}, {
|
||||
'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
|
||||
'info_dict': {
|
||||
'id': 'VPWON_1233944',
|
||||
'ext': 'mp4',
|
||||
'title': 'Aap, poot, pies',
|
||||
'description': 'md5:4b46b1b9553b4c036a04d2a532a137e6',
|
||||
'upload_date': '20150508',
|
||||
'duration': 599,
|
||||
'episode': 'Aap, poot, pies',
|
||||
'thumbnail': 'https://images.poms.omroep.nl/image/s1280/c1280x720/608118.jpg',
|
||||
'timestamp': 1431064200,
|
||||
'series': 'Aap, poot, pies',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
|
||||
'info_dict': {
|
||||
'id': 'POW_00996502',
|
||||
'ext': 'm4v',
|
||||
'title': '''"Dit is wel een 'landslide'..."''',
|
||||
'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
|
||||
'upload_date': '20150508',
|
||||
'duration': 462,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'Video was removed',
|
||||
}, {
|
||||
# audio
|
||||
'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437',
|
||||
'info_dict': {
|
||||
'id': 'RBX_FUNX_6683215',
|
||||
'ext': 'mp3',
|
||||
'title': 'Jouw Stad Rotterdam',
|
||||
'description': 'md5:db251505244f097717ec59fabc372d9f',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'Video was removed',
|
||||
}, {
|
||||
'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# live stream
|
||||
'url': 'npo:LI_NL1_4188102',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.npostart.nl/broodje-gezond-ei/28-05-2018/KN_1698996',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://npo.nl/KN_1698996',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.npo3.nl/the-genius/21-11-2022/VPWON_1341105',
|
||||
'info_dict': {
|
||||
'id': 'VPWON_1341105',
|
||||
'ext': 'mp4',
|
||||
'duration': 2658,
|
||||
'series': 'The Genius',
|
||||
'description': 'md5:db02f1456939ca63f7c408f858044e94',
|
||||
'title': 'The Genius',
|
||||
'timestamp': 1669062000,
|
||||
'creator': 'NED3',
|
||||
'episode': 'The Genius',
|
||||
'thumbnail': 'https://images.npo.nl/tile/1280x720/1827650.jpg',
|
||||
'episode_number': 8,
|
||||
'upload_date': '20221121',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return (False if any(ie.suitable(url)
|
||||
for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE))
|
||||
else super().suitable(url))
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
if urllib.parse.urlparse(url).netloc in ['www.ntr.nl', 'ntr.nl']:
|
||||
player = self._download_json(
|
||||
f'https://www.ntr.nl/ajax/player/embed/{video_id}', video_id,
|
||||
'Downloading player JSON', query={
|
||||
'parameters[elementId]': f'npo{random.randint(0, 999)}',
|
||||
'parameters[sterReferralUrl]': url,
|
||||
'parameters[autoplay]': 0,
|
||||
})
|
||||
else:
|
||||
self._request_webpage(
|
||||
'https://www.npostart.nl/api/token', video_id,
|
||||
'Downloading token', headers={
|
||||
'Referer': url,
|
||||
'X-Requested-With': 'XMLHttpRequest',
|
||||
})
|
||||
player = self._download_json(
|
||||
f'https://www.npostart.nl/player/{video_id}', video_id,
|
||||
'Downloading player JSON', data=urlencode_postdata({
|
||||
'autoplay': 0,
|
||||
'share': 1,
|
||||
'pageUrl': url,
|
||||
'hasAdConsent': 0,
|
||||
}), headers={
|
||||
'x-xsrf-token': try_call(lambda: urllib.parse.unquote(
|
||||
self._get_cookies('https://www.npostart.nl')['XSRF-TOKEN'].value)),
|
||||
})
|
||||
|
||||
player_token = player['token']
|
||||
|
||||
drm = False
|
||||
format_urls = set()
|
||||
def _extract_info_from_token(self, video_id, token):
|
||||
data = {
|
||||
'id': video_id,
|
||||
}
|
||||
formats = []
|
||||
for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'):
|
||||
