requests库爬取需要登录的网站

#!usr/bin/env python

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

"""

@author:lenovo

@file: 登录人人网.py

@time: 2019/10/{DAY}

"""

# import requests

# # 创建session对象，可以保存Cookie值

# ssion = requests.session()

#

# # 处理 headers

# headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}

#

# #需要登录的用户名和密码

# data = {"email":"1868156XXXX", "password":"XXXX"}

#

# # 发送附带用户名和密码的请求，并获取登录后的Cookie值，保存在ssion里

# ssion.post("http://www.renren.com/PLogin.do", data = data)

#

# #  ssion包含用户登录后的Cookie值，可以直接访问那些登录后才可以访问的页面

# response = ssion.get("http://www.renren.com/972540941/newsfeed/photo")

#

# result = response.content

#

# html = result.decode('utf-8')

# print(html)

# filename = "log.html"

# with open(filename,'w',encoding='utf-8') as f:

#     f.write(html)