新浪微博登陆

使用python实现新浪微博登陆
首先打开charles，记录从打开浏览器到新浪微博登陆成功的全部http请求
打开新浪微博，等待页面加载完成后，输入账号密码点击登陆，charles停止抓包，关闭浏览器。并将抓包结果进行保存。
找到登陆的POST请求https://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.19)

登陆POST请求
理论上我们只需要能完整的提交这个表单就能实现新浪微博的登陆。但是如果进行试验的话，会发现将该表单完整复制之后使用requests进行post提交是无法登陆的，所以可以断定其中某些字段是通过动态获取。
由于新浪微博的首页内容太多太杂
我们将上文中拿到的登陆post请求https://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.19)进行访问发现是一个单独的登陆页面。
登陆页面
打开F12，对登陆按钮进行定位，根据前后台交互的方式可以知道后台应该是通过<input>中某一个内容判断用户点击了登陆按钮，在Source中的js代码部分检索<input>的type：submit。
按钮定位
js代码查找登陆操作
初步断定该js中进行了一些加密操作
根据命名规则尝试检索用户名username很容易的找到了一段username的转换操作

this.prelogin = function(config, callback) {
    var url = location.protocol == "https:" ? ssoPreLoginUrl.replace(/^http:/, "https:") : ssoPreLoginUrl;
    var username = config.username || "";
    username = sinaSSOEncoder.base64.encode(urlencode(username));
    delete config.username;
    var arrQuery = {
      entry: me.entry,
      callback: me.name + ".preloginCallBack",
      su: username,
      rsakt: "mod"
    };

从username = sinaSSOEncoder.base64.encode(urlencode(username));可以看出来，用户名经过了url编码后再进行了base64转码，从键值对可以看出来su提交的就是转码后的账号
使用python实现

def get_username(self):
    username_quote = urllib.parse.quote_plus(self.user_name)
    username_base64 = base64.b64encode(username_quote.encode("utf-8"))
    return username_base64.decode("utf-8")

下面检索password一下子就发现了关键的一句话，而且明目张胆的写着RSA
password = RSAKey.encrypt([me.servertime, me.nonce].join("\t") + "\n" + password)
要进行RSA加密需要公钥PublicKey,检索一下Public找到了公钥RSAKey.setPublic(me.rsaPubkey, "10001");这样还不够，再找找看me.rsaPubkey是什么东西me.rsaPubkey = result.pubkey;所以应是返回值中有带咯，在charles里面找一下pubkey

公钥
这个返回值中有很多眼熟的东西servertime,nonce都在这里面了。记下这个有用的url：
https://login.sina.com.cn/sso/prelogin.php?entry=weibo&callback=sinaSSOController.preloginCallBack&su=&rsakt=mod&client=ssologin.js(v1.4.19)&_=1536460959875

sinaSSOController.preloginCallBack
({
"retcode":0,
"servertime":1536460961,
"pcid":"gz-1c8cc52b95dad5397635083e4ddcd33994aa",
"nonce":"42KG80",
"pubkey":"EB2A38568661887FA180BDDB5CABD5F21C7BFD59C090CB2D245A87AC253062882729293E5506350508E7F9AA3BB77F4333231490F915F6D63C55FE2F08A49B353F444AD3993CACC02DB784ABBB8E42A9B1BBFFFB38BE18D78E87A0E41B9B8F73A928EE0CCEE1F6739884B9777E4FE9E88A1BBE495927AC4A799B3181D6442443",
"rsakv":"1330428213",
"uid":"2239053435",
"exectime":6
})

这个url有点复杂，看到了?，&等内容使用requests里面get的params=传入

def get_json_data(self, su_value):
    params = {
        "entry": "weibo",
        "callback": "sinaSSOController.preloginCallBack",
        "rsakt": "mod",
        "checkpin": "1",
        "client": "ssologin.js(v1.4.18)",
        "su": su_value,
        "_": int(time.time()*1000),
    }
    try:
        response = self.session.get("http://login.sina.com.cn/sso/prelogin.php", params=params)
        json_data = json.loads(re.search(r"\((?P<data>.*)\)", response.text).group("data"))
    except Exception as excep:
        json_data = {}
        logging.error("WeiBoLogin get_json_data error: %s", excep)

    logging.debug("WeiBoLogin get_json_data: %s", json_data)
    return json_data

根据password = RSAKey.encrypt([me.servertime, me.nonce].join("\t") + "\n" + password)用python写一下rsa加密

def get_password(self, servertime, nonce, pubkey):
    string = (str(servertime) + "\t" + str(nonce) + "\n" + str(self.pass_word)).encode("utf-8")
    public_key = rsa.PublicKey(int(pubkey, 16), int("10001", 16))
    password = rsa.encrypt(string, public_key)
    password = binascii.b2a_hex(password)
    return password.decode()

文章开头的表单的动态内容都动态获取了接下来就是post表单提交了,然后拿一下user_uniqueid和user_nick就可以（用你的账户）爬必须登录才能获取的数据了

login_url_1 = "http://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.18)&_=%d" % int(time.time())
json_data_1 = self.session.post(login_url_1, data=post_data).json()


if json_data_1["retcode"] == "0":
    params = {
        "callback": "sinaSSOController.callbackLoginStatus",
        "client": "ssologin.js(v1.4.18)",
        "ticket": json_data_1["ticket"],
        "ssosavestate": int(time.time()),
        "_": int(time.time()*1000),
    }
    response = self.session.get("https://passport.weibo.com/wbsso/login", params=params)
    json_data_2 = json.loads(re.search(r"\((?P<result>.*)\)", response.text).group("result"))
    if json_data_2["result"] is True:
        self.user_uniqueid = json_data_2["userinfo"]["uniqueid"]
        self.user_nick = json_data_2["userinfo"]["displayname"]
        logging.warning("WeiBoLogin succeed: %s", json_data_2)
    else:
        logging.warning("WeiBoLogin failed: %s", json_data_2)
else:
    logging.warning("WeiBoLogin failed: %s", json_data_1)
return True if self.user_uniqueid and self.user_nick else False

