import os
import sys
import time
+import urllib3
+import importlib.util
from ftplib import FTP
-from optparse import OptionParser
+from argparse import ArgumentParser
+
+import pytz
import requests
import zeep.cache
import zeep.transports
-__version__ = '2.0.0'
+__version__ = '3.2.1'
LOG = logging.getLogger(__name__)
LOG.setLevel(logging.NOTSET)
+urllib3.disable_warnings()
+
def get_parser():
"""Return OptionParser for this program"""
- parser = OptionParser(version=__version__)
+ parser = ArgumentParser()
- parser.add_option("--config",
- dest="config",
- metavar="FILE",
- help="location of config file")
+ parser.add_argument("--version",
+ action="version",
+ version=__version__)
- parser.add_option("--log-level",
- dest="log_level",
- default=None,
- help="set the log level (debug, info, warning)")
+ parser.add_argument("--config",
+ dest="config",
+ metavar="FILE",
+ help="location of config file")
- parser.add_option("--dry-run",
- action="store_true",
- dest="dry_run",
- default=False,
- help="fetch data but don't upload to InfoEx")
+ parser.add_argument("--log-level",
+ dest="log_level",
+ default=None,
+ help="set the log level (debug, info, warning)")
+
+ parser.add_argument("--dry-run",
+ action="store_true",
+ dest="dry_run",
+ default=False,
+ help="fetch data but don't upload to InfoEx")
return parser
'wx_data': {}, # placeholder key, values to come later
}
- data = dict()
- data['provider'] = config['station']['type']
+ station = dict()
+ station['provider'] = config['station']['type']
- if data['provider'] not in ['nrcs', 'mesowest']:
+ if station['provider'] not in ['nrcs', 'mesowest', 'python']:
print("Please specify either nrcs or mesowest as the station type.")
sys.exit(1)
- if data['provider'] == 'nrcs':
- data['source'] = 'https://www.wcc.nrcs.usda.gov/awdbWebService/services?WSDL'
- data['station_id'] = config['station']['station_id']
+ if station['provider'] == 'nrcs':
+ station['source'] = 'https://www.wcc.nrcs.usda.gov/awdbWebService/services?WSDL'
+ station['station_id'] = config['station']['station_id']
+ station['desired_data'] = config['station']['desired_data'].split(',')
+ station['units'] = config['station']['units']
- try:
- data['desired_data'] = config['station']['desired_data'].split(',')
- except:
- # desired_data malformed or missing, setting default
- data['desired_data'] = [
- 'TOBS', # AIR TEMPERATURE OBSERVED (degF)
- 'SNWD', # SNOW DEPTH (in)
- 'PREC' # PRECIPITATION ACCUMULATION (in)
- ]
-
- # XXX: For NRCS, we're manually overriding units for now! Once
- # unit conversion is supported for NRCS, REMOVE THIS!
