BeautifulSoup模块过滤掉html标签,只拿文本内容(处理XSS攻击)

from bs4 import BeautifulSoup
#kindeditor
def kindeditor(request):
    s = '''
        
默认值: false
    　　'''

    bs = BeautifulSoup(s,"html.parser")
    print(bs.text)
    return render(request,"KindEditor.html")


结果:
　　只获取到了   默认值: false

s = '''
    
默认值: false
    test
'''

bs = BeautifulSoup(s,"html.parser")
print(bs.text)

for tag in bs.find_all(): #查找所有的标签 按层级查找的
    print(tag.name)  #显示标签名
    print(tag.get("href")) #获取href标签的内容
    if tag.name in ["span"]: #里面是否有span标签
        tag.decompose()   #删除span 标签
print(bs)

return render(request,"KindEditor.html")

转载于:https://www.cnblogs.com/ajaxa/p/10413265.html