orchestrator/seed_data.py

import sqlite3
import os

# 获取当前脚本所在目录的绝对路径，并构造数据库文件路径
base_dir = os.path.dirname(os.path.abspath(__file__))
db_path = os.path.join(base_dir, 'data', 'mvp.db')

def seed_data():
    print(f"正在连接数据库: {db_path}")
    conn = sqlite3.connect(db_path)
    cursor = conn.cursor()

    # 10个医疗健康相关的测试关键词
    keywords = [
        ("医疗健康",),
        ("中医养生",),
        ("康复治疗",),
        ("三甲医院",),
        ("体检套餐",),
        ("健康饮食",),
        ("减肥瘦身",),
        ("心理咨询",),
        ("慢性病管理",),
        ("妇科健康",)
    ]

    # 10个竞品账号（以医疗健康领域为例）
    competitor_accounts = [
        ("丁香医生", "小红书"),
        ("春雨医生", "小红书"),
        ("平安好医生", "小红书"),
        ("微医", "小红书"),
        ("好大夫在线", "小红书"),
        ("企鹅杏仁", "小红书"),
        ("阿里健康", "小红书"),
        ("京东健康", "小红书"),
        ("医学界", "小红书"),
        ("健康时报", "小红书")
    ]

    try:
        # 清理已有测试数据（可选，防止重复运行脚本导致数据不断增加）
        cursor.execute("DELETE FROM keyword")
        cursor.execute("DELETE FROM competitor_account")
        
        # 插入关键词数据
        cursor.executemany(
            "INSERT INTO keyword (word) VALUES (?)",
            keywords
        )
        print(f"成功插入 {len(keywords)} 条关键词数据。")

        # 插入竞品账号数据
        cursor.executemany(
            "INSERT INTO competitor_account (account_name, platform) VALUES (?, ?)",
            competitor_accounts
        )
        print(f"成功插入 {len(competitor_accounts)} 条竞品账号数据。")

        conn.commit()
        print("数据保存成功！")
    except Exception as e:
        print(f"发生错误: {e}")
        conn.rollback()
    finally:
        conn.close()

if __name__ == "__main__":
    seed_data()