Miroirs/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2025-01-16 03:40:50 +01:00
Code Issues Projects Releases Packages Wiki Activity

use re.sub instead in description extraction

Browse source 
Co-authored-by: dirkf <fieldhouse@gmx.net>
This commit is contained in:
N/Ame 2024-10-18 13:34:07 +13:00 committed by GitHub
parent 28a1163010
commit 38383ea313
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
yt_dlp/extractor/boomplay.py
View file

@ -110,12 +110,10 @@ class BoomplayBaseIE(InfoExtractor):
def _extract_page_metadata(self, webpage, _id, playlist=False):
metadata_div = self._get_element_by_class_and_tag('summary', 'div', webpage) or ''
metadata_entries = re.findall(r'(?si)<strong>(?P<entry>.*?)</strong>', metadata_div) or []
description = (
self._get_element_by_class_and_tag('description_content', 'span', webpage)
or 'Listen and download music for free on Boomplay!')
description = clean_html(description.strip())
if description == 'Listen and download music for free on Boomplay!':
description = None
description = re.sub(
'(?i)Listen and download music for free on Boomplay!', '',
clean_html(self._get_element_by_class_and_tag(
'description_content', 'span', webpage)) or '') or None
details_section = self._get_element_by_class_and_tag('songDetailInfo', 'section', webpage) or ''
metadata_entries.extend(re.findall(r'(?si)<li>(?P<entry>.*?)</li>', details_section) or [])