update panini spider 7.22.1

panini_coming_soon_spider/YamlLoader.py

@@ -0,0 +1,74 @@
+# -*- coding: utf-8 -*-
+#
+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'] != 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'] != 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, env: str = None):
+        try:
+            match = regex.match(self.config[key])
+            group = match.groupdict()
+            if group['ENV'] != None:
+                env = group['ENV'][:-1]
+                return bool(os.getenv(env, group['VAL']))
+            return False
+        except:
+            return bool(self.config[key])
+    
+def readYaml(path:str = 'application.yml', profile:str = None) -> YamlConfig:
+    if os.path.exists(path):
+        with open(path) as fd:
+            conf = yaml.load(fd, Loader=yaml.FullLoader)
+
+    if profile != None:
+        result = path.split('.')
+        profiledYaml = f'{result[0]}-{profile}.{result[1]}'
+        if os.path.exists(profiledYaml):
+            with open(profiledYaml) as fd:
+                conf.update(yaml.load(fd, Loader=yaml.FullLoader))
+
+    return YamlConfig(conf)
+
+# res = readYaml()
+# mysqlConf = res.get('mysql')
+# print(mysqlConf)
+
+# print(res.getValueAsString("host"))
+# mysqlYaml = mysqlConf.getValueAsString("host")
+# print(mysqlYaml)
+# host = mysqlYaml.get("host").split(':')[-1][:-1]
+# port = mysqlYaml.get("port").split(':')[-1][:-1]
+# username = mysqlYaml.get("username").split(':')[-1][:-1]
+# password = mysqlYaml.get("password").split(':')[-1][:-1]
+# mysql_db = mysqlYaml.get("db").split(':')[-1][:-1]
+# print(host,port,username,password)

panini_coming_soon_spider/application.yml

@@ -0,0 +1,6 @@
+mysql:
+  host: ${MYSQL_HOST:100.64.0.23}
+  port: ${MYSQL_PROT:3306}
+  username: ${MYSQL_USERNAME:crawler}
+  password: ${MYSQL_PASSWORD:Pass2022}
+  db: ${MYSQL_DATABASE:crawler}

panini_coming_soon_spider/mysql_pool.py

@@ -0,0 +1,562 @@
+# -*- 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=4, maxcached=5, maxconnections=10, 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=0  # 每次连接使用时自动检查有效性（0=不检查,1=执行query前检查,2=每次执行前检查）
+        )
+
+    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:
+                conn.rollback()
+            self.log.error(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}, Rows: {len(args_list)}")
+            self.log.info('>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>data insert_all 入库中>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>')
+        except Exception as e:
+            conn.rollback()
+            self.log.error(f"Batch insertion failed after 5 attempts. Trying single inserts. Error: {e}")
+            # 如果批量插入失败，则逐条插入
+            rowcount = 0
+            for args in args_list:
+                self.insert_one(query, args)
+                rowcount += 1
+            self.log.debug(f"Batch insertion failed. Inserted {rowcount} rows individually.")
+        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))
+
+            # query = f"INSERT INTO {self._safe_identifier(table)} ({keys}) VALUES ({values})"
+            # 构建 INSERT IGNORE 语句
+            ignore_clause = "IGNORE" if ignore else ""
+            # insert_sql = f"INSERT {ignore_clause} INTO {table} ({columns}) VALUES ({placeholders})"
+            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")
+
+        # 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
+
+        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}")
+                # print("插入失败：重复条目", 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: {e}")
+                # print("插入失败：完整性错误", e)
+                raise e
+        except Exception as e:
+            self.log.error(f"未知错误: {e}", exc_info=True)
+            # print("插入失败：未知错误", e)
+            raise e
+
+    def insert_many(self, table=None, data_list=None, query=None, args_list=None, batch_size=500, 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 ""
+            # insert_sql = f"INSERT {ignore_clause} INTO {table} ({columns}) VALUES ({placeholders})"
+            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.Error as e:
+                if "Duplicate entry" in str(e):
+                    # self.log.warning(f"检测到重复条目，开始逐条插入。错误详情: {e}")
+                    raise  e
+                    # rowcount = 0
+                    # for args in batch:
+                    #     try:
+                    #         self.insert_one_or_dict(table=table, data=dict(zip(data_list[0].keys(), args)),
+                    #                                 commit=commit)
+                    #         rowcount += 1
+                    #     except pymysql.err.IntegrityError as e2:
+                    #         if "Duplicate entry" in str(e2):
+                    #             self.log.warning(f"跳过重复条目: {args}")
+                    #         else:
+                    #             self.log.error(f"插入失败: {e2}, 参数: {args}")
+                    # total += rowcount
+                else:
+                    self.log.error(f"数据库错误: {e}")
+                    if commit:
+                        conn.rollback()
+                    raise e
+                # 重新抛出异常，供外部捕获
+                # 降级为单条插入
+                # for args in batch:
+                #     try:
+                #         self.insert_one_or_dict(table=None, query=query, args=args, commit=commit)
+                #         total += 1
+                #     except Exception as e2:
+                #         self.log.error(f"Single insert failed: {e2}")
+                        # continue
+        self.log.info(f"sql insert_many, Table: {table}, Total Rows: {total}")
+        return total
+
+    def insert_many_two(self, table=None, data_list=None, query=None, args_list=None, batch_size=500, commit=True):
+        """
+        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
+        :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]))
+            query = f"INSERT 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:
+                        # 添加调试日志：输出 SQL 和参数示例
+                        # self.log.debug(f"Batch insert SQL: {query}")
+                        # self.log.debug(f"Sample args: {batch[0] if batch else 'None'}")
+                        cursor.executemany(query, batch)
+                        if commit:
+                            conn.commit()
+                        total += cursor.rowcount
+                        # self.log.debug(f"Batch insert succeeded. Rows: {cursor.rowcount}")
+            except Exception as e:  # 明确捕获数据库异常
+                self.log.exception(f"Batch insert failed: {e}")  # 使用 exception 记录堆栈
+                self.log.error(f"Failed SQL: {query}, Args count: {len(batch)}")
+                if commit:
+                    conn.rollback()
+                # 降级为单条插入，并记录每个错误
+                rowcount = 0
+                for args in batch:
+                    try:
+                        self.insert_one(query, args)
+                        rowcount += 1
+                    except Exception as e2:
+                        self.log.error(f"Single insert failed: {e2}, Args: {args}")
+                total += rowcount
+                self.log.debug(f"Inserted {rowcount}/{len(batch)} rows individually.")
+        self.log.info(f"sql insert_many, 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
+        """
+        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()
+            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
+
+    @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
+

