spider_work/zhongjian_spider/mysql_pool.py

# -*- coding: utf-8 -*-
# Author : Charley
# Python : 3.10.8
# Date   : 2025/3/25 14:14
import re
import pymysql
import YamlLoader
from loguru import logger
from dbutils.pooled_db import PooledDB

# 获取yaml配置
yaml = YamlLoader.readYaml()
mysqlYaml = yaml.get("mysql")
sql_host = mysqlYaml.getValueAsString("host")
sql_port = mysqlYaml.getValueAsInt("port")
sql_user = mysqlYaml.getValueAsString("username")
sql_password = mysqlYaml.getValueAsString("password")
sql_db = mysqlYaml.getValueAsString("db")


class MySQLConnectionPool:
    """
    MySQL连接池
    """

    def __init__(self, mincached=1, maxcached=2, maxconnections=3, log=None):
        """
        初始化连接池
        :param mincached: 初始化时，链接池中至少创建的链接，0表示不创建
        :param maxcached: 池中空闲连接的最大数目（0 或 None 表示池大小不受限制）
        :param maxconnections: 允许的最大连接数（0 或 None 表示任意数量的连接）
        :param log: 自定义日志记录器
        """
        # 使用 loguru 的 logger，如果传入了其他 logger，则使用传入的 logger
        self.log = log or logger
        self.pool = PooledDB(
            creator=pymysql,
            mincached=mincached,
            maxcached=maxcached,
            maxconnections=maxconnections,
            blocking=True,  # 连接池中如果没有可用连接后，是否阻塞等待。True，等待；False，不等待然后报错
            host=sql_host,
            port=sql_port,
            user=sql_user,
            password=sql_password,
            database=sql_db,
            charset="utf8mb4",
            use_unicode=True,
            init_command="SET NAMES utf8mb4",
            ping=1,  # 0:完全关闭（更快）, 1:仅在取连接时检查, 2:每次执行前检查连接有效性，防止使用已断开的连接
            connect_timeout=5,  # 连接超时时间（秒）
            # read_timeout=30,  # 读取超时时间（秒）
            write_timeout=30  # 写入超时时间（秒）
        )

    def _execute(self, query, args=None, commit=False):
        """
        执行SQL
        :param query: SQL语句
        :param args: SQL参数
        :param commit: 是否提交事务
        :return: 查询结果
        """
        try:
            with self.pool.connection() as conn:
                with conn.cursor() as cursor:
                    cursor.execute(query, args)
                    if commit:
                        conn.commit()
                    self.log.debug(f"sql _execute, Query: {query}, Rows: {cursor.rowcount}")
                    return cursor
        except Exception as e:
            if commit and conn:
                conn.rollback()
            self.log.exception(f"Error executing query: {e}, Query: {query}, Args: {args}")
            raise e

    def select_one(self, query, args=None):
        """
        执行查询，返回单个结果
        :param query: 查询语句
        :param args: 查询参数
        :return: 查询结果
        """
        cursor = self._execute(query, args)
        return cursor.fetchone()

    def select_all(self, query, args=None):
        """
        执行查询，返回所有结果
        :param query: 查询语句
        :param args: 查询参数
        :return: 查询结果
        """
        cursor = self._execute(query, args)
        return cursor.fetchall()

    def insert_one(self, query, args):
        """
        执行单条插入语句
        :param query: 插入语句
        :param args: 插入参数
        """
        self.log.info('>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>data insert_one 入库中>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>')
        cursor = self._execute(query, args, commit=True)
        return cursor.lastrowid  # 返回插入的ID

    def insert_all(self, query, args_list):
        """
        执行批量插入语句,如果失败则逐条插入
        :param query: 插入语句
        :param args_list: 插入参数列表
        """
        conn = None
        cursor = None
        try:
            conn = self.pool.connection()
            cursor = conn.cursor()
            cursor.executemany(query, args_list)
            conn.commit()
            self.log.debug(f"sql insert_all, SQL: {query[:100]}..., Rows: {cursor.rowcount}")
            self.log.info('>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>data insert_all 入库中>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>')
        except pymysql.err.IntegrityError as e:
            if "Duplicate entry" in str(e):
                conn.rollback()
                self.log.warning(f"批量插入遇到重复,开始逐条插入。错误: {e}")
                rowcount = 0
                for args in args_list:
                    try:
                        self.insert_one(query, args)
                        rowcount += 1
                    except pymysql.err.IntegrityError as e2:
                        if "Duplicate entry" in str(e2):
                            self.log.debug(f"跳过重复条目: {e2}")
                        else:
                            self.log.error(f"插入失败: {e2}")
                    except Exception as e2:
                        self.log.error(f"插入失败: {e2}")
                self.log.info(f"逐条插入完成: {rowcount}/{len(args_list)}条")
            else:
                conn.rollback()
                self.log.exception(f"数据库完整性错误: {e}")
                raise e
        except Exception as e:
            conn.rollback()
            self.log.exception(f"批量插入失败: {e}")
            raise e
        finally:
            if cursor:
                cursor.close()
            if conn:
                conn.close()

    def insert_one_or_dict(self, table=None, data=None, query=None, args=None, commit=True, ignore=False):
        """
        单条插入（支持字典或原始SQL）
        :param table: 表名（字典插入时必需）
        :param data: 字典数据 {列名: 值}
        :param query: 直接SQL语句（与data二选一）
        :param args: SQL参数（query使用时必需）
        :param commit: 是否自动提交
        :param ignore: 是否使用ignore
        :return: 最后插入ID
        """
        if data is not None:
            if not isinstance(data, dict):
                raise ValueError("Data must be a dictionary")

            keys = ', '.join([self._safe_identifier(k) for k in data.keys()])
            values = ', '.join(['%s'] * len(data))

            # 构建 INSERT IGNORE 语句
            ignore_clause = "IGNORE" if ignore else ""
            query = f"INSERT {ignore_clause} INTO {self._safe_identifier(table)} ({keys}) VALUES ({values})"
            args = tuple(data.values())
        elif query is None:
            raise ValueError("Either data or query must be provided")

        try:
            cursor = self._execute(query, args, commit)
            self.log.info(f"sql insert_one_or_dict, Table: {table}, Rows: {cursor.rowcount}")
            self.log.info('>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>data insert_one_or_dict 入库中>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>')
            return cursor.lastrowid
        except pymysql.err.IntegrityError as e:
            if "Duplicate entry" in str(e):
                self.log.warning(f"插入失败：重复条目，已跳过。错误详情: {e}")
                return -1  # 返回 -1 表示重复条目被跳过
            else:
                self.log.exception(f"数据库完整性错误: {e}")
                raise
        except Exception as e:
            self.log.exception(f"未知错误: {e}")
            raise

    def insert_many(self, table=None, data_list=None, query=None, args_list=None, batch_size=1000, commit=True,
                    ignore=False):
        """
        批量插入（支持字典列表或原始SQL）
        :param table: 表名（字典插入时必需）
        :param data_list: 字典列表 [{列名: 值}]
        :param query: 直接SQL语句（与data_list二选一）
        :param args_list: SQL参数列表（query使用时必需）
        :param batch_size: 分批大小
        :param commit: 是否自动提交
        :param ignore: 是否使用ignore
        :return: 影响行数
        """
        if data_list is not None:
            if not data_list or not isinstance(data_list[0], dict):
                raise ValueError("Data_list must be a non-empty list of dictionaries")

            keys = ', '.join([self._safe_identifier(k) for k in data_list[0].keys()])
            values = ', '.join(['%s'] * len(data_list[0]))

            # 构建 INSERT IGNORE 语句
            ignore_clause = "IGNORE" if ignore else ""
            query = f"INSERT {ignore_clause} INTO {self._safe_identifier(table)} ({keys}) VALUES ({values})"
            args_list = [tuple(d.values()) for d in data_list]
        elif query is None:
            raise ValueError("Either data_list or query must be provided")

        total = 0
        for i in range(0, len(args_list), batch_size):
            batch = args_list[i:i + batch_size]
            try:
                with self.pool.connection() as conn:
                    with conn.cursor() as cursor:
                        cursor.executemany(query, batch)
                        if commit:
                            conn.commit()
                        total += cursor.rowcount
            except pymysql.err.IntegrityError as e:
                # 处理唯一索引冲突
                if "Duplicate entry" in str(e):
                    if ignore:
                        # 如果使用了 INSERT IGNORE,理论上不会进这里,但以防万一
                        self.log.warning(f"批量插入遇到重复条目(ignore模式): {e}")
                    else:
                        # 没有使用 IGNORE,降级为逐条插入
                        self.log.warning(f"批量插入遇到重复条目,开始逐条插入。错误: {e}")
                        if commit:
                            conn.rollback()
                        
                        rowcount = 0
                        for j, args in enumerate(batch):
                            try:
                                if data_list:
                                    # 字典模式
                                    self.insert_one_or_dict(
                                        table=table,
                                        data=dict(zip(data_list[0].keys(), args)),
                                        commit=commit,
                                        ignore=False  # 单条插入时手动捕获重复
                                    )
                                else:
                                    # 原始SQL模式
                                    self.insert_one(query, args)
                                rowcount += 1
                            except pymysql.err.IntegrityError as e2:
                                if "Duplicate entry" in str(e2):
                                    self.log.debug(f"跳过重复条目[{i+j+1}]: {e2}")
                                else:
                                    self.log.error(f"插入失败[{i+j+1}]: {e2}")
                            except Exception as e2:
                                self.log.error(f"插入失败[{i+j+1}]: {e2}")
                        total += rowcount
                        self.log.info(f"批次逐条插入完成: 成功{rowcount}/{len(batch)}条")
                else:
                    # 其他完整性错误
                    self.log.exception(f"数据库完整性错误: {e}")
                    if commit:
                        conn.rollback()
                    raise e
            except Exception as e:
                # 其他数据库错误
                self.log.exception(f"批量插入失败: {e}")
                if commit:
                    conn.rollback()
                raise e
        if table:
            self.log.info(f"sql insert_many, Table: {table}, Total Rows: {total}")
        else:
            self.log.info(f"sql insert_many, Query: {query}, Total Rows: {total}")
        return total

    def insert_many_two(self, table=None, data_list=None, query=None, args_list=None, batch_size=1000, commit=True,
                        ignore=False):
        """
        批量插入(支持字典列表或原始SQL) - 备用方法
        :param table: 表名(字典插入时必需)
        :param data_list: 字典列表 [{列名: 值}]
        :param query: 直接SQL语句(与data_list二选一)
        :param args_list: SQL参数列表(query使用时必需)
        :param batch_size: 分批大小
        :param commit: 是否自动提交
        :param ignore: 是否使用INSERT IGNORE
        :return: 影响行数
        """
        if data_list is not None:
            if not data_list or not isinstance(data_list[0], dict):
                raise ValueError("Data_list must be a non-empty list of dictionaries")
            keys = ', '.join([self._safe_identifier(k) for k in data_list[0].keys()])
            values = ', '.join(['%s'] * len(data_list[0]))
            ignore_clause = "IGNORE" if ignore else ""
            query = f"INSERT {ignore_clause} INTO {self._safe_identifier(table)} ({keys}) VALUES ({values})"
            args_list = [tuple(d.values()) for d in data_list]
        elif query is None:
            raise ValueError("Either data_list or query must be provided")
    
