"""
定时任务调度器 - 修复版
集成 APScheduler 实现爬虫自动化
"""
import logging
from apscheduler.schedulers.blocking import BlockingScheduler
from apscheduler.triggers.cron import CronTrigger
from apscheduler.triggers.interval import IntervalTrigger

logger = logging.getLogger(__name__)

# 全局调度器实例
scheduler = BlockingScheduler(timezone="Asia/Shanghai")

def crawl_today_job():
    """每日采集任务"""
    from crawlers.crawl_today import YichensTodaySpider
    logger.info("[定时任务] 开始执行一尘网今日采集")
    try:
        spider = YichensTodaySpider()
        result = spider.run()
        logger.info(f"[定时任务] 采集完成，新增 {result} 条")
    except Exception as e:
        logger.error(f"[定时任务] 采集失败: {e}")

def crawl_incremental_job():
    """增量采集任务（每小时）"""
    from crawlers.crawl_today import YichensTodaySpider
    logger.info("[定时任务] 开始执行增量采集")
    try:
        spider = YichensTodaySpider()
        spider.max_pages = 2  # 增量只扫2页
        result = spider.crawl_today()
        logger.info(f"[定时任务] 增量采集完成，新增 {result} 条")
    except Exception as e:
        logger.error(f"[定时任务] 增量采集失败: {e}")

def init_scheduler():
    """初始化定时任务"""
    # 每天早上 8 点采集
    scheduler.add_job(
        crawl_today_job,
        CronTrigger(hour=8, minute=0, timezone="Asia/Shanghai"),
        id='yichens_daily_crawl',
        name='一尘网每日采集',
        replace_existing=True
    )
    
    # 每小时增量采集（如果需要）
    scheduler.add_job(
        crawl_incremental_job,
        IntervalTrigger(hours=1, timezone="Asia/Shanghai"),
        id='yichens_incremental',
        name='一尘网增量采集',
        replace_existing=True
    )
    
    logger.info("定时任务已注册: 每日8点采集 + 每小时增量")
    return scheduler

def start_scheduler():
    """启动调度器"""
    init_scheduler()
    logger.info("调度器启动")
    try:
        scheduler.start()
    except (KeyboardInterrupt, SystemExit):
        logger.info("调度器停止")
        scheduler.shutdown()

if __name__ == "__main__":
    logging.basicConfig(level=logging.INFO)
    start_scheduler()