streams = self._download_json(
|
||||
f'https://start-player.npo.nl/video/{video_id}/streams',
|
||||
video_id, f'Downloading {profile} profile JSON', fatal=False,
|
||||
query={
|
||||
'profile': profile,
|
||||
'quality': 'npoplus',
|
||||
'tokenId': player_token,
|
||||
'streamType': 'broadcast',
|
||||
}, data=b'') # endpoint requires POST
|
||||
if not streams:
|
||||
continue
|
||||
stream = streams.get('stream')
|
||||
if not isinstance(stream, dict):
|
||||
continue
|
||||
stream_url = url_or_none(stream.get('src'))
|
||||
if not stream_url or stream_url in format_urls:
|
||||
continue
|
||||
format_urls.add(stream_url)
|
||||
if stream.get('protection') is not None or stream.get('keySystemOptions') is not None:
|
||||
drm = True
|
||||
continue
|
||||
stream_type = stream.get('type')
|
||||
thumbnails = []
|
||||
subtitles = {}
|
||||
for profile_name in ('dash', 'hls', 'smooth'):
|
||||
profile = self._download_json(
|
||||
'https://prod.npoplayer.nl/stream-link',
|
||||
video_id,
|
||||
f'Downloading profile {profile_name} JSON',
|
||||
data=json.dumps({'profileName': profile_name}).encode(),
|
||||
headers={'Authorization': token},
|
||||
fatal=False,
|
||||
)
|
||||
metadata = profile.get('metadata')
|
||||
if metadata is not None:
|
||||
duration = metadata.get('duration')
|
||||
thumbnail = metadata.get('poster')
|
||||
data['title'] = metadata.get('title')
|
||||
data['description'] = metadata.get('description')
|
||||
data['channel_id'] = metadata.get('channel')
|
||||
data['uploader_id'] = metadata.get('channel')
|
||||
data['genres'] = metadata.get('genres')
|
||||
if duration:
|
||||
data['duration'] = duration / 1000
|
||||
if thumbnail and not any(thumb['url'] == thumbnail for thumb in thumbnails):
|
||||
thumbnails.append({
|
||||
'url': thumbnail,
|
||||
})
|
||||
raw_subtitles = traverse_obj(profile, ('assets', 'subtitles'))
|
||||
stream_url = traverse_obj(profile, ('stream', 'streamURL'))
|
||||
stream_ext = determine_ext(stream_url)
|
||||
if stream_type == 'application/dash+xml' or stream_ext == 'mpd':
|
||||
if stream_ext == 'mpd':
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
stream_url, video_id, mpd_id='dash', fatal=False))
|
||||
elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8':
|
||||
stream_url, video_id=video_id, mpd_id='dash', fatal=False))
|
||||
elif stream_ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
stream_url, video_id, ext='mp4',
|
||||
stream_url, video_id=video_id, ext='mp4',
|
||||
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
|
||||
elif re.search(r'\.isml?/Manifest', stream_url):
|
||||
formats.extend(self._extract_ism_formats(
|
||||
stream_url, video_id, ism_id='mss', fatal=False))
|
||||
stream_url, video_id=video_id, ism_id='mss', fatal=False))
|
||||
else:
|
||||
formats.append({
|
||||
'url': stream_url,
|
||||
})
|
||||
|
||||
if not formats:
|
||||
if not self.get_param('allow_unplayable_formats') and drm:
|
||||
self.report_drm(video_id)
|
||||
|
||||
info = {
|
||||
'id': video_id,
|
||||
'title': video_id,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
embed_url = url_or_none(player.get('embedUrl'))
|
||||
if embed_url:
|
||||
webpage = self._download_webpage(
|
||||
embed_url, video_id, 'Downloading embed page', fatal=False)
|
||||
if webpage:
|
||||
video = self._parse_json(
|
||||
self._search_regex(
|
||||
r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video',
|
||||
default='{}'), video_id)
|
||||
if video:
|
||||
title = video.get('episodeTitle')
|
||||
subtitles = {}
|
||||
subtitles_list = video.get('subtitles')
