Develop Reference

Running a Python web scraper every hour [duplicate]

I'm looking for a library in Python which will provide at and cron like functionality.
I'd quite like have a pure Python solution, rather than relying on tools installed on the box; this way I run on machines with no cron.
For those unfamiliar with cron: you can schedule tasks based upon an expression like:
0 2 * * 7 /usr/bin/run-backup # run the backups at 0200 on Every Sunday
0 9-17/2 * * 1-5 /usr/bin/purge-temps # run the purge temps command, every 2 hours between 9am and 5pm on Mondays to Fridays.
The cron time expression syntax is less important, but I would like to have something with this sort of flexibility.
If there isn't something that does this for me out-the-box, any suggestions for the building blocks to make something like this would be gratefully received.
Edit
I'm not interested in launching processes, just "jobs" also written in Python - python functions. By necessity I think this would be a different thread, but not in a different process.
To this end, I'm looking for the expressivity of the cron time expression, but in Python.
Cron has been around for years, but I'm trying to be as portable as possible. I cannot rely on its presence.

If you're looking for something lightweight checkout schedule:
import schedule
import time
def job():
print("I'm working...")
schedule.every(10).minutes.do(job)
schedule.every().hour.do(job)
schedule.every().day.at("10:30").do(job)
while 1:
schedule.run_pending()
time.sleep(1)
Disclosure: I'm the author of that library.

You could just use normal Python argument passing syntax to specify your crontab. For example, suppose we define an Event class as below:
from datetime import datetime, timedelta
import time
# Some utility classes / functions first
class AllMatch(set):
"""Universal set - match everything"""
def __contains__(self, item): return True
allMatch = AllMatch()
def conv_to_set(obj): # Allow single integer to be provided
if isinstance(obj, (int,long)):
return set([obj]) # Single item
if not isinstance(obj, set):
obj = set(obj)
return obj
# The actual Event class
class Event(object):
def __init__(self, action, min=allMatch, hour=allMatch,
day=allMatch, month=allMatch, dow=allMatch,
args=(), kwargs={}):
self.mins = conv_to_set(min)
self.hours= conv_to_set(hour)
self.days = conv_to_set(day)
self.months = conv_to_set(month)
self.dow = conv_to_set(dow)
self.action = action
self.args = args
self.kwargs = kwargs
def matchtime(self, t):
"""Return True if this event should trigger at the specified datetime"""
return ((t.minute in self.mins) and
(t.hour in self.hours) and
(t.day in self.days) and
(t.month in self.months) and
(t.weekday() in self.dow))
def check(self, t):
if self.matchtime(t):
self.action(*self.args, **self.kwargs)
(Note: Not thoroughly tested)
Then your CronTab can be specified in normal python syntax as:
c = CronTab(
Event(perform_backup, 0, 2, dow=6 ),
Event(purge_temps, 0, range(9,18,2), dow=range(0,5))
)
This way you get the full power of Python's argument mechanics (mixing positional and keyword args, and can use symbolic names for names of weeks and months)
The CronTab class would be defined as simply sleeping in minute increments, and calling check() on each event. (There are probably some subtleties with daylight savings time / timezones to be wary of though). Here's a quick implementation:
class CronTab(object):
def __init__(self, *events):
self.events = events
def run(self):
t=datetime(*datetime.now().timetuple()[:5])
while 1:
for e in self.events:
e.check(t)
t += timedelta(minutes=1)
while datetime.now() < t:
time.sleep((t - datetime.now()).seconds)
A few things to note: Python's weekdays / months are zero indexed (unlike cron), and that range excludes the last element, hence syntax like "1-5" becomes range(0,5) - ie [0,1,2,3,4]. If you prefer cron syntax, parsing it shouldn't be too difficult however.

