Question

怎么用python的BeautifulSoup来获取html中div的内容

Answer 1

# -*- coding:utf-8 -*-

#标签操作

from bs4 import BeautifulSoup
import urllib.request
import re

#如果是网址，可以用这个办法来读取网页
#html_doc = ""
#req = urllib.request.Request(html_doc)
#webpage = urllib.request.urlopen(req)
#html = webpage.read()

html="""
"""
soup = BeautifulSoup(html, 'html.parser') #文档对象

# 类名为xxx而且文本内容为hahaha的div
for k in soup.find_all('div',class_='atcTit_more'):#,string='更多'
print(k)