|
||||
if isinstance(subtitles_list, list):
|
||||
for cc in subtitles_list:
|
||||
cc_url = url_or_none(cc.get('src'))
|
||||
if not cc_url:
|
||||
continue
|
||||
lang = str_or_none(cc.get('language')) or 'nl'
|
||||
subtitles.setdefault(lang, []).append({
|
||||
'url': cc_url,
|
||||
if (raw_subtitles):
|
||||
for subtitle in raw_subtitles:
|
||||
tag = subtitle.get('iso')
|
||||
if tag not in subtitles:
|
||||
subtitles[tag] = []
|
||||
if not any(sub['url'] == subtitle['location'] for sub in subtitles[tag]):
|
||||
subtitles[tag].append({
|
||||
'url': subtitle.get('location'),
|
||||
'name': subtitle.get('name'),
|
||||
})
|
||||
return merge_dicts({
|
||||
'title': title,
|
||||
'description': video.get('description'),
|
||||
'thumbnail': url_or_none(
|
||||
video.get('still_image_url') or video.get('orig_image_url')),
|
||||
'duration': int_or_none(video.get('duration')),
|
||||
'timestamp': unified_timestamp(video.get('broadcastDate')),
|
||||
'creator': video.get('channel'),
|
||||
'series': video.get('title'),
|
||||
'episode': title,
|
||||
'episode_number': int_or_none(video.get('episodeNumber')),
|
||||
'subtitles': subtitles,
|
||||
}, info)
|
||||
|
||||
return info
|
||||
data['formats'] = formats
|
||||
data['subtitles'] = subtitles
|
||||
data['thumbnails'] = thumbnails
|
||||
return data
|
||||
|
||||
|
||||
class NPOLiveIE(InfoExtractor):
|
||||
IE_NAME = 'npo.nl:live'
|
||||
_VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P<id>[^/?#&]+))?'
|
||||
class NPOStartIE(NPOBaseIE):
|
||||
IE_NAME = 'npo.nl:start'
|
||||
_VALID_URL = r'https?://(?:www\.)?npo\.nl/start/serie/(?:[^/]+/){2}(?P<id>[^/?#&]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.npo.nl/live/npo-1',
|
||||
'url': 'https://npo.nl/start/serie/vpro-tegenlicht/seizoen-11/zwart-geld-de-toekomst-komt-uit-afrika/afspelen',
|
||||
'md5': '8c30593a81ac80d65b531eaf2a92ac02',
|
||||
'info_dict': {
|
||||
'id': 'LI_NL1_4188102',
|
||||
'display_id': 'npo-1',
|
||||
'id': 'VPWON_1169289',
|
||||
'ext': 'mp4',
|
||||
'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||
'is_live': True,
|
||||
'title': 'Zwart geld: de toekomst komt uit Afrika',
|
||||
'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
|
||||
'duration': 3000,
|
||||
'uploader_id': 'NED2',
|
||||
'series': 'VPRO Tegenlicht',
|
||||
'timestamp': 1361822340,
|
||||
'thumbnail': 'https://assets-start.npo.nl/resources/2023/06/30/d9879593-1944-4249-990c-1561dac14d8e.jpg',
|
||||
'episode': 'Zwart geld: de toekomst komt uit Afrika',
|
||||
'episode_number': 18,
|
||||
'channel_id': 'NED2',
|
||||
'genres': [],
|
||||
'release_date': '20130225',
|
||||
'release_timestamp': 1361822340,
|
||||
'season': 'Season 11',
|
||||
'season_id': 'df5e2334-e07a-4301-b3d3-8e224d8c1f07',
|
||||
'season_number': 11,
|
||||
'series_id': '6727dcdf-4bd2-477c-bf96-1ead69fad6c9',
|
||||
'upload_date': '20130225',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.npo.nl/live',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.npostart.nl/live/npo-1',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url) or 'npo-1'
|
||||
slug = self._match_id(url)
|
||||
metadata = self._download_json(f'https://npo.nl/start/api/domain/program-detail?slug={slug}', video_id=slug, note='Downloading program details JSON')
|
||||
video_id = metadata['productId']
|
||||
data = self._extract_product_id_information(video_id)
|
||||
thumbnails = []
|
||||
for image in metadata.get('images'):
|
||||
thumbnails.append({
|
||||
'id': image.get('guid'),
|
||||
'url': image.get('url'),
|
||||
})
|
||||
break
