快速为mysql创造100万假数据

以你之姓@ 2024-04-08 12:57 60阅读 0赞

**目录**

第一种方式：利用navicat16的新功能！

第二种方式：写python脚本

--------------------

### 第一种方式：利用navicat16的新功能！（破解版私聊博主） ###

打开一张表。

![4b86f676b0eb42689782871b24a709fa.png][]

--------------------

设置数量。

![59d5c449addf4ba681b2785ce179cc95.png][]

除了自动推断外，还可以对每个字段单独设置生成属性。

![4201536fe02a48aab0af1ebcd477625f.png][]

### 第二种方式：写python脚本 ###

1.安装依赖：

pip install Faker -i https://pypi.tuna.tsinghua.edu.cn/simple
    pip install peewee -i https://pypi.tuna.tsinghua.edu.cn/simple
    pip install pymysql -i https://pypi.tuna.tsinghua.edu.cn/simple
    pip install tomorrow -i https://pypi.tuna.tsinghua.edu.cn/simple

2.建表

CREATE TABLE `user` (
      `id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '主键',
      `user_name` varchar(255) NOT NULL COMMENT '账号',
      `ssn` varchar(255) NOT NULL COMMENT '身份证',
      `name` varchar(255) NOT NULL COMMENT '名字',
      `phone_number` varchar(32) NOT NULL COMMENT '手机号',
      `plate` varchar(255) NOT NULL COMMENT '车牌',
      `address` varchar(255) NOT NULL COMMENT '地址',
      `building_number` varchar(255) NOT NULL COMMENT '楼名',
      `country` varchar(255) NOT NULL COMMENT '国家',
      `birth` varchar(255) NOT NULL COMMENT '生日',
      `company` varchar(255) NOT NULL COMMENT '公司',
      `job` varchar(255) NOT NULL COMMENT '职位',
      `card_number` varchar(255) NOT NULL COMMENT '信用卡号',
      `city` varchar(255) NOT NULL COMMENT '城市',
      `week` varchar(255) NOT NULL COMMENT '星期',
      `email` varchar(255) NOT NULL COMMENT '邮件',
      `title` varchar(255) NOT NULL COMMENT '标题',
      `paragraphs` longtext NOT NULL COMMENT '内容',
      `create_time` timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT '创建时间',
      `update_time` timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP COMMENT '更新时间',
      PRIMARY KEY (`id`)
    ) ENGINE=InnoDB AUTO_INCREMENT=75528 DEFAULT CHARSET=utf8mb4;

3.构建模型

db_mysql = MySQLDatabase('fast_generator', user='root', password='123456', host='localhost', port=3306)
    
    class User(Model):
        user_name = TextField()
        ssn = TextField()
        name = TextField()
        phone_number = TextField()
        plate = TextField()
        address = TextField()
        building_number = TextField()
        country = TextField()
        birth = TextField()
        company = TextField()
        job = TextField()
        card_number = TextField()
        city = TextField()
        week = TextField()
        email = TextField()
        title = TextField()
        paragraphs = TextField()
    
        class Meta:
            database = db_mysql

4.存储数据（多线程会报错：参考[python多线程tomorrow的使用\_苍穹之跃的博客-CSDN博客\_python tomorrow][python_tomorrow_-CSDN_python tomorrow]）

@threads(20)
    def produce_data() -> User:
        fake = Faker(locale='zh_CN')
        # 账号
        user_name = fake.user_name()
        # 身份证
        ssn = fake.ssn(min_age=18, max_age=90)
        # 名字
        name = fake.name()
        # 手机号
        phone_number = fake.phone_number()
        # 车牌
        plate = fake.license_plate()
        # 地址
        address = fake.address()
        # 楼名
        building_number = fake.building_number()
        # 国家
        country = fake.country()
        # 生日
        birth = fake.date_of_birth(tzinfo=None, minimum_age=0, maximum_age=115)
        # 公司
        company = fake.company()
        # 职位
        job = fake.job()
        # 信用卡号
        card_number = fake.credit_card_number(card_type=None)
        # 城市
        city = fake.city()
        # 星期
        week = fake.day_of_week()
        # 邮件
        email = fake.ascii_free_email()
        # 单句
        sentence = fake.sentence(nb_words=6, variable_nb_words=True, ext_word_list=None)
        # 段落
        paragraphs = fake.paragraphs(nb=3, ext_word_list=None)
    