panini_coming_soon_spider/panini_control_price.py

@@ -0,0 +1,137 @@
+# -*- coding: utf-8 -*-
+# Author : Charley
+# Python : 3.10.8
+# Date   : 2025/2/12 13:16
+import time
+import datetime
+from loguru import logger
+from CloudflareBypasser import CloudflareBypasser
+from DrissionPage import ChromiumPage, ChromiumOptions
+from tenacity import retry, stop_after_attempt, wait_fixed
+
+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")
+
+
+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")
+
+
+def get_screen_shot(log, page, end_time):
+    """
+    每分钟刷新页面并截图
+    :param log:
+    :param page:
+    :param end_time:
+    """
+    log.info("开始截图....................")
+    while datetime.datetime.now() < end_time:
+        page.refresh()
+
+        page.wait.load_start()  # 等待页面进入加载状态
+
+        page.wait.eles_loaded('.card-body')  # 等待 class 为 div1 的元素加载
+
+        time.sleep(3)
+        page.wait.load_start()  # 等待页面进入加载状态
+
+        path = "./panini_screenshot_images"
+        current_time = datetime.datetime.now()
+        screenshot_filename = current_time.strftime("%Y%m%d%H%M%S") + ".jpg"
+
+        # full_page参数   为True截取的是整页截图, 为False截取可视窗口  默认为False
+        # page.get_screenshot(path, name=screenshot_filename, full_page=True)
+        page.get_screenshot(path, name=screenshot_filename)
+        log.info(f"已保存截图: {screenshot_filename}")
+        time.sleep(60)  # 每隔1分钟刷新一次
+
+
+def get_screen_cast(log, tab, end_time):
+    """
+    每分钟刷新页面并录制视频
+    :param log:
+    :param tab:
+    :param end_time:
+    """
+    tab.screencast.set_save_path('video')  # 设置视频存放路径
+    tab.screencast.set_mode.video_mode()  # 设置录制模式
+    tab.screencast.start()  # 开始录制
+
+    try:
+        while datetime.datetime.now() < end_time:
+            tab.refresh()
+            tab.wait.load_start()  # 等待页面进入加载状态
+
+            current_time = datetime.datetime.now()
+            screenshot_filename = current_time.strftime("%Y%m%d%H%M%S") + ".jpg"
+            tab.get_screenshot('./panini_screenshot_video', name=screenshot_filename)
+            log.info(f"已保存截图: {screenshot_filename}")
+            time.sleep(60)  # 每隔1分钟刷新一次
+    except Exception as e:
+        log.error(f"录制过程中发生错误: {e}")
+    finally:
+        tab.screencast.stop()  # 停止录制
+
+
+@retry(stop=stop_after_attempt(2), wait=wait_fixed(1), after=after_log)
+def panini_control_price(log):
+    log.info("开始请求页面....................")
+    options = ChromiumOptions().set_paths(local_port=9103,
+                                          user_data_path=r'D:\Drissionpage_temp\panini_control_price_port_9103')
+    options.set_argument("--disable-gpu")
+    options.set_argument("-accept-lang=en-US")
+    page = ChromiumPage(options)
+    page.set.window.full()
+
+    try:
+        url = "https://www.paniniamerica.net/2024-25-select-basketball-white-sparkle-pack-3-cards-per-pack-on-average-look-for-randomly-inserted-1-1-autographs.html"
+        page.get(url, timeout=20)
+
+        # page_title = page.title.lower()
+        # print(page_title)
+        # if "just a moment" in page_title:
+        #     cf_bypasser = CloudflareBypasser(page, max_retries=5, log=log)
+        #     cf_bypasser.bypass()
+        #     page.wait.load_start()  # 等待页面进入加载状态
+        # else:
+        #     logger.info("无需绕过")
+
+        # 设置开始时间和结束时间
+        # start_time = datetime.datetime.strptime("2025-02-12 23:55:00", "%Y-%m-%d %H:%M:%S")
+        start_time = datetime.datetime.strptime("2025-07-21 23:55:50", "%Y-%m-%d %H:%M:%S")
+        end_time = start_time + datetime.timedelta(hours=2.5)
+
+        # 等待到开始时间
+        while datetime.datetime.now() < start_time:
+            time.sleep(1)
+
+        get_screen_shot(log, page, end_time)
+
+
+    except Exception as e:
+        log.error(f"操作失败: {e}")
+    finally:
+        log.info("结束请求页面....................")
+        page.close()
+        page.quit()
+
+
+if __name__ == '__main__':
+    panini_control_price(logger)
+#     http://grafana.ipangyou.com/explore?panes=%7B%220xD%22:%7B%22datasource%22:%22e0f7c4fb-4dc6-4665-9d15-2c5faa0f4fc2%22,%22queries%22:%5B%7B%22refId%22:%22A%22,%22expr%22:%22%7Bapplication%3D%5C%22ins-python%5C%22%7D%22,%22queryType%22:%22range%22,%22datasource%22:%7B%22type%22:%22loki%22,%22uid%22:%22e0f7c4fb-4dc6-4665-9d15-2c5faa0f4fc2%22%7D,%22editorMode%22:%22builder%22,%22legendFormat%22:%22%22%7D%5D,%22range%22:%7B%22from%22:%22now-2d%22,%22to%22:%22now%22%7D%7D%7D&schemaVersion=1&orgId=1

panini_coming_soon_spider/requirements.txt

@@ -0,0 +1,10 @@
+-i https://mirrors.aliyun.com/pypi/simple/
+curl_cffi==0.11.1
+DBUtils==3.1.0
+DrissionPage==4.1.0.18
+loguru==0.7.3
+PyMySQL==1.1.1
+PyYAML==6.0.2
+schedule==1.2.2
+tenacity==9.0.0
+user_agent==0.1.10