spider_work/jiwu_spider/init_db.py

# -*- coding: utf-8 -*-
# Author : Charley
# Python : 3.12.10
# Date   : 2026/08/18
"""读取 schema.sql 幂等建表（集物星球爬虫库）。"""
import os
import sys

from loguru import logger
from mysql_pool import MySQLConnectionPool


def init_db(log) -> None:
    """读取同目录 schema.sql，逐条执行建表语句。

    Args:
        log: 日志对象。

    Raises:
        FileNotFoundError: schema.sql 不存在时抛出。
    """
    sql_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "schema.sql")
    if not os.path.isfile(sql_path):
        raise FileNotFoundError(f"schema.sql 不存在: {sql_path}")

    with open(sql_path, "r", encoding="utf-8") as f:
        content = f.read()

    pool = MySQLConnectionPool(log=log)
    if not pool.check_pool_health():
        log.error("数据库连接池异常")
        return

    # 按分号切分逐条执行，跳过空行与注释行
    stmts = [s.strip() for s in content.split(";") if s.strip()]
    for stmt in stmts:
        lines = [ln for ln in stmt.splitlines() if not ln.strip().startswith("--")]
        clean = "\n".join(lines).strip()
        if not clean:
            continue
        try:
            pool._execute(clean, commit=True)
            head = clean.splitlines()[0][:60]
            log.success(f"执行成功: {head}")
        except Exception as e:
            log.warning(f"执行失败(可能已存在): {e}")


if __name__ == "__main__":
    logger.remove()
    logger.add(sys.stderr, level="INFO", format="[{time:HH:mm:ss}] {level} {message}")
    init_db(logger)