Python3 使用requests库读取本地保存的cookie文件实现免登录访问

1.  读取selenium模块保存的本地cookie文件来访问知乎

读取http://www.cnblogs.com/strivepy/p/9233389.html保存的本地cookie来访问知乎的用户设置界面，用selenium保存下来的json文件如下格式：

 [{"domain": "www.zhihu.com", "expiry": 1527855266.402958, "httpOnly": false, "name": "tgw_l7_route", "path": "/", "secure": false, "value": "200d77f3369d188920b797ddf09ec8d1"},
  {"domain": ".zhihu.com", "expiry": 1622462366.40309, "httpOnly": false, "name": "d_c0", "path": "/", "secure": false, "value": "\"AFAkkY_hrg2PTvLVtweW-Ok8mRLKop4IJZY=|1527854371\""},
  {"domain": ".zhihu.com", "httpOnly": false, "name": "_xsrf", "path": "/", "secure": false, "value": "7da6b4e4-c77d-47a4-81fa-68b1262235c8"}....后面的删掉了]

包含很多用不到的信息，比如path、secure等，在读取cookie只需要读取每个cookie的name和value属性。代码放在名为zhihu.py模块中：

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

 import requests
 import json
 import os
 from requests.cookies import RequestsCookieJar

 def parse_index():
     url = 'https://www.zhihu.com/settings/account'
     headers = {
         'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36'
     }
     cookies = getcookies_decode_to_dict()
     # cookies = getcookies_decode_to_cookiejar()
     # requests.get()方法的cookies参数只接收Dict或者CookieJar对象
     response = requests.get(url=url, headers=headers, cookies=cookies)
     print(response.url)
     print(response.text)

 def getcookies_decode_to_dict():
     path = os.getcwd() + '/cookies/'
     if not os.path.exists(path):
         print('Cookie文件不存在，请先运行cookiesload.py')
     else:
         cookies_dict = {}
         with open(path + 'cookies.txt', 'r') as f:
             cookies = json.loads(f.read())
             for cookie in cookies:
                 cookies_dict[cookie['name']] = cookie['value']
             return cookies_dict

 def getcookies_decode_to_cookiejar():
     path = os.getcwd() + '/cookies/'
     if not os.path.exists(path):
         print('Cookie文件不存在，请先运行cookiesload.py')
     else:
         cookiejar = RequestsCookieJar()
         with open(path + 'cookies.txt', 'r') as f:
             cookies = json.loads(f.read())
             for cookie in cookies:
                 cookiejar.set(cookie['name'], cookie['value'])
             return cookiejar

 if __name__ == '__main__':
     parse_index()

获取到的源码显示，已经成功抓取到知乎用户设置页面。