- if 'units' not in data:
- data['units'] = 'imperial'
-
- if data['provider'] == 'mesowest':
- data['source'] = 'https://api.synopticdata.com/v2/stations/timeseries'
- data['station_id'] = config['station']['station_id']
- data['units'] = config['station']['units']
-
- try:
- data['desired_data'] = config['station']['desired_data']
- except:
- # desired_data malformed or missing, setting default
- data['desired_data'] = 'air_temp,snow_depth'
+ if station['provider'] == 'mesowest':
+ station['source'] = 'https://api.synopticdata.com/v2/stations/timeseries'
+ station['station_id'] = config['station']['station_id']
+ station['units'] = config['station']['units']
+ station['desired_data'] = config['station']['desired_data']
# construct full API URL (sans start/end time, added later)
- data['source'] = data['source'] + '?token=' + config['station']['token'] + '&within=60&units=' + data['units'] + '&stid=' + data['station_id'] + '&vars=' + data['desired_data']
+ station['source'] = station['source'] + '?token=' + \
+ config['station']['token'] + \
+ '&within=60&units=' + station['units'] + \
+ '&stid=' + station['station_id'] + \
+ '&vars=' + station['desired_data']
+
+ if station['provider'] == 'python':
+ station['path'] = config['station']['path']
- except KeyError as e:
- LOG.critical("%s not defined in %s" % (e, options.config))
- exit(1)
- except Exception as exc:
- LOG.critical("Exception occurred in config parsing: '%s'" % (exc))
- exit(1)
+ tz = 'America/Los_Angeles'
+
+ if 'tz' in config['station']:
+ tz = config['station']['tz']
+
+ try:
+ station['tz'] = pytz.timezone(tz)
+ except pytz.exceptions.UnknownTimeZoneError:
+ LOG.critical("%s is not a valid timezone", tz)
+ sys.exit(1)
+
+ except KeyError as err:
+ LOG.critical("%s not defined in configuration file", err)
+ sys.exit(1)
# all sections/values present in config file, final sanity check
try:
for key in config.sections():
for subkey in config[key]:
- if not len(config[key][subkey]):
- raise ValueError;
- except ValueError as exc:
- LOG.critical("Config value '%s.%s' is empty" % (key, subkey))
- exit(1)
+ if not config[key][subkey]:
+ raise ValueError
+ except ValueError:
+ LOG.critical("Config value '%s.%s' is empty", key, subkey)
+ sys.exit(1)
- return (infoex, data)
+ return (infoex, station)
def setup_logging(log_level):
"""Setup our logging infrastructure"""
try:
from systemd.journal import JournalHandler
LOG.addHandler(JournalHandler())
- except:
+ except ImportError:
## fallback to syslog
#import logging.handlers
#LOG.addHandler(logging.handlers.SysLogHandler())
def main():
"""Main routine: sort through args, decide what to do, then do it"""
parser = get_parser()
- (options, args) = parser.parse_args()
+ options = parser.parse_args()
config = configparser.ConfigParser(allow_no_value=False)
print("\nPlease select an appropriate log level or remove the switch (--log-level).")
sys.exit(1)
- (infoex, data) = setup_config(config)
+ (infoex, station) = setup_config(config)
LOG.debug('Config parsed, starting up')
# create mappings
(fmap, final_data) = setup_infoex_fields_mapping(infoex['location_uuid'])
- iemap = setup_infoex_counterparts_mapping(data['provider'])
+ iemap = setup_infoex_counterparts_mapping(station['provider'])
# override units if user selected metric
- #
- # NOTE: to update this, use the fmap<->final_data mapping laid out above
- #
- # NOTE: this only 'works' with MesoWest for now, as the MesoWest API
- # itself handles the unit conversion; in the future, we will also
- # support NRCS unit conversion, but this must be done by this
- # program.
- if data['units'] == 'metric':
- final_data[fmap['tempPresUnit']] = 'C'
- final_data[fmap['hsUnit']] = 'm'
- final_data[fmap['windSpeedUnit']] = 'm/s'
- final_data[fmap['windGustSpeedNumUnit']] = 'm/s'
+ if 'units' not in station:
+ if station['provider'] != 'python':
+ LOG.error("Please specify the units in the configuration "
+ "file")
+ sys.exit(1)
