使用python去除HTML中标签的几种

In [96]: test
Out[96]: '<p>just for test</p><br/><font>just for test</font><b>test</b>'

In [97]: str_ = ''
    ...: flag = 1
    ...: for ele in test:
    ...:     if ele == "<":
    ...:         flag = 0
    ...:     elif ele == '>':
    ...:         flag = 1
    ...:         continue
    ...:     if flag == 1:
    ...:         str_ += ele
    ...:         

In [98]: str_
Out[98]: 'just for testjust for testtest'

In [99]: str_ = ''
    ...: flag = 1
    ...: for ele in test:
    ...:     if ele == "<":
    ...:         flag = 0
    ...:     elif ele == '>':
    ...:         flag = 1
    ...:         ele = ' '
    ...:     if flag == 1:
    ...:         str_ += ele
    ...:         

In [100]: str_
Out[100]: ' just for test   just for test  test '

import re

In [156]: pat = re.compile('(?<=\>).*?(?=\<)')

In [157]: pat.findall(test)
Out[157]: ['just for test', '', '', 'just for test', '', 'test']

In [158]: ''.join(pat.findall(test))
Out[158]: 'just for testjust for testtest'

pat = re.compile('>(.*?)<')
''.join(pat.findall(test))

In [167]: pat = re.compile('<[^>]+>', re.S)

In [168]: pat.sub('', test)
Out[168]: 'just for testjust for testtest'