Python3正則去掉HTML標簽

1.引用一段代碼

import re
 
html = '<pre class="line mt-10 q-content" accuse="qContent">\
目的是通過第一次soup.find按class粗略篩選並通過soup.find_all篩選出列表中的a標簽並讀入href和title屬性<br><br>\
但是由於目標鏈接可能有圖片鏈接,而這是我不想要的.請問如何去除?<br></pre>'
 
reg = re.compile('<[^>]*>')
 
print(reg.sub('',html))

2.重點

reg = re.compile('<[^>]*>')
 
print(reg.sub('',html))

3.實例

開始

import requests
import re
from bs4 import BeautifulSoup
retxt=open('test.log','r')
for x in range(250,999):
    #rurl=rurl.strip('\n')
    url='http://ananas.mooc1.mti100.com/tologin?fid={0}'.format(x)
    #print(url)
    try:

        response=requests.get(url,timeout=1).text
        #print(response)
        soup=BeautifulSoup(response,features="lxml")
        result=soup.find_all('span',attrs={'class':'l_schoolName2'})
        print('學校：{0}'.format(result))
    except requests.exceptions.InvalidURL:
        pass
    except requests.exceptions.ConnectionError:
        pass
    except requests.exceptions.ReadTimeout:
        pass

輸出

學校：[<span class="l_schoolName2" id="schoolName2">
                                杭州師范大學
                        </span>]
學校：[<span class="l_schoolName2" id="schoolName2">

去除標簽之后

import requests
import re
from bs4 import BeautifulSoup
#retxt=open('test.log','r')
for x in range(250,999):
    #rurl=rurl.strip('\n')
    url='http://ananas.mooc1.mti100.com/tologin?fid={0}'.format(x)
    #print(url)
    try:

        response=requests.get(url,timeout=1).text
        #print(response)
        soup=BeautifulSoup(response,features="lxml")
        result=soup.find_all('span',attrs={'class':'l_schoolName2'})
        reg=re.compile('<[^>]*>',re.S)
        print('學校：{0}'.format(reg.sub('',str(result))))
    except requests.exceptions.InvalidURL:
        pass
    except requests.exceptions.ConnectionError:
        pass
    except requests.exceptions.ReadTimeout:
        pass

輸出

學校：[]
學校：[]
學校：[
                                上海電子信息職業技術學院
                        ]
學校：[]
學校：[
                                超星大學