- # floor time to nearest hour
- dt = datetime.datetime.now()
- end_date = dt - datetime.timedelta(minutes=dt.minute % 60,
- seconds=dt.second,
- microseconds=dt.microsecond)
- begin_date = end_date - datetime.timedelta(hours=3)
+ if station['units'] == 'metric':
+ final_data = switch_units_to_metric(final_data, fmap)
- # get the data
- LOG.debug("Getting %s data from %s to %s" % (str(data['desired_data']),
- str(begin_date), str(end_date)))
+ (begin_date, end_date) = setup_time_values(station)
+
+ if station['provider'] == 'python':
+ LOG.debug("Getting custom data from external Python program")
+ else:
+ LOG.debug("Getting %s data from %s to %s (%s)",
+ str(station['desired_data']),
+ str(begin_date), str(end_date), end_date.tzinfo.zone)
time_all_elements = time.time()
# get the data
- if data['provider'] == 'nrcs':
- infoex['wx_data'] = get_nrcs_data(begin_date, end_date, data)
- elif data['provider'] == 'mesowest':
+ if station['provider'] == 'nrcs':
+ infoex['wx_data'] = get_nrcs_data(begin_date, end_date, station)
+ elif station['provider'] == 'mesowest':
infoex['wx_data'] = get_mesowest_data(begin_date, end_date,
- data)
+ station)
+ elif station['provider'] == 'python':
+ try:
+ spec = importlib.util.spec_from_file_location('custom_wx',
+ station['path'])
+ mod = importlib.util.module_from_spec(spec)
+ spec.loader.exec_module(mod)
+ mod.LOG = LOG
- LOG.info("Time to get all data : %.3f sec" % (time.time() -
- time_all_elements))
+ try:
+ infoex['wx_data'] = mod.get_custom_data()
+
+ if infoex['wx_data'] is None:
+ infoex['wx_data'] = []
+ except Exception as exc:
+ LOG.error("Python program for custom Wx data failed in "
+ "execution: %s", str(exc))
+ sys.exit(1)
+
+ LOG.info("Successfully executed external Python program")
+ except ImportError:
+ LOG.error("Please upgrade to Python 3.3 or later")
+ sys.exit(1)
+ except FileNotFoundError:
+ LOG.error("Specified Python program for custom Wx data "
+ "was not found")
+ sys.exit(1)
+ except Exception as exc:
+ LOG.error("A problem was encountered when attempting to "
+ "load your custom Wx program: %s", str(exc))
+ sys.exit(1)
+
+ LOG.info("Time taken to get all data : %.3f sec", time.time() -
+ time_all_elements)
LOG.debug("infoex[wx_data]: %s", str(infoex['wx_data']))
+ # timezone massaging
+ final_end_date = end_date.astimezone(station['tz'])
+
# Now we only need to add in what we want to change thanks to that
# abomination of a variable declaration earlier
final_data[fmap['Location UUID']] = infoex['location_uuid']
- final_data[fmap['obDate']] = end_date.strftime('%m/%d/%Y')
- final_data[fmap['obTime']] = end_date.strftime('%H:%M')
+ final_data[fmap['obDate']] = final_end_date.strftime('%m/%d/%Y')
+ final_data[fmap['obTime']] = final_end_date.strftime('%H:%M')
+ final_data[fmap['timeZone']] = station['tz'].zone
- for elementCd in infoex['wx_data']:
- if elementCd not in iemap:
- LOG.warning("BAD KEY wx_data['%s']" % (elementCd))
+ for element_cd in infoex['wx_data']:
+ if element_cd not in iemap:
+ LOG.warning("BAD KEY wx_data['%s']", element_cd)
continue
+ # do the conversion before the rounding
+ if station['provider'] == 'nrcs' and station['units'] == 'metric':
+ infoex['wx_data'][element_cd] = convert_nrcs_units_to_metric(element_cd, infoex['wx_data'][element_cd])
+
+ # Massage precision of certain values to fit InfoEx's
+ # expectations
+ #
+ # 0 decimal places: relative humidity, wind speed, wind
+ # direction, wind gust, snow depth
+ # 1 decimal place: air temp, baro
+ # Avoid transforming None values
+ if infoex['wx_data'][element_cd] is None:
+ continue
+ elif element_cd in ['wind_speed', 'WSPD', 'wind_direction',
+ 'RHUM', 'relative_humidity', 'WDIR',
+ 'wind_gust', 'SNWD', 'snow_depth']:
+ infoex['wx_data'][element_cd] = round(infoex['wx_data'][element_cd])
+ elif element_cd in ['TOBS', 'air_temp', 'PRES', 'pressure']:
+ infoex['wx_data'][element_cd] = round(infoex['wx_data'][element_cd], 1)