More or less same as above but concurrent using gevent :)
"""Gevent based crontab implementation"""
from datetime import datetime, timedelta
import gevent
# Some utility classes / functions first
def conv_to_set(obj):
"""Converts to set allowing single integer to be provided"""
if isinstance(obj, (int, long)):
return set([obj]) # Single item
if not isinstance(obj, set):
obj = set(obj)
return obj
class AllMatch(set):
"""Universal set - match everything"""
def __contains__(self, item):
return True
allMatch = AllMatch()
class Event(object):
"""The Actual Event Class"""
def __init__(self, action, minute=allMatch, hour=allMatch,
day=allMatch, month=allMatch, daysofweek=allMatch,
args=(), kwargs={}):
self.mins = conv_to_set(minute)
self.hours = conv_to_set(hour)
self.days = conv_to_set(day)
self.months = conv_to_set(month)
self.daysofweek = conv_to_set(daysofweek)
self.action = action
self.args = args
self.kwargs = kwargs
def matchtime(self, t1):
"""Return True if this event should trigger at the specified datetime"""
return ((t1.minute in self.mins) and
(t1.hour in self.hours) and
(t1.day in self.days) and
(t1.month in self.months) and
(t1.weekday() in self.daysofweek))
def check(self, t):
"""Check and run action if needed"""
if self.matchtime(t):
self.action(*self.args, **self.kwargs)
class CronTab(object):
"""The crontab implementation"""
def __init__(self, *events):
self.events = events
def _check(self):
"""Check all events in separate greenlets"""
t1 = datetime(*datetime.now().timetuple()[:5])
for event in self.events:
gevent.spawn(event.check, t1)
t1 += timedelta(minutes=1)
s1 = (t1 - datetime.now()).seconds + 1
print "Checking again in %s seconds" % s1
job = gevent.spawn_later(s1, self._check)
def run(self):
"""Run the cron forever"""
self._check()
while True:
gevent.sleep(60)
import os
def test_task():
"""Just an example that sends a bell and asd to all terminals"""
os.system('echo asd | wall')
cron = CronTab(
Event(test_task, 22, 1 ),
Event(test_task, 0, range(9,18,2), daysofweek=range(0,5)),
)
cron.run()

None of the listed solutions even attempt to parse a complex cron schedule string. So, here is my version, using croniter. Basic gist:
schedule = "*/5 * * * *" # Run every five minutes
nextRunTime = getNextCronRunTime(schedule)
while True:
roundedDownTime = roundDownTime()
if (roundedDownTime == nextRunTime):
####################################
### Do your periodic thing here. ###
####################################
nextRunTime = getNextCronRunTime(schedule)
elif (roundedDownTime > nextRunTime):
# We missed an execution. Error. Re initialize.
nextRunTime = getNextCronRunTime(schedule)
sleepTillTopOfNextMinute()
Helper routines:
from croniter import croniter
from datetime import datetime, timedelta
# Round time down to the top of the previous minute
def roundDownTime(dt=None, dateDelta=timedelta(minutes=1)):
roundTo = dateDelta.total_seconds()
if dt == None : dt = datetime.now()
seconds = (dt - dt.min).seconds
rounding = (seconds+roundTo/2) // roundTo * roundTo
return dt + timedelta(0,rounding-seconds,-dt.microsecond)
# Get next run time from now, based on schedule specified by cron string
def getNextCronRunTime(schedule):
return croniter(schedule, datetime.now()).get_next(datetime)
# Sleep till the top of the next minute
def sleepTillTopOfNextMinute():
t = datetime.utcnow()
sleeptime = 60 - (t.second + t.microsecond/1000000.0)
time.sleep(sleeptime)

I know there are a lot of answers, but another solution could be to go with decorators. This is an example to repeat a function everyday at a specific time. The cool think about using this way is that you only need to add the Syntactic Sugar to the function you want to schedule:
#repeatEveryDay(hour=6, minutes=30)
def sayHello(name):
print(f"Hello {name}")
sayHello("Bob") # Now this function will be invoked every day at 6.30 a.m
And the decorator will look like:
def repeatEveryDay(hour, minutes=0, seconds=0):
"""
Decorator that will run the decorated function everyday at that hour, minutes and seconds.
:param hour: 0-24
:param minutes: 0-60 (Optional)
:param seconds: 0-60 (Optional)
"""
def decoratorRepeat(func):
#functools.wraps(func)
def wrapperRepeat(*args, **kwargs):
def getLocalTime():
return datetime.datetime.fromtimestamp(time.mktime(time.localtime()))
# Get the datetime of the first function call
td = datetime.timedelta(seconds=15)
if wrapperRepeat.nextSent == None:
now = getLocalTime()
wrapperRepeat.nextSent = datetime.datetime(now.year, now.month, now.day, hour, minutes, seconds)
if wrapperRepeat.nextSent < now:
wrapperRepeat.nextSent += td
# Waiting till next day
while getLocalTime() < wrapperRepeat.nextSent:
time.sleep(1)
# Call the function
func(*args, **kwargs)
# Get the datetime of the next function call
wrapperRepeat.nextSent += td
wrapperRepeat(*args, **kwargs)
wrapperRepeat.nextSent = None
return wrapperRepeat
return decoratorRepeat

