import pymysql
import pandas as pd
from datetime import datetime

# 数据库连接配置
db_config = {
    "host": "192.144.230.75",
    "port": 3306,
    "user": "db_vidcon",
    "password": "rexdK4fhCCiRE4BZ",
    "database": "db_vidcon",
    "charset": "utf8mb4",
}

def get_rn_list():
    """获取所有地区列表"""
    sql = "SELECT DISTINCT rn FROM sh_dm_video_op_v2;"
    conn = pymysql.connect(**db_config)
    df = pd.read_sql(sql, conn)
    conn.close()
    return df['rn'].tolist()

def get_data_for_rn(rn: str) -> pd.DataFrame:
    """针对指定 rn 拉取数据"""
    # 注意：这里把 SQL 中的 rn 和 level 参数化
    sql = f"""
        SELECT
          op.id                AS ID,
          v.v_name             AS 片名,
          v.link               AS 视频连接,
          v.is_piracy          AS 是否盗版,
          op.`level`           AS 优先级,
          op.rn                AS 地区,
          NULL                 AS 投诉日期,
          NULL                 AS 下线日期,
          op.keyword           AS 关键词,
          v.title              AS 标题,
          v.duration           AS 时长,
          v.watch_number       AS 观看数量,
          v.public_time        AS 上传时间,
          v.u_pic              AS 头像,
          CASE
            WHEN dup.cnt > 1 THEN 1
            ELSE 2
          END                  AS 是否重复,
          op.sort              AS 排序,
          op.batch             AS 批次,
          op.machine           AS 机器号,
          v.u_id               AS 用户id,
          v.u_xid              AS u_xid,
          v.u_name             AS 用户名称
        FROM sh_dm_video_op_v2 AS op
        LEFT JOIN (
          SELECT
            t.v_xid,
            COUNT(*) AS cnt
          FROM sh_dm_video_op_v2 AS t
          WHERE t.batch IN (1747324254, 1747323990)
          GROUP BY t.v_xid
        ) AS dup
          ON op.v_xid = dup.v_xid
        LEFT JOIN sh_dm_video_v2 AS v
          ON op.v_xid = v.v_xid
        WHERE op.rn = %s
          AND op.batch IN (1747324254, 1747323990)
        ORDER BY op.id;
    """
    conn = pymysql.connect(**db_config)
    df = pd.read_sql(sql, conn, params=(rn))
    conn.close()
    return df

def export_all():
    """循环所有地区，导出 Excel"""
    rn_list = get_rn_list()
    for rn in rn_list:
        df = get_data_for_rn(rn)
        if df.empty:
            continue

        timestamp = datetime.now().strftime("%Y%m%d")
        safe_rn = rn.replace(" ", "_")  # 如果地区名里有空格或特殊字符
        filename = f"{timestamp}_T0T1_{safe_rn}.xlsx"

        df.to_excel(filename, index=False)
        print(f"已导出：{filename}")

if __name__ == "__main__":
    export_all()