Download selected Missouri professional registration files

getMOLicenses.py

#! /usr/bin/python
# Download selected Missouri professional registration files from
# http://pr.mo.gov/listings.asp

# Typically run via a cron job, e.g., grab at 6:05 AM every Sunday:
# min(0-59) hr(0-23) day(1-31) month(1-12) weekday(0-6) command
# 05 6 * * 0 /home/xxxxxx/data/Missouri-Licenses/get-MOLicenses.py >/dev/null 2>&1

# efg, UMKC CHI, 1 Aug 2014.

import urllib
import os
import time
import datetime
from   subprocess import *

os.chdir("/home/xxxxxx/data/Missouri-Licenses/")

ts = time.time()
timestamp = datetime.datetime.fromtimestamp(ts).strftime('%Y%m%d-%H%M%S')

if not os.path.exists(timestamp):
    os.makedirs(timestamp)

# Missouri professional registrations to grab
files = [
    ('Dentistry',   'Dentist',                 'DEN.ZIP'),
    ('Dentistry',   'DentalHygienist',         'DHY.ZIP'),
    ('Nursing',     'RegisteredNurse',         'ORN.ZIP'),
    ('Nursing',     'LicensedPracticalNurse',  'LPN.ZIP'),
    ('Optometry',   'Optometrist',             'OPT.ZIP'),
    ('Pharmacy',    'Pharmacist',              'PHA.ZIP'),
    ('Pharmacy',    'Pharmacy',                'PHY.ZIP'),
    ('HealingArts', 'Audiologist',             'AUD.ZIP'),
    ('HealingArts', 'MedicalPhysicianSurgeon', 'MED.ZIP'),
    ('HealingArts', 'OsteopathicPhysicians',   'OPS.ZIP'),
    ('HealingArts', 'PhysicianAssistant',      'PYA.ZIP'),
    ('Psychology',  'Psychologist',            'PSY.ZIP')
]

# Download ZIP files in timestamp directory
for license_file in files:
    fromfile = "http://pr.mo.gov/downloadables/" + license_file[2]
    tofile   = timestamp + "/" + license_file[0] + "-" + license_file[1] + "-" + license_file[2]
    urllib.urlretrieve(fromfile, filename=tofile)

# Send E-mail confirmation
readBody = Popen(["/bin/ls", "/home/xxxxxx/data/Missouri-Licenses/"+timestamp], stdout=PIPE)
mail = Popen(["/bin/mailx", "-s", "get-MOLicences.py", "xxxxxx@xxxx.edu"], stdin=readBody.stdout, stdout=PIPE)
output = mail.communicate()[0]