Python清除常见的网页空格格式

def clean(string):
    pattern = re.compile(r'<[^>]+>', re.S)
    string = pattern.sub('', string)
    string = string.replace('
', ' ').replace('
', ' ').replace('&nbsp;', ' ').replace('	', ' ').replace(" ",'')
    string = string.strip()
    return string