Develop Reference

is there a way to automate VMware snapshot deletion by setting a schedule through Ansible or rest API

I am trying to figure out if there is a way to automate VMware snapshot deletion through Ansible.
I have found vmware_guest_powerstate.py"to be closest to it and tried to modified it but it's failing with "Failed to create scheduled task present as specifications given are invalid: A specified parameter was not correct: spec.action"
pstate = {
'present': vim.VirtualMachine.CreateSnapshot,
'absent': vim.VirtualMachine.RemoveAllSnapshots,
}
dt = ""
try:
dt = datetime.strptime(scheduled_at, "%d/%m/%Y %H:%M")
except ValueError as e:
module.fail_json(
msg="Failed to convert given date and time string to Python datetime object,"
"please specify string in 'dd/mm/yyyy hh:mm' format: %s"
% to_native(e)
)
schedule_task_spec = vim.scheduler.ScheduledTaskSpec()
schedule_task_name = module.params["schedule_task_name"] or "task_%s" % str(
randint(10000, 99999)
)
schedule_task_desc = module.params["schedule_task_description"]
if schedule_task_desc is None:
schedule_task_desc = (
"Schedule task for vm %s for "
"operation %s at %s"
% (vm.name, scheduled_at)
)
schedule_task_spec.name = schedule_task_name
schedule_task_spec.description = schedule_task_desc
schedule_task_spec.scheduler = vim.scheduler.OnceTaskScheduler()
schedule_task_spec.scheduler.runAt = dt
schedule_task_spec.action = vim.action.MethodAction()
schedule_task_spec.action.name = pstate[module.params['state']]
schedule_task_spec.enabled = module.params["schedule_task_enabled"]

Suggest trying "vim.VirtualMachine.CreateSnapshot_Task" and "RemoveAllSnapshots_Task" instead of "vim.VirtualMachine.CreateSnapshot" and "vim.VirtualMachine.RemoveAllSnapshots" to see if that works.
pstate = {'present': vim.VirtualMachine.CreateSnapshot_Task,'absent': vim.VirtualMachine.RemoveAllSnapshots_Task}
....
schedule_task_spec.name = schedule_task_name
schedule_task_spec.description = schedule_task_desc
schedule_task_spec.scheduler = vim.scheduler.OnceTaskScheduler()
schedule_task_spec.scheduler.runAt = dt
schedule_task_spec.action = vim.action.MethodAction()
schedule_task_spec.action.name = pstate[module.params['state']]
schedule_task_spec.enabled = module.params["schedule_task_enabled"]
print(schedule_task_spec.action)

Check if the number of slots is > 0 before picking a date and an hour?

I am building a vaccination appointment program that automatically assigns a slot to the user.
This builds the table and saves it into a CSV file:
import pandas
start_date = '1/1/2022'
end_date = '31/12/2022'
list_of_date = pandas.date_range(start=start_date, end=end_date)
df = pandas.DataFrame(list_of_date)
df.columns = ['Date/Time']
df['8:00'] = 100
df['9:00'] = 100
df['10:00'] = 100
df['11:00'] = 100
df['12:00'] = 100
df['13:00'] = 100
df['14:00'] = 100
df['15:00'] = 100
df['16:00'] = 100
df['17:00'] = 100
df.to_csv(r'C:\Users\Ric\PycharmProjects\pythonProject\new.csv')
And this code randomly pick a date and an hour from that date in the CSV table we just created:
import pandas
import random
from random import randrange
#randrange randomly picks an index for date and time for the user
random_date = randrange(365)
random_hour = randrange(10)
list = ["8:00", "9:00", "10:00", "11:00", "12:00", "13:00", "14:00", "15:00", "16:00", "17:00"]
hour = random.choice(list)
df = pandas.read_csv('new.csv')
date=df.iloc[random_date][0]
# 1 is substracted from that cell as 1 slot will be assigned to the user
df.loc[random_date, hour] -= 1
df.to_csv(r'C:\Users\Ric\PycharmProjects\pythonProject\new.csv',index=False)
print(date)
print(hour)
I need help with making the program check if the random hour it chose on that date has vacant slots. I can manage the while loops that are needed if the number of vacant slots is 0. And no, I have not tried much because I have no clue of how to do this.
P.S. If you're going to try running the code, please remember to change the save and read location.

