mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-06-27 17:08:32 +00:00
Code Issues Projects Releases Wiki Activity

[ie/IlPost] Fix extractor - merge review

Browse Source
This commit is contained in:
Simone Dotto 2025-05-30 00:56:16 +02:00
parent 060092e5f3
commit f736c9627f
1 changed files with 74 additions and 65 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

139
yt_dlp/extractor/ilpost.py
View File

@ -1,52 +1,67 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError,
clean_html, clean_html,
float_or_none, float_or_none,
int_or_none, int_or_none,
unescapeHTML, str_or_none,
url_or_none, url_or_none,
) )
from ..utils.traversal import traverse_obj from ..utils.traversal import traverse_obj
class IlPostIE(InfoExtractor): class IlPostIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ilpost\.it/podcasts/[^/]+/(?P<id>[^/?#]+)' _VALID_URL = r'https?://(?:www\.)?ilpost\.it/podcasts/[^/?#]+/(?P<id>[^/?#]+)'
_TESTS = [{ _TESTS = [
'url': 'https://www.ilpost.it/podcasts/l-invasione/1-avis-akvasas-ka/', {
'md5': '43649f002d85e1c2f319bb478d479c40', 'url': 'https://www.ilpost.it/podcasts/timbuctu/ep-323-lanno-record-della-pena-di-morte/',
'info_dict': { 'md5': '55d88cc23bcab991639ebcbf1b4c0aa1',
'id': '2972047', 'info_dict': {
'ext': 'mp3', 'id': '3326553',
'display_id': '1-avis-akvasas-ka', 'ext': 'mp3',
'title': '1. Avis akvasas ka', 'display_id': 'ep-323-lanno-record-della-pena-di-morte',
'url': 'https://www.ilpost.it/wp-content/uploads/2023/12/28/1703781217-l-invasione-pt1-v6.mp3', 'title': 'Ep. 323 – L’anno record della pena di morte',
'timestamp': 1703835014, 'url': 'https://static-prod.cdnilpost.com/wp-content/uploads/2025/05/25/1748196012-timbuctu_250526_v1_-16lufs.mp3',
'upload_date': '20231229', 'timestamp': 1748235641,
'description': 'md5:54c5f12fb5b90f6c7cca6476a0802a99', 'upload_date': '20250526',
'duration': 2495.0, 'description': 'md5:331514a14779fab06e902160ec8c89ba',
'availability': 'public', 'duration': 751,
'series_id': '235598', 'availability': 'public',
'thumbnail': 'https://www.ilpost.it/wp-content/uploads/2023/12/22/1703238848-copertina500x500.jpg', 'series_id': '233679',
'thumbnail': 'https://www.ilpost.it/wp-content/uploads/2023/05/19/1684536738-copertina500x500.jpg',
},
}, },
}] {
'url': 'https://www.ilpost.it/podcasts/l-invasione/1-avis-akvasas-ka/',
'md5': '43649f002d85e1c2f319bb478d479c40',
'info_dict': {
'id': '2972047',
'ext': 'mp3',
'display_id': '1-avis-akvasas-ka',
'title': '1. Avis akvasas ka',
'url': 'https://www.ilpost.it/wp-content/uploads/2023/12/28/1703781217-l-invasione-pt1-v6.mp3',
'timestamp': 1703835014,
'upload_date': '20231229',
'description': 'md5:57d147951b522c92095f64e28570cf4a',
'duration': 2495.0,
'availability': 'public',
'series_id': '235598',
'thumbnail': 'https://www.ilpost.it/wp-content/uploads/2023/12/22/1703238848-copertina500x500.jpg',
},
},
]
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
try: episode = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['data']['data']['episode']['data'][0]
episode = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['data']['data']['episode']['data'][0]
episode_id = episode['id']
except KeyError:
raise ExtractorError('Failed to extract episode')
return { return {
'id': str(episode_id), 'id': str(episode['id']),
'display_id': display_id, 'display_id': display_id,
**traverse_obj(episode, { **traverse_obj(episode, {
'series_id': ('parent', 'id', {int_or_none}), 'series_id': ('parent', 'id', {str_or_none}),
'title': ('title', {unescapeHTML}), 'title': ('title', {clean_html}),
'description': ('content_html', {clean_html}), 'description': ('content_html', {clean_html}),
'url': ('episode_raw_url', {url_or_none}), 'url': ('episode_raw_url', {url_or_none}),
'thumbnail': ('image', {url_or_none}), 'thumbnail': ('image', {url_or_none}),
@ -58,50 +73,44 @@ def _real_extract(self, url):
class IlPostPodcastIE(InfoExtractor): class IlPostPodcastIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ilpost\.it/podcasts/(?P<id>[\w\-]+)[/?#]?$' _VALID_URL = r'https?://(?:www\.)?ilpost\.it/podcasts/(?P<id>[^/?#]+)/?(?:[?#]|$)'
_TESTS = [{ _TESTS = [
'url': 'https://www.ilpost.it/podcasts/morning/', {
'info_dict': { 'url': 'https://www.ilpost.it/podcasts/basaglia-e-i-suoi/',
'id': 'morning', 'info_dict': {
'display_id': 'morning', 'id': '239295',
'title': 'Morning', 'title': 'Basaglia e i suoi',
'series': 'Morning', },
'playlist_mincount': 5,
}, },
'playlist_mincount': 20, {
}, { 'url': 'https://www.ilpost.it/podcasts/morning/',
'url': 'https://www.ilpost.it/podcasts/basaglia-e-i-suoi/', 'info_dict': {
'info_dict': { 'id': '227474',
'id': 'basaglia-e-i-suoi', 'title': 'Morning',
'display_id': 'basaglia-e-i-suoi', },
'title': 'Basaglia e i suoi', 'playlist_mincount': 20,
'series': 'Basaglia e i suoi',
}, },
'playlist_mincount': 5, ]
}]
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_valid_url(url).group('id') display_id = self._match_id(url)
data = self._download_json(f'https://api-prod.ilpost.it/podcast/v1/podcast/{display_id}?hits=20', display_id)
try: data = self._download_json(f'https://api-prod.ilpost.it/podcast/v1/podcast/{display_id}', display_id, query={'hits': '20'})
podcast = data['data'][0]['parent'] data = self._download_json(f'https://api-prod.ilpost.it/podcast/v1/podcast/{display_id}', display_id, query={'hits': data['head']['data']['total']})
except KeyError:
raise ExtractorError('Failed to extract series') podcast = data['data'][0]['parent']
entries = [{ entries = [{
'_type': 'url', '_type': 'url',
'ie_key': 'IlPost', 'ie_key': IlPostIE.ie_key(),
'url': episode['url'], 'url': episode['url'],
'episode_id': episode['id'], **traverse_obj(episode, {
'title': unescapeHTML(episode.get('title')), 'episode_id': ('id', {str_or_none}),
'description': clean_html(episode.get('content_html')), 'title': ('title', {clean_html}),
'series': unescapeHTML(podcast.get('title')), 'description': ('content_html', {clean_html}),
} for episode in traverse_obj(data, ('data'))] }),
} for episode in traverse_obj(data, ('data', lambda _, v: url_or_none(v['url'])))]
return { return self.playlist_result(entries,
'_type': 'playlist', str(podcast['id']), clean_html(podcast.get('title')))
'id': podcast.get('id'),
'display_id': display_id,
'title': unescapeHTML(podcast.get('title')),
'entries': entries,
}