登录结果

完整代码来自：https://github.com/xianhu/LearnPython/blob/master/python_wechat.py

#coding=utf-8
import re
import rsa
import time
import json
import base64
import logging
import binascii
import requests
import urllib.parse


class WeiBoLogin(object):
    """
    class of WeiBoLogin, to login weibo.com
    """

    def __init__(self):
        """
        constructor
        """
        self.user_name = None
        self.pass_word = None
        self.user_uniqueid = None
        self.user_nick = None

        self.session = requests.Session()
        self.session.headers.update({"User-Agent": "Mozilla/5.0 (Windows NT 6.3; WOW64; rv:41.0) Gecko/20100101 Firefox/41.0"})
        self.session.get("http://weibo.com/login.php")
        return

    def login(self, user_name, pass_word):
        """
        login weibo.com, return True or False
        """
        self.user_name = user_name
        self.pass_word = pass_word
        self.user_uniqueid = None
        self.user_nick = None

        # get json data
        s_user_name = self.get_username()
        json_data = self.get_json_data(su_value=s_user_name)
        if not json_data:
            return False
        s_pass_word = self.get_password(json_data["servertime"], json_data["nonce"], json_data["pubkey"])

        # make post_data
        post_data = {
            "entry": "weibo",
            "gateway": "1",
            "from": "",
            "savestate": "7",
            "userticket": "1",
            "vsnf": "1",
            "service": "miniblog",
            "encoding": "UTF-8",
            "pwencode": "rsa2",
            "sr": "1280*800",
            "prelt": "529",
            "url": "http://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack",
            "rsakv": json_data["rsakv"],
            "servertime": json_data["servertime"],
            "nonce": json_data["nonce"],
            "su": s_user_name,
            "sp": s_pass_word,
            "returntype": "TEXT",
        }

        # get captcha code
        if json_data["showpin"] == 1:
            url = "http://login.sina.com.cn/cgi/pin.php?r=%d&s=0&p=%s" % (int(time.time()), json_data["pcid"])
            with open("captcha.jpeg", "wb") as file_out:
                file_out.write(self.session.get(url).content)
            code = input("请输入验证码:")
            post_data["pcid"] = json_data["pcid"]
            post_data["door"] = code

        # login weibo.com
        login_url_1 = "http://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.18)&_=%d" % int(time.time())
        json_data_1 = self.session.post(login_url_1, data=post_data).json()
        if json_data_1["retcode"] == "0":
            params = {
                "callback": "sinaSSOController.callbackLoginStatus",
                "client": "ssologin.js(v1.4.18)",
                "ticket": json_data_1["ticket"],
                "ssosavestate": int(time.time()),
                "_": int(time.time()*1000),
            }
            response = self.session.get("https://passport.weibo.com/wbsso/login", params=params)
            json_data_2 = json.loads(re.search(r"\((?P<result>.*)\)", response.text).group("result"))
            if json_data_2["result"] is True:
                self.user_uniqueid = json_data_2["userinfo"]["uniqueid"]
                self.user_nick = json_data_2["userinfo"]["displayname"]
                logging.warning("WeiBoLogin succeed: %s", json_data_2)
            else:
                logging.warning("WeiBoLogin failed: %s", json_data_2)
        else:
            logging.warning("WeiBoLogin failed: %s", json_data_1)
        return True if self.user_uniqueid and self.user_nick else False

    def get_username(self):
        """
        get legal username
        """
        username_quote = urllib.parse.quote_plus(self.user_name)
        username_base64 = base64.b64encode(username_quote.encode("utf-8"))
        return username_base64.decode("utf-8")

    def get_json_data(self, su_value):
        """
        get the value of "servertime", "nonce", "pubkey", "rsakv" and "showpin", etc
        """
        params = {
            "entry": "weibo",
            "callback": "sinaSSOController.preloginCallBack",
            "rsakt": "mod",
            "checkpin": "1",
            "client": "ssologin.js(v1.4.18)",
            "su": su_value,
            "_": int(time.time()*1000),
        }
        try:
            response = self.session.get("http://login.sina.com.cn/sso/prelogin.php", params=params)
            json_data = json.loads(re.search(r"\((?P<data>.*)\)", response.text).group("data"))
        except Exception as excep:
            json_data = {}
            logging.error("WeiBoLogin get_json_data error: %s", excep)

        logging.debug("WeiBoLogin get_json_data: %s", json_data)
        return json_data

    def get_password(self, servertime, nonce, pubkey):
        """
        get legal password
        """
        string = (str(servertime) + "\t" + str(nonce) + "\n" + str(self.pass_word)).encode("utf-8")
        public_key = rsa.PublicKey(int(pubkey, 16), int("10001", 16))
        password = rsa.encrypt(string, public_key)
        password = binascii.b2a_hex(password)
        return password.decode()


if __name__ == "__main__":
    logging.basicConfig(level=logging.DEBUG, format="%(asctime)s\t%(levelname)s\t%(message)s")
    weibo = WeiBoLogin()
    weibo.login("username", "password")