re.sub提取替换字符

text ='<h1 align=left”class=~nnn”>姓名:李隆基</h1><h3 align=~right”class="mum>打开第三方坤宁宫</h3>'

import re
htm = re.findall(r"<h.*?</h\d>",text)
print(htm)
for t in htm:
    k = re.sub("<h.*?>",'',t)
    print(k)

评论