I like how the pycron package solves this problem.
import pycron
import time
while True:
if pycron.is_now('0 2 * * 0'): # True Every Sunday at 02:00
print('running backup')
time.sleep(60) # The process should take at least 60 sec
# to avoid running twice in one minute
else:
time.sleep(15) # Check again in 15 seconds

There isn't a "pure python" way to do this because some other process would have to launch python in order to run your solution. Every platform will have one or twenty different ways to launch processes and monitor their progress. On unix platforms, cron is the old standard. On Mac OS X there is also launchd, which combines cron-like launching with watchdog functionality that can keep your process alive if that's what you want. Once python is running, then you can use the sched module to schedule tasks.

Another trivial solution would be:
from aqcron import At
from time import sleep
from datetime import datetime
# Event scheduling
event_1 = At( second=5 )
event_2 = At( second=[0,20,40] )
while True:
now = datetime.now()
# Event check
if now in event_1: print "event_1"
if now in event_2: print "event_2"
sleep(1)
And the class aqcron.At is:
# aqcron.py
class At(object):
def __init__(self, year=None, month=None,
day=None, weekday=None,
hour=None, minute=None,
second=None):
loc = locals()
loc.pop("self")
self.at = dict((k, v) for k, v in loc.iteritems() if v != None)
def __contains__(self, now):
for k in self.at.keys():
try:
if not getattr(now, k) in self.at[k]: return False
except TypeError:
if self.at[k] != getattr(now, k): return False
return True

I don't know if something like that already exists. It would be easy to write your own with time, datetime and/or calendar modules, see http://docs.python.org/library/time.html
The only concern for a python solution is that your job needs to be always running and possibly be automatically "resurrected" after a reboot, something for which you do need to rely on system dependent solutions.

Python decorator to time recursive functions

I have a simple decorator to track the runtime of a function call:
def timed(f):
def caller(*args):
start = time.time()
res = f(*args)
end = time.time()
return res, end - start
return caller
This can be used as follows, and returns a tuple of the function result and the execution time.
#timed
def test(n):
for _ in range(n):
pass
return 0
print(test(900)) # prints (0, 2.69e-05)
Simple enough. But now I want to apply this to recursive functions. Applying the above wrapper to a recursive function results in nested tuples with the times of each recursive call, as is expected.
#timed
def rec(n):
if n:
return rec(n - 1)
else:
return 0
print(rec(3)) # Prints ((((0, 1.90e-06), 8.10e-06), 1.28e-05), 1.90e-05)
What's an elegant way to write the decorator so that it handles recursion properly? Obviously, you could wrap the call if a timed function:
#timed
def wrapper():
return rec(3)
This will give a tuple of the result and the time, but I want all of it to be handled by the decorator so that the caller does not need to worry about defining a new function for every call. Ideas?

The problem here isn't really the decorator. The problem is that rec needs rec to be a function that behaves one way, but you want rec to be a function that behaves differently. There's no clean way to reconcile that with a single rec function.
The cleanest option is to stop requiring rec to be two things at once. Instead of using decorator notation, assign timed(rec) to a different name:
def rec(n):
...
timed_rec = timed(rec)
If you don't want two names, then rec needs to be written to understand the actual value that the decorated rec will return. For example,
#timed
def rec(n):
if n:
val, runtime = rec(n-1)
return val
else:
return 0

I prefer the other answers so far (particularly user2357112's answer), but you can also make a class-based decorator that detects whether the function has been activated, and if so, bypasses the timing:
import time
class fancy_timed(object):
def __init__(self, f):
self.f = f
self.active = False
def __call__(self, *args):
if self.active:
return self.f(*args)
start = time.time()
self.active = True
res = self.f(*args)
end = time.time()
self.active = False
return res, end - start
#fancy_timed
def rec(n):
if n:
time.sleep(0.01)
return rec(n - 1)
else:
return 0
print(rec(3))
(class written with (object) so that this is compatible with py2k and py3k).
Note that to really work properly, the outermost call should use try and finally. Here's the fancied up fancy version of __call__:
def __call__(self, *args):
if self.active:
return self.f(*args)
try:
start = time.time()
self.active = True
res = self.f(*args)
end = time.time()
return res, end - start
finally:
self.active = False