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
live_id = self._search_regex(
|
||||
[r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'url': f'npo:{live_id}',
|
||||
'ie_key': NPOIE.ie_key(),
|
||||
'id': live_id,
|
||||
'display_id': display_id,
|
||||
}
|
||||
data['title'] = metadata.get('title') or data.get('title')
|
||||
data['episode'] = metadata.get('title') or data.get('title')
|
||||
data['episode_number'] = int_or_none(metadata.get('programKey'))
|
||||
data['duration'] = int_or_none(metadata.get('durationInSeconds'), default=data.get('duration'))
|
||||
data['description'] = traverse_obj(metadata, ('synopsis', 'long')) or traverse_obj(metadata, ('synopsis', 'short')) or traverse_obj(metadata, ('synopsis', 'brief')) or data.get('description')
|
||||
data['thumbnails'] = thumbnails
|
||||
data['genres'] = metadata.get('genres') or data.get('genres')
|
||||
data['series'] = traverse_obj(metadata, ('series', 'title'))
|
||||
data['series_id'] = traverse_obj(metadata, ('series', 'guid'))
|
||||
data['season_number'] = int_or_none(traverse_obj(metadata, ('season', 'seasonKey')))
|
||||
data['season_id'] = traverse_obj(metadata, ('season', 'guid'))
|
||||
data['release_timestamp'] = int_or_none(metadata.get('firstBroadcastDate'))
|
||||
data['timestamp'] = int_or_none(metadata.get('publishedDateTime'))
|
||||
return data
|
||||
|
||||
|
||||
class NPORadioIE(InfoExtractor):
|
||||
class NPORadioIE(NPOBaseIE):
|
||||
IE_NAME = 'npo.nl:radio'
|
||||
_VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?nporadio(?P<n>\d)\.nl(?:/[^/]+)*/(?P<id>[^/]+)?'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.npo.nl/radio/radio-1',
|
||||
_TESTS = [{
|
||||
'url': 'https://www.nporadio1.nl/',
|
||||
'info_dict': {
|
||||
'id': 'radio-1',
|
||||
'ext': 'mp3',
|
||||
'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||
'id': 'live',
|
||||
'ext': 'mp4',
|
||||
'title': r're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||
'live_status': 'is_live',
|
||||
'thumbnail': r're:^https?://.*\.jpg',
|
||||
'description': 'Live programmering',
|
||||
'is_live': True,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return False if NPORadioFragmentIE.suitable(url) else super().suitable(url)
|
||||
|
||||
@staticmethod
|
||||
def _html_get_attribute_regex(attribute):
|
||||
return rf'{attribute}\s*=\s*\'([^\']+)\''
|
||||
},
|
||||
{
|
||||
'url': 'https://www.nporadio1.nl/nieuws/binnenland/15bcad75-22c5-4226-a3fe-d54a76175da3/utrecht-zet-rolmodellen-in-voor-bewustwording-mentale-gezondheid',
|
||||
'md5': '8ad04123febc07716f45e324d7fb792d',
|
||||
'info_dict': {
|
||||
'id': 'utrecht-zet-rolmodellen-in-voor-bewustwording-mentale-gezondheid',
|
||||
'ext': 'mp4',
|
||||
'duration': 262,
|
||||
'channel_id': 'RAD1',
|
||||
'description': 'md5:7d36b72407e757e6c748a6cdf27c7628',
|
||||
'title': 'Utrecht zet rolmodellen in voor bewustzijn mentale gezondheid ',
|
||||
'genres': ['Informatief'],
|
||||
'uploader_id': 'RAD1',
|
||||
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2217026',
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'https://www.nporadio2.nl/fragmenten/janwillemstartop/9d35b8fb-a07b-41f9-9cc5-a9c89dd60dbb/2024-10-10-nancy-zet-zich-in-voor-daklozen-voor-mij-was-het-op-het-randje',
|
||||
'md5': '432b0e106082ffaa0e31c4549db09b0c',
|
||||
'info_dict': {
|
||||
'id': '2024-10-10-nancy-zet-zich-in-voor-daklozen-voor-mij-was-het-op-het-randje',
|
||||
'ext': 'mp4',
|
||||
'genres': ['Muziek'],
|
||||
'title': 'Nancy zet zich in voor daklozen: "Voor mij was het op het randje" ',
|
||||
'duration': 235,
|
||||
