Python：正则匹配中文字符

isChinese = re.compile("([\u4e00-\u9fa5]+)+?")
chinese_list = isChinese.findall(str(content))

# -*- coding: utf-8-*-
import re
def filter_tags(htmlstr):
    re_cdata = re.compile('//<!\[CDATA\[[^>]*//\]\]>', re.I)  # 匹配CDATA
    re_script = re.compile('<\s*script[^>]*>[^<]*<\s*/\s*script\s*>', re.I)  # Script
    re_style = re.compile('<\s*style[^>]*>[^<]*<\s*/\s*style\s*>', re.I)  # style
    re_br = re.compile('<br\s*?/?>')  # 处理换行
    re_h = re.compile('</?\w+[^>]*>')  # HTML标签
    re_comment = re.compile('<!--[^>]*-->')  # HTML注释
    s = re_cdata.sub('', htmlstr)  # 去掉CDATA
    s = re_script.sub('', s)  # 去掉SCRIPT
    s = re_style.sub('', s)  # 去掉style
    s = re_br.sub('\n', s)  # 将br转换为换行
    s = re_h.sub('', s)  # 去掉HTML 标签
    s = re_comment.sub('', s)  # 去掉HTML注释
    blank_line = re.compile('\n+')
    s = blank_line.sub('\n', s)
    s = replaceCharEntity(s)  # 替换实体
    return s

def replaceCharEntity(htmlstr):
    CHAR_ENTITIES = {'nbsp': ' ', '160': ' ',
                     'lt': '<', '60': '<',
                     'gt': '>', '62': '>',
                     'amp': '&', '38': '&',
                     'quot': '"', '34': '"', }

    re_charEntity = re.compile(r'&#?(?P<name>\w+);')
    sz = re_charEntity.search(htmlstr)
    while sz:
        entity = sz.group()
        key = sz.group('name')
        try:
            htmlstr = re_charEntity.sub(CHAR_ENTITIES[key], htmlstr, 1)
            sz = re_charEntity.search(htmlstr)
        except KeyError:

            htmlstr = re_charEntity.sub('', htmlstr, 1)
            sz = re_charEntity.search(htmlstr)
    return htmlstr


def repalce(s, re_exp, repl_string):
    return re_exp.sub(repl_string, s)


if __name__ == '__main__':
    s = """1"""
    news = filter_tags(s).strip()