Before I ask, Cron Jobs and Task Scheduler will be my last options, this script will be used across Windows and Linux and I'd prefer to have a coded out method of doing this than leaving this to the end user to complete.
Is there a library for Python that I can use to schedule tasks? I will need to run a function once every hour, however, over time if I run a script once every hour and use .sleep, "once every hour" will run at a different part of the hour from the previous day due to the delay inherent to executing/running the script and/or function.
What is the best way to schedule a function to run at a specific time of day (more than once) without using a Cron Job or scheduling it with Task Scheduler?
Or if this is not possible, I would like your input as well.
AP Scheduler fit my needs exactly.
Version < 3.0
import datetime
import time
from apscheduler.scheduler import Scheduler
# Start the scheduler
sched = Scheduler()
sched.daemonic = False
sched.start()
def job_function():
print("Hello World")
print(datetime.datetime.now())
time.sleep(20)
# Schedules job_function to be run once each minute
sched.add_cron_job(job_function, minute='0-59')
out:
>Hello World
>2014-03-28 09:44:00.016.492
>Hello World
>2014-03-28 09:45:00.0.14110
Version > 3.0
(From Animesh Pandey's answer below)
from apscheduler.schedulers.blocking import BlockingScheduler
sched = BlockingScheduler()
#sched.scheduled_job('interval', seconds=10)
def timed_job():
print('This job is run every 10 seconds.')
#sched.scheduled_job('cron', day_of_week='mon-fri', hour=10)
def scheduled_job():
print('This job is run every weekday at 10am.')
sched.configure(options_from_ini_file)
sched.start()
Maybe this can help: Advanced Python Scheduler
Here's a small piece of code from their documentation:
from apscheduler.schedulers.blocking import BlockingScheduler
def some_job():
print "Decorated job"
scheduler = BlockingScheduler()
scheduler.add_job(some_job, 'interval', hours=1)
scheduler.start()
To run something every 10 minutes past the hour.
from datetime import datetime, timedelta
while 1:
print 'Run something..'
dt = datetime.now() + timedelta(hours=1)
dt = dt.replace(minute=10)
while datetime.now() < dt:
time.sleep(1)
For apscheduler < 3.0, see Unknown's answer.
For apscheduler > 3.0
from apscheduler.schedulers.blocking import BlockingScheduler
sched = BlockingScheduler()
#sched.scheduled_job('interval', seconds=10)
def timed_job():
print('This job is run every 10 seconds.')
#sched.scheduled_job('cron', day_of_week='mon-fri', hour=10)
def scheduled_job():
print('This job is run every weekday at 10am.')
sched.configure(options_from_ini_file)
sched.start()
Update:
apscheduler documentation.
This for apscheduler-3.3.1 on Python 3.6.2.
"""
Following configurations are set for the scheduler:
- a MongoDBJobStore named “mongo”
- an SQLAlchemyJobStore named “default” (using SQLite)
- a ThreadPoolExecutor named “default”, with a worker count of 20
- a ProcessPoolExecutor named “processpool”, with a worker count of 5
- UTC as the scheduler’s timezone
- coalescing turned off for new jobs by default
- a default maximum instance limit of 3 for new jobs
"""
from pytz import utc
from apscheduler.schedulers.blocking import BlockingScheduler
from apscheduler.jobstores.sqlalchemy import SQLAlchemyJobStore
from apscheduler.executors.pool import ProcessPoolExecutor
"""
Method 1:
"""
jobstores = {
'mongo': {'type': 'mongodb'},
'default': SQLAlchemyJobStore(url='sqlite:///jobs.sqlite')
}
executors = {
'default': {'type': 'threadpool', 'max_workers': 20},
'processpool': ProcessPoolExecutor(max_workers=5)
}
job_defaults = {
'coalesce': False,
'max_instances': 3
}
"""
Method 2 (ini format):
"""
gconfig = {
'apscheduler.jobstores.mongo': {
'type': 'mongodb'
},
'apscheduler.jobstores.default': {
'type': 'sqlalchemy',
'url': 'sqlite:///jobs.sqlite'
},
'apscheduler.executors.default': {
'class': 'apscheduler.executors.pool:ThreadPoolExecutor',
'max_workers': '20'
},
'apscheduler.executors.processpool': {
'type': 'processpool',
'max_workers': '5'
},
'apscheduler.job_defaults.coalesce': 'false',
'apscheduler.job_defaults.max_instances': '3',
'apscheduler.timezone': 'UTC',
}
sched_method1 = BlockingScheduler() # uses overrides from Method1
sched_method2 = BlockingScheduler() # uses same overrides from Method2 but in an ini format
#sched_method1.scheduled_job('interval', seconds=10)
def timed_job():
print('This job is run every 10 seconds.')