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2216783',
|
||||
'description': 'md5:26925e8bd2c715b160cc864efa731583',
|
||||
'uploader_id': 'RAD2',
|
||||
'channel_id': 'RAD2',
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'https://www.nporadio2.nl/uitzendingen/dit-is-tannaz/9bc1ab7e-77f6-4444-986b-1cd7c25ff4bf/2024-10-11-dit-is-tannaz',
|
||||
'md5': 'a1212f4d2fe361aafcced5bcd3cf939b',
|
||||
'info_dict': {
|
||||
'id': '2024-10-11-dit-is-tannaz',
|
||||
'ext': 'mp3',
|
||||
'uploader_id': 'RAD2',
|
||||
'genres': ['Muziek'],
|
||||
'title': 'Dit is Tannaz',
|
||||
'channel_id': 'RAD2',
|
||||
'description': 'md5:3f2b5dad3e965ae7915a5f9a5a2decc5',
|
||||
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2190854',
|
||||
'duration': 7200.026,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
parsed = self._match_valid_url(url)
|
||||
video_id = parsed.group('id') or 'live'
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
title = self._html_search_regex(
|
||||
self._html_get_attribute_regex('data-channel'), webpage, 'title')
|
||||
|
||||
stream = self._parse_json(
|
||||
self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
|
||||
video_id)
|
||||
|
||||
codec = stream.get('codec')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': stream['url'],
|
||||
'title': title,
|
||||
'acodec': codec,
|
||||
'ext': codec,
|
||||
'is_live': True,
|
||||
}
|
||||
if video_id == 'live':
|
||||
radio_number = parsed.group('n')
|
||||
token_url = self._download_json(f'https://www.nporadio{radio_number}.nl/api/player/npo-radio-{radio_number}', video_id)['tokenUrl']
|
||||
else:
|
||||
props = self._search_nextjs_data(self._download_webpage(url, video_id), video_id)['props']['pageProps']
|
||||
token_url = traverse_obj(props, ('article', 'content', 0, 'value', 'player', 'tokenUrl')) or traverse_obj(props, ('fragmentDetail', 'bodyContent', 0, 'payload', 'player', 'tokenUrl')) or traverse_obj(props, ('radioBroadcast', 'showAssets', 0, 'player', 'tokenUrl'))
|
||||
if token_url is None:
|
||||
raise ExtractorError('Token url not found')
|
||||
data = self._extract_info_from_token(video_id, self._download_json(token_url, video_id, 'Downloading token JSON')['playerToken'])
|
||||
data['is_live'] = video_id == 'live'
|
||||
return data
|
||||
|
||||
|
||||
class NPORadioFragmentIE(InfoExtractor):
|
||||
IE_NAME = 'npo.nl:radio:fragment'
|
||||
_VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
|
||||
class NPO3IE(NPOBaseIE):
|
||||
IE_NAME = 'npo.nl:npo3'
|
||||
_VALID_URL = r'https?://(?:www\.)?npo\.nl/npo3/(?:[^/]+/){2}(?P<id>[^/?#&]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
|
||||
'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
|
||||
'url': 'https://npo.nl/npo3/vlees-smakelijk/11-10-2024/WO_KN_20222563',
|
||||
'md5': 'e0cd5b96c712edea2e7f0700d348bc98',
|
||||
'info_dict': {
|
||||
'id': '174356',
|
||||
'ext': 'mp3',
|
||||
'title': 'Jubileumconcert Willeke Alberti',
|
||||
'id': 'WO_KN_20222563',
|
||||
'ext': 'mp4',
|
||||
'description': 'md5:31f5ffff8c70af1635cbb93a8205e0c4',
|
||||
'duration': 1021.994,
|
||||
'title': 'Vlees smakelijk',
|
||||
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/2215940',
|
||||
'genres': ['Human Interest', 'Reality TV'],
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
audio_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, audio_id)
|
||||
|
||||
title = self._html_search_regex(
|
||||
rf'href="/radio/[^/]+/fragment/{audio_id}" title="([^"]+)"',
|
||||
webpage, 'title')
|
||||
|
||||
audio_url = self._search_regex(
|
||||