You could structure your timer in a different way by *ahem* abusing the contextmanager and function attribute a little...
from contextlib import contextmanager
import time
#contextmanager
def timed(func):
timed.start = time.time()
try:
yield func
finally:
timed.duration = time.time() - timed.start
def test(n):
for _ in range(n):
pass
return n
def rec(n):
if n:
time.sleep(0.05) # extra delay to notice the difference
return rec(n - 1)
else:
return n
with timed(rec) as r:
print(t(10))
print(t(20))
print(timed.duration)
with timed(test) as t:
print(t(555555))
print(t(666666))
print(timed.duration)
Results:
# recursive
0
0
1.5130000114440918
# non-recursive
555555
666666
0.053999900817871094
If this is deemed a bad hack I'll gladly accept your criticism.

Although it is not an overall solution to the problem of integrating recursion with decorators, for the problem of timing only, I have verified that the last element of the tuple of the times is the overall run time, as this is the time from the upper-most recursive call. Thus if you had
#timed
def rec():
...
to get the overall runtime given the original function definitions you could simply do
rec()[1]
Getting the result of the call, on the other hand, would then require recusing through the nested tuple:
def get(tup):
if isinstance(tup, tuple):
return get(tup[0])
else:
return tup
This might be too complicated to simply get the result of your function.

I encountered the same issue when trying to profile a simple quicksort implementation.
The main issue is that decorators are executed on each function call and we need something that can keep a state, so we can sum all calls at the end. Decorators are not the right tool the job
However, one idea is to abuse the fact that functions are objects and can have atributes. This is explored below with a simple decorator. Something that must be understood is that, by using decorator's sintax sugar (#), the function will always be accumulating its timings.
from typing import Any, Callable
from time import perf_counter
class timeit:
def __init__(self, func: Callable) -> None:
self.func = func
self.timed = []
def __call__(self, *args: Any, **kwds: Any) -> Any:
start = perf_counter()
res = self.func(*args, **kwds)
end = perf_counter()
self.timed.append(end - start)
return res
# usage
#timeit
def rec(n):
...
if __name__ == "__main__":
result = rec(4) # rec result
print(f"Took {rec.timed:.2f} seconds")
# Out: Took 3.39 seconds
result = rec(4) # rec result
# timings between calls are accumulated
# Out: Took 6.78 seconds
Which brings us to a solution inspired by #r.ook, below is a simple context manager that stores each run timing and prints its sum at the end (__exit__). Notice that, because for each timing we require a with statement, this will not accumulate different runs.
from typing import Any, Callable
from time import perf_counter
class timeit:
def __init__(self, func: Callable) -> None:
self.func = func
self.timed = []
def __call__(self, *args: Any, **kwds: Any) -> Any:
start = perf_counter()
res = self.func(*args, **kwds)
end = perf_counter()
self.timed.append(end - start)
return res
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, exc_traceback):
# TODO: report `exc_*` if an exception get raised
print(f"Took {sum(self.timed):.2f} seconds")
return
# usage
def rec(n):
...
if __name__ == "__main__":
with timeit(rec) as f:
result = f(a) # rec result
# Out: Took 3.39 seconds

How to slow down asynchrounous API calls to match API limits?

I have a list of ~300K URLs for an API i need to get data from.
The API limit is 100 calls per second.
I have made a class for the asynchronous but this is working to fast and I am hitting an error on the API.
How do I slow down the asynchronous, so that I can make 100 calls per second?
import grequests
lst = ['url.com','url2.com']
class Test:
def __init__(self):
self.urls = lst
def exception(self, request, exception):
print ("Problem: {}: {}".format(request.url, exception))
def async(self):
return grequests.map((grequests.get(u) for u in self.urls), exception_handler=self.exception, size=5)
def collate_responses(self, results):
return [x.text for x in results]
test = Test()
#here we collect the results returned by the async function
results = test.async()
response_text = test.collate_responses(results)

