Python 去掉文本中的HTML

Python 去掉文本中的HTML，同时还去掉了回车、空格、制表符、JS、CSS

from bs4 import BeautifulSoup as bs

if __name__ == '__main__':
    content='xxxx'
    content_text = bs(content, "lxml")
    [script.extract() for script in content_text.findAll('script')]
    [style.extract() for style in content_text.findAll('style')]
    content_text = content_text.get_text().replace(' ', '').replace('\n', '').replace('\r', '').replace('\t', '').replace('　', '').replace(' ', '')
    print(content_text )