[ie/orf:podcast] Add extractor (#8486)

Closes #5265
Authored by: Esokrates
This commit is contained in:
Esokrates 2023-11-11 20:06:25 +00:00 committed by GitHub
parent f6e97090d2
commit 6ba3085616
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 44 additions and 2 deletions

View file

@ -1420,6 +1420,7 @@ from .orf import (
ORFTVthekIE, ORFTVthekIE,
ORFFM4StoryIE, ORFFM4StoryIE,
ORFRadioIE, ORFRadioIE,
ORFPodcastIE,
ORFIPTVIE, ORFIPTVIE,
) )
from .outsidetv import OutsideTVIE from .outsidetv import OutsideTVIE

View file

@ -4,15 +4,16 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..networking import HEADRequest from ..networking import HEADRequest
from ..utils import ( from ..utils import (
InAdvancePagedList,
clean_html, clean_html,
determine_ext, determine_ext,
float_or_none, float_or_none,
InAdvancePagedList,
int_or_none, int_or_none,
join_nonempty, join_nonempty,
make_archive_id,
mimetype2ext,
orderedSet, orderedSet,
remove_end, remove_end,
make_archive_id,
smuggle_url, smuggle_url,
strip_jsonp, strip_jsonp,
try_call, try_call,
@ -21,6 +22,7 @@ from ..utils import (
unsmuggle_url, unsmuggle_url,
url_or_none, url_or_none,
) )
from ..utils.traversal import traverse_obj
class ORFTVthekIE(InfoExtractor): class ORFTVthekIE(InfoExtractor):
@ -334,6 +336,45 @@ class ORFRadioIE(InfoExtractor):
self._entries(data, station or station2), show_id, data.get('title'), clean_html(data.get('subtitle'))) self._entries(data, station or station2), show_id, data.get('title'), clean_html(data.get('subtitle')))
class ORFPodcastIE(InfoExtractor):
IE_NAME = 'orf:podcast'
_STATION_RE = '|'.join(map(re.escape, (
'bgl', 'fm4', 'ktn', 'noe', 'oe1', 'oe3',
'ooe', 'sbg', 'stm', 'tir', 'tv', 'vbg', 'wie')))
_VALID_URL = rf'https?://sound\.orf\.at/podcast/(?P<station>{_STATION_RE})/(?P<show>[\w-]+)/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://sound.orf.at/podcast/oe3/fruehstueck-bei-mir/nicolas-stockhammer-15102023',
'md5': '526a5700e03d271a1505386a8721ab9b',
'info_dict': {
'id': 'nicolas-stockhammer-15102023',
'ext': 'mp3',
'title': 'Nicolas Stockhammer (15.10.2023)',
'duration': 3396.0,
'series': 'Frühstück bei mir',
},
'skip': 'ORF podcasts are only available for a limited time'
}]
def _real_extract(self, url):
station, show, show_id = self._match_valid_url(url).group('station', 'show', 'id')
data = self._download_json(
f'https://audioapi.orf.at/radiothek/api/2.0/podcast/{station}/{show}/{show_id}', show_id)
return {
'id': show_id,
'ext': 'mp3',
'vcodec': 'none',
**traverse_obj(data, ('payload', {
'url': ('enclosures', 0, 'url'),
'ext': ('enclosures', 0, 'type', {mimetype2ext}),
'title': 'title',
'description': ('description', {clean_html}),
'duration': ('duration', {functools.partial(float_or_none, scale=1000)}),
'series': ('podcast', 'title'),
})),
}
class ORFIPTVIE(InfoExtractor): class ORFIPTVIE(InfoExtractor):
IE_NAME = 'orf:iptv' IE_NAME = 'orf:iptv'
IE_DESC = 'iptv.ORF.at' IE_DESC = 'iptv.ORF.at'