原理概述
该系统采用的传统的cs架构,客户端和服务器的语言都是采用python写的。服务器采用的django框架部署在本地,主要用于自动登陆淘宝,阿里妈妈等平台采集信息,客户端通过hook微信,接受用户的消息,进行判断以及回复。
其中核心代码为:
Login.py
import re
import os
import json
import requests
s = requests.Session()
# cookies序列化文件
COOKIES_FILE_PATH = 'taobao_login_cookies.txt'
class UsernameLogin:
def __init__(self, username, ua, TPL_password2):
"""
账号登录对象
:param username: 用户名
:param ua: 淘宝的ua参数
:param TPL_password2: 加密后的密码
"""
# 检测是否需要验证码的URL
self.user_check_url = 'https://login.taobao.com/member/request_nick_check.do?_input_charset=utf-8'
# 验证淘宝用户名密码URL
self.verify_password_url = "https://login.taobao.com/member/login.jhtml"
# 访问st码URL
self.vst_url = 'https://login.taobao.com/member/vst.htm?st={}'
# 淘宝个人 主页
self.my_taobao_url = 'http://i.taobao.com/my_taobao.htm'
# 淘宝用户名
self.username = username
# 淘宝关键参数,包含用户浏览器等一些信息,很多地方会使用,从浏览器或抓包工具中复制,可重复使用
self.ua = ua
# 加密后的密码,从浏览器或抓包工具中复制,可重复使用
self.TPL_password2 = TPL_password2
# 请求超时时间
self.timeout = 3
def _user_check(self):
"""
检测账号是否需要验证码
:return:
"""
data = {
'username': self.username,
'ua': self.ua
}
try:
response = s.post(self.user_check_url, data=data, timeout=self.timeout)
response.raise_for_status()
except Exception as e:
print('检测是否需要验证码请求失败,原因:')
raise e
needcode = response.json()['needcode']
print('是否需要滑块验证:{}'.format(needcode))
return needcode
def _verify_password(self):
"""
验证用户名密码,并获取st码申请URL
:return: 验证成功返回st码申请地址
"""
verify_password_headers = {
'Connection': 'keep-alive',
'Cache-Control': 'max-age=0',
'Origin': 'https://login.taobao.com',
'Upgrade-Insecure-Requests': '1',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': 'https://login.taobao.com/member/login.jhtml?from=taobaoindex&f=top&style=&sub=true&redirect_url=https%3A%2F%2Fi.taobao.com%2Fmy_taobao.htm',
}
# 登录toabao.com提交的数据,如果登录失败,可以从浏览器复制你的form data
verify_password_data = {
'TPL_username': self.username,
'ncoToken': 'cdf05a89ad5104403ebb12ebc9b7626af277b066',
'slideCodeShow': 'false',
'useMobile': 'false',
'lang': 'zh_CN',
'loginsite': 0,
'newlogin': 0,
'TPL_redirect_url': 'https://s.taobao.com/search?q=%E9%80%9F%E5%BA%A6%E9%80%9F%E5%BA%A6&imgfile=&commend=all&ssid=s5-e&search_type=item&sourceId=tb.index&spm=a21bo.2017.201856-taobao-item.1&ie=utf8&initiative_id=tbindexz_20170306',
'from': 'tb',
'fc': 'default',
'style': 'default',
'keyLogin': 'false',
'qrLogin': 'true',
'newMini': 'false',
'newMini2': 'false',
'loginType': '3',
'gvfdcname': '10',
'gvfdcre': '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',
'TPL_password_2': self.TPL_password2,
'loginASR': '1',
'loginASRSuc': '1',
'oslanguage': 'zh-CN',
'sr': '1440*900',
'osVer': 'macos|10.145',
'naviVer': 'chrome|76.038091',
'osACN': 'Mozilla',
'osAV': '5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36',
'osPF': 'MacIntel',
'appkey': '00000000',
'mobileLoginLink': 'https://login.taobao.com/member/login.jhtml?redirectURL=https://s.taobao.com/search?q=%E9%80%9F%E5%BA%A6%E9%80%9F%E5%BA%A6&imgfile=&commend=all&ssid=s5-e&search_type=item&sourceId=tb.index&spm=a21bo.2017.201856-taobao-item.1&ie=utf8&initiative_id=tbindexz_20170306&useMobile=true',
'showAssistantLink': '',
'um_token': 'T898C0FDF1A3CEE5389D682340C5F299FFE590F51543C8E3DDA8341C869',
'ua': self.ua
}
try:
response = s.post(self.verify_password_url, headers=verify_password_headers, data=verify_password_data,
