beautifulsoup4模块

from bs4 import BeautifulSoup

soup = BeautifulSoup(content,‘html.parser‘)
#1.生成一个BeautifulSoup对象
for tag  in  soup.find_all():
    #针对script标签 应该直接删除
   if tag.name == ‘script‘:
        tag.decompose() #将符合条件的标签删除

desc = soup.text[0:150]  #截取文章简介  150个文本内容