#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ BUFF饰品属性信息获取脚本（使用连接池版本） 特点： 1. 使用DBUtils连接池管理数据库连接 2. 自动处理连接失效和重连 3. 更稳定的长连接管理 4. 避免频繁创建和关闭连接的开销 5. 直接请求接口，无代理 快速补齐缺失属性：可设置环境变量调大每轮处理量，例如： BATCH_SIZE=200 python sync_goods_attr.py （当前为串行模式：每次 1 个请求，间隔 5-6 秒随机；连续请求 1 分钟后休息 1 分钟） 安装依赖： pip install DBUtils==3.0.2 """ import os import random import sys import time import logging import threading import json import requests import pymysql from dbutils.pooled_db import PooledDB import concurrent.futures from datetime import datetime from typing import List, Dict, Any, Optional, Tuple def _scalar_for_db(val: Any) -> Any: """将 API 返回的 list/dict 等转为 DB 单值，避免 'not all arguments converted during string formatting'""" if val is None or isinstance(val, (str, int, float)): return val if isinstance(val, datetime): return val if isinstance(val, (list, dict)): return json.dumps(val, ensure_ascii=False) if val else None # 元组、集合等可迭代但非标量一律转成字符串，避免被当成多个参数 return str(val) if val is not None else None # 与 buff_goods_attr 表 INSERT 列顺序一致（不含 create_time/update_time，用 NOW()） INSERT_ATTR_COLUMNS = [ 'goods_id', 'name', 'icon_url', 'type', 'type_name', 'category', 'category_name', 'category_group', 'category_group_name', 'rarity', 'rarity_name', 'quality', 'quality_name', 'exterior', 'exterior_name', 'weapon', 'weapon_name', 'series', 'series_name', 'custom', 'custom_name', 'itemset', 'itemset_name', 'extra_tag_ids', 'extra_tag_ids_name', 'custom_patch', 'custom_patch_name', 'custom_charm', 'custom_charm_name', 'stat_time', ] INSERT_ATTR_SQL = """ INSERT INTO buff_goods_attr (goods_id, name, icon_url, type, type_name, category, category_name, category_group, category_group_name, rarity, rarity_name, quality, quality_name, exterior, exterior_name, weapon, weapon_name, series, series_name, custom, custom_name, itemset, itemset_name, extra_tag_ids, extra_tag_ids_name, custom_patch, custom_patch_name, custom_charm, custom_charm_name, stat_time, create_time, update_time) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, NOW(), NOW()) """ # ============================================================ # 配置信息 # ============================================================ # BUFF API配置 BUFF_API_BASE_URL = "https://buff.163.com/api/market/goods/sell_order" GAME = "csgo" # 数据库配置 DB_HOST = os.getenv("DB_HOST", "47.99.164.66") DB_PORT = int(os.getenv("DB_PORT", "3306")) DB_USER = os.getenv("DB_USER", "root") DB_PASSWORD = os.getenv("DB_PASSWORD", "hn02le.34lkdLKD") DB_NAME = os.getenv("DB_NAME", "buff") # 连接池配置 DB_POOL_CONFIG = { 'creator': pymysql, 'host': DB_HOST, 'port': DB_PORT, 'user': DB_USER, 'password': DB_PASSWORD, 'database': DB_NAME, 'charset': 'utf8mb4', 'cursorclass': pymysql.cursors.DictCursor, 'autocommit': True, # 自动提交事务 'maxconnections': 10, # 最大连接数 'mincached': 3, # 初始空闲连接数 'maxcached': 5, # 最大空闲连接数 'maxusage': 1000, # 单个连接最大使用次数 'ping': 7, # 使用ping检查连接：0=从不, 1=创建时, 2=获取时, 4=归还时, 7=总是 'blocking': True, # 连接池满时是否等待 'setsession': [], # 可选的会话命令列表 } # 请求配置（可通过环境变量 BATCH_SIZE 