The first step that I took was to create an object who can distribute a maximum of n coins every t ms.
import time
class CoinsDistribution:
"""Object that distribute a maximum of maxCoins every timeLimit ms"""
def __init__(self, maxCoins, timeLimit):
self.maxCoins = maxCoins
self.timeLimit = timeLimit
self.coin = maxCoins
self.time = time.perf_counter()
def getCoin(self):
if self.coin <= 0 and not self.restock():
return False
self.coin -= 1
return True
def restock(self):
t = time.perf_counter()
if (t - self.time) * 1000 < self.timeLimit:
return False
self.coin = self.maxCoins
self.time = t
return True
Now we need a way of forcing function to only get called if they can get a coin.
To do that we can write a decorator function that we could use like that:
#limitCalls(callLimit=1, timeLimit=1000)
def uniqFunctionRequestingServer1():
return 'response from s1'
But sometimes, multiple functions are calling requesting the same server so we would want them to get coins from the the same CoinsDistribution object.
Therefor, another use of the decorator would be by supplying the CoinsDistribution object:
server_2_limit = CoinsDistribution(3, 1000)
#limitCalls(server_2_limit)
def sendRequestToServer2():
return 'it worked !!'
#limitCalls(server_2_limit)
def sendAnOtherRequestToServer2():
return 'it worked too !!'
We now have to create the decorator, it can take either a CoinsDistribution object or enough data to create a new one.
import functools
def limitCalls(obj=None, *, callLimit=100, timeLimit=1000):
if obj is None:
obj = CoinsDistribution(callLimit, timeLimit)
def limit_decorator(func):
#functools.wraps(func)
def limit_wrapper(*args, **kwargs):
if obj.getCoin():
return func(*args, **kwargs)
return 'limit reached, please wait'
return limit_wrapper
return limit_decorator
And it's done ! Now you can limit the number of calls any API that you use and you can build a dictionary to keep track of your CoinsDistribution objects if you have to manage a lot of them (to differrent API endpoints or to different APIs).
Note: Here I have choosen to return an error message if there are no coins available. You should adapt this behaviour to your needs.

You can just keep track of how much time has passed and decide if you want to do more requests or not.
This will print 100 numbers per second, for example:
from datetime import datetime
import time
start = datetime.now()
time.sleep(1);
counter = 0
while (True):
end = datetime.now()
s = (end-start).seconds
if (counter >= 100):
if (s <= 1):
time.sleep(1) # You can keep track of the time and sleep less, actually
start = datetime.now()
counter = 0
print(counter)
counter += 1

This other question in SO shows exactly how to do this. By the way, what you need is usually called throttling.

Function as argument in python

I need to pass some function as argument in another function. So, I want to add current time to class attribute every second, for example
import time
class Measurement():
values = []
def add_value(self, value):
print "added value"
self.values.append(value)
def smart_delay(input_function,args):
start_time = time.time()
while 5 > (time.time() - start_time):
print "Calling function"
input_function(args)
time.sleep(1)
measurement = Measurement()
smart_delay(measurement.add_value,time.time())
Ok, but after checking contents of measurement.values, I get
[1425980407.173, 1425980407.173, 1425980407.173, 1425980407.173] - so values are the same!!!
What happened? And how to get proper values?
Updated:
Actually, this question is about the way to allow to call some function, passed as the argument to another function. What do you think about this:
import time
class Measurement():
values = []
def add_value(self, value):
print "added value"
self.values.append(value)
def smart_delay(input_function):
start_time = time.time()
while 5 > (time.time() - start_time):
print "Calling function"
input_function()
time.sleep(1)
measurement = Measurement()
smart_delay(lambda: measurement.add_value(time.time()))

Your call to time.time() is executed before the call to smart_delay(...), so smart_delay(measurement.addvalue, time.time()) will first get the return value from time.time() and pass that forward to smart_delay.
You need to pass the time.time function itself, and call it inside of the smart_delay method, instead of passing its return value:
import time
class Measurement():
values = []
def add_value(self, value):
print "added value"
self.values.append(value)
def smart_delay(output_f, input_f):
start_time = time.time()
while 5 > (time.time() - start_time):
print "Calling function"
output_f(input_f())
time.sleep(1)
measurement = Measurement()
smart_delay(measurement.add_value, time.time)
Notice, that this is not the best way to do what you're doing, but it works.
Here's how I'd do it:
import time
# Why do you need a measurement class which only acts as a list anyways?
my_measurements = []
def repeat(duration, function, args=(), kwargs={}, interval=1):
"""Repeat a function call for the given duration."""
start_time = time.time()
while duration > time.time() - start_time:
function(*args, **kwargs)
time.sleep(interval)
def add_time_measurement(measurements):
measurements.append(time.time())
repeat(5, add_time_measurement, (my_measurements,))
And if you want some prints, you can just add them in the add_time_measurement function.

