# 防止xss攻击,过滤script标签，获取出标签外的内容

 

from bs4 import BeautifulSoup
s = '<h1>123</h1> <span>456<span>'
soup =  BeautifulSoup(s,'html.parser')
print(soup.text)  # 结果  123    456

# 构建摘要数据,获取标签字符串的文本前150个符号

soup=BeautifulSoup(content,"html.parser")

desc=soup.text[0:150]+"..."

 # 防止xss攻击,过滤script标签

s = '<h1>123</h1> <span>456<span> <script>alert('66')</script>'

soup.find_all()   # 获取标签名

for tag in soup.find_all():

    print(tag.name)
    if tag.name=="script":
        tag.decompose()    # 删除

转载于:https://www.cnblogs.com/ApolloZ/p/10483572.html