爬虫设置定时任务

import time
#设置定时
def main(h, m):
    while True:  
        now = datetime.datetime.now()  #获取当前时间
        print (now.hour, now.minute)
        #判断时间
        if now.hour in h and now.minute in m:
            doSth()
        time.sleep(60)


if __name__ ==‘__main__‘:
    main(h=[8,10,12,14,16,18,20], m=[0,30])

import time
import os
while 1:
    os.system("scrapy crawl News")

time.sleep(86400)

import sched
# 初始化sched模块的scheduler类
# 第一个参数是一个可以返回时间戳的函数，第二个参数可以定时未到之前阻塞
schedule = sched.scheduler(time.time, time.sleep)

#被周期性调度出发的函数
def fun():
    os.system("scrapy crawl News")

def perform1(inc):
    schedule.enter(inc,0, perform1, (inc,))
    func()  # 需要周期执行函数

def mymain():
    schedule.enter(0,0, perform1, (86400))

if __name__ = "__main__":
    mymain()
    schedule.run() # 开始运行，直到计划时间队列变为空为止

0 */24 * * * cd /data/spider && scrapy crawl article