only .decompose() when it's an empty and unknown tag

This commit is contained in:
jesopo 2019-11-04 12:51:24 +00:00
parent 62781badc4
commit 516884acb8

View file

@ -77,9 +77,10 @@ def _normalise_note(content):
lines = [] lines = []
for element in soup.find_all(): for element in soup.find_all():
if not element.name in KNOWN_TAGS: if not element.name in KNOWN_TAGS:
element.unwrap() if element.text.strip() == "":
elif element.text.strip() == "": element.decompose()
element.decompose() else:
element.unwrap()
out = "" out = ""
for element in soup.children: for element in soup.children: