feat(spider): 新增hugginsandscott拍卖爬虫及MySQL连接池

- 新增爬虫脚本hug_spider.py，实现从hugginsandscott.com爬取拍卖数据
- 支持分页获取拍卖列表及详情页数据解析和入库
- 使用requests结合代理和用户代理头，保障请求稳定性
- 集成tenacity实现重试机制，提升爬取健壮性
- 增加定时调度功能，每半月执行增量采集任务
- 新增MySQLConnectionPool类，封装MySQL连接池操作，支持单条和批量增删改查
- 增加YamlLoader配置加载，支持环境变量动态覆盖数据库配置
- 日志采用loguru，支持按日期轮转和多级别日志记录
- application.yml文件支持MySQL数据库连接配置，默认启用环境变量覆盖机制

hugginsandscott_spider/YamlLoader.py

@@ -0,0 +1,98 @@
+# -*- coding: utf-8 -*-
+# Author : Charley
+# Python : 3.10.8
+# Date   : 2025/12/22 10:44
+import os, re
+import yaml
+
+regex = re.compile(r'^\$\{(?P<ENV>[A-Z_\-]+:)?(?P<VAL>[\w.]+)}$')
+
+
+class YamlConfig:
+    def __init__(self, config):
+        self.config = config
+
+    def get(self, key: str):
+        return YamlConfig(self.config.get(key))
+
+    def getValueAsString(self, key: str):
+        try:
+            match = regex.match(self.config[key])
+            group = match.groupdict()
+            if group['ENV'] is not None:
+                env = group['ENV'][:-1]
+                return os.getenv(env, group['VAL'])
+            return None
+        except:
+            return self.config[key]
+
+    def getValueAsInt(self, key: str):
+        try:
+            match = regex.match(self.config[key])
+            group = match.groupdict()
+            if group['ENV'] is not None:
+                env = group['ENV'][:-1]
+                return int(os.getenv(env, group['VAL']))
+            return 0
+        except:
+            return int(self.config[key])
+
+    def getValueAsBool(self, key: str):
+        try:
+            match = regex.match(self.config[key])
+            group = match.groupdict()
+            if group['ENV'] is not None:
+                env = group['ENV'][:-1]
+                return bool(os.getenv(env, group['VAL']))
+            return False
+        except:
+            return bool(self.config[key])
+
+
+def _resolve_path(path: str) -> str:
+    """
+    解析 yaml 文件路径，按优先级查找：
+      1) 绝对路径或 cwd 下存在 → 直接用（保留旧行为，向后兼容）
+      2) 调用方主脚本所在目录 → 兜底，方便打包后从任意 cwd 启动
+    :param path: (str) 用户传入的路径，默认 'application.yml'
+    :return: (str) 实际可读取的完整路径；找不到则返回原 path 让 open() 抛错
+    """
+    # 1) 旧行为：cwd 或绝对路径
+    if os.path.exists(path):
+        return path
+
+    # 2) 主脚本目录（__main__.__file__）
+    try:
+        import __main__
+        main_file = getattr(__main__, '__file__', None)
+        if main_file:
+            candidate = os.path.join(os.path.dirname(os.path.abspath(main_file)), path)
+            if os.path.exists(candidate):
+                return candidate
+    except Exception:
+        pass
+
+    return path
+
+
+def readYaml(path: str = 'application.yml', profile: str = None) -> YamlConfig:
+    """
+    读取 yaml 配置。
+    :param path: (str) yaml 文件路径，默认 'application.yml'。
+                       优先 cwd / 绝对路径（保留旧行为），找不到再 fallback 到主脚本所在目录。
+    :param profile: (str) 可选环境后缀，如 'dev' 会额外加载 'application-dev.yml' 并 update
+    :return: (YamlConfig) 配置访问对象
+    :raises FileNotFoundError: cwd 和主脚本目录都找不到时抛出
+    """
+    real_path = _resolve_path(path)
+    with open(real_path, encoding='utf-8') as fd:
+        conf = yaml.load(fd, Loader=yaml.FullLoader)
+
+    if profile is not None:
+        result = real_path.rsplit('.', 1)
+        profiledYaml = f'{result[0]}-{profile}.{result[1]}'
+        if os.path.exists(profiledYaml):
+            with open(profiledYaml, encoding='utf-8') as fd:
+                conf.update(yaml.load(fd, Loader=yaml.FullLoader))
+
+    return YamlConfig(conf)

hugginsandscott_spider/application.yml

@@ -0,0 +1,6 @@
+mysql:
+  host: ${MYSQL_HOST:100.64.0.21}
+  port: ${MYSQL_PROT:3306}
+  username: ${MYSQL_USERNAME:crawler}
+  password: ${MYSQL_PASSWORD:Pass2022}
+  db: ${MYSQL_DATABASE:crawler}

hugginsandscott_spider/hug_spider.py

@@ -0,0 +1,288 @@
+# -*- coding: utf-8 -*-
+# Author : Charley
+# Python : 3.12.10
+# Date   : 2026/5/19 16:56
+import time
+import inspect
+import requests
+import schedule
+import user_agent
+from loguru import logger
+from parsel import Selector
+from mysql_pool import MySQLConnectionPool
+from tenacity import retry, stop_after_attempt, wait_fixed
+
+"""
+目标网站: https://hugginsandscott.com/auction/2026/winter/
+"""
+
+logger.remove()
+logger.add("./logs/{time:YYYYMMDD}.log", encoding='utf-8', rotation="00:00",
+           format="[{time:YYYY-MM-DD HH:mm:ss.SSS}] {level} {message}",
+           level="DEBUG", retention="7 day")
+
+headers = {
+    "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+    "user-agent": user_agent.generate_user_agent()
+}
+
+
+def after_log(retry_state):
+    """
+    retry 回调
+    :param retry_state: RetryCallState 对象
+    """
+    # 检查 args 是否存在且不为空
+    if retry_state.args and len(retry_state.args) > 0:
+        log = retry_state.args[0]  # 获取传入的 logger
+    else:
+        log = logger  # 使用全局 logger
+
+    if retry_state.outcome.failed:
+        log.warning(
+            f"Function '{retry_state.fn.__name__}', Attempt {retry_state.attempt_number} Times")
+    else:
+        log.info(f"Function '{retry_state.fn.__name__}', Attempt {retry_state.attempt_number} succeeded")
+
+
+@retry(stop=stop_after_attempt(5), wait=wait_fixed(2), after=after_log)
+def get_proxys(log):
+    http_proxy = "http://u1952150085001297:sJMHl4qc4bM0@proxy.123proxy.cn:36931"
+    https_proxy = "http://u1952150085001297:sJMHl4qc4bM0@proxy.123proxy.cn:36931"
+
+    try:
+        proxySettings = {
+            "http": http_proxy,
+            "https": https_proxy,
+        }
+        return proxySettings
+    except Exception as e:
+        log.error(f"Error getting proxy: {e}")
+        raise e
+
+
+@retry(stop=stop_after_attempt(5), wait=wait_fixed(2), after=after_log)
+def get_details(log, url, sql_pool, sql_id):
+    """
+    获取详情数据
+    :param log: logger对象
+    :param url: 详情页URL
+    :param sql_pool: MySQL连接池
+    :param sql_id: 数据ID
+    :return: 标题和描述
+    """
+    log.info(f">>>>>>>>>>>>>> 正在爬取详情数据URL: {url} <<<<<<<<<<<<<<")
+    response = requests.get(url, headers=headers, timeout=10, proxies=get_proxys(log))
+    response.raise_for_status()
+    selector = Selector(response.text)
+    year = selector.xpath('//section//div/ul/li[2]/text()').get()
+    year = year.replace('Year: ', '') if year else None
+
+    auction = selector.xpath('//section//div/ul/li[3]/text()').get()
+    auction = auction.replace('Auction: ', '') if auction else None
+
+    imgs = selector.xpath('//section//button/span/img/@src').getall()
+    imgs = ','.join(imgs) if imgs else None
+    # print(year, auction, imgs)
+
+    # 更新数据和状态
+    sql_pool.update_one_or_dict(
+        table="hugginsandscott_record",
+        data={"year": year, "auction": auction, "imgs": imgs, "state": 1},
+        condition={"id": sql_id}
+    )
+
+
+@retry(stop=stop_after_attempt(5), wait=wait_fixed(2), after=after_log)
+def get_single_page(log, page, auc_url, sql_pool):
+    """
+    获取单页数据
+    :param log: logger对象
+    :param page: 页码
+    :param auc_url: 拍卖会URL
+    :param sql_pool: MySQL连接池
+    :return: 该页数据条数
+    """
+    log.info(f"Requesting page {page} for auction:{auc_url}........................... started")
+    # url = "https://hugginsandscott.com/auction/2026/winter/"
+    params = {
+        # "page": "3"
+        "page": page
+    }
+    response = requests.get(auc_url, headers=headers, params=params, timeout=10, proxies=get_proxys(log))
+    # print(response.text)
+    response.raise_for_status()
+
+    selector = Selector(response.text)
+    tag_tr_list = selector.xpath("//table/tbody/tr")
+
+    info_list = []
+    for tag_tr in tag_tr_list:
+        lot_no = tag_tr.xpath("./td[1]/text()").get()
+        title = tag_tr.xpath("./td[2]/a/text()").get()
+        title = title.strip() if title else ""
+
+        detail_url = tag_tr.xpath("./td[2]/a/@href").get()
+        detail_url = 'https://hugginsandscott.com' + detail_url if detail_url else ""
+
+        category = tag_tr.xpath("./td[3]/text()").get()
+        sold_for = tag_tr.xpath("./td[4]/text()").get()
+        sold_for = sold_for.replace(",", "").replace("$", "") if sold_for else "0"
+
+        data_dict = {
+            "auction_url": auc_url,
+            "lot_no": lot_no,
+            "title": title,
+            "detail_url": detail_url,
+            "category": category,
+            "sold_for": sold_for
+        }
+        # print(data_dict)
+        info_list.append(data_dict)
+
+    # save
+    if info_list:
+        sql_pool.insert_many(table="hugginsandscott_record", data_list=info_list, ignore=True)
+
+    return len(info_list)
+
+
+def get_sold_list(log, auc_url, sql_pool):
+    """
+    获取已售列表
+    :param log: logger对象
+    :param auc_url: 拍卖会URL
+    :param sql_pool: MySQL连接池
+    :return: 无
+    """
+    page = 1
+    max_page = 10
+
+    while page <= max_page:
+        try:
+            len_list = get_single_page(log, page, auc_url, sql_pool)
+        except Exception as e:
+            log.error(f"Error getting page {page}: {e}")
+            continue
+
+        if len_list < 10:
+            log.warning(f"No data on page {page}, stopping further requests")
+            break
+
+        page += 1
+
+
+@retry(stop=stop_after_attempt(5), wait=wait_fixed(2), after=after_log)
+def get_all_auctions(log, sql_pool):
+    """
+    获取所有拍卖会
+    :param log: logger对象
+    :param sql_pool: MySQL连接池
+    :return: 无
+    """
+    log.info(">>>>>>>>>>>>>> 正在获取所有拍卖会 <<<<<<<<<<<<")
+    # //div[@class="max-w-screen-xl px-4 py-8 mx-auto"]//a/@href
+    url = 'https://hugginsandscott.com/search'
+    response = requests.get(url, headers=headers, timeout=10, proxies=get_proxys(log))
+    response.raise_for_status()
+    selector = Selector(response.text)
+    tag_a_list = selector.xpath("//div[@class='max-w-screen-xl px-4 py-8 mx-auto']//a/@href").getall()
+    log.info(f"Total auctions: {len(tag_a_list)}")
+    # 补全 https://hugginsandscott.com/
+    tag_a_list = [f"https://hugginsandscott.com{tag_a}" for tag_a in tag_a_list]
+
+    # 批量查询库中已存在的 URL，避免 N 次单条查询
+    if tag_a_list:
+        placeholders = ','.join(['%s'] * len(tag_a_list))
+        sql = f"SELECT auction_url FROM hugginsandscott_record WHERE auction_url IN ({placeholders})"
+        existed_rows = sql_pool.select_all(sql, tuple(tag_a_list))
+        # 库中已存在的 URL 集合，便于 O(1) 查找
+        existed_urls = {row[0] for row in existed_rows}
+        # 用集合差集筛选出不在库中的新拍卖会 URL
+        new_tag_a_list = [tag_a for tag_a in tag_a_list if tag_a not in existed_urls]
+    else:
+        new_tag_a_list = []
+
+    log.info(f"Total auctions after filter: {len(new_tag_a_list)}")
+
+    # 打印不在库中的新 URL 列表
+    for auc_url in new_tag_a_list:
+        try:
+            log.info(f"Getting sold list for:{auc_url}...........................")
+            get_sold_list(log, auc_url, sql_pool)
+        except Exception as e:
+            log.error(f"{inspect.currentframe().f_code.co_name} -> getting sold list for:{auc_url}: {e}")
+
+
+@retry(stop=stop_after_attempt(100), wait=wait_fixed(3600), after=after_log)
+def hug_main(log):
+    """
+    主函数
+    :param log: logger对象
+    """
+    log.info(
+        f'开始运行 {inspect.currentframe().f_code.co_name} 爬虫任务....................................................')
+
+    # 配置 MySQL 连接池
+    sql_pool = MySQLConnectionPool(log=log)
+    if not sql_pool:
+        log.error("MySQL数据库连接失败")
+        raise Exception("MySQL数据库连接失败")
+
+    try:
+        try:
+            get_all_auctions(log, sql_pool)
+        except Exception as e:
+            log.error(f'Error getting all auctions list: {e}')
+
+        # 更新详情页
+        log.debug('Updating detail pages........................... started')
+        # sql_result = sql_pool.select_all('select id, detail_url from hugginsandscott_record where state = 0')
+        sql_result = sql_pool.select_all(
+            'select id, detail_url from hugginsandscott_record where state != 1 order by id')
+        for row in sql_result:
+            sql_id = row[0]
+            detail_url = row[1]
+            try:
+                get_details(log, detail_url, sql_pool, sql_id)
+            except Exception as e:
+                log.error(f'Error getting details for {detail_url}: {e}')
+                # 更新数据和状态
+                sql_pool.update_one_or_dict(
+                    table="hugginsandscott_record",
+                    data={"state": 2},
+                    condition={"id": sql_id}
+                )
+
+    except Exception as e:
+        log.error(f'{inspect.currentframe().f_code.co_name} error: {e}')
+    finally:
+        log.info(f'爬虫程序 {inspect.currentframe().f_code.co_name} 运行结束,等待下一轮的采集任务............')
+
+
+def schedule_task():
+    """每半个月 跑一次增量"""
+    hug_main(log=logger)
+
+    def run_semimonthly():
+        # 每月 1 号和 15 号执行（半月一次）
+        from datetime import date
+        if date.today().day in (1, 15):
+            hug_main(log=logger)
+
+    schedule.every().day.at("05:00").do(run_semimonthly)
+    while True:
+        schedule.run_pending()
+        time.sleep(1)
+
+
+if __name__ == '__main__':
+    # get_single_page(logger, 1, None)d
+    # get_details(logger,
+    #             "https://hugginsandscott.com/auction/2026/Winter/1/1952-topps-311-mickey-mantle-high-number-psa-vg-3-mba-silver-diamond-centered",
+    #             None, 1)
+
+    # hug_main(log=logger)
+    schedule_task()
+    # sql_pool_ = MySQLConnectionPool(log=logger)
+    # get_all_auctions(logger, sql_pool_)

