简单的爬百度一个搜索页面

本次搜索了JAVA

# -*- coding: utf-8 -*-
import re
from urllib.request import urlopen
from urllib.request import Request
from bs4 import BeautifulSoup
from lxml import etree

#添加模拟浏览器协议头
headers = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'}
url = "https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=0&rsv_idx=1&tn=baidu&wd=java&rsv_pq=e2a469100000275e&rsv_t=8544DlzD%2F9efPS0lqtxbirlgzVuKOQieqbfUd3s6HCYerkQ38Aa%2B8lAnf2k&rqlang=cn&rsv_enter=0&rsv_sug3=5&rsv_sug1=3&rsv_sug7=100&inputT=2074&rsv_sug4=4070"
req_timeout = 5
req = Request(url=url,headers=headers)
f = urlopen(req,None,req_timeout)
s = f.read()
s = s.decode('utf-8')

ss = str(s)

#print(ss)
spath = './baidu.html'
f=open(spath,"w",encoding='utf-8')
f.write(ss)
f.close()