调大每轮处理量） REQUEST_TIMEOUT = 30 REQUEST_INTERVAL_MIN = 5 # 请求间隔下限（秒） REQUEST_INTERVAL_MAX = 6 # 请求间隔上限（秒），每次在 [MIN, MAX] 间随机 WORK_DURATION_SEC = 60 # 连续请求时长（秒），满后进入休息 REST_DURATION_SEC = 60 # 休息时长（秒），降低被 BUFF 检测限流风险 CONCURRENT_WORKERS = int(os.getenv("CONCURRENT_WORKERS", "1")) # 并发请求数（1=串行，间隔5-6秒随机） MAX_RETRIES = 3 RETRY_DELAY = 2 BATCH_SIZE = int(os.getenv("BATCH_SIZE", "30")) # 每轮拉取的饰品数量，每批提交一次，调小便于数据及时入库 FAILURE_LONG_REST_THRESHOLD = int(os.getenv("FAILURE_LONG_REST_THRESHOLD", "5")) # 连续请求失败达到阈值后触发长休息 FAILURE_LONG_REST_MIN_SEC = int(os.getenv("FAILURE_LONG_REST_MIN_SEC", "300")) # 失败触发长休息最短秒数（默认 5 分钟） FAILURE_LONG_REST_MAX_SEC = int(os.getenv("FAILURE_LONG_REST_MAX_SEC", "600")) # 失败触发长休息最长秒数（默认 10 分钟） SUCCESS_CONTINUOUS_SAVE_THRESHOLD = int(os.getenv("SUCCESS_CONTINUOUS_SAVE_THRESHOLD", "100")) # 连续成功入库数量阈值 SUCCESS_REST_SEC = int(os.getenv("SUCCESS_REST_SEC", "180")) # 连续成功入库达到阈值后的固定休息秒数（默认 3 分钟） CONTINUOUS_RUN_LIMIT_SEC = int(os.getenv("CONTINUOUS_RUN_LIMIT_SEC", "7200")) # 连续运行时长阈值（秒），默认 2 小时 CONTINUOUS_RUN_REST_SEC = int(os.getenv("CONTINUOUS_RUN_REST_SEC", "600")) # 连续运行达到阈值后的休息秒数（默认 10 分钟） FORBIDDEN_STOP_THRESHOLD = int(os.getenv("FORBIDDEN_STOP_THRESHOLD", "3")) # 连续检测到 403 后直接停止脚本的阈值 # ============================================================ # 配置日志 # ============================================================ def setup_logging(): """配置日志系统""" log_dir = os.path.dirname(os.path.abspath(__file__)) log_file = os.path.join(log_dir, "logs", f"sync_goods_attr_{datetime.now().strftime('%Y%m%d')}.log") os.makedirs(os.path.dirname(log_file), exist_ok=True) logging.basicConfig( level=logging.INFO, format='%(asctime)s - %(levelname)s - [%(threadName)s] - %(message)s', handlers=[ logging.StreamHandler(sys.stdout), logging.FileHandler(log_file, encoding='utf-8') ] ) return logging.getLogger(__name__) logger = setup_logging() # 请求频率限制：每次请求间隔在 [REQUEST_INTERVAL_MIN, REQUEST_INTERVAL_MAX] 秒随机（多线程安全） _request_lock = threading.Lock() _last_request_time = [0.0] # 使用列表以便在闭包中修改 _work_window_start = [0.0] # 当前「连续请求」窗口开始时间，满 WORK_DURATION_SEC 后休息 REST_DURATION_SEC _consecutive_request_failures = [0] # 连续请求失败计数（网络错误 / API 返回错误） _consecutive_403_errors = [0] # 连续 403 错误计数 def _record_request_failure(): """ 记录一次请求失败（网络错误、状态码/业务code异常等）， 当连续失败次数达到阈值时随机长休息 5-10 分钟以降低被封 IP 风险。 """ with _request_lock: _consecutive_request_failures[0] += 1 current_failures = _consecutive_request_failures[0] if current_failures >= FAILURE_LONG_REST_THRESHOLD: rest_sec = random.randint(FAILURE_LONG_REST_MIN_SEC, FAILURE_LONG_REST_MAX_SEC) logger.warning( "请求连续失败 %s 次，触发防封长休息，脚本将休息 %s 秒后再继续请求...", current_failures, rest_sec, ) time.sleep(rest_sec) with _request_lock: _consecutive_request_failures[0] = 0 def _reset_request_failures(): """请求成功（包括正常返回但未找到该饰品）时重置连续失败计数。""" with _request_lock: if _consecutive_request_failures[0] != 0: _consecutive_request_failures[0] = 0 def _record_403_and_maybe_stop(): """ 记录一次 403 错误。 当连续 403 次数达到 FORBIDDEN_STOP_THRESHOLD 时，认为当前 IP / 行为已被 BUFF 强风控， 直接终止脚本运行，避免继续打压力。 """ with _request_lock: _consecutive_403_errors[0] += 1 current_403 = _consecutive_403_errors[0] logger.error("检测到 403 Forbidden 错误（连续第 %s 次）", current_403) if current_403 >= FORBIDDEN_STOP_THRESHOLD: logger.critical( "连续检测到 %s 次 403 Forbidden，可能已被 BUFF 风控，脚本将自动退出，请人工检查后再重启。", current_403, ) # 直接退出整个脚本进程 sys.exit(1) def _reset_403_errors(): """请求成功（含正常业务失败）时重置 403 计数。""" with _request_lock: if _consecutive_403_errors[0] != 0: _consecutive_403_errors[0] = 0 # ============================================================ # 数据库连接池操作类 # ============================================================ class DatabaseConnectionPool: """数据库连接池管理类""" _instance = None _pool = None def __new__(cls): if cls._instance is None: cls._instance = super().__new__(cls) cls._instance._init_pool() return cls._instance def _init_pool(self): """初始化连接池""" try: self._pool = PooledDB(**DB_POOL_CONFIG) logger.info(f"数据库连接池初始化成功: {DB_HOST}:{DB_PORT}/{DB_NAME}") logger.info(f"连接池配置: maxconnections={DB_POOL_CONFIG['maxconnections']}, mincached={DB_POOL_CONFIG['mincached']}") except Exception as e: logger.error(f"数据库连接池初始化失败: {e}") raise def get_connection(self): """从连接池获取连接""" try: conn = self._pool.connection() return conn except Exception as e: logger.error(f"从连接池获取连接失败: {e}") # 尝试重新初始化连接池 time.sleep(2) self._init_pool() return self._pool.connection() def close_pool(self): """关闭连接池""" if self._pool: self._pool.close() logger.info("数据库连接池已关闭") class GoodsAttrDatabase: """饰品属性数据库操作类（使用连接池）""" def __init__(self): self.pool = DatabaseConnectionPool() def execute_query(self, sql: str, params=None, fetch_all=True): """执行查询""" conn = None cursor = None try: conn = self.pool.get_connection() cursor = conn.cursor() if params: cursor.execute(sql, params) else: cursor.execute(sql) if fetch_all: return cursor.fetchall() else: return cursor.fetchone() except pymysql.Error as e: logger.error(f"数据库查询失败: {e}, SQL: {sql}") raise finally: if cursor: cursor.close() # 注意：这里不需要关闭conn，连接池会自动管理 def execute_update(self, sql: str, params=None, many=False): """执行更新操作""" conn = None cursor = None try: conn = self.pool.get_connection() cursor = conn.cursor() if many and params: cursor.executemany(sql, params) elif params: cursor.execute(sql, params) else: cursor.execute(sql) affected_rows = cursor.rowcount return affected_rows except pymysql.Error as e: logger.error(f"数据库更新失败: {e}, SQL: {sql}") raise finally: if cursor: cursor.close() def execute_transaction(self, operations: List[Tuple[str, tuple]]): """执行事务（一组操作要么全部成功，要么全部回滚）""" conn = None cursor = None try: conn = self.pool.get_connection() cursor = conn.cursor() # 开始事务 conn.begin() for sql, params in operations: if params: cursor.execute(sql, params) else: cursor.execute(sql) # 提交事务 conn.commit() return True except Exception as e: logger.error(f"事务执行失败: {e}") if conn: try: conn.rollback() except: pass return False finally: if cursor: cursor.close() def get_goods_without_attr(self, limit: int = BATCH_SIZE, offset: int = 0) -> List[Dict[str, Any]]: """ 获取没有属性信息的饰品列表（支持分页，便于每轮拉取不同批次） 从 buff_goods_info 表中找出在 buff_goods_attr 表中不存在的饰品。 