Requests 模拟知乎登录

常见 http_status_code

• 200 请求被成功处理
• 301/302 永久重定向/临时重定向
• 403 没有权限访问
• 404 没有相对应的资源
• 500 服务器错误
• 503 服务器停机/正在维护

实际上这些 Status_code 一般是由服务器指定的，某些情况下是框架，或自动定义的

代码示例：

# -*- coding: utf-8 -*-
__author__ = 'Well'

import requests

try:
 # py2 中是cookielib
 import cookielib
except:
 import http.cookiejar as cookielib

import re

# 实例化 session
session = requests.sessions()
# 实例化 LWPCookieJar ，以保存 cookies
session.cookies = cookielib.LWPCookieJar()
try:
 session.cookies.load(ignore_discard=True)
except:
 print('cookie 未能加载')

user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:76.0) Gecko/20100101 Firefox/76.0'
header = {
 'Host': 'www.zhihu.com',
 'Referer': 'https://www.zhihu.com/signin?next=%2F',
 'User-Agent': user_agent
}
def is_login():
 # 判断登录状态
 rep = session.get('https://www.zhihu.com/settings/account', headers=header, allow_redirects=False)
 if rep.status_code != 200:
     return False
 else:
     return True

def get_xxrf():
 # 获取xsrf code
 response = session.get('www.zhihu.com', headers=header).text
 return re.match('', response).group(1)

def get_index():
 # 保存HTML
 response = session.get('www.zhihu.com', headers=header).text
 with open('index_page.html', 'wb') as fp:
     fp.write(response.encode('utf-8'))
 print('ok')

def zhihu_login(account, password):
 # 知乎登录
 if re.match(r'^1\d{10}', account):
     post_url = 'https://www.zhihu.com/login/phone'
     post_data = {
         'xsrf': get_xxrf(),
         'phone_num': account,
         'password': password
     }
 elif '@' in account:
     post_url = 'https://www.zhihu.com/login/email'
     post_data = {
         'xsrf': get_xxrf(),
         'phone_num': account,
         'password': password
     }
 else:
     print('账号有误')
 rep = session.post(url=post_url, data=post_data, headers=header).text
 session.cookies.save()