r"data-streams='([^']+)'", webpage, 'audio url')
|
||||
|
||||
return {
|
||||
'id': audio_id,
|
||||
'url': audio_url,
|
||||
'title': title,
|
||||
}
|
||||
return self._extract_product_id_information(self._match_id(url))
|
||||
|
||||
|
||||
class NPODataMidEmbedIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
video_id = self._search_regex(
|
||||
r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': 'NPO',
|
||||
'url': f'npo:{video_id}',
|
||||
'display_id': display_id,
|
||||
}
|
||||
|
||||
|
||||
class SchoolTVIE(NPODataMidEmbedIE):
|
||||
class SchoolTVIE(NPOBaseIE):
|
||||
IE_NAME = 'schooltv'
|
||||
_VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video-item/(?P<id>[^/?#&]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
|
||||
'url': 'https://schooltv.nl/video-item/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
|
||||
'info_dict': {
|
||||
'id': 'WO_NTR_429477',
|
||||
'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
|
||||
'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
|
||||
'ext': 'mp4',
|
||||
'description': 'md5:abfa0ff690adb73fd0297fd033aaa631',
|
||||
},
|
||||
'params': {
|
||||
# Skip because of m3u8 download
|
||||
'skip_download': True,
|
||||
'duration': 51.0,
|
||||
'genres': ['Jeugd'],
|
||||
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/242560',
|
||||
'title': 'Ademhaling',
|
||||
'description': 'md5:db41d874d9ebe597686dda69e892ba49',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._search_regex(r'id=([a-zA-Z0-9_]+)', self._html_search_meta(('og:video', 'og:video:secure_url'), self._download_webpage(url, self._match_id(url))), 'video id')
|
||||
return self._extract_info_from_token(video_id, self._download_json(f'https://api3.schooltv.nl/player/{video_id}', video_id, 'Downloading token JSON')['data']['token'])
|
||||
|
||||
class HetKlokhuisIE(NPODataMidEmbedIE):
|
||||
|
||||
class HetKlokhuisIE(NPOBaseIE):
|
||||
IE_NAME = 'hetklokhuis'
|
||||
_VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
|
||||
'url': 'https://hetklokhuis.nl/dossier/142/zoek-het-uit/tv-uitzending/2987/aliens',
|
||||
'md5': '679d610017689ecc798b316b8daa34e7',
|
||||
'info_dict': {
|
||||
'id': 'VPWON_1260528',
|
||||
'display_id': 'Zwaartekrachtsgolven',
|
||||
'ext': 'm4v',
|
||||
'title': 'Het Klokhuis: Zwaartekrachtsgolven',
|
||||
'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
|
||||
'upload_date': '20170223',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
'id': 'VPWON_1225126',
|
||||
'ext': 'mp4',
|
||||
'duration': 852.27,
|
||||
'channel_id': 'NED3',
|
||||
'description': 'md5:17681c9644521344a0573e04c78912d7',
|
||||
'title': 'Aliens',
|
||||
'genres': ['Jeugd', 'Informatief'],
|
||||
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/624824',
|
||||
'uploader_id': 'NED3',
|
||||
'series': 'Zoek Het Uit!',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
webpage = self._download_webpage(url, self._match_id(url))
|
||||
series, title = self._og_search_title(webpage).split(' - ')
|
||||
video_id = self._html_search_regex(r'data-mid="([a-zA-Z0-9_]+)"', webpage, 'video id')
|
||||
data = self._extract_info_from_token(video_id, self._download_json(f'https://api3.schooltv.nl/player/{video_id}', video_id, 'Downloading token JSON')['data']['token'])
|
||||
data['series'] = series
|
||||
data['title'] = title
|
||||
return data
|
||||
|
||||
|
||||
class ZappIE(NPOBaseIE):
|
||||
IE_NAME = 'zapp.nl'
|
||||
_VALID_URL = r'https?://(?:www\.)?zapp\.nl/programmas/(?:[^/]+/){2}(?P<id>[^/?#&]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://www.zapp.nl/programmas/zappsport/gemist/POMS_AT_811523',
