代码github地址:zhihu

首先分析知乎登录页，一般模拟登录走的都是手机页，比较方便

分析登录过程

为了得到验证码我特意都输错了几次密码，知乎的登录不一定有验证码，所以我们在代码实现的过程中需要做判断是否需要验证码

引入依赖：

from urllib import request,parse
from bs4 import BeautifulSoup
import http.cookiejar 
import json
import random
import time
import configparser

构建全局请求头

因为要模拟手机，所以这里我们用的是手机的user-Agent

def build_opener():
    cookie = http.cookiejar.CookieJar()
    cookie_processor = request.HTTPCookieProcessor(cookie)
    opener = request.build_opener(cookie_processor) 
    opener.addheaders = [("User-Agent", "Mozilla/5.0 (iPhone; CPU iPhone OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1"),
    ("Referer", "https://www.zhihu.com/"),
    ("Origin", "https://www.zhihu.com/"),
    ("Host", "www.zhihu.com")]
    request.install_opener(opener)

登录过程

def login(code=0):
    login_data = configparser.ConfigParser()
    login_data.read("user.ini") #将用户名密码放在user.ini配置文件

    username = login_data.get("LoginInfo", "email")
    password = login_data.get("LoginInfo", "password")
    url = 'https://www.zhihu.com/signin'
    login_url = 'https://www.zhihu.com/login/email'
    captcha_url = 'https://www.zhihu.com/captcha.gif'
    req = request.Request(url)
    res = request.urlopen(req)

    html = res.read().decode('utf-8')
    soup = BeautifulSoup(html)
    inputs = soup.find_all('input')

    _xsrf = inputs[0]['value']


    # 构造登录参数
    params = {
        'email': username,
        'password': password,
        '_xsrf': _xsrf
    }

    #如果code是1,说明需要验证码，读取验证码并写入到本地,然后手动输入验证码
    if code == 1:
        cap_parms = parse.urlencode({"r": time.time(), "type": "login"}).encode('utf-8')
        captcha_req = request.Request(captcha_url,cap_parms,method="GET")
        captcha_res = request.urlopen(captcha_req)
        fo = open('captcha.jpg','wb+')
        fo.write(captcha_res.read())
        fo.close()
        captcha = input("请输入验证码:\n")
        params['captcha'] = captcha

    params = parse.urlencode(params).encode('utf-8')

    req = request.Request(login_url,params,method="POST")
    res = request.urlopen(req)
    
    result = res.read().decode('utf-8')
    login_result = json.loads(result)


    if login_result['r'] == 0:
        print('登陆成功')
    else:
        if login_result['errcode'] == 1991829: 
            login(1)
        else:
            print(login_result['msg'])
            login()

最后

if __name__ == '__main__':
    build_opener()
    login()

实例效果

zhihu.gif

代码地址：https://github.com/vincenth520/Spider/tree/master/zhihu