Why is this recursive statement wrong?

This is a bank simulation that takes into account 20 different serving lines with a single queue, customers arrive following an exponential rate and they are served during a time that follows a normal probability distribution with mean 40 and standard deviation 20.
Things were working just fine till I decided to exclude the negative values given by the normal distribution using this method:
def getNormal(self):
normal = normalvariate(40,20)
if (normal>=1):
return normal
else:
getNormal(self)
Am I screwing up the recursive call? I don't get why it wouldn't work. I have changed the getNormal() method to:
def getNormal(self):
normal = normalvariate(40,20)
while (normal <=1):
normal = normalvariate (40,20)
return normal
But I'm curious on why the previous recursive statement gets busted.
This is the complete source code, in case you're interested.
""" bank21: One counter with impatient customers """
from SimPy.SimulationTrace import *
from random import *
## Model components ------------------------
class Source(Process):
""" Source generates customers randomly """
def generate(self,number):
for i in range(number):
c = Customer(name = "Customer%02d"%(i,))
activate(c,c.visit(tiempoDeUso=15.0))
validateTime=now()
if validateTime<=600:
interval = getLambda(self)
t = expovariate(interval)
yield hold,self,t #esta es la rata de generación
else:
detenerGeneracion=999
yield hold,self,detenerGeneracion
class Customer(Process):
""" Customer arrives, is served and leaves """
def visit(self,tiempoDeUso=0):
arrive = now() # arrival time
print "%8.3f %s: Here I am "%(now(),self.name)
yield (request,self,counter),(hold,self,maxWaitTime)
wait = now()-arrive # waiting time
if self.acquired(counter):
print "%8.3f %s: Waited %6.3f"%(now(),self.name,wait)
tiempoDeUso=getNormal(self)
yield hold,self,tiempoDeUso
yield release,self,counter
print "%8.3f %s: Completed"%(now(),self.name)
else:
print "%8.3f %s: Waited %6.3f. I am off"%(now(),self.name,wait)
## Experiment data -------------------------
maxTime = 60*10.5 # minutes
maxWaitTime = 12.0 # minutes. maximum time to wait
## Model ----------------------------------
def model():
global counter
#seed(98989)
counter = Resource(name="Las maquinas",capacity=20)
initialize()
source = Source('Source')
firstArrival= expovariate(20.0/60.0) #chequear el expovariate
activate(source,
source.generate(number=99999),at=firstArrival)
simulate(until=maxTime)
def getNormal(self):
normal = normalvariate(40,20)
if (normal>=1):
return normal
else:
getNormal(self)
def getLambda (self):
actualTime=now()
if (actualTime <=60):
return 20.0/60.0
if (actualTime>60)and (actualTime<=120):
return 25.0/60.0
if (actualTime>120)and (actualTime<=180):
return 40.0/60.0
if (actualTime>180)and (actualTime<=240):
return 30.0/60.0
if (actualTime>240)and (actualTime<=300):
return 35.0/60.0
if (actualTime>300)and (actualTime<=360):
return 42.0/60.0
if (actualTime>360)and (actualTime<=420):
return 50.0/60.0
if (actualTime>420)and (actualTime<=480):
return 55.0/60.0
if (actualTime>480)and (actualTime<=540):
return 45.0/60.0
if (actualTime>540)and (actualTime<=600):
return 10.0/60.0
## Experiment ----------------------------------
model()

I think you want
return getnormal(self)
instead of
getnormal(self)
If the function exits without hitting a return statement, then it returns the special value None, which is a NoneType object - that's why Python complains about a 'NoneType.' The abs() function wants a number, and it doesn't know what to do with a None.
Also, you could avoid recursion (and the cost of creating a new stack frame) by using
def getNormal(self):
normal = 0
while normal < 1:
normal = normalvariate(40,20)
return normal

I am not entirely sure, but I think you need to change your method to the following:
def getNormal(self):
normal = normalvariate(40,20)
if (normal>=1):
return normal
else:
return getNormal(self)

You need to have:
return getNormal(self)
instead of
getNormal(self)
Really though, there's no need for recursion:
def getNormal(self):
normal = 0
while normal < 1:
normal = normalvariate(40,20)
return normal