urllib2 爬取网页信息

# coding:utf-8
import cookielib
import urllib2
import bs4


url = 'http://www.baidu.com'
response1 = urllib2.urlopen(url)
print '状态码', response1.getcode()
print len(response1.read())

print '第二种方法，可以加入请求数据'
request = urllib2.Request(url)
request.add_header('user-agent', 'Mozilla/5.0')
response2 = urllib2.urlopen(request)
print '状态码', response2.getcode()
print len(response2.read())

print '第三种方法'
cj = cookielib.CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
urllib2.install_opener(opener)
response3 = urllib2.urlopen(url)
print '状态码', response3.getcode()
print '获取cookie信息',cj
print 'content', response3.read()