Here is how I would do it. I've also cleaned it up a bit.
import random
import pandas as pd
start_date, end_date = '1/1/2022', '31/12/2022'
hours = [f'{hour}:00' for hour in range(8, 18)]
df = pd.DataFrame(
data=pd.date_range(start_date, end_date),
columns=['Date/Time']
)
for hour in hours:
df[hour] = 100
# 1000 simulations
for _ in range(1000):
random_date, random_hour = random.randrange(365), random.choice(hours)
# Check if slot has vacant slot
if df.at[random_date, random_hour] > 0:
df.at[random_date, random_hour] -= 1
else:
# Pass here, but you can add whatever logic you want
# for instance you could give it the next free slot in the same day
pass
print(df.describe())

import pandas
import random
from random import randrange
# randrange randomly picks an index for date and time for the user
random_date = randrange(365)
# random_hour = randrange(10) #consider removing this line since it's not used
lista = [# consider avoid using Python preserved names
"8:00",
"9:00",
"10:00",
"11:00",
"12:00",
"13:00",
"14:00",
"15:00",
"16:00",
"17:00",
]
hour = random.choice(lista)
df = pandas.read_csv("new.csv")
date = df.iloc[random_date][0]
# 1 is substracted from that cell as 1 slot will be assigned to the user
if df.loc[random_date, hour] > 0:#here is what you asked for
df.loc[random_date, hour] -= 1
else:
print(f"No Vacant Slots in {random_date}, {hour}")
df.to_csv(r"new.csv", index=False)
print(date)
print(hour)

Here's another alternative. I'm not sure you really need the very large and slow-to-load pandas module for this. This does it with plan Python structures. I tried to run the simulation until it got a failure, but with 365,000 open slots, and flushing the database to disk each time, it takes too long. I changed the 100 to 8, just to see it find a dup in reasonable time.
import csv
import datetime
import random
def create():
start = datetime.date( 2022, 1, 1 )
oneday = datetime.timedelta(days=1)
headers = ["date"] + [f"{i}:00" for i in range(8,18)]
data = []
for _ in range(365):
data.append( [start.strftime("%Y-%m-%d")] + [8]*10 ) # not 100
start += oneday
write( headers, data )
def write(headers, rows):
fcsv = csv.writer(open('data.csv','w',newline=''))
fcsv.writerow( headers )
fcsv.writerows( rows )
def read():
days = []
headers = []
for row in csv.reader(open('data.csv')):
if not headers:
headers = row
else:
days.append( [row[0]] + list(map(int,row[1:])))
return headers, days
def choose( headers, days ):
random_date = random.randrange(365)
random_hour = random.randrange(len(headers)-1)+1
choice = days[random_date][0] + " " + headers[random_hour]
print( "Chose", choice )
if days[random_date][random_hour]:
days[random_date][random_hour] -= 1
write(headers,days)
return choice
else:
print("Randomly chosen slot is full.")
return None
create()
data = read()
while choose( *data ):
pass

