整理了一下代码

.gitignore

@@ -36,6 +36,9 @@ scripts/config/chrome_profile/
 drivers/*
 !drivers/chromedriver.exe
 
+# Rankings config directory
+handlers/Rankings/config/
+
 # Environment variables
 .env
 .venv

Timer_worker.py

@@ -11,12 +11,16 @@
 
 import schedule
 import time
-import subprocess
 import sys
 import os
 import logging
 from pathlib import Path
 from datetime import datetime
+import config
+
+# 添加项目路径到 Python 路径
+sys.path.append(os.path.join(os.path.dirname(__file__), 'handlers', 'Rankings'))
+from rank_data_scraper import DouyinPlayVVScraper
 
 # 配置日志的函数
 def setup_logging():
@@ -48,43 +52,30 @@ class DouyinAutoScheduler:
             # 设置环境变量，确保自动模式
             os.environ['AUTO_CONTINUE'] = '1'
 
-            # 构建脚本路径 - 指向Rankings目录中的脚本
+            # 直接创建并运行 DouyinPlayVVScraper 实例
-            script_path = Path(__file__).parent / 'handlers' / 'Rankings' / 'rank_data_scraper.py'
+            scraper = DouyinPlayVVScraper(
+                start_url="https://www.douyin.com/user/self?showTab=favorite_collection&showSubTab=compilation",
+                auto_continue=True,
+                duration_s=60
+            )
             
-            if not script_path.exists():
+            logging.info("📁 开始执行抓取任务...")
-                logging.error(f"❌ 脚本文件不存在: {script_path}")
+            scraper.run()
-                return
             
-            logging.info(f"📁 执行脚本: {script_path}")
+            logging.info("✅ 抖音播放量抓取任务执行成功")
-
-            # 使用subprocess执行脚本
-            result = subprocess.run([
-                sys.executable,
-                str(script_path),
-                '--auto',
-                '--duration', '60'
-            ], capture_output=True, text=True, encoding='utf-8', errors='ignore')
-
-            if result.returncode == 0:
-                logging.info("✅ 抖音播放量抓取任务执行成功")
-                if result.stdout:
-                    logging.info(f"📄 输出: {result.stdout.strip()}")
-            else:
-                logging.error(f"❌ 任务执行失败，返回码: {result.returncode}")
-                if result.stderr:
-                    logging.error(f"💥 错误信息: {result.stderr.strip()}")
-                if result.stdout:
-                    logging.info(f"📄 输出: {result.stdout.strip()}")
 
         except Exception as e:
             logging.error(f"💥 执行任务时发生异常: {e}")
+            import traceback
+            logging.error(f"详细错误信息: {traceback.format_exc()}")
 
     def setup_schedule(self):
         """设置定时任务"""
-        # 主执行时间：每晚24:00（午夜）
+        # 从配置文件读取执行时间
-        schedule.every().day.at("00:00").do(self.run_douyin_scraper)
+        scheduler_time = config.SCHEDULER_TIME
+        schedule.every().day.at(scheduler_time).do(self.run_douyin_scraper)
 
-        logging.info("⏰ 定时器已设置：每晚24:00执行抖音播放量抓取")
+        logging.info(f"⏰ 定时器已设置：每晚{scheduler_time}执行抖音播放量抓取")
 
     def show_next_run(self):
         """显示下次执行时间"""
@@ -107,13 +98,11 @@ class DouyinAutoScheduler:
         """启动定时器"""
         self.is_running = True
         logging.info("🚀 抖音播放量自动抓取定时器已启动")
-        logging.info("⏰ 执行时间：每晚24:00")
+        logging.info(f"⏰ 执行时间：每天{config.SCHEDULER_TIME}执行抖音播放量抓取")
         logging.info("📁 目标脚本：rank_data_scraper.py")
         logging.info("💾 数据保存：MongoDB")
         logging.info("⏹️  按 Ctrl+C 停止定时器")
 
-        self.show_next_run()
-
         try:
             while self.is_running:
                 schedule.run_pending()

config.py

@@ -3,7 +3,8 @@ import importlib
 
 # 数据库配置
 MONGO_URI = "mongodb://localhost:27017"
-MONGO_DB_NAME = "Rankings"
+# MONGO_URI = "mongodb://mongouser:Jdei2243afN@172.16.0.6:27017,172.16.0.4:27017/test?replicaSet=cmgo-r6qkaern_0&authSource=admin"
+MONGO_DB_NAME = "jubian"
 