        total = 0
        for i in range(0, len(args_list), batch_size):
            batch = args_list[i:i + batch_size]
            try:
                with self.pool.connection() as conn:
                    with conn.cursor() as cursor:
                        cursor.executemany(query, batch)
                        if commit:
                            conn.commit()
                        total += cursor.rowcount
            except pymysql.err.IntegrityError as e:
                if "Duplicate entry" in str(e) and not ignore:
                    self.log.warning(f"批量插入遇到重复,降级为逐条插入: {e}")
                    if commit:
                        conn.rollback()
                    rowcount = 0
                    for args in batch:
                        try:
                            self.insert_one(query, args)
                            rowcount += 1
                        except pymysql.err.IntegrityError as e2:
                            if "Duplicate entry" in str(e2):
                                self.log.debug(f"跳过重复条目: {e2}")
                            else:
                                self.log.error(f"插入失败: {e2}")
                        except Exception as e2:
                            self.log.error(f"插入失败: {e2}")
                    total += rowcount
                else:
                    self.log.exception(f"数据库完整性错误: {e}")
                    if commit:
                        conn.rollback()
                    raise e
            except Exception as e:
                self.log.exception(f"批量插入失败: {e}")
                if commit:
                    conn.rollback()
                raise e
        self.log.info(f"sql insert_many_two, Table: {table}, Total Rows: {total}")
        return total

    def insert_too_many(self, query, args_list, batch_size=1000):
        """
        执行批量插入语句，分片提交, 单次插入大于十万+时可用, 如果失败则降级为逐条插入
        :param query: 插入语句
        :param args_list: 插入参数列表
        :param batch_size: 每次插入的条数
        """
        self.log.info(f"sql insert_too_many, Query: {query}, Total Rows: {len(args_list)}")
        for i in range(0, len(args_list), batch_size):
            batch = args_list[i:i + batch_size]
            try:
                with self.pool.connection() as conn:
                    with conn.cursor() as cursor:
                        cursor.executemany(query, batch)
                        conn.commit()
                        self.log.debug(f"insert_too_many -> Total Rows: {len(batch)}")
            except Exception as e:
                self.log.error(f"insert_too_many error. Trying single insert. Error: {e}")
                # 当前批次降级为单条插入
                for args in batch:
                    self.insert_one(query, args)

    def update_one(self, query, args):
        """
        执行单条更新语句
        :param query: 更新语句
        :param args: 更新参数
        """
        self.log.info('>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>data update_one 更新中>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>')
        return self._execute(query, args, commit=True)

    def update_all(self, query, args_list):
        """
        执行批量更新语句，如果失败则逐条更新
        :param query: 更新语句
        :param args_list: 更新参数列表
        """
        conn = None
        cursor = None
        try:
            conn = self.pool.connection()
            cursor = conn.cursor()
            cursor.executemany(query, args_list)
            conn.commit()
            self.log.debug(f"sql update_all, SQL: {query}, Rows: {len(args_list)}")
            self.log.info('>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>data update_all 更新中>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>')
        except Exception as e:
            conn.rollback()
            self.log.error(f"Error executing query: {e}")
            # 如果批量更新失败，则逐条更新
            rowcount = 0
            for args in args_list:
                self.update_one(query, args)
                rowcount += 1
            self.log.debug(f'Batch update failed. Updated {rowcount} rows individually.')
        finally:
            if cursor:
                cursor.close()
            if conn:
                conn.close()

    def update_one_or_dict(self, table=None, data=None, condition=None, query=None, args=None, commit=True):
        """
        单条更新（支持字典或原始SQL）
        :param table: 表名（字典模式必需）
        :param data: 字典数据 {列名: 值}（与 query 二选一）
        :param condition: 更新条件，支持以下格式：
            - 字典: {"id": 1} → "WHERE id = %s"
            - 字符串: "id = 1" → "WHERE id = 1"（需自行确保安全）
            - 元组: ("id = %s", [1]) → "WHERE id = %s"（参数化查询）
        :param query: 直接SQL语句（与 data 二选一）
        :param args: SQL参数（query 模式下必需）
        :param commit: 是否自动提交
        :return: 影响行数
        :raises: ValueError 参数校验失败时抛出
        """
        # 参数校验
        if data is not None:
            if not isinstance(data, dict):
                raise ValueError("Data must be a dictionary")
            if table is None:
                raise ValueError("Table name is required for dictionary update")
            if condition is None:
                raise ValueError("Condition is required for dictionary update")

            # 构建 SET 子句
            set_clause = ", ".join([f"{self._safe_identifier(k)} = %s" for k in data.keys()])
            set_values = list(data.values())