How can I speed up a python loop with a timestamp interval condition

I have this code that is rather done in a hurry but it works in general. The only thing it runs forever. The idea is to update 2 columns on a table that is holding 1495748 rows, so the number of the list of timestamp being queried in first place. For each update value there has to be done a comparison in which the timestamp has to be in an hourly interval that is formed by two timestamps coming from the api in two different dicts. Is there a way to speed up things a little or maybe multiprocess it?
Hint: db_mac = db_connection to a Postgres database.
the response looks like this:
{'meta': {'source': 'National Oceanic and Atmospheric Administration, Deutscher Wetterdienst'}, 'data': [{'time': '2019-11-26 23:00:00', 'time_local': '2019-11-27 00:00', 'temperature': 8.3, 'dewpoint': 5.9, 'humidity': 85, 'precipitation': 0, 'precipitation_3': None, 'precipitation_6': None, 'snowdepth': None, 'windspeed': 11, 'peakgust': 21, 'winddirection': 160, 'pressure': 1004.2, 'condition': 4}, {'time': '2019-11-27 00:00:00', ....
import requests
import db_mac
from collections import defaultdict
import datetime
import time
t = time.time()
station = [10382,"DE","Berlin / Tegel",52.5667,13.3167,37,"EDDT",10382,"TXL","Europe/Berlin"]
dates = [("2019-11-20","2019-11-22"), ("2019-11-27","2019-12-02") ]
insert_dict = defaultdict(tuple)
hist_weather_list = []
for d in dates:
end = d[1]
start = d[0]
print(start, end)
url = "https://api.meteostat.net/v1/history/hourly?station={station}&start={start}&end={end}&time_zone={timezone}&&time_format=Y-m-d%20H:i&key=<APIKEY>".format(station=station[0], start=start, end=end, timezone=station[-1])
response = requests.get(url)
weather = response.json()
print(weather)
for i in weather["data"]:
hist_weather_list.append(i)
sql = "select timestamp from dump order by timestamp asc"
result = db_mac.execute(sql)
hours, rem = divmod(time.time() - t, 3600)
minutes, seconds = divmod(rem, 60)
print("step1 {:0>2}:{:0>2}:{:05.2f}".format(int(hours),int(minutes),seconds))
for row in result:
try:
ts_dump = datetime.datetime.timestamp(row[0])
for i, hour in enumerate(hist_weather_list):
ts1 = datetime.datetime.timestamp(datetime.datetime.strptime(hour["time"], '%Y-%m-%d %H:%M:%S'))
ts2 = datetime.datetime.timestamp(datetime.datetime.strptime(hist_weather_list[i + 1]["time"], '%Y-%m-%d %H:%M:%S'))
if ts1 <= ts_dump and ts_dump < ts2:
insert_dict[row[0]] = (hour["temperature"], hour["pressure"])
except Exception as e:
pass
hours, rem = divmod(time.time() - t, 3600)
minutes, seconds = divmod(rem, 60)
print("step2 {:0>2}:{:0>2}:{:05.2f}".format(int(hours),int(minutes),seconds))
for key, value in insert_dict.items():
sql2 = """UPDATE dump SET temperature = """ + str(value[0]) + """, pressure = """+ str(value[1]) + """ WHERE timestamp = '"""+ str(key) + """';"""
db_mac.execute(sql2)
hours, rem = divmod(time.time() - t, 3600)
minutes, seconds = divmod(rem, 60)
print("step3 {:0>2}:{:0>2}:{:05.2f}".format(int(hours),int(minutes),seconds))
UPDATE the code for multiprocessing. I'll let it run the night and give an update of the running time.
import requests
import db_mac
from collections import defaultdict
import datetime
import time
import multiprocessing as mp
t = time.time()
station = [10382,"DE","Berlin / Tegel",52.5667,13.3167,37,"EDDT",10382,"TXL","Europe/Berlin"]
dates = [("2019-11-20","2019-11-22"), ("2019-11-27","2019-12-02") ]
insert_dict = defaultdict(tuple)
hist_weather_list = []
for d in dates:
end = d[1]
start = d[0]
print(start, end)
url = "https://api.meteostat.net/v1/history/hourly?station={station}&start={start}&end={end}&time_zone={timezone}&&time_format=Y-m-d%20H:i&key=wzwi2YR5".format(station=station[0], start=start, end=end, timezone=station[-1])
response = requests.get(url)
weather = response.json()
print(weather)
for i in weather["data"]:
hist_weather_list.append(i)
sql = "select timestamp from dump order by timestamp asc"
result = db_mac.execute(sql)
hours, rem = divmod(time.time() - t, 3600)
minutes, seconds = divmod(rem, 60)
print("step1 {:0>2}:{:0>2}:{:05.2f}".format(int(hours),int(minutes),seconds))
def find_parameters(x):
for row in result[x[0]:x[1]]:
try:
ts_dump = datetime.datetime.timestamp(row[0])
for i, hour in enumerate(hist_weather_list):
ts1 = datetime.datetime.timestamp(datetime.datetime.strptime(hour["time"], '%Y-%m-%d %H:%M:%S'))
ts2 = datetime.datetime.timestamp(datetime.datetime.strptime(hist_weather_list[i + 1]["time"], '%Y-%m-%d %H:%M:%S'))
if ts1 <= ts_dump and ts_dump < ts2:
insert_dict[row[0]] = (hour["temperature"], hour["pressure"])
except Exception as e:
pass
step1 = int(len(result) /4)
step2 = 2 * step1
step3 = 3 * step1
step4 = len(result)
steps = [[0,step1],[step1,step2],[step2,step3], [step3,step4]]
pool = mp.Pool(mp.cpu_count())
pool.map(find_parameters, steps)
hours, rem = divmod(time.time() - t, 3600)
minutes, seconds = divmod(rem, 60)
print("step2 {:0>2}:{:0>2}:{:05.2f}".format(int(hours),int(minutes),seconds))
for key, value in insert_dict.items():
sql2 = """UPDATE dump SET temperature = """ + str(value[0]) + """, pressure = """+ str(value[1]) + """ WHERE timestamp = '"""+ str(key) + """';"""
db_mac.execute(sql2)
hours, rem = divmod(time.time() - t, 3600)
minutes, seconds = divmod(rem, 60)
print("step3 {:0>2}:{:0>2}:{:05.2f}".format(int(hours),int(minutes),seconds))
UPDATE 2
It finished and ran for 2:45 hours in 4 cores on a raspberry pi. Though is there a more efficient way to do such things?

So theres a few minor things I can think of to speed this up a little. I figure anything little bit helps especially if you have a lot of rows to process. For starters, print statements can slow down your code a lot. I'd get rid of those if they are unneeded.
Most importantly, you are calling the api in every iteration of the loop. Waiting for a response from the API is probably taking up the bulk of your time. I looked a bit at the api you are using, but don't know the exact case you're using it for or what your dates "start" and "end" look like, but if you could do it in less calls that would surely speed up this loop by a lot. Another way you can do this is, it looks like the api has a .csv version of the data you can download and use. Running this on local data would be way faster. If you choose to go this route i'd suggest using pandas. (Sorry if you already know pandas and i'm over explaining) You can use: df = pd.read_csv("filename.csv") and edit the table from there easily. You can also do df.to_sql(params) to write to your data base. Let me know if you want help forming a pandas version of this code.
Also, not sure from your code if this would cause an error, but I would try, instead of your for loop (for i in weather["data"]).
hist_weather_list += weather["data"]
or possibly
hist_weather_list += [weather["data"]
Let me know how it goes!

