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

Posted 2020-11-20 StrivePy

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：

1 [{"domain": "www.zhihu.com", "expiry": 1527855266.402958, "httpOnly": false, "name": "tgw_l7_route", "path": "/", "secure": false, "value": "200d77f3369d188920b797ddf09ec8d1"},
2  {"domain": ".zhihu.com", "expiry": 1622462366.40309, "httpOnly": false, "name": "d_c0", "path": "/", "secure": false, "value": "\\"AFAkkY_hrg2PTvLVtweW-Ok8mRLKop4IJZY=|1527854371\\""}, 
3  {"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：

 1 # -*- coding: utf-8 -*-
 2 
 3 import requests
 4 import json
 5 import os
 6 from requests.cookies import RequestsCookieJar
 7 
 8 
 9 def parse_index():
10     url = \'https://www.zhihu.com/settings/account\'
11     headers = {
12         \'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\'
13     }
14     cookies = getcookies_decode_to_dict()
15     # cookies = getcookies_decode_to_cookiejar()
16     # requests.get()方法的cookies参数只接收Dict或者CookieJar对象
17     response = requests.get(url=url, headers=headers, cookies=cookies)
18     print(response.url)
19     print(response.text)
20 
21 
22 def getcookies_decode_to_dict():
23     path = os.getcwd() + \'/cookies/\'
24     if not os.path.exists(path):
25         print(\'Cookie文件不存在，请先运行cookiesload.py\')
26     else:
27         cookies_dict = {}
28         with open(path + \'cookies.txt\', \'r\') as f:
29             cookies = json.loads(f.read())
30             for cookie in cookies:
31                 cookies_dict[cookie[\'name\']] = cookie[\'value\']
32             return cookies_dict
33 
34 
35 def getcookies_decode_to_cookiejar():
36     path = os.getcwd() + \'/cookies/\'
37     if not os.path.exists(path):
38         print(\'Cookie文件不存在，请先运行cookiesload.py\')
39     else:
40         cookiejar = RequestsCookieJar()
41         with open(path + \'cookies.txt\', \'r\') as f:
42             cookies = json.loads(f.read())
43             for cookie in cookies:
44                 cookiejar.set(cookie[\'name\'], cookie[\'value\'])
45             return cookiejar
46 
47 
48 if __name__ == \'__main__\':
49     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。