 # 应用配置
 APP_ENV = os.getenv('APP_ENV', 'development')
@@ -13,4 +14,7 @@ DEBUG = APP_ENV == 'development'
 LOG_LEVEL = 'INFO'
 LOG_DIR = 'logs'
 
+# 定时器配置
+SCHEDULER_TIME = "20:23"  # 定时器执行时间，格式为 HH:MM (24小时制)
+
 print(f"Successfully loaded configuration for environment: {APP_ENV}")

handlers/Rankings/rank_data_scraper.py

@@ -31,8 +31,11 @@ from selenium.webdriver.chrome.options import Options
 # 保留导入但默认不使用webdriver_manager，避免网络下载卡顿
 from webdriver_manager.chrome import ChromeDriverManager  # noqa: F401
 import chromedriver_autoinstaller
-from pymongo import MongoClient
+import sys
-from pymongo.errors import ConnectionFailure
+import os
+# 添加项目根目录到 Python 路径
+sys.path.append(os.path.join(os.path.dirname(__file__), '..', '..'))
+from database import db
 
 
 # 配置日志
@@ -60,7 +63,6 @@ class DouyinPlayVVScraper:
         self.driver = None
         self.play_vv_items = []  # list of dicts: {play_vv, formatted, url, request_id, mix_name, watched_item}
         self.captured_responses = []
-        self.mongo_client = None
         self.db = None
         self.collection = None
         self._cleanup_old_profiles()
@@ -69,33 +71,17 @@ class DouyinPlayVVScraper:
     def _setup_mongodb(self):
         """设置MongoDB连接"""
         try:
-            # MongoDB连接配置
+            # 使用 database.py 中的连接
-            mongo_host = os.environ.get('MONGO_HOST', 'localhost')
+            self.db = db
-            mongo_port = int(os.environ.get('MONGO_PORT', 27017))
+            
-            mongo_db = os.environ.get('MONGO_DB', 'Rankings')
+            # 设置集合
             mongo_collection = os.environ.get('MONGO_COLLECTION', 'Rankings_list')
-            
-            # 创建MongoDB连接
-            self.mongo_client = MongoClient(mongo_host, mongo_port, serverSelectionTimeoutMS=5000)
-            
-            # 测试连接
-            self.mongo_client.admin.command('ping')
-            
-            # 设置数据库和集合
-            self.db = self.mongo_client[mongo_db]
             self.collection = self.db[mongo_collection]
             
-            logging.info(f'MongoDB连接成功: {mongo_host}:{mongo_port}/{mongo_db}.{mongo_collection}')
+            logging.info(f'MongoDB连接成功，使用数据库: {self.db.name}，集合: {mongo_collection}')
             
-        except ConnectionFailure as e:
-            logging.warning(f'MongoDB连接失败: {e}')
-            logging.info('将仅保存到本地文件')
-            self.mongo_client = None
-            self.db = None
-            self.collection = None
         except Exception as e:
             logging.warning(f'MongoDB设置出错: {e}')
-            self.mongo_client = None
             self.db = None
             self.collection = None
 
@@ -649,10 +635,10 @@ class DouyinPlayVVScraper:
             elapsed = int(time.time() - start)
             if elapsed - last_progress >= 5:
                 last_progress = elapsed
-                logging.info(f'进度: {elapsed}/{duration_s}s, 已发现play_vv候选 {len(self.play_vv_items)}')
+                logging.info(f'进度: {elapsed}/{duration_s}, 目标数量： {len(self.play_vv_items)}')
             time.sleep(0.8)
 
-        logging.info(f'网络收集完成，共发现 {len(self.play_vv_items)} 个play_vv候选')
+        logging.info(f'网络收集完成，共发现 {len(self.play_vv_items)} 个目标')
         
 
     def parse_ssr_data(self):
@@ -712,7 +698,7 @@ class DouyinPlayVVScraper:
     
     def save_to_mongodb(self):
         """将数据保存到MongoDB"""
-        if self.mongo_client is None or self.collection is None:
+        if self.collection is None:
             logging.warning('MongoDB未连接，跳过数据库保存')
             return
         
@@ -797,6 +783,5 @@ if __name__ == '__main__':
         os.environ['AUTO_CONTINUE'] = '1'
 
     print('=== Selenium+CDP 抖音play_vv抓取器 ===')
-    print('将复用本地Chrome配置并抓取网络响应中的play_vv')
     scraper = DouyinPlayVVScraper(args.url, auto_continue=args.auto, duration_s=args.duration)
     scraper.run()