Python 3 verification script not checking properly

I've been working on a python script and am having issues with some verification's I set up. I have this procedure file that has a function that uses a order number and a customer number to check some past history about the customers orders. Ive been testing live on our server and I keep failing the last if statement. The order number and customer number Im using does have more than one order and some are over 60 days so it should pass the test but it doesnt. Ive been looking over my code and I just cant see what could be causing this
edit: here are the print results of current and retrieved timestamps:
current_timestamp = 1531849617.921927
retrieved_timestamp = 1489622400
two_month_seconds = 5184000
one_month_seconds = 2592000
Python3
from classes import helper
from classes import api
from classes import order
from procedures import orderReleaseProcedure
import time
import datetime
import re
def verifyCustomer(customer_id, order_id):
self_helper = helper.Helper()
customer_blocked_reasons = self_helper.getConfig('customer_blocked_reasons')
order_statuses = self_helper.getConfig('order_statuses')
customer_is_blocked = False
self_api = api.Api()
self_order =order.Order(order_id)
status = {
'success' : 0,
'message' :'verify_payment_method'
}
results = self_api.which_api('orders?customer_id={}'.format(customer_id))
order_count = results['total_count']
if order_count > 1:
for result in results['orders']:
order_status_info= self_api.which_api('order_statuses/%d' % result['order_status_id'])
for customer_blocked_reason in customer_blocked_reasons:
if customer_blocked_reason in order_status_info['name']:
customer_is_blocked = True
order_id = 0
order_date = result['ordered_at']
two_month_seconds = (3600 * 24) * 60
one_month_seconds = (3600 * 24) * 30
stripped_date = order_date[:order_date.find("T")]
current_timestamp = time.time()
retrieved_timestamp = int(datetime.datetime.strptime(stripped_date, '%Y-%m-%d').strftime("%s"))
if retrieved_timestamp > (current_timestamp - one_month_seconds) and not customer_is_blocked:
status['success'] = 1
status['message'] = "Customer Verified with orders older than 30 days and no blocking reasons"
print(' 30 day check was triggered ')
print(status)
break
elif customer_is_blocked:
status_change_result = self_order.update_status(order_statuses['order_hold_manager_review'])
status['success'] = 1
status['message'] = "Changed order status to Order Hold - Manager Review"
print(' Customer block was triggered ')
print(status_change_result)
break
elif not retrieved_timestamp < (current_timestamp - two_month_seconds):
status['success'] = 0
status['message'] = "There is more than 1 order, and none are greater than 60 days, we need to check manually"
print(' 60 day check was triggered ')
print(status)
break
return status

returning different time frames from datetime

I am parsing a file this way :
for d in csvReader:
print datetime.datetime.strptime(d["Date"]+"-"+d["Time"], "%d-%b-%Y-%H:%M:%S.%f").date()
date() returns : 2000-01-08, which is correct
time() returns : 06:20:00, which is also correct
How would I go about returning informations like "date+time" or "date+hours+minutes"
EDIT
Sorry I should have been more precise, here is what I am trying to achieve :
lmb = lambda d: datetime.datetime.strptime(d["Date"]+"-"+d["Time"], "%d-%b-%Y-%H:%M:%S.%f").date()
daily_quotes = {}
for k, g in itertools.groupby(csvReader, key = lmb):
lowBids = []
highBids = []
openBids = []
closeBids = []
for i in g:
lowBids.append(float(i["Low Bid"]))
highBids.append(float(i["High Bid"]))
openBids.append(float(i["Open Bid"]))
closeBids.append(float(i["Close Bid"]))
dayMin = min(lowBids)
dayMax = max(highBids)
open = openBids[0]
close = closeBids[-1]
daily_quotes[k.strftime("%Y-%m-%d")] = [dayMin,dayMax,open,close]
As you can see, right now I'm grouping values by day, I would like to group them by hour ( for which I would need date + hour ) or minutes ( date + hour + minute )
thanks in advance !

Don't use the date method of the datetime object you're getting from strptime. Instead, apply strftime directly to the return from strptime, which gets you access to all the member fields, including year, month, day, hour, minute, seconds, etc...
d = {"Date": "01-Jan-2000", "Time": "01:02:03.456"}
dt = datetime.datetime.strptime(d["Date"]+"-"+d["Time"], "%d-%b-%Y-%H:%M:%S.%f")
print dt.strftime("%Y-%m-%d-%H-%M-%S")