python3爬虫，最短时间实现（四）

代码实现网站的模拟登陆：

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

import urllib.request
import urllib
import http.cookiejar
import re


def makeMyOpener(head = {
    'Connection':'Keep-Alive',
    'Accept':'text/html,application/xhtml,*/*',
    'Accept-language':'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3',
    'User-Agent':'Molizlla/5.0(Windows NT 6.3;WOW64;Trident/7.0;rv:11.0)like Gecko',
    }):
    cj = http.cookiejar.CookieJar()
    opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
    header = []
    for key,value in head.items():
        elem = (key,value)
        header.append(elem)


    opener.addheaders = header
    return opener


opener = makeMyOpener()
uop = opener.open('http://www.zhihu.com/')
temp_data = uop.read().decode()
#print(data)
r = re.compile(r'name="_xsrf" value="(.+?)"')
value = r.findall(temp_data)
_xsrf = value[0]


url = 'http://www.zhihu.com/#signin'
id = ''
password = ''
postdict = {
    '_xsrf':_xsrf,
    'email':id,
    'password':password,
    'rememberme':'y'
}
postData = urllib.parse.urlencode(postdict).encode()
op = opener.open(url,postData)
data = op.read()

print(data)

参考如下链接：http://jecvay.com/2014/10/python3-web-bug-series4.html（足够详细）