[extractor/sverigesradio] Support slug URLs (#7220)

Closes #7145
Authored by: bashonly
This commit is contained in:
bashonly 2023-06-04 07:15:09 -05:00 committed by GitHub
parent 971d901d12
commit 5ee9a7d6e1
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23

View file

@ -1,8 +1,13 @@
from .common import InfoExtractor
from ..utils import (
determine_ext,
extract_attributes,
get_element_by_id,
get_element_html_by_class,
int_or_none,
str_or_none,
traverse_obj,
url_or_none,
)
@ -21,7 +26,15 @@ class SverigesRadioBaseIE(InfoExtractor):
}
def _real_extract(self, url):
audio_id = self._match_id(url)
audio_id, display_id = self._match_valid_url(url).group('id', 'slug')
if not audio_id:
webpage = self._download_webpage(url, display_id)
audio_id = (
traverse_obj(
get_element_html_by_class('audio-button', webpage),
({extract_attributes}, ('data-audio-id', 'data-publication-id')), get_all=False)
or self._parse_json(get_element_by_id('gtm-metadata', webpage), display_id)['pageId'])
query = {
'id': audio_id,
'type': self._AUDIO_TYPE,
@ -30,7 +43,6 @@ def _real_extract(self, url):
item = self._download_json(
self._BASE_URL + 'audiometadata', audio_id,
'Downloading audio JSON metadata', query=query)['items'][0]
title = item['subtitle']
query['format'] = 'iis'
urls = []
@ -61,18 +73,20 @@ def _real_extract(self, url):
return {
'id': audio_id,
'title': title,
'formats': formats,
'series': item.get('title'),
'duration': int_or_none(item.get('duration')),
'thumbnail': item.get('displayimageurl'),
'description': item.get('description'),
**traverse_obj(item, {
'title': 'subtitle',
'series': 'title',
'duration': ('duration', {int_or_none}),
'thumbnail': ('displayimageurl', {url_or_none}),
'description': 'description',
}),
}
class SverigesRadioPublicationIE(SverigesRadioBaseIE):
IE_NAME = 'sverigesradio:publication'
_VALID_URL = r'https?://(?:www\.)?sverigesradio\.se/sida/(?:artikel|gruppsida)\.aspx\?.*?\bartikel=(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:www\.)?sverigesradio\.se/(?:sida/)?(?:artikel|gruppsida)(?:\.aspx\?.*?\bartikel=(?P<id>[0-9]+)|/(?P<slug>[\w-]+))'
_TESTS = [{
'url': 'https://sverigesradio.se/sida/artikel.aspx?programid=83&artikel=7038546',
'md5': '6a4917e1923fccb080e5a206a5afa542',
@ -85,6 +99,18 @@ class SverigesRadioPublicationIE(SverigesRadioBaseIE):
'description': 'md5:daf7ce66a8f0a53d5465a5984d3839df',
'thumbnail': r're:^https?://.*\.jpg',
},
}, {
'url': 'https://sverigesradio.se/artikel/tysk-fotbollsfeber-bayern-munchens-10-ariga-segersvit-kan-brytas',
'md5': 'f8a914ad50f491bb74eed403ab4bfef6',
'info_dict': {
'id': '8360345',
'ext': 'm4a',
'title': 'Tysk fotbollsfeber när Bayern Münchens 10-åriga segersvit kan brytas',
'series': 'Radiosporten',
'description': 'md5:5254610e20ce527ecb3a6102a06dcc5f',
'duration': 72,
'thumbnail': r're:^https?://.*\.jpg',
},
}, {
'url': 'https://sverigesradio.se/sida/gruppsida.aspx?programid=3304&grupp=6247&artikel=7146887',
'only_matching': True,
@ -94,8 +120,8 @@ class SverigesRadioPublicationIE(SverigesRadioBaseIE):
class SverigesRadioEpisodeIE(SverigesRadioBaseIE):
IE_NAME = 'sverigesradio:episode'
_VALID_URL = r'https?://(?:www\.)?sverigesradio\.se/(?:sida/)?avsnitt/(?P<id>[0-9]+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?sverigesradio\.se/(?:sida/)?avsnitt/(?:(?P<id>\d+)|(?P<slug>[\w-]+))(?:$|[#?])'
_TESTS = [{
'url': 'https://sverigesradio.se/avsnitt/1140922?programid=1300',
'md5': '20dc4d8db24228f846be390b0c59a07c',
'info_dict': {
@ -106,6 +132,18 @@ class SverigesRadioEpisodeIE(SverigesRadioBaseIE):
'title': 'Metoo och valen',
'description': 'md5:fcb5c1f667f00badcc702b196f10a27e',
'thumbnail': r're:^https?://.*\.jpg',
}
}
},
}, {
'url': 'https://sverigesradio.se/avsnitt/p4-live-med-first-aid-kit-scandinavium-mars-2023',
'md5': 'ce17fb82520a8033dbb846993d5589fe',
'info_dict': {
'id': '2160416',
'ext': 'm4a',
'title': 'P4 Live med First Aid Kit',
'description': 'md5:6d5b78eed3d2b65f6de04daa45e9285d',
'thumbnail': r're:^https?://.*\.jpg',
'series': 'P4 Live',
'duration': 5640,
},
}]
_AUDIO_TYPE = 'episode'