#sched_method2.scheduled_job('cron', day_of_week='mon-fri', hour=10)
def scheduled_job():
print('This job is run every weekday at 10am.')
sched_method1.configure(jobstores=jobstores, executors=executors, job_defaults=job_defaults, timezone=utc)
sched_method1.start()
sched_method2.configure(gconfig=gconfig)
sched_method2.start()
the simplest option I can suggest is using the schedule library.
In your question, you said "I will need to run a function once every hour"
the code to do this is very simple:
import schedule
def thing_you_wanna_do():
...
...
return
schedule.every().hour.do(thing_you_wanna_do)
while True:
schedule.run_pending()
you also asked how to do something at a certain time of the day
some examples of how to do this are:
import schedule
def thing_you_wanna_do():
...
...
return
schedule.every().day.at("10:30").do(thing_you_wanna_do)
schedule.every().monday.do(thing_you_wanna_do)
schedule.every().wednesday.at("13:15").do(thing_you_wanna_do)
# If you would like some randomness / variation you could also do something like this
schedule.every(1).to(2).hours.do(thing_you_wanna_do)
while True:
schedule.run_pending()
90% of the code used is the example code of the schedule library. Happy scheduling!
Run the script every 15 minutes of the hour.
For example, you want to receive 15 minute stock price quotes, which are updated every 15 minutes.
while True:
print("Update data:", datetime.now())
sleep = 15 - datetime.now().minute % 15
if sleep == 15:
run_strategy()
time.sleep(sleep * 60)
else:
time.sleep(sleep * 60)
#For scheduling task execution
import schedule
import time
def job():
print("I'm working...")
schedule.every(1).minutes.do(job)
#schedule.every().hour.do(job)
#schedule.every().day.at("10:30").do(job)
#schedule.every(5).to(10).minutes.do(job)
#schedule.every().monday.do(job)
#schedule.every().wednesday.at("13:15").do(job)
#schedule.every().minute.at(":17").do(job)
while True:
schedule.run_pending()
time.sleep(1)
The Python standard library does provide sched and threading for this task. But this means your scheduler script will have be running all the time instead of leaving its execution to the OS, which may or may not be what you want.
On the version posted by sunshinekitty called "Version < 3.0" , you may need to specify apscheduler 2.1.2 . I accidentally had version 3 on my 2.7 install, so I went:
pip uninstall apscheduler
pip install apscheduler==2.1.2
It worked correctly after that. Hope that helps.
clock.py
from apscheduler.schedulers.blocking import BlockingScheduler
import pytz
sched = BlockingScheduler(timezone=pytz.timezone('Africa/Lagos'))
#sched.scheduled_job('cron', day_of_week='mon-sun', hour=22)
def scheduled_job():
print('This job is run every week at 10pm.')
#your job here
sched.start()
Procfile
clock: python clock.py
requirements.txt
APScheduler==3.0.0
After deployment, the final step is to scale up the clock process. This is a singleton process, meaning you’ll never need to scale up more than 1 of these processes. If you run two, the work will be duplicated.
$ heroku ps:scale clock=1
Source: https://devcenter.heroku.com/articles/clock-processes-python
Perhaps Rocketry suits your needs. It's a powerful scheduler that is very easy to use, has a lot of built-in scheduling options and it is easy to extend:
from rocketry import Rocketry
from rocketry.conds import daily, every, after_success
app = Rocketry()
#app.task(every("1 hour 30 minutes"))
def do_things():
...
#app.task(daily.between("12:00", "17:00"))
def do_daily_afternoon():
...
#app.task(daily & after_success(do_things))
def do_daily_after_task():
...
if __name__ == "__main__":
app.run()
It has much more though:
String based scheduling syntax
Logical statements (AND, OR, NOT)
A lot of built-in scheduling options
Easy to customize (custom conditions, parameters etc.)
Parallelization (run on separate thread or process)
Paramatrization (execution order and input-output)
Persistence: put the logs anywhere you like
Modify scheduler on runtime (ie. build API on top of it)
Links:
Documentation: https://rocketry.readthedocs.io/
Source code: https://github.com/Miksus/rocketry
Disclaimer: I'm the author
Probably you got the solution already #lukik, but if you wanna remove a scheduling, you should use:
job = scheduler.add_job(myfunc, 'interval', minutes=2)
job.remove()
or
scheduler.add_job(myfunc, 'interval', minutes=2, id='my_job_id')
scheduler.remove_job('my_job_id')
if you need to use a explicit job ID
For more information, you should check: https://apscheduler.readthedocs.io/en/stable/userguide.html#removing-jobs
I found that scheduler needs to run the program every second. If using a online server it would be costly.
So I have following:
It run at each minute at the 5th second, and you can change it to hours days by recalculating waiting period in seconds
import time
import datetime
Initiating = True
print(datetime.datetime.now())
while True:
if Initiating == True:
print("Initiate")
print( datetime.datetime.now())
time.sleep(60 - time.time() % 60+5)
Initiating = False
else:
time.sleep(60)
print("working")
print(datetime.datetime.now())
This method worked for me using relativedelta and datetime and a modulo boolean check for every hour.
It runs every hour from the time you start it.
import time
from datetime import datetime, timedelta
from dateutil.relativedelta import relativedelta
#Track next run outside loop and update the next run time within the loop
nxt_run=datetime.now()
#because while loops evaluate at microseconds we basically need to use a boolean evaluation to track when it should run next
while True:
cnow = datetime.now() #track the current time
time.sleep(1) #good to have so cpu doesn't spike
if (cnow.hour % 1 == 0 and cnow >= nxt_run):
print(f"start #{cnow}: next run #{nxt_run}")
nxt_run=cnow+relativedelta(hours=1) #add an hour to the next run
else:
print(f"next run #{nxt_run}")
One option is to write a C/C++ wrapper that executes the python script on a regular basis. Your end-user would run the C/C++ executable, which would remain running in the background, and periodically execute the python script. This may not be the best solution, and may not work if you don't know C/C++ or want to keep this 100% python. But it does seem like the most user-friendly approach, since people are used to clicking on executables. All of this assumes that python is installed on your end user's computer.
Another option is to use cron job/Task Scheduler but to put it in the installer as a script so your end user doesn't have to do it.
I am trying to use Apschedulers to Run a code Daily But i am facing some issue
Here is Code :
async def job():
print("Boss Wake Up")
scheduler = AsyncIOScheduler()
scheduler.add_job(job, "cron", day_of_week="mon-sun", hour=21, minute=10)
scheduler.start()
But its not working starting from today. why? i wanna make it start from day one and run daily. Can anyone help me ? Thanks !
Can you try the following
from apscheduler.schedulers.blocking import BlockingScheduler
from apscheduler.triggers.interval import IntervalTrigger
sched = BlockingScheduler()
#sched.scheduled_job(IntervalTrigger(seconds=10)) #set the interval you need
def timed_job():
print('This job is run every 10 seconds.')
sched.start()
You can use BackgroundScheduler() if you want to run this in background
You still need to run the asyncio event loop. Add the following block:
try:
asyncio.get_event_loop().run_forever()
except (KeyboardInterrupt, SystemExit):
pass
When I run this it waits a minute then it prints 'Lights on' then waits two minutes and prints 'Lights off'. After that apscheduler seems to go nuts and quickly alternates between the two very fast.
Did i just stumble into a apscheduler bug or why does this happen?
from datetime import datetime, timedelta
import time
import os, signal, logging
logging.basicConfig(level=logging.DEBUG)
from apscheduler.schedulers.background import BackgroundScheduler
scheduler = BackgroundScheduler()
def turn_on():
#Turn ON
print('##############################Lights on')
def turn_off():
#Turn off
print('#############################Lights off')
def schedule():
print('Lights will turn on at'.format(lights_on_time))
if __name__ == '__main__':
while True:
lights_on_time = (str(datetime.now() + timedelta(minutes=1)))
lights_off_time = (str(datetime.now() + timedelta(minutes=2)))
scheduler.add_job(turn_on, 'date', run_date=lights_on_time)
scheduler.add_job(turn_off, 'date', run_date=lights_off_time)
try:
scheduler.start()
signal.pause()
except:
pass
print('Press Ctrl+{0} to exit'.format('Break' if os.name == 'nt' else 'C'))
try:
# This is here to simulate application activity (which keeps the main thread alive).
while True:
time.sleep(2)
except (KeyboardInterrupt, SystemExit):
# Not strictly necessary if daemonic mode is enabled but should be done if possible
scheduler.shutdown()
You are flooding the scheduler with events. You are using the BackgroundScheduler, meaning that scheduler.start() is exiting and not waiting for the event to happen. The simplest fix may be to not use the BackgroundScheduler (use the BlockingScheduler), or put a sleep(180) on your loop.
Try this:
from datetime import datetime, timedelta
from apscheduler.schedulers.background import BackgroundScheduler
import time
scheduler = BackgroundScheduler()
def turn_on():
print('Turn on', datetime.now())
def turn_off():
print('Turn off', datetime.now())
scheduler.start()
while True:
scheduler.add_job(func=turn_on, trigger='date', next_run_time=datetime.now() + timedelta(minutes=1))
scheduler.add_job(func=turn_off, trigger='date', next_run_time=datetime.now() + timedelta(minutes=2))
time.sleep(180)
You should only start the scheduler once.
I'm trying to schedule an interval job with APScheduler (v3.0.0).
I've tried:
from apscheduler.schedulers.blocking import BlockingScheduler
sched = BlockingScheduler()
def my_interval_job():
print 'Hello World!'
sched.add_job(my_interval_job, 'interval', seconds=5)
sched.start()
and
from apscheduler.schedulers.blocking import BlockingScheduler
sched = BlockingScheduler()
#sched.scheduled_job('interval', id='my_job_id', seconds=5)
def my_interval_job():
print 'Hello World!'
sched.start()
Either should work according to the docs, but the job never fires...
UPDATE:
It turns out there was something else, environment-related, preventing the task from running. This morning, the task is working fine without any modifications to the code from yesterday.
UPDATE 2:
After further testing, I've found that 'interval' jobs seem to be generally flaky... The above code now works in my dev environment, but not when I deploy to a staging env (I'm using a heroku app for staging). I have other apscheduler 'cron' jobs that work just fine in the staging/production envs.
When I turn on DEBUG logging for the "apscheduler.schedulers" logger, the log indicates that the interval job is added:
Added job "my_cron_job1" to job store "default"
Added job "my_cron_job2" to job store "default"
Added job "my_interval_job" to job store "default"
Scheduler started
Adding job tentatively -- it will be properly scheduled when the scheduler starts
Adding job tentatively -- it will be properly scheduled when the scheduler starts
Looking for jobs to run
Next wakeup is due at 2015-03-24 15:05:00-07:00 (in 254.210542 seconds)
How can the next wakeup be due 254 seconds from now when the interval job is set to 5 seconds??
You need to keep the thread alive. Here is a example of how I used it.
from subprocess import call
import time
import os
from pytz import utc
from apscheduler.schedulers.background import BackgroundScheduler
def job():
print("In job")
call(['python', 'scheduler/main.py'])
if __name__ == '__main__':
scheduler = BackgroundScheduler()
scheduler.configure(timezone=utc)
scheduler.add_job(job, 'interval', seconds=10)
scheduler.start()
print('Press Ctrl+{0} to exit'.format('Break' if os.name == 'nt' else 'C'))
try:
# This is here to simulate application activity (which keeps the main thread alive).
while True:
time.sleep(5)
except (KeyboardInterrupt, SystemExit):
# Not strictly necessary if daemonic mode is enabled but should be done if possible
scheduler.shutdown()
I haven't figured out what caused the original issue, but I got around it by swapping the order in which the jobs are scheduled, so that the 'interval' job is scheduled BEFORE the 'cron' jobs.
