lunax/haruhi-dl
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

[polskieradio] fix PR4 audition shit

Browse source
This commit is contained in:
Lauren Liberda 2021-08-31 20:25:12 +02:00
parent a550e21b8c
commit 19602fb3f5
1 changed files with 23 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

28
haruhi_dl/extractor/polskieradio.py
View file

@ -91,6 +91,14 @@ class PolskieRadioIE(PolskieRadioBaseExtractor):
'upload_date': '20201116', 'upload_date': '20201116',
}, },
}] }]
}, {
# PR4 audition - other frontend
'url': 'https://www.polskieradio.pl/10/6071/Artykul/2610977,Poglos-29-pazdziernika-godz-2301',
'info_dict': {
'id': '2610977',
'ext': 'mp3',
'title': 'Pogłos 29 października godz. 23:01',
},
}, { }, {
'url': 'http://polskieradio.pl/9/305/Artykul/1632955,Bardzo-popularne-slowo-remis', 'url': 'http://polskieradio.pl/9/305/Artykul/1632955,Bardzo-popularne-slowo-remis',
'only_matching': True, 'only_matching': True,
@ -113,24 +121,34 @@ class PolskieRadioIE(PolskieRadioBaseExtractor):
content = self._search_regex( content = self._search_regex(
r'(?s)<div[^>]+class="\s*this-article\s*"[^>]*>(.+?)<div[^>]+class="tags"[^>]*>', r'(?s)<div[^>]+class="\s*this-article\s*"[^>]*>(.+?)<div[^>]+class="tags"[^>]*>',
webpage, 'content') webpage, 'content', default=None)
timestamp = unified_timestamp(self._html_search_regex( timestamp = unified_timestamp(self._html_search_regex(
r'(?s)<span[^>]+id="datetime2"[^>]*>(.+?)</span>', r'(?s)<span[^>]+id="datetime2"[^>]*>(.+?)</span>',
webpage, 'timestamp', fatal=False)) webpage, 'timestamp', default=None))
thumbnail_url = self._og_search_thumbnail(webpage) thumbnail_url = self._og_search_thumbnail(webpage, default=None)
title = self._og_search_title(webpage).strip() title = self._og_search_title(webpage).strip()
description = strip_or_none(self._og_search_description(webpage, default=None))
if not content:
return {
'id': playlist_id,
'url': 'https:' + self._search_regex(r"source:\s*'(//static\.prsa\.pl/[^']+)'", webpage, 'audition record url'),
'title': title,
'description': description,
'timestamp': timestamp,
'thumbnail': thumbnail_url,
}
entries = self._extract_webpage_player_entries(content, playlist_id, { entries = self._extract_webpage_player_entries(content, playlist_id, {
'title': title, 'title': title,
'timestamp': timestamp, 'timestamp': timestamp,
'thumbnail': thumbnail_url, 'thumbnail': thumbnail_url,
}) })
description = strip_or_none(self._og_search_description(webpage))
return self.playlist_result(entries, playlist_id, title, description) return self.playlist_result(entries, playlist_id, title, description)