python 模拟知乎登陆

最新推荐文章于 2024-08-06 04:17:42 发布

原创最新推荐文章于 2024-08-06 04:17:42 发布 · 320 阅读

2 ·

CC 4.0 BY-SA版权

爬虫专栏收录该内容

2 篇文章

订阅专栏

本文介绍了一个使用Python模拟知乎网站登录过程的方法。通过requests库发送HTTP请求，并利用正则表达式解析返回的内容来获取必要的参数。此外，还涉及验证码的处理及整个登录流程的实现。

python 模拟知乎登陆

一、Python 模拟知乎登陆的实现

# coding=utf-8
import requests
import re
import time
class LogIn:
    def __init__(self):
        self.indexURL = 'https://www.zhihu.com'
        self.loginURL = 'https://www.zhihu.com/login/email'
        self.headers = {
            'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36',
            'Origin':'https://www.zhihu.com',
            'Referer':'https://www.zhihu.com/',
            'Accept':'*/*',
            'Accept-Encoding':'gzip,deflate,br',
            'Accept-Language':'zh-CN,zh'
        }
        self.session = requests.session()

    def getXSRF(self):
        content = self.session.get(self.indexURL, headers=self.headers).content
        xsrf_pattern = re.compile(r'<input type="hidden" name="_xsrf" value="(.*?)"')
        xsrf = re.findall(xsrf_pattern, content)[0]
        print xsrf
        return xsrf

    def getCaptcha(self):
        captcha = self.session.get('https://www.zhihu.com/captcha.gif?r=%d&type=login' % (time.time() * 1000),headers=self.headers).content
        with open('captcha.gif', 'wb') as fp:
            fp.write(captcha)

    def logInZhiHu(self,userName,password):
        _xsrf = self.getXSRF()
        self.getCaptcha()
        captcha = raw_input('captcha:')
        data = {
            '_xsrf': _xsrf,
            'password': password,
            'captcha': captcha,
            'email': userName,
            'remember_me': 'true'
        }
        resp = self.session.post('https://www.zhihu.com/login/email', data=data, headers=self.headers).content
        #print resp
        return self.session
if __name__ == '__main__':
    a = LogIn()
    session = a.logInZhiHu('2287266007@qq.com','www1234')
    print session.get("https://www.zhihu.com", headers=a.headers).content