            # 解析条件
            condition_clause, condition_args = self._parse_condition(condition)
            query = f"UPDATE {self._safe_identifier(table)} SET {set_clause} WHERE {condition_clause}"
            args = set_values + condition_args

        elif query is None:
            raise ValueError("Either data or query must be provided")

        # 执行更新
        cursor = self._execute(query, args, commit)
        # self.log.debug(
        #     f"Updated table={table}, rows={cursor.rowcount}, query={query[:100]}...",
        #     extra={"table": table, "rows": cursor.rowcount}
        # )
        return cursor.rowcount

    def _parse_condition(self, condition):
        """
        解析条件为 (clause, args) 格式
        :param condition: 字典/字符串/元组
        :return: (str, list) SQL 子句和参数列表
        """
        if isinstance(condition, dict):
            clause = " AND ".join([f"{self._safe_identifier(k)} = %s" for k in condition.keys()])
            args = list(condition.values())
        elif isinstance(condition, str):
            clause = condition  # 注意：需调用方确保安全
            args = []
        elif isinstance(condition, (tuple, list)) and len(condition) == 2:
            clause, args = condition[0], condition[1]
            if not isinstance(args, (list, tuple)):
                args = [args]
        else:
            raise ValueError("Condition must be dict/str/(clause, args)")
        return clause, args

    def update_many(self, table=None, data_list=None, condition_list=None, query=None, args_list=None, batch_size=500,
                    commit=True):
        """
        批量更新（支持字典列表或原始SQL）
        :param table: 表名（字典插入时必需）
        :param data_list: 字典列表 [{列名: 值}]
        :param condition_list: 条件列表（必须为字典，与data_list等长）
        :param query: 直接SQL语句（与data_list二选一）
        :param args_list: SQL参数列表（query使用时必需）
        :param batch_size: 分批大小
        :param commit: 是否自动提交
        :return: 影响行数
        """
        if data_list is not None:
            if not data_list or not isinstance(data_list[0], dict):
                raise ValueError("Data_list must be a non-empty list of dictionaries")
            if condition_list is None or len(data_list) != len(condition_list):
                raise ValueError("Condition_list must be provided and match the length of data_list")
            if not all(isinstance(cond, dict) for cond in condition_list):
                raise ValueError("All elements in condition_list must be dictionaries")

            # 获取第一个数据项和条件项的键
            first_data_keys = set(data_list[0].keys())
            first_cond_keys = set(condition_list[0].keys())

            # 构造基础SQL
            set_clause = ', '.join([self._safe_identifier(k) + ' = %s' for k in data_list[0].keys()])
            condition_clause = ' AND '.join([self._safe_identifier(k) + ' = %s' for k in condition_list[0].keys()])
            base_query = f"UPDATE {self._safe_identifier(table)} SET {set_clause} WHERE {condition_clause}"
            total = 0

            # 分批次处理
            for i in range(0, len(data_list), batch_size):
                batch_data = data_list[i:i + batch_size]
                batch_conds = condition_list[i:i + batch_size]
                batch_args = []

                # 检查当前批次的结构是否一致
                can_batch = True
                for data, cond in zip(batch_data, batch_conds):
                    data_keys = set(data.keys())
                    cond_keys = set(cond.keys())
                    if data_keys != first_data_keys or cond_keys != first_cond_keys:
                        can_batch = False
                        break
                    batch_args.append(tuple(data.values()) + tuple(cond.values()))

                if not can_batch:
                    # 结构不一致，转为单条更新
                    for data, cond in zip(batch_data, batch_conds):
                        self.update_one_or_dict(table=table, data=data, condition=cond, commit=commit)
                        total += 1
                    continue