i.e. I switched from this:
def my_cron_job1():
print "cron job 1"
def my_cron_job2():
print "cron job 2"
def my_interval_job():
print "interval job"
if __name__ == '__main__':
from apscheduler.schedulers.blocking import BlockingScheduler
sched = BlockingScheduler(timezone='MST')
sched.add_job(my_cron_job1, 'cron', id='my_cron_job1', minute=10)
sched.add_job(my_cron_job2, 'cron', id='my_cron_job2', minute=20)
sched.add_job(my_interval_job, 'interval', id='my_job_id', seconds=5)
to this:
def my_cron_job1():
print "cron job 1"
def my_cron_job2():
print "cron job 2"
def my_interval_job():
print "interval job"
if __name__ == '__main__':
from apscheduler.schedulers.blocking import BlockingScheduler
sched = BlockingScheduler(timezone='MST')
sched.add_job(my_interval_job, 'interval', id='my_job_id', seconds=5)
sched.add_job(my_cron_job1, 'cron', id='my_cron_job1', minute=10)
sched.add_job(my_cron_job2, 'cron', id='my_cron_job2', minute=20)
and now both the cron jobs and the interval jobs run without a problem in both environments.
How can the next wakeup be due 254 seconds from now when the interval
job is set to 5 seconds??
It's simple:
you have many pending executions as your most of the jobs didn't completed in the interval-window of time.
You could use the following parameters in order to sort this out:
**misfire_grace_time**: Maximum time in seconds for the job execution to be allowed to delay before it is considered a misfire
**coalesce**: Roll several pending executions of jobs into one
To read more, check the documentation here.
The documentation had an error there. I've fixed it now.
That first line should be:
from apscheduler.schedulers.blocking import BlockingScheduler
It would've raised an ImportError though, but you didn't mention any.
Did you try any of the provided examples?
Ok, I've looked at the updated question.
The reason you're having problems may be that you could be using the wrong timezone. Your country is currently using daylight saving time in most locations, so the correct timezone would probably be MDT (Mountain Daylight Time). But that will break again when you move back to standard time. So I advise you to use a timezone like "America/Denver". That will take care of the DST switches.
Question: Are you using CentOS? So far it's the only known operating system where automatic detection of the local timezone is impossible.
I have python code that I am developing for a website that, among other things, creates an excel sheet and then converts it into a json file. I need for this code to run continuously unless it is killed by the website administrator.
To this end, I am using APscheduler.
The code runs perfectly without APscheduler but when I attempt to add the rest of the code one of two things happens; 1) It runs forever and will not stop despite using "ctrl+C" and I need to stop it using task manager or 2) It only runs once, and then it stops
Code That doesn't Stop:
from apscheduler.scheduler import Scheduler
import logging
import time
logging.basicConfig()
sched = Scheduler()
sched.start()
(...)
code to make excel sheet and json file
(...)
#sched.interval_schedule(seconds = 15)
def job():
excelapi_final()
while True:
time.sleep(10)
sched.shutdown(wait=False)
Code that stops running after one time:
from apscheduler.scheduler import Scheduler
import logging
import time
logging.basicConfig()
sched = Scheduler()
(...)
#create excel sheet and json file
(...)
#sched.interval_schedule(seconds = 15)
def job():
excelapi_final()
sched.start()
while True:
time.sleep(10)
sched.shutdown(wait=False)
I understand from other questions, a few tutorials and the documentation that sched.shutdown should allow for the code to be killed by ctrl+C - however that is not working. Any ideas? Thanks in advance!
You could use the standalone mode:
sched = Scheduler(standalone=True)
and then start the scheduler like this:
try:
sched.start()
except (KeyboardInterrupt):
logger.debug('Got SIGTERM! Terminating...')
Your corrected code should look like this:
from apscheduler.scheduler import Scheduler
import logging
import time
logging.basicConfig()
sched = Scheduler(standalone=True)
(...)
code to make excel sheet and json file
(...)
#sched.interval_schedule(seconds = 15)
def job():
excelapi_final()
try:
sched.start()
except (KeyboardInterrupt):
logger.debug('Got SIGTERM! Terminating...')
This way the program will stop when Ctrl-C is pressed
You can gracefully shut it down:
import signal
from apscheduler.scheduler import Scheduler
import logging
import time
logging.basicConfig()
sched = Scheduler()
(...)
#create excel sheet and json file
(...)
#sched.interval_schedule(seconds = 15)
def job():
excelapi_final()
sched.start()
def gracefully_exit(signum, frame):
print('Stopping...')
sched.shutdown()
signal.signal(signal.SIGINT, gracefully_exit)
signal.signal(signal.SIGTERM, gracefully_exit)