feat: 导出修改

mysql_to_xlsx.py

@@ -1,9 +1,8 @@
-import pymysql
 import pandas as pd
 from datetime import datetime
+from sqlalchemy import create_engine, text
 
-# 数据库连接配置
+DB_CONFIG = {
-db_config = {
     "host": "192.144.230.75",
     "port": 3306,
     "user": "db_vidcon",
@@ -12,18 +11,24 @@ db_config = {
     "charset": "utf8mb4",
 }
 
-def get_rn_list():
+URL = (
-    """获取所有地区列表"""
+    f"mysql+pymysql://{DB_CONFIG['user']}:{DB_CONFIG['password']}"
-    sql = "SELECT DISTINCT rn FROM sh_dm_video_op_v2;"
+    f"@{DB_CONFIG['host']}:{DB_CONFIG['port']}/{DB_CONFIG['database']}"
-    conn = pymysql.connect(**db_config)
+    f"?charset={DB_CONFIG['charset']}"
-    df = pd.read_sql(sql, conn)
+)
-    conn.close()
-    return df['rn'].tolist()
 
-def get_data_for_rn(rn: str) -> pd.DataFrame:
+engine = create_engine(URL, pool_pre_ping=True)
-    """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"""
+def get_rn_list() -> list[str]:
+    sql = "SELECT DISTINCT rn FROM sh_dm_video_op_v2;"
+    with engine.connect() as conn:
+        result = conn.execute(text(sql))
+        return [row[0] for row in result]
+
+
+def fetch_all_data_for_rn(rn: str) -> pd.DataFrame:
+    sql = """
     SELECT
         op.id                AS ID,
         v.v_name             AS 片名,
@@ -39,7 +44,7 @@ def get_data_for_rn(rn: str) -> pd.DataFrame:
         v.watch_number       AS 观看数量,
         v.public_time        AS 上传时间,
         v.u_pic              AS 头像,
-            v.is_repeat          AS 是否重复,   -- 直接用字段
+        v.is_repeat          AS 是否重复,
         op.sort              AS 排序,
         op.batch             AS 批次,
         op.machine           AS 机器号,
@@ -51,27 +56,39 @@ def get_data_for_rn(rn: str) -> pd.DataFrame:
       ON op.v_xid = v.v_xid
     WHERE op.rn = %s
       AND op.batch IN (1747324254, 1747323990)
-        ORDER BY op.id;
+    ORDER BY op.id
     """
-    conn = pymysql.connect(**db_config)
+    # 注意：params 用列表或元组
-    df = pd.read_sql(sql, conn, params=(rn))
+    chunks = pd.read_sql_query(
-    conn.close()
+        sql,
+        engine,
+        params=(rn,),
+        chunksize=10000
+    )
+    dfs = []
+    for i, chunk in enumerate(chunks, start=1):
+        print(f"[{rn}] 正在拉取第 {i} 块数据，行数：{len(chunk)}")
+        dfs.append(chunk)
+    df = pd.concat(dfs, ignore_index=True) if dfs else pd.DataFrame()
+    print(f"[{rn}] 全部拉取完成，共 {len(df)} 行")
     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
+    for rn in rn_list:
+        print(f"开始处理地区：{rn}")
+        df = fetch_all_data_for_rn(rn)
+        if df.empty:
+            print(f"[{rn}] 无数据，跳过导出")
+            continue
+        safe_rn = rn.replace(" ", "_")
         filename = f"{timestamp}_T0T1_{safe_rn}.xlsx"
-
+        print(f"[{rn}] 导出到文件：{filename} …")
         df.to_excel(filename, index=False)
-        print(f"已导出：{filename}")
+        print(f"[{rn}] 导出完成\n")
+
 
 if __name__ == "__main__":
     export_all()