                # 执行批量更新
                try:
                    with self.pool.connection() as conn:
                        with conn.cursor() as cursor:
                            cursor.executemany(base_query, batch_args)
                            if commit:
                                conn.commit()
                            total += cursor.rowcount
                            self.log.debug(f"Batch update succeeded. Rows: {cursor.rowcount}")
                except Exception as e:
                    if commit:
                        conn.rollback()
                    self.log.error(f"Batch update failed: {e}")
                    # 降级为单条更新
                    for args, data, cond in zip(batch_args, batch_data, batch_conds):
                        try:
                            self._execute(base_query, args, commit=commit)
                            total += 1
                        except Exception as e2:
                            self.log.error(f"Single update failed: {e2}, Data: {data}, Condition: {cond}")
            self.log.info(f"Total updated rows: {total}")
            return total
        elif query is not None:
            # 处理原始SQL和参数列表
            if args_list is None:
                raise ValueError("args_list must be provided when using query")

            total = 0
            for i in range(0, len(args_list), batch_size):
                batch_args = args_list[i:i + batch_size]
                try:
                    with self.pool.connection() as conn:
                        with conn.cursor() as cursor:
                            cursor.executemany(query, batch_args)
                            if commit:
                                conn.commit()
                            total += cursor.rowcount
                            self.log.debug(f"Batch update succeeded. Rows: {cursor.rowcount}")
                except Exception as e:
                    if commit:
                        conn.rollback()
                    self.log.error(f"Batch update failed: {e}")
                    # 降级为单条更新
                    for args in batch_args:
                        try:
                            self._execute(query, args, commit=commit)
                            total += 1
                        except Exception as e2:
                            self.log.error(f"Single update failed: {e2}, Args: {args}")
            self.log.info(f"Total updated rows: {total}")
            return total
        else:
            raise ValueError("Either data_list or query must be provided")

    def check_pool_health(self):
        """
        检查连接池中有效连接数

        # 使用示例
        # 配置 MySQL 连接池
        sql_pool = MySQLConnectionPool(log=log)
        if not sql_pool.check_pool_health():
            log.error("数据库连接池异常")
            raise RuntimeError("数据库连接池异常")
        """
        try:
            with self.pool.connection() as conn:
                conn.ping(reconnect=True)
                return True
        except Exception as e:
            self.log.error(f"Connection pool health check failed: {e}")
            return False

    def close(self):
        """
        关闭连接池，释放所有连接
        """
        try:
            if hasattr(self, 'pool') and self.pool:
                self.pool.close()
                self.log.info("数据库连接池已关闭")
        except Exception as e:
            self.log.error(f"关闭连接池失败: {e}")

    @staticmethod
    def _safe_identifier(name):
        """SQL标识符安全校验"""
        if not re.match(r'^[a-zA-Z_][a-zA-Z0-9_]*$', name):
            raise ValueError(f"Invalid SQL identifier: {name}")
        return name


if __name__ == '__main__':
    sql_pool = MySQLConnectionPool()
    # data_dic = {'card_type_id': 111, 'card_type_name': '补充包 继承的意志【OPC-13】', 'card_type_position': 964,
    #             'card_id': 5284, 'card_name': '蒙奇·D·路飞', 'card_number': 'OP13-001', 'card_rarity': 'L',
    #             'card_img': 'https://source.windoent.com/OnePiecePc/Picture/1757929283612OP13-001.png',
    #             'card_life': '4', 'card_attribute': '打', 'card_power': '5000', 'card_attack': '-',
    #             'card_color': '红/绿', 'subscript': 4, 'card_features': '超新星/草帽一伙',
    #             'card_text_desc': '【咚!!×1】【对方的攻击时】我方处于活跃状态的咚!!不多于5张的场合，可以将我方任意张数的咚!!转为休息状态。每有1张转为休息状态的咚!!，本次战斗中，此领袖或我方最多1张拥有《草帽一伙》特征的角色力量+2000。',
    #             'card_offer_type': '补充包 继承的意志【OPC-13】', 'crawler_language': '简中'}
    # sql_pool.insert_one_or_dict(table="one_piece_record", data=data_dic)

    sql_pool.insert_many(
        table="jhs_product_record",
        data_list=[
            {
                "product_id": 99999991,
                "seller_username": "浣熊小助理（裸卡版）",
                "auction_product_name": "2000 日文 无编号 #175 U 波克比 有瑕疵",
            },
            {
                "product_id": 99999992,
                "seller_username": "测试商家二号",
                "auction_product_name": "中文批量插入测试",
            },
        ],
        ignore=False
    )