优雅的过滤HTML

clean html.py

from w3lib.html import remove_tags, strip_html5_whitespace
# keep参数为需要保留的标签名称
remove_tags(text, keep=('img',)) 


# 移除HTML标签，并删除前后的空白字符
def clean_tags(text, which_ones=(), keep=(), encoding=None) -> str:
  if not text:
    return None
  content = remove_tags(text, which_ones, keep, encoding)
  content = remove_tags(content)
  content = strip_html5_whitespace(content)
  return content