scheduler.py

from apscheduler.schedulers.background import BackgroundScheduler
from apscheduler.triggers.cron import CronTrigger
import logging
from datetime import datetime
import os
from tools.arxiv_tool import save_daily_papers

# Configure logging
logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
    handlers=[
        logging.FileHandler('arxiv_scheduler.log'),
        logging.StreamHandler()
    ]
)

logger = logging.getLogger(__name__)

def scheduled_paper_search():
    """Run the daily paper search and log the results."""
    try:
        logger.info("Starting daily ArXiv paper search...")
        papers = save_daily_papers()
        logger.info(f"Found {len(papers)} new AI papers today")
        
        # Log paper titles
        if papers:
            logger.info("Today's papers:")
            for paper in papers:
                logger.info(f"- {paper['title']}")
        
    except Exception as e:
        logger.error(f"Error in scheduled paper search: {str(e)}")

def initialize_scheduler():
    """Initialize and start the scheduler."""
    try:
        scheduler = BackgroundScheduler()
        
        # Schedule the job to run at 8 AM every day
        scheduler.add_job(
            scheduled_paper_search,
            trigger=CronTrigger(hour=8, minute=0),
            id='daily_arxiv_search',
            name='Daily ArXiv AI Paper Search',
            replace_existing=True
        )
        
        # Start the scheduler
        scheduler.start()
        logger.info("Scheduler initialized and started")
        
        return scheduler
    except Exception as e:
        logger.error(f"Error initializing scheduler: {str(e)}")
        # Return a dummy scheduler object that does nothing
        class DummyScheduler:
            def shutdown(self): pass
        return DummyScheduler()