fix: clean html tag stripping regex
This commit is contained in:
@@ -18,7 +18,7 @@ logger = logging.getLogger(__name__)
|
||||
def _clean_html(raw_html: str) -> str:
|
||||
if not raw_html:
|
||||
return ""
|
||||
text = re.sub(r'<[^>]+>', ' ', raw_html)
|
||||
text = re.sub(r'<[^>]+>', '', raw_html)
|
||||
text = html.unescape(text)
|
||||
return re.sub(r'\s+', ' ', text).strip()
|
||||
|
||||
|
||||
Reference in New Issue
Block a user