去除指定標簽
from bs4 import BeautifulSoup
#去除屬性ul
[s.extract() for s in soup("ul")]
# 去除屬性svg
[s.extract() for s in soup("svg")]
# 去除屬性script
[s.extract() for s in soup("script")]
去除注釋
from bs4 import BeautifulSoup, Comment
#去除注釋
comments = soup.findAll(text=lambda text: isinstance(text, Comment))
[comment.extract() for comment in comments]