|
||||
'md5': 'faf6811abea03ba8a52298c97bd0146b',
|
||||
'info_dict': {
|
||||
'id': 'POMS_AT_811523',
|
||||
'ext': 'mp4',
|
||||
'genres': [],
|
||||
'uploader_id': 'NED3',
|
||||
'description': 'Kindersportprogramma waarin alle takken van sport voorbijkomen.',
|
||||
'channel_id': 'NED3',
|
||||
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/586056',
|
||||
'duration': 900.0,
|
||||
'title': 'Running Team 2015 - aflevering 1',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
return self._extract_product_id_information(self._match_id(url))
|
||||
|
||||
|
||||
class NPOPlaylistBaseIE(NPOBaseIE):
|
||||
def _mid_result(self, mid, title, url):
|
||||
token = self._download_token(mid, url)
|
||||
data = self._extract_info_from_token(mid, token)
|
||||
# The API returns the same title for every video so overwrite it with the video title
|
||||
data['title'] = title
|
||||
return data
|
||||
|
||||
class NPOPlaylistBaseIE(NPOIE): # XXX: Do not subclass from concrete IE
|
||||
def _real_extract(self, url):
|
||||
playlist_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, playlist_id)
|
||||
|
||||
entries = [
|
||||
self.url_result(f'npo:{video_id}' if not video_id.startswith('http') else video_id)
|
||||
for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
|
||||
]
|
||||
|
||||
playlist_title = self._html_search_regex(
|
||||
self._PLAYLIST_TITLE_RE, webpage, 'playlist title',
|
||||
default=None) or self._og_search_title(webpage)
|
||||
|
||||
entries = [
|
||||
self._mid_result(video_id, playlist_title, url)
|
||||
for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
|
||||
]
|
||||
|
||||
return self.playlist_result(entries, playlist_id, playlist_title)
|
||||
|
||||
|
||||
class VPROIE(NPOPlaylistBaseIE):
|
||||
IE_NAME = 'vpro'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
|
||||
_PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)',
|
||||
r'<h5[^>]+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)')
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/.]+)'
|
||||
_PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)')
|
||||
_PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
|
||||
'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
|
||||
'info_dict': {
|
||||
'id': 'VPWON_1169289',
|
||||
'ext': 'm4v',
|
||||
'title': 'De toekomst komt uit Afrika',
|
||||
'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
|
||||
'upload_date': '20130225',
|
||||
},
|
||||
'skip': 'Video gone',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
|
||||
'url': 'https://www.vpro.nl/programmas/3doc/2015/sergio-herman.html',
|
||||
'info_dict': {
|
||||
'id': 'sergio-herman',
|
||||
'title': 'sergio herman: fucking perfect',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
},
|
||||
{
|
||||
# playlist with youtube embed
|
||||
'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
|
||||
'info_dict': {
|
||||
'id': 'education-education',
|
||||
'title': 'education education',
|
||||
'title': 'Sergio Herman: Fucking Perfect',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
},
|
||||
{
|
||||
'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
|
||||
'md5': '87a4cc5a62da942ca9270e4da1d2b8b5',
|
||||
'info_dict': {
|
||||
'id': 'de-tegenprestatie',
|
||||
'id': 'VPWON_1223413',
|
||||
'ext': 'mp4',
|
||||
'title': 'De Tegenprestatie',
|
||||
'duration': 2992.45,
|
||||
'genres': ['Documentaire'],
|
||||
'channel_id': 'NED2',
|
||||
'description': 'Er wordt van burgers steeds meer eigen verantwoordelijkheid en zelfredzaamheid gevraagd.',
|
||||
'uploader_id': 'NED2',
|
||||
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/663342',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
}, {
|
||||
'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
|
||||
'url': 'https://www.2doc.nl/documentaires/2018/07/het-verdriet-van-nederland.html',
|
||||
'md5': '9ae67f6bdcb16a62f99e01198674fe10',
|
||||
'info_dict': {
|
||||
'id': 'VARA_101375237',
|
||||
'ext': 'm4v',
|
||||
'title': 'MH17: Het verdriet van Nederland',
|
||||
'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
|
||||
'upload_date': '20150716',
|
||||
},
|
||||
'params': {
|
||||
# Skip because of m3u8 download
|
||||
'skip_download': True,
|
||||
'ext': 'mp4',
|
||||
'uploader_id': 'NED1',
|
||||
'channel_id': 'NED1',
|
||||
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/1608566',
|
||||
'duration': 4259.63,
|
||||
'genres': ['Documentaire'],
|
||||
'title': 'Het verdriet van Nederland',
|
||||
'description': 'md5:d19b745af196f6cb98daf50ac7cb01fc',
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
def _download_token(self, mid, url):
|
||||
return self._download_json('https://rs.vpro.nl/v3/api/npoplayer/token', mid, 'Downloading token JSON', data=json.dumps({'mid': mid}).encode(), headers={
|
||||
'Content-Type': 'application/json',
|
||||
'Referer': url,
|
||||
})['token']
|
||||
|
||||
class WNLIE(NPOPlaylistBaseIE):
|
||||
IE_NAME = 'wnl'
|
||||
_VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
|
||||
_PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>'
|
||||
_PLAYLIST_ENTRY_RE = r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+'
|
||||
|
||||
class NTRIE(NPOPlaylistBaseIE):
|
||||
IE_NAME = 'ntr'
|
||||
_VALID_URL = r'https?://(?:www\.)?ntr\.nl/(?:[^/]+/)+(?P<id>[^/?#&]+)'
|
||||
_PLAYLIST_TITLE_RE = r'<h2[^>]*>\s*(.+)\s*</h2>'
|
||||
_PLAYLIST_ENTRY_RE = r'<div[^>]+class=["\']npo_wrapper["\'][^>]+data-mid=["\'](.+?)["\']'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
|
||||
'url': 'https://ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944',
|
||||
'md5': '5b7b45c15750c9a74f8b70ea69f0b55a',
|
||||
'info_dict': {
|
||||
'id': 'vandaag-de-dag-6-mei',
|
||||
'title': 'Vandaag de Dag 6 mei',
|
||||
'id': 'VPWON_1233944',
|
||||
'ext': 'mp4',
|
||||
'duration': 599.98,
|
||||
'channel_id': 'NED3',
|
||||
'genres': ['Jeugd', 'Serie'],
|
||||
'description': 'Appie en Aisia mogen beurtelings mee met hun vader Luc, die in de dierentuin werkt.',
|
||||
'uploader_id': 'NED3',
|
||||
'title': 'Aap, poot, pies',
|
||||
'thumbnail': 'https://images.poms.omroep.nl/image/s1080/608116',
|
||||
},
|
||||
'playlist_count': 4,
|
||||
}]
|
||||
|
||||
def _download_token(self, mid, url):
|
||||
return self._download_json(f'https://ntr.nl/ajax/player/embed/{mid}', mid, 'Downloading token JSON')['jwt']
|
||||
|
||||
class AndereTijdenIE(NPOPlaylistBaseIE):
|
||||
|
||||
class AndereTijdenIE(NTRIE):
|
||||
IE_NAME = 'anderetijden'
|
||||
_VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P<id>[^/?#&]+)'
|
||||
_PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class=["\'].*?\bpage-title\b.*?["\'][^>]*>(.+?)</h1>'
|
||||
_PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']'
|
||||
_PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container\s+episode-page["\'][^>]+data-mid=["\'](.+?)["\']'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',
|
||||
|
|
|
|||
105
yt_dlp/extractor/radioradicale.py
Normal file
105
yt_dlp/extractor/radioradicale.py
Normal 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)
|
||||
Loading…
Reference in New Issue
Block a user