piaoquan_crawler/common/getuser.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2023/2/2
"""
创建虚拟站内 UID
https://w42nne6hzg.feishu.cn/docx/PhbhdXScYo9CxpxTT3gcOle4nIs
"""
import os
import sys
import uuid
import requests

sys.path.append(os.getcwd())
from common.common import Common
from common.db import MysqlHelper


class getUser:

    @classmethod
    def get_default_user(cls):
        url = "https://api-internal.piaoquantv.com/user-center/info/getDefaultUserInfo"
        payload = {"params": {"mid": str(uuid.uuid1())}}
        headers = {
            'Content-Type': 'application/json'
        }
        response = requests.request("POST", url, headers=headers, json=payload).json()
        return response['data']

    @classmethod
    def create_uid(cls, log_type, crawler, user_dict, env):
        """
        创建站内虚拟 UID
        :param log_type: 日志
        :param crawler: 哪款爬虫
        :param user_dict: 字典{'nickName': 用户名, 'avatarUrl': 头像, 'tagName': 站内用户标签}
        :param env: 环境
        :return: 站内 UID
        """
        try:
            if env == 'dev':
                # 外网
                url = 'https://videotest.yishihui.com/longvideoapi/user/virtual/crawler/registerVirtualUser'
                # 内网
                # url = 'http://videotest-internal.yishihui.com/longvideoapi/user/virtual/crawler/registerVirtualUser'
            elif env == 'prod':
                # 外网
                url = 'https://longvideoapi.piaoquantv.com/longvideoapi/user/virtual/crawler/registerVirtualUser'
                # 内网
                # url = 'http://longvideoapi-internal.piaoquantv.com/longvideoapi/user/virtual/crawler/registerVirtualUser'
            else:
                # 外网
                url = 'https://longvideoapi.piaoquantv.com/longvideoapi/user/virtual/crawler/registerVirtualUser'
                # 内网
                # url = 'http://longvideoapi-internal.piaoquantv.com/longvideoapi/user/virtual/crawler/registerVirtualUser'
            params = {
                # 'count': 1,     # （必须）账号个数：传1
                # 'accountType': 4,   # （必须）账号类型 ：传 4 app虚拟账号
                'recommendStatus': user_dict.get('recommendStatus', -6),
                'appRecommendStatus': user_dict.get('appRecommendStatus', -6),
                'pwd': '',  # 密码 默认 12346
                'nickName': user_dict['nickName'],  # 昵称  默认 vuser......
                'avatarUrl': user_dict['avatarUrl'],
                # 头像Url  默认 http://weapppiccdn.yishihui.com/resources/images/pic_normal.png
                'tagName': user_dict['tagName'],  # 多条数据用英文逗号分割
            }
            response = requests.post(url=url, params=params)
            # print(response.text)
            user_id = response.json()['data']
            return user_id
        except Exception as e:
            Common.logger(log_type, crawler).error(f"create_user异常:{e}\n")

    @classmethod
    def create_user(cls, log_type, crawler, out_user_dict, env, machine):
        """
        补全飞书用户表信息，并返回
        :param log_type: 日志
        :param crawler: 哪款爬虫
        :param out_user_dict: 站外用户信息字典
        :param env: 正式环境:prod，测试环境:dev
        :param machine: 部署机器，阿里云填写 aliyun，aliyun_hk ，线下分别填写 macpro，macair，local
        :return: user_list
        """
        try:
            # 获取站外账号信息
            out_uid = out_user_dict['out_uid']  # 站外uid
            user_name = out_user_dict['user_name']  # 站外用户名
            out_avatar_url = out_user_dict['out_avatar_url']  # 站外头像
            out_create_time = out_user_dict['out_create_time']  # 站外注册时间，格式: YYYY-MM-DD HH:MM:SS
            out_tag = out_user_dict['out_tag']  # 站外标签，例如：搞笑博主
            out_play_cnt = out_user_dict['out_play_cnt']  # 站外总播放量
            out_fans = out_user_dict['out_fans']  # 站外粉丝数量
            out_follow = out_user_dict['out_follow']  # 站外关注量
            out_friend = out_user_dict['out_friend']  # 站外好友量
            out_like = out_user_dict['out_like']  # 站外点赞量
            platform = out_user_dict['platform']  # 抓取平台，例如：小年糕、西瓜视频
            tag = out_user_dict['tag']  # 站内身份标签，例如：小年糕爬虫,小时榜爬虫策略；好看爬虫,频道榜爬虫策略；youtube爬虫,定向爬虫策略
            sql = f""" select * from crawler_user where platform="{platform}" and out_user_id="{out_uid}" """
            our_user_info = MysqlHelper.get_values(log_type, crawler, sql, env, machine)
            # 数据库中（youtube + out_user_id）返回数量 == 0，则创建站内账号UID，并写入定向账号飞书表。并结合站外用户信息，一并写入爬虫账号数据库
            if our_user_info is None or len(our_user_info) == 0:
                # 创建站内账号
                create_user_dict = {
                    'nickName': user_name,
                    'avatarUrl': out_avatar_url,
                    'tagName': tag,  # 例如 'youtube爬虫,定向爬虫策略'
                }
                our_uid = cls.create_uid(log_type, crawler, create_user_dict, env)
                Common.logger(log_type, crawler).info(f'新创建的站内UID:{our_uid}')
                if env == 'prod':
                    our_user_link = f'https://admin.piaoquantv.com/ums/user/{our_uid}/post'
                else:
                    our_user_link = f'https://testadmin.piaoquantv.com/ums/user/{our_uid}/post'
                Common.logger(log_type, crawler).info(f'站内用户主页链接:{our_user_link}')

                # 用户信息写入数据库
                sql = f""" insert into crawler_user(user_id, 
                                        out_user_id, 
                                        out_user_name, 
                                        out_avatar_url, 
                                        out_create_time, 
                                        out_tag,
                                        out_play_cnt, 
                                        out_fans, 
                                        out_follow, 
                                        out_friend, 
                                        out_like, 
                                        platform, 
                                        tag)
                                        values({our_uid}, 
                                        "{out_uid}", 
                                        "{user_name}", 
                                        "{out_avatar_url}", 
                                        "{out_create_time}", 
                                        "{out_tag}", 
                                        {out_play_cnt}, 
                                        {out_fans}, 
                                        {out_follow}, 
                                        {out_friend}, 
                                        {out_like}, 
                                        "{platform}",
                                        "{tag}") """
                Common.logger(log_type, crawler).info(f'sql:{sql}')
                MysqlHelper.update_values(log_type, crawler, sql, env, machine)
                Common.logger(log_type, crawler).info('用户信息插入数据库成功！')
                # 数据库中（youtube + out_user_id）返回数量 != 0，则直接把数据库中的站内 UID 写入飞书
            else:
                our_uid = our_user_info[0][1]
                if env == 'prod':
                    our_user_link = f'https://admin.piaoquantv.com/ums/user/{our_uid}/post'
                else:
                    our_user_link = f'https://testadmin.piaoquantv.com/ums/user/{our_uid}/post'
                Common.logger(log_type, crawler).info(f'站内用户主页链接:{our_user_link}')
            user_dict = {
                'out_uid': out_uid,
                'user_name': user_name,
                'our_uid': our_uid,
                'our_user_link': our_user_link,
            }
            return user_dict
        except Exception as e:
            Common.logger(log_type, crawler).error(f"create_user:{e}\n")


if __name__ == "__main__":
    uid = getUser.create_uid('log', 'kanyikan', 'youtube爬虫,定向爬虫策略', 'dev')
    print(uid)