新浪微博登陆 - 袁佳佳

新浪微博登陆

import rsa
import re
import json
import time
import requests
import base64
import urllib3
import binascii
urllib3.disable_warnings()
class Weibo_login():
    def __init__(self,username,password):
        self.user_name = username
        self.pass_word = password
        self.session = requests.session()
    def login(self):
        json_data = self.get_json_data()  #第一次请求， 获取服务端返回的参数
        if not json_data:
            return False
        pass_word = self.get_password(json_data[\'servertime\'],json_data[\'nonce\'],json_data[\'pubkey\'])

        post_data = {
            \'entry\': \'weibo\',
            \'gateway\': \'1\',
            \'from\': \'\',
            \'savestate\': \'7\',
            \'qrcode_flag\': \'false\',
            \'useticket\': \'1\',
            #\'pagerefer\': \'https://www.baidu.com/\',
            \'vsnf\': \'1\',
            \'su\': self.username,  #通过bs64加密后的得到的
            \'service\': \'miniblog\',
            \'servertime\': json_data[\'servertime\'],
            \'nonce\': json_data[\'nonce\'],
            \'pwencode\': \'rsa2\',
            \'rsakv\': json_data[\'rsakv\'],
            \'sp\': pass_word,   #通过rsa加密过的pass_word
            \'sr\': \'1920*1080\',
            \'encoding\': \'UTF-8\',
            \'prelt\': 28,
            \'url\': \'https://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack\',
            \'returntype\': \'META\'
        }
        login_url = \'https://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.19)\'
        response_data = self.session.post(login_url,data=post_data,verify=False)

        print(response_data.content.decode(\'gbk\'))  #先转成二进制， 然后转成dbk

        #第一次跳转
        url1 = re.findall(r\'location.replace\("(.*?)"\)\',response_data.content.decode(\'gbk\'))[0]   #加上[0]就会变的 只剩下想要的数据
        print("要打印的url:",url1)

        #打印，获取第二次跳转的url
        result = self.session.get(url1).content.decode(\'gbk\')
        print("result",result)

        #第三次跳转
        url1 = re.findall(r"location.replace\(\'(.*?)\'\)",result)[0]
        print("打印url1******************:",url1)

        #访问url1
        self.session.get(url1,verify=False)
        print(self.session.get("https://weibo.com/u/6382564064/home",verify=False).content.decode())   #可以随意访问已经登录的网页

    def get_password(self,servertime,nonce,pubkey):
        s = str(servertime)+\'\t\'+str(nonce)+\'\n\'+str(self.pass_word)
        public_key = rsa.PublicKey(int(pubkey,16),int(\'10001\',16))
        password = rsa.encrypt(s.encode(),public_key)
        #print(binascii.b2a_hex(password))
        return binascii.b2a_hex(password).decode()

    def get_username(self):
        self.username = base64.b64encode(self.user_name.encode())  #对传进去的进行编码
    def get_json_data(self,):
        \'\'\'
            #这个就是按下tab以后， 产生的get请求
            前面的请求就是为了给后面的post请求铺路
        \'\'\'
        params = {
        \'entry\':\'weibo\',
        \'callback\':\'sinaSSOController.preloginCallBack\',
        \'su\':self.username,
        \'rsakt\':\'mod\',
        \'checkpin\':\'1\',
        \'client\':\'ssologin.js(v1.4.19)\',
        \'_\':int(time.time()*1000),
        }
        response = self.session.get(\'https://login.sina.com.cn/sso/prelogin.php?\',params = params,verify=False)   #?号后面的都是一些参数
        #这个正则表达式很棒
        \'\'\'
        preloginCallBack\( 开始
        （.*？）这里面的都要 
        \) 为结束

        json.loads  转成字典格式
        \'\'\'
        try:
            json_loads = json.loads(re.findall(r\'preloginCallBack\((.*?)\)\',response.text)[0])    #****重点来了\(的意思是从preloginCallBack(开始  ，到\)结束的所有都要   （.*？）匹配全部
        except:
            json_loads = {}
        #print(json_loads)
        return json_loads
if __name__ == \'__main__\':
    login = Weibo_login(\'手机号\',\'密码\')  #先设置账号密码
    login.get_username()                  #给传过去的账号密码进行加密
    login.get_json_data()                 #开始请求
    login.login()