python获取百度页面,并格式化
from urllib import request
from bs4 import BeautifulSoup
import re
req=request.urlopen("http://www.baidu.com")
html_doc=req.read().decode("utf-8")
soup = BeautifulSoup(html_doc,'html.parser')
#print(soup.prettify())
#print(soup.title.string)