offset 用于轮次推进：每轮取下一批，全部取完后从 0 再开始。 """ try: sql = """ SELECT g.goods_id, g.name, g.buff_url, g.stat_time FROM buff_goods_info g LEFT JOIN buff_goods_attr a ON g.goods_id = a.goods_id WHERE a.goods_id IS NULL ORDER BY g.goods_id ASC LIMIT %s OFFSET %s """ results = self.execute_query(sql, (limit, offset)) goods_list = [] for row in results: goods_list.append({ 'goods_id': row['goods_id'], 'name': row['name'], 'buff_url': row['buff_url'], 'stat_time': row['stat_time'] }) logger.info(f"找到 {len(goods_list)} 个没有属性信息的饰品") return goods_list except Exception as e: logger.error(f"查询没有属性信息的饰品失败: {e}") return [] def _attr_row_for_insert(self, attr_data: Dict[str, Any]) -> tuple: """按表列顺序生成一条 INSERT 参数元组，保证每项均为标量（30 个占位符对应 30 列）""" row = [] for k in INSERT_ATTR_COLUMNS: v = attr_data.get(k) if k != 'stat_time' else attr_data.get('stat_time', datetime.now()) row.append(_scalar_for_db(v)) return tuple(row) def batch_insert_goods_attrs(self, attr_data_list: List[Dict[str, Any]]) -> int: """批量插入饰品属性信息：先全部 DELETE，再 executemany INSERT，避免占位符与参数数量错位""" if not attr_data_list: return 0 delete_sql = "DELETE FROM buff_goods_attr WHERE goods_id = %s" rows = [self._attr_row_for_insert(attr_data) for attr_data in attr_data_list] # 每行必须是 30 个标量，与 INSERT_ATTR_SQL 中 30 个 %s 一致 assert len(INSERT_ATTR_COLUMNS) == 30, "INSERT_ATTR_COLUMNS 须为 30 项" try: conn = None cursor = None try: conn = self.pool.get_connection() cursor = conn.cursor() conn.begin() # 先删除 for attr_data in attr_data_list: gid = _scalar_for_db(attr_data['goods_id']) cursor.execute(delete_sql, (gid,)) # 再批量插入 cursor.executemany(INSERT_ATTR_SQL, rows) conn.commit() logger.info(f"成功批量插入 {len(attr_data_list)} 个饰品的属性信息") return len(attr_data_list) except Exception as e: logger.exception("事务执行失败") if conn: try: conn.rollback() except Exception: pass return 0 finally: if cursor: cursor.close() except Exception as e: logger.error(f"批量插入饰品属性信息异常: {e}") return 0 def insert_goods_attr(self, attr_data: Dict[str, Any]) -> bool: """插入单个饰品属性信息""" try: delete_sql = "DELETE FROM buff_goods_attr WHERE goods_id = %s" row = self._attr_row_for_insert(attr_data) operations = [ (delete_sql, (_scalar_for_db(attr_data['goods_id']),)), (INSERT_ATTR_SQL, row), ] success = self.execute_transaction(operations) if success: logger.debug(f"成功插入饰品 {attr_data['goods_id']} 的属性信息") else: logger.error(f"插入饰品 {attr_data['goods_id']} 属性信息失败") return success except Exception as e: logger.error(f"插入饰品 {attr_data.get('goods_id', '未知')} 属性信息异常: {e}") return False def check_connection(self): """检查连接是否正常""" try: self.execute_query("SELECT 1") return True except Exception as e: logger.error(f"数据库连接检查失败: {e}") return False # ============================================================ # BUFF API 操作类 # ============================================================ class BuffGoodsAPI: """BUFF饰品API操作类（直连请求）""" def __init__(self): self.session = requests.Session() self.session.headers.update({ "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36", "Accept": "application/json, text/plain, */*", "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8", "Accept-Encoding": "gzip, deflate, br", "Connection": "keep-alive", "Referer": "https://buff.163.com/", "Sec-Fetch-Dest": "empty", "Sec-Fetch-Mode": "cors", "Sec-Fetch-Site": "same-origin" }) def fetch_goods_info(self, goods_id: str) -> Optional[Dict[str, Any]]: """获取单个饰品的详细信息""" url = f"{BUFF_API_BASE_URL}?game={GAME}&goods_id={goods_id}" for retry in range(MAX_RETRIES): try: logger.debug(f"请求饰品 {goods_id} (第{retry + 1}次尝试)...") # 每次间隔 5-6 秒随机，多线程下串行控制；满 1 分钟请求后休息 1 分钟 with _request_lock: now = time.time() if _work_window_start[0] <= 0: _work_window_start[0] = now work_elapsed = now - _work_window_start[0] if work_elapsed >= WORK_DURATION_SEC: logger.info(f"已连续请求满 {WORK_DURATION_SEC} 秒，休息 {REST_DURATION_SEC} 秒后再继续...") time.sleep(REST_DURATION_SEC) _work_window_start[0] = time.time() elapsed = time.time() - _last_request_time[0] interval = random.uniform(REQUEST_INTERVAL_MIN, REQUEST_INTERVAL_MAX) if elapsed < interval: time.sleep(interval - elapsed) _last_request_time[0] = time.time() # 使用 requests.get 避免多线程共享 Session，保证并发安全，直连请求 response = requests.get( url, headers=self.session.headers, timeout=REQUEST_TIMEOUT, ) response.raise_for_status() data = response.json() # 检查API响应状态 if data.get("code") != "OK": logger.warning(f"饰品 {goods_id} API返回错误: {data.get('msg', '未知错误')}") _record_request_failure() return None # 提取饰品信息 goods_info = self._extract_goods_info(data, goods_id) if goods_info: _reset_request_failures() _reset_403_errors() logger.info(f"成功获取饰品 {goods_id} 的属性信息") return goods_info else: # 请求成功但未找到该饰品，视为正常请求，重置失败计数 _reset_request_failures() _reset_403_errors() logger.warning(f"饰品 {goods_id} 未找到属性信息") return None except requests.exceptions.RequestException as e: logger.error(f"请求饰品 {goods_id} 失败 (尝试 {retry + 1}/{MAX_RETRIES}): {e}") # 如果是 HTTP 403，记录连续 403 并在达到阈值时直接终止脚本 try: response = getattr(e, "response", None) if response is not None and response.status_code == 403: _record_403_and_maybe_stop() else: _record_request_failure() except Exception: _record_request_failure() if retry < MAX_RETRIES - 1: time.sleep(RETRY_DELAY * (retry + 1)) else: logger.error(f"饰品 {goods_id} 请求失败，已重试{MAX_RETRIES}次") return None except json.JSONDecodeError as e: logger.error(f"饰品 {goods_id} 响应JSON解析失败: {e}") _record_request_failure() return None except Exception as e: logger.error(f"处理饰品 {goods_id} 时发生未知错误: {e}") _record_request_failure() return None return None def _extract_goods_info(self, api_data: Dict[str, Any], goods_id: str) -> Optional[Dict[str, Any]]: """从API响应中提取饰品属性信息""" try: data = api_data.get("data", {}) goods_infos = data.get("goods_infos", {}) # 获取指定goods_id的饰品信息 goods_data = goods_infos.get(str(goods_id)) if not goods_data: logger.warning(f"饰品 {goods_id} 未在响应中找到") return None # 提取tags信息 tags = goods_data.get("tags", {}) # 构建属性字典 attr_data = { 'goods_id': goods_id, 'name': goods_data.get("name", ""), 