从入门到精通详解Python APScheduler实现定时任务的完整指南

from apscheduler.triggers.cron import CronTrigger
# 每月1号凌晨2点执行
trigger = CronTrigger(day=1, hour=2)

from apscheduler.executors.pool import ProcessPoolExecutor
executors = {
    'default': ThreadPoolExecutor(20),  # 线程池最大20线程
    'processpool': ProcessPoolExecutor(5)  # 进程池最大5进程
}

from apscheduler.jobstores.sqlalchemy import SQLAlchemyJobStore
jobstores = {
    'default': SQLAlchemyJobStore(url='sqlite:///jobs.db')
}

from apscheduler.schedulers.background import BackgroundScheduler
scheduler = BackgroundScheduler(
    jobstores=jobstores,
    executors=executors,
    timezone='Asia/Shanghai'
)

from apscheduler.schedulers.blocking import BlockingScheduler
import time

def print_time():
    print(f"当前时间: {time.strftime('%Y-%m-%d %H:%M:%S')}")

scheduler = BlockingScheduler()
scheduler.add_job(print_time, 'interval', seconds=5)
scheduler.start()

from apscheduler.schedulers.blocking import BlockingScheduler
import smtplib
from email.mime.text import MIMEText
from datetime import datetime

def send_email():
    msg = MIMEText("这是定时发送的测试邮件", 'plain', 'utf-8')
    msg['From'] = "your_email@qq.com"
    msg['To'] = "recipient@example.com"
    msg['Subject'] = "APScheduler测试邮件"
    
    with smtplib.SMTP_SSL("smtp.qq.com", 465) as server:
        server.login("your_email@qq.com", "your_auth_code")
        server.sendmail("your_email@qq.com", ["recipient@example.com"], msg.as_string())
    print("邮件发送成功")

scheduler = BlockingScheduler()
# 设置2025年10月10日15点执行
scheduler.add_job(send_email, 'date', run_date=datetime(2025, 10, 10, 15, 0))
scheduler.start()

from apscheduler.schedulers.background import BackgroundScheduler
import requests

def fetch_weather():
    try:
        response = requests.get("https://api.example.com/weather")
        print(f"天气数据: {response.json()}")
    except Exception as e:
        print(f"抓取失败: {str(e)}")

scheduler = BackgroundScheduler()
# 每天8:30执行
scheduler.add_job(fetch_weather, 'cron', hour=8, minute=30)
scheduler.start()

# 保持程序运行（Web应用中通常不需要）
import time
while True:
    time.sleep(1)

from apscheduler.jobstores.sqlalchemy import SQLAlchemyJobStore

jobstores = {
    'default': SQLAlchemyJobStore(url='mysql://user:pass@localhost/apscheduler')
}

scheduler = BackgroundScheduler(jobstores=jobstores)
# 即使程序重启，任务也会从数据库恢复

# 添加任务
def dynamic_task():
    print("动态添加的任务执行了")

job = scheduler.add_job(dynamic_task, 'interval', minutes=1, id='dynamic_job')

# 暂停任务
scheduler.pause_job('dynamic_job')

# 恢复任务
scheduler.resume_job('dynamic_job')

# 删除任务
scheduler.remove_job('dynamic_job')

# 获取所有任务
all_jobs = scheduler.get_jobs()
for job in all_jobs:
    print(f"任务ID: {job.id}, 下次执行时间: {job.next_run_time}")

import logging

logging.basicConfig(
    filename='scheduler.log',
    level=logging.INFO,
    format='%(asctime)s - %(levelname)s - %(message)s'
)

def safe_task():
    try:
        # 可能出错的代码
        1 / 0
    except Exception as e:
        logging.error(f"任务执行失败: {str(e)}")
        raise  # 重新抛出异常让APScheduler记录

scheduler.add_job(safe_task, 'interval', seconds=5)

# 使用Redis作为任务存储和锁机制
from apscheduler.jobstores.redis import RedisJobStore
from apscheduler.jobstores.base import ConflictingIdError

jobstores = {
    'default': RedisJobStore(host='localhost', port=6379, db=0)
}

# 配合分布式锁使用（需额外实现）
def distributed_task():
    try:
        # 获取锁
        if acquire_lock("task_lock"):
            # 执行任务
            print("执行分布式任务")
            # 释放锁
            release_lock("task_lock")
    except ConflictingIdError:
        print("其他实例正在执行该任务")

# 明确设置时区
from pytz import timezone
scheduler = BackgroundScheduler(timezone=timezone('Asia/Shanghai'))

# 或者在CronTrigger中指定
scheduler.add_job(
    my_job,
    'cron',
    hour=8,
    minute=30,
    timezone='Asia/Shanghai'
)

# 限制同一任务的并发实例数
scheduler.add_job(
    my_job,
    'interval',
    minutes=1,
    max_instances=3  # 最多同时运行3个实例
)

# 对于耗时任务，考虑使用进程池
executors = {
    'default': ProcessPoolExecutor(5)  # 最多5个进程
}

from flask import Flask
from apscheduler.schedulers.background import BackgroundScheduler

app = Flask(__name__)
scheduler = BackgroundScheduler()

def cron_job():
    print("Flask应用中的定时任务执行了")

@app.route('/')
def index():
    return "APScheduler与Flask集成成功"

if __name__ == '__main__':
    scheduler.add_job(cron_job, 'cron', minute='*/1')  # 每分钟执行
    scheduler.start()
    app.run()

# 在apps.py中初始化
from django.apps import AppConfig
from apscheduler.schedulers.background import BackgroundScheduler

class MyAppConfig(AppConfig):
    name = 'myapp'

    def ready(self):
        scheduler = BackgroundScheduler()
        scheduler.add_job(my_django_task, 'interval', hours=1)
        scheduler.start()

def job_monitor(event):
    if event.exception:
        send_alert(f"任务{event.job_id}失败: {str(event.exception)}")

scheduler.add_listener(job_monitor, apscheduler.events.EVENT_JOB_ERROR)

# 限制线程池大小
executors = {
    'default': ThreadPoolExecutor(20)  # 最多20个线程
}