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 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

41
yt_dlp/extractor/ilpost.py
View File

@ -1,3 +1,5 @@
import itertools
from .common import InfoExtractor
from ..utils import (
clean_html,
@ -11,8 +13,7 @@
class IlPostIE(InfoExtractor):
_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/',
'md5': '55d88cc23bcab991639ebcbf1b4c0aa1',
'info_dict': {
@ -47,14 +48,14 @@ class IlPostIE(InfoExtractor):
'series_id': '235598',
'thumbnail': 'https://www.ilpost.it/wp-content/uploads/2023/12/22/1703238848-copertina500x500.jpg',
},
},
]
}]
def _real_extract(self, url):
display_id = self._match_id(url)
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 {
'id': str(episode['id']),
@ -74,8 +75,7 @@ def _real_extract(self, url):
class IlPostPodcastIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ilpost\.it/podcasts/(?P<id>[^/?#]+)/?(?:[?#]|$)'
_TESTS = [
{
_TESTS = [{
'url': 'https://www.ilpost.it/podcasts/basaglia-e-i-suoi/',
'info_dict': {
'id': '239295',
@ -90,18 +90,30 @@ class IlPostPodcastIE(InfoExtractor):
'title': 'Morning',
},
'playlist_mincount': 20,
},
]
}]
def _real_extract(self, 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'})
data = self._download_json(f'https://api-prod.ilpost.it/podcast/v1/podcast/{display_id}', display_id, query={'hits': data['head']['data']['total']})
max_hits = 10000 # found experimentally
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:
podcast = traverse_obj(data, ('data', 0, 'parent'))
if data.get('data') is None:
break
entries += [{
'_type': 'url',
'ie_key': IlPostIE.ie_key(),
'url': episode['url'],
@ -112,5 +124,4 @@ def _real_extract(self, url):
}),
} for episode in traverse_obj(data, ('data', lambda _, v: url_or_none(v['url'])))]
return self.playlist_result(entries,
str(podcast['id']), clean_html(podcast.get('title')))
return self.playlist_result(entries, str_or_none(podcast.get('id')), clean_html(podcast.get('title')))