'icon_url': goods_data.get("icon_url"), 'stat_time': datetime.now(), 'create_time': datetime.now() } # 映射tags到对应字段 tag_mapping = { 'type': ('type', 'type_name'), 'rarity': ('rarity', 'rarity_name'), 'category': ('category', 'category_name'), 'category_group': ('category_group', 'category_group_name'), 'quality': ('quality', 'quality_name'), 'exterior': ('exterior', 'exterior_name'), 'weapon': ('weapon', 'weapon_name'), 'series': ('series', 'series_name'), 'custom': ('custom', 'custom_name'), 'itemset': ('itemset', 'itemset_name') } # 处理每个tag for tag_key, (field_key, field_name_key) in tag_mapping.items(): if tag_key in tags: tag_data = tags[tag_key] attr_data[field_key] = tag_data.get("internal_name") attr_data[field_name_key] = tag_data.get("localized_name") logger.debug(f"饰品 {goods_id} 属性提取成功") return attr_data except Exception as e: logger.error(f"提取饰品 {goods_id} 属性时出错: {e}") return None # ============================================================ # 主逻辑 # ============================================================ class GoodsAttrSyncTask: """饰品属性同步任务""" def __init__(self): self.db = GoodsAttrDatabase() self.api = BuffGoodsAPI() # 每轮取「下一批」无属性饰品，全部取完后再从 0 开始，避免每轮都从同一批（如 40295）开始 self._sync_offset = 0 # 连续成功写入的属性总数，用于达到一定数量后让脚本主动休息一段时间 self._continuous_saved_success = 0 # 连续运行起始时间，用于控制“连续跑 2 小时休息 10 分钟” self._continuous_run_start = time.time() def fetch_and_save_goods_attrs(self, goods_ids: List[str]) -> Dict[str, int]: """获取并保存饰品属性信息（每次最多 CONCURRENT_WORKERS 个并发请求）""" results = {'success': 0, 'failed': 0, 'total': len(goods_ids)} batch_attr_data: List[Dict[str, Any]] = [] def fetch_one(goods_id: str) -> Optional[Dict[str, Any]]: try: return self.api.fetch_goods_info(goods_id) except Exception as e: logger.error(f"获取饰品 {goods_id} 属性异常: {e}") return None with concurrent.futures.ThreadPoolExecutor(max_workers=CONCURRENT_WORKERS) as executor: future_to_id = {executor.submit(fetch_one, gid): gid for gid in goods_ids} for future in concurrent.futures.as_completed(future_to_id): goods_id = future_to_id[future] try: attr_data = future.result() if attr_data: batch_attr_data.append(attr_data) logger.info(f"获取饰品 {goods_id} 属性成功") else: results['failed'] += 1 logger.warning(f"获取饰品 {goods_id} 属性失败") except Exception as e: results['failed'] += 1 logger.error(f"获取饰品 {goods_id} 异常: {e}") if batch_attr_data: logger.info(f"本批次共获取 {len(batch_attr_data)} 条属性，即将写入数据库 {DB_HOST}/{DB_NAME} 表 buff_goods_attr ...") saved_count = self.db.batch_insert_goods_attrs(batch_attr_data) results['success'] += saved_count if saved_count < len(batch_attr_data): results['failed'] += len(batch_attr_data) - saved_count return results def run_single_batch(self) -> bool: """执行单次批次同步任务""" start_time = datetime.now() logger.info("=" * 60) logger.info(f"开始执行饰品属性同步任务: {start_time}") logger.info("=" * 60) try: # 检查数据库连接 if not self.db.check_connection(): logger.error("数据库连接不可用，任务中止") return False # Step 1: 获取需要同步的饰品列表（本轮使用当前 offset，下一轮会用下一批） logger.info("[Step 1/3] 查询需要同步的饰品...") goods_list = self.db.get_goods_without_attr(BATCH_SIZE, self._sync_offset) if not goods_list: logger.info("没有需要同步的饰品（本轮回零 offset，下一轮从头开始）") self._sync_offset = 0 return True logger.info(f"找到 {len(goods_list)} 个需要同步的饰品（offset=%s）", self._sync_offset) # 提取goods_id列表 goods_ids = [goods['goods_id'] for goods in goods_list] # Step 2: 获取并保存饰品属性信息 logger.info("[Step 2/3] 获取并保存饰品属性信息...") results = self.fetch_and_save_goods_attrs(goods_ids) # Step 3: 任务完成统计 end_time = datetime.now() duration = (end_time - start_time).total_seconds() logger.info("=" * 60) logger.info(f"饰品属性同步任务完成!") logger.info(f"处理饰品总数: {results['total']}") logger.info(f"成功获取并保存: {results['success']}") logger.info(f"失败: {results['failed']}") logger.info(f"耗时: {duration:.2f}秒") logger.info("=" * 60) # 连续成功入库计数：本批有成功则累加，否则清零 if results['success'] > 0: self._continuous_saved_success += results['success'] else: self._continuous_saved_success = 0 # 当连续成功入库数量达到阈值时，脚本固定休息一段时间（默认 3 分钟），然后重置计数 if self._continuous_saved_success >= SUCCESS_CONTINUOUS_SAVE_THRESHOLD: logger.info( "连续成功入库 %s 条属性，脚本将休息 %s 秒以降低对 BUFF 的压力...", self._continuous_saved_success, SUCCESS_REST_SEC, ) time.sleep(SUCCESS_REST_SEC) self._continuous_saved_success = 0 # 本批已处理，下一轮取下一批；若本批不足 BATCH_SIZE 说明已到末尾，下轮会得到 0 条并回零 self._sync_offset += len(goods_list) return results['success'] > 0 except Exception as e: logger.exception(f"同步任务失败: {e}") return False def run_continuous(self): """连续运行模式，每次执行后随机暂停""" execution_count = 0 while True: # 检查是否已经连续运行超过设定的时长，如果是则休息一段时间再继续 elapsed_run = time.time() - self._continuous_run_start if elapsed_run >= CONTINUOUS_RUN_LIMIT_SEC: logger.info( "脚本已连续运行约 %.1f 分钟，达到阈值，将休息 %s 秒以降低风险...", elapsed_run / 60.0, CONTINUOUS_RUN_REST_SEC, ) time.sleep(CONTINUOUS_RUN_REST_SEC) # 休息完重新计时 self._continuous_run_start = time.time() execution_count += 1 logger.info(f"\n{'='*60}") logger.info(f"开始第 {execution_count} 次执行") logger.info(f"{'='*60}") # 执行同步任务 success = self.run_single_batch() if success: logger.info(f"第 {execution_count} 次执行成功") else: logger.warning(f"第 {execution_count} 次执行失败") # 直接进入下一轮，不再等待 def cleanup(self): """清理资源""" try: # 关闭连接池 DatabaseConnectionPool().close_pool() logger.info("资源清理完成") except: pass # ============================================================ # 主函数 # ============================================================ def main(): """主函数""" task = None try: logger.info("启动饰品属性同步脚本（连接池版本）...") logger.info(f"数据库写入目标: {DB_HOST}:{DB_PORT}/{DB_NAME} 表 buff_goods_attr（请确认您查询的是同一库）") logger.info(f"配置信息: 每次处理 {BATCH_SIZE} 个饰品, 串行请求间隔 {REQUEST_INTERVAL_MIN}-{REQUEST_INTERVAL_MAX} 秒, 请求满 {WORK_DURATION_SEC} 秒休息 {REST_DURATION_SEC} 秒, 直连请求") # 创建任务实例 task = GoodsAttrSyncTask() # 运行连续模式 task.run_continuous() except KeyboardInterrupt: logger.info("\n收到中断信号，正在退出...") if task: task.cleanup() sys.exit(0) except Exception as e: logger.exception(f"程序运行异常: {e}") if task: task.cleanup() sys.exit(1) if __name__ == "__main__": # 安装依赖提示 try: import dbutils except ImportError: print("请先安装依赖: pip install DBUtils==3.0.2") sys.exit(1) main()