timeout=self.timeout)
response.raise_for_status()
# 从返回的页面中提取申请st码地址
except Exception as e:
print('验证用户名和密码请求失败,原因:')
raise e
# 提取申请st码url
apply_st_url_match = re.search(r'<script src="(.*?)"></script>', response.text)
# 存在则返回
if apply_st_url_match:
print('验证用户名密码成功,st码申请地址:{}'.format(apply_st_url_match.group(1)))
return apply_st_url_match.group(1)
else:
raise RuntimeError('用户名密码验证失败!response:{}'.format(response.text))
def _apply_st(self):
"""
申请st码
:return: st码
"""
apply_st_url = self._verify_password()
try:
response = s.get(apply_st_url)
response.raise_for_status()
except Exception as e:
print('申请st码请求失败,原因:')
raise e
st_match = re.search(r'"data":{"st":"(.*?)"}', response.text)
if st_match:
print('获取st码成功,st码:{}'.format(st_match.group(1)))
return st_match.group(1)
else:
raise RuntimeError('获取st码失败!response:{}'.format(response.text))
def login(self):
"""
使用st码登录
:return:
"""
# 加载cookies文件
if self._load_cookies():
return True
# 判断是否需要滑块验证
self._user_check()
st = self._apply_st()
headers = {
'Host': 'login.taobao.com',
'Connection': 'Keep-Alive',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}
try:
response = s.get(self.vst_url.format(st), headers=headers)
response.raise_for_status()
except Exception as e:
print('st码登录请求,原因:')
raise e
# 登录成功,提取跳转淘宝用户主页url
my_taobao_match = re.search(r'top.location.href = "(.*?)"', response.text)
if my_taobao_match:
print('登录淘宝成功,跳转链接:{}'.format(my_taobao_match.group(1)))
self._serialization_cookies()
return True
else:
raise RuntimeError('登录失败!response:{}'.format(response.text))
def _load_cookies(self):
# 1、判断cookies序列化文件是否存在
if not os.path.exists(COOKIES_FILE_PATH):
return False
# 2、加载cookies
s.cookies = self._deserialization_cookies()
# 3、判断cookies是否过期
try:
self.get_taobao_nick_name()
except Exception as e:
os.remove(COOKIES_FILE_PATH)
print('cookies过期,删除cookies文件!')
return False
print('加载淘宝登录cookies成功!!!')
return True
def _serialization_cookies(self):
"""
序列化cookies
:return:
"""
cookies_dict = requests.utils.dict_from_cookiejar(s.cookies)
with open(COOKIES_FILE_PATH, 'w+', encoding='utf-8') as file:
json.dump(cookies_dict, file)
print('保存cookies文件成功!')
def _deserialization_cookies(self):
"""
反序列化cookies
:return:
"""
with open(COOKIES_FILE_PATH, 'r+', encoding='utf-8') as file:
cookies_dict = json.load(file)
cookies = requests.utils.cookiejar_from_dict(cookies_dict)
return cookies
def get_taobao_nick_name(self):
"""
获取淘宝昵称
:return: 淘宝昵称
"""
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}
try:
response = s.get(self.my_taobao_url, headers=headers)
response.raise_for_status()
except Exception as e:
print('获取淘宝主页请求失败!原因:')
raise e
# 提取淘宝昵称
nick_name_match = re.search(r'<input id="mtb-nickname" type="hidden" value="(.*?)"/>', response.text)
if nick_name_match:
print('登录淘宝成功,你的用户名是:{}'.format(nick_name_match.group(1)))
return nick_name_match.group(1)
else:
raise RuntimeError('获取淘宝昵称失败!response:{}'.format(response.text))
if __name__ == '__main__':
# 淘宝用户名
username = '你的淘宝账号'
# 淘宝重要参数,从浏览器或抓包工具中复制,可重复使用
ua = '119#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'
# 加密后的密码,从浏览器或抓包工具中复制,可重复使用
TPL_password2 = '你的加密后密码'
ul = UsernameLogin(username, ua, TPL_password2)
ul.login()
至于为什么是这样写的,如果有兴趣的小伙伴可以回复留言,人数多的话,我另开一篇文章讲解淘宝的抓包技术。
摘自:王惠亮的个人博客