Python中過濾HTML標簽的函數

#用正則簡單過濾html的<>標簽
import re
str = "<img /><a>srcd</a>hello</br><br/>"
str = re.sub(r'</?\w+[^>]*>','',str)
print (str)

import re

test='<p>just for test</p><br/><font>just for test</font><b>test</b>'
pat = re.compile('(?<=\>).*?(?=\<)')
result=''.join(pat.findall(test))