        user = User(
            user_name=user_name,
            ssn=ssn,
            name=name,
            phone_number=phone_number,
            plate=plate,
            address=address,
            building_number=building_number,
            country=country,
            birth=birth,
            company=company,
            job=job,
            card_number=card_number,
            city=city,
            week=week,
            email=email,
            title=sentence,
            paragraphs=paragraphs
        )
        user.save()
    
    
    if __name__ == '__main__':
        for i in range(1000000):
            produce_data()

5.完整代码

from peewee import MySQLDatabase, Model, TextField
    from faker import Faker
    from tomorrow import threads
    
    db_mysql = MySQLDatabase('fast_generator', user='root', password='123456', host='localhost', port=3306)
    
    
    class User(Model):
        user_name = TextField()
        ssn = TextField()
        name = TextField()
        phone_number = TextField()
        plate = TextField()
        address = TextField()
        building_number = TextField()
        country = TextField()
        birth = TextField()
        company = TextField()
        job = TextField()
        card_number = TextField()
        city = TextField()
        week = TextField()
        email = TextField()
        title = TextField()
        paragraphs = TextField()
    
        class Meta:
            database = db_mysql
    
    
    @threads(20)
    def produce_data() -> User:
        fake = Faker(locale='zh_CN')
        # 账号
        user_name = fake.user_name()
        # 身份证
        ssn = fake.ssn(min_age=18, max_age=90)
        # 名字
        name = fake.name()
        # 手机号
        phone_number = fake.phone_number()
        # 车牌
        plate = fake.license_plate()
        # 地址
        address = fake.address()
        # 楼名
        building_number = fake.building_number()
        # 国家
        country = fake.country()
        # 生日
        birth = fake.date_of_birth(tzinfo=None, minimum_age=0, maximum_age=115)
        # 公司
        company = fake.company()
        # 职位
        job = fake.job()
        # 信用卡号
        card_number = fake.credit_card_number(card_type=None)
        # 城市
        city = fake.city()
        # 星期
        week = fake.day_of_week()
        # 邮件
        email = fake.ascii_free_email()
        # 单句
        sentence = fake.sentence(nb_words=6, variable_nb_words=True, ext_word_list=None)
        # 段落
        paragraphs = fake.paragraphs(nb=3, ext_word_list=None)
    
        user = User(
            user_name=user_name,
            ssn=ssn,
            name=name,
            phone_number=phone_number,
            plate=plate,
            address=address,
            building_number=building_number,
            country=country,
            birth=birth,
            company=company,
            job=job,
            card_number=card_number,
            city=city,
            week=week,
            email=email,
            title=sentence,
            paragraphs=paragraphs
        )
        user.save()
    
    
    if __name__ == '__main__':
        for i in range(1000000):
            produce_data()

[4b86f676b0eb42689782871b24a709fa.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/08/ef1450848a714ae495a8d35c7dcca775.png
[59d5c449addf4ba681b2785ce179cc95.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/08/abafaa0df93b4cc5b5eddbcda40260de.png
[4201536fe02a48aab0af1ebcd477625f.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/08/5098f0d79f9e492b8dcaeb635fa67ec3.png
[python_tomorrow_-CSDN_python tomorrow]: https://blog.csdn.net/wenxingchen/article/details/118363678?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522166159761316782246443443%2522%252C%2522scm%2522%253A%252220140713.130102334.pc%255Fblog.%2522%257D&request_id=166159761316782246443443&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_ecpm_v1~rank_v31_ecpm-1-118363678-null-null.nonecase&utm_term=%E5%A4%9A%E7%BA%BF%E7%A8%8B&spm=1018.2226.3001.4450