mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-06-27 08:58:30 +00:00
Code Issues Projects Releases Wiki Activity

[ie/IlPost] Fix extractor - merge review pt2

Browse Source
This commit is contained in:
Simone Dotto 2025-06-15 16:16:48 +02:00
parent f736c9627f
commit 1b4110c8de
1 changed files with 57 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

103
yt_dlp/extractor/ilpost.py
View File

@ -1,3 +1,5 @@
import itertools
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
clean_html, clean_html,
@ -11,25 +13,24 @@
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/timbuctu/ep-323-lanno-record-della-pena-di-morte/',
'url': 'https://www.ilpost.it/podcasts/timbuctu/ep-323-lanno-record-della-pena-di-morte/', 'md5': '55d88cc23bcab991639ebcbf1b4c0aa1',
'md5': '55d88cc23bcab991639ebcbf1b4c0aa1', 'info_dict': {
'info_dict': { 'id': '3326553',
'id': '3326553', 'ext': 'mp3',
'ext': 'mp3', 'display_id': 'ep-323-lanno-record-della-pena-di-morte',
'display_id': 'ep-323-lanno-record-della-pena-di-morte', 'title': 'Ep. 323 – L’anno record della pena di morte',
'title': 'Ep. 323 – L’anno record della pena di morte', 'url': 'https://static-prod.cdnilpost.com/wp-content/uploads/2025/05/25/1748196012-timbuctu_250526_v1_-16lufs.mp3',
'url': 'https://static-prod.cdnilpost.com/wp-content/uploads/2025/05/25/1748196012-timbuctu_250526_v1_-16lufs.mp3', 'timestamp': 1748235641,
'timestamp': 1748235641, 'upload_date': '20250526',
'upload_date': '20250526', 'description': 'md5:331514a14779fab06e902160ec8c89ba',
'description': 'md5:331514a14779fab06e902160ec8c89ba', 'duration': 751,
'duration': 751, 'availability': 'public',
'availability': 'public', 'series_id': '233679',
'series_id': '233679', 'thumbnail': 'https://www.ilpost.it/wp-content/uploads/2023/05/19/1684536738-copertina500x500.jpg',
'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/', 'url': 'https://www.ilpost.it/podcasts/l-invasione/1-avis-akvasas-ka/',
'md5': '43649f002d85e1c2f319bb478d479c40', 'md5': '43649f002d85e1c2f319bb478d479c40',
@ -47,14 +48,14 @@ class IlPostIE(InfoExtractor):
'series_id': '235598', 'series_id': '235598',
'thumbnail': 'https://www.ilpost.it/wp-content/uploads/2023/12/22/1703238848-copertina500x500.jpg', '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)
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]
return { return {
'id': str(episode['id']), 'id': str(episode['id']),
@ -74,15 +75,14 @@ def _real_extract(self, url):
class IlPostPodcastIE(InfoExtractor): class IlPostPodcastIE(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/basaglia-e-i-suoi/',
'url': 'https://www.ilpost.it/podcasts/basaglia-e-i-suoi/', 'info_dict': {
'info_dict': { 'id': '239295',
'id': '239295', 'title': 'Basaglia e i suoi',
'title': 'Basaglia e i suoi',
},
'playlist_mincount': 5,
}, },
'playlist_mincount': 5,
},
{ {
'url': 'https://www.ilpost.it/podcasts/morning/', 'url': 'https://www.ilpost.it/podcasts/morning/',
'info_dict': { 'info_dict': {
@ -90,27 +90,38 @@ class IlPostPodcastIE(InfoExtractor):
'title': 'Morning', 'title': 'Morning',
}, },
'playlist_mincount': 20, 'playlist_mincount': 20,
}, }]
]
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
entries = []
podcast = None
data = self._download_json(f'https://api-prod.ilpost.it/podcast/v1/podcast/{display_id}', display_id, query={'hits': '20'}) max_hits = 10000 # found experimentally
data = self._download_json(f'https://api-prod.ilpost.it/podcast/v1/podcast/{display_id}', display_id, query={'hits': data['head']['data']['total']})
podcast = data['data'][0]['parent'] for page in itertools.count(1):
data = self._download_json(
f'https://api-prod.ilpost.it/podcast/v1/podcast/{display_id}',
display_id,
query={'hits': max_hits, 'pg': page},
expected_status=500,
)
entries = [{ if podcast is None:
'_type': 'url', podcast = traverse_obj(data, ('data', 0, 'parent'))
'ie_key': IlPostIE.ie_key(),
'url': episode['url'],
**traverse_obj(episode, {
'episode_id': ('id', {str_or_none}),
'title': ('title', {clean_html}),
'description': ('content_html', {clean_html}),
}),
} for episode in traverse_obj(data, ('data', lambda _, v: url_or_none(v['url'])))]
return self.playlist_result(entries, if data.get('data') is None:
str(podcast['id']), clean_html(podcast.get('title'))) break
entries += [{
'_type': 'url',
'ie_key': IlPostIE.ie_key(),
'url': episode['url'],
**traverse_obj(episode, {
'episode_id': ('id', {str_or_none}),
'title': ('title', {clean_html}),
'description': ('content_html', {clean_html}),
}),
} for episode in traverse_obj(data, ('data', lambda _, v: url_or_none(v['url'])))]
return self.playlist_result(entries, str_or_none(podcast.get('id')), clean_html(podcast.get('title')))