hugginsandscott_spider/mysql_pool.py

@@ -0,0 +1,671 @@
+# -*- 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,
+            ping=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 _execute(self, query, args=None, commit=False):
+        """
+        执行SQL（带断连重试）
+        :param query: SQL语句
+        :param args: SQL参数
+        :param commit: 是否提交事务
+        :return: 查询结果
+        """
+        conn = None
+        for attempt in range(2):  # 最多重试1次
+            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 pymysql.err.InterfaceError as e:
+                # 连接已断开，重试一次
+                if attempt == 0:
+                    self.log.warning(f"数据库连接断开，正在重试... Error: {e}")
+                    continue
+                self.log.error(f"重试后仍失败: {e}, Query: {query}")
+                raise e
+            except pymysql.err.IntegrityError:
+                # 完整性错误（如重复条目）交由上层处理，避免在此打印完整堆栈污染日志
+                if commit and conn:
+                    try:
+                        conn.rollback()
+                    except Exception:
+                        pass
+                raise
+            except Exception as e:
+                if commit and conn:
+                    try:
+                        conn.rollback()
+                    except Exception:
+                        pass
+                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):
+                # 重复条目用 warning 简短输出，不打印堆栈
+                self.log.warning(f"插入跳过-重复条目 Table: {table}, {e.args[1] if len(e.args) > 1 else e}")
+                return -1  # 返回 -1 表示重复条目被跳过
+            else:
+                self.log.error(f"数据库完整性错误 Table: {table}, Error: {e}")
+                raise
+        except Exception as e:
+            self.log.error(f"insert_one_or_dict 失败 Table: {table}, Error: {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)

hugginsandscott_spider/requirements.txt

@@ -0,0 +1,10 @@
+-i https://mirrors.aliyun.com/pypi/simple/
+DBUtils==3.1.2
+loguru==0.7.3
+parsel==1.11.0
+PyMySQL==1.1.2
+PyYAML==6.0.3
+requests==2.33.1
+schedule==1.2.2
+tenacity==9.1.4
+user_agent==0.1.14