+
# CONSIDER: Casting every value to Float() -- need to investigate if
# any possible elementCds we may want are any other data
# type than float.
# storedUnitCd. But that's pretty network-intensive and
# may not even be worth it if there's only e.g. one or two
# exceptions to any otherwise uniformly Float value set.
- final_data[fmap[iemap[elementCd]]] = infoex['wx_data'][elementCd]
+ final_data[fmap[iemap[element_cd]]] = infoex['wx_data'][element_cd]
- LOG.debug("final_data: %s" % (str(final_data)))
+ LOG.debug("final_data: %s", str(final_data))
- if not write_local_csv(infoex['csv_filename'], final_data):
- LOG.warning('Could not write local CSV file: %s',
- infoex['csv_filename'])
- return 1;
+ if infoex['wx_data']:
+ if not write_local_csv(infoex['csv_filename'], final_data):
+ LOG.warning('Could not write local CSV file: %s',
+ infoex['csv_filename'])
+ return 1
- if not options.dry_run:
- upload_csv(infoex['csv_filename'], infoex)
+ if not options.dry_run:
+ upload_csv(infoex['csv_filename'], infoex)
LOG.debug('DONE')
return 0
Create a mapping of InfoEx fields to the local data's indexing scheme.
INFOEX FIELDS
-
+
This won't earn style points in Python, but here we establish a couple
of helpful mappings variables. The reason this is helpful is that the
end result is simply an ordered set, the CSV file. But we still may
want to manipulate the values arbitrarily before writing that file.
-
+
Also note that the current Auto Wx InfoEx documentation shows these
keys in a graphical table with the "index" beginning at 1, but here we
sanely index beginning at 0.
"""
+ # pylint: disable=too-many-statements,multiple-statements,bad-whitespace
fmap = {} ; final_data = [None] * 29
fmap['Location UUID'] = 0 ; final_data[0] = location_uuid
fmap['obDate'] = 1 ; final_data[1] = None
if provider == 'nrcs':
iemap['PREC'] = 'precipitationGauge'
iemap['TOBS'] = 'tempPres'
+ iemap['TMAX'] = 'tempMaxHour'
+ iemap['TMIN'] = 'tempMinHour'
iemap['SNWD'] = 'hS'
iemap['PRES'] = 'baro'
iemap['RHUM'] = 'rH'
elif provider == 'mesowest':
iemap['precip_accum'] = 'precipitationGauge'
iemap['air_temp'] = 'tempPres'
+ iemap['air_temp_high_24_hour'] = 'tempMaxHour'
+ iemap['air_temp_low_24_hour'] = 'tempMinHour'
iemap['snow_depth'] = 'hS'
iemap['pressure'] = 'baro'
iemap['relative_humidity'] = 'rH'
iemap['wind_speed'] = 'windSpeedNum'
iemap['wind_direction'] = 'windDirectionNum'
iemap['wind_gust'] = 'windGustSpeedNum'
+ elif provider == 'python':
+ # we expect Python programs to use the InfoEx data type names
+ iemap['precipitationGauge'] = 'precipitationGauge'
+ iemap['tempPres'] = 'tempPres'
+ iemap['tempMaxHour'] = 'tempMaxHour'
+ iemap['tempMinHour'] = 'tempMinHour'
+ iemap['hS'] = 'hS'
+ iemap['baro'] = 'baro'
+ iemap['rH'] = 'rH'
+ iemap['windSpeedNum'] = 'windSpeedNum'
+ iemap['windDirectionNum'] = 'windDirectionNum'
+ iemap['windGustSpeedNum'] = 'windGustSpeedNum'
return iemap
# provider-specific operations
-def get_nrcs_data(begin, end, data):
+def get_nrcs_data(begin, end, station):
"""get the data we're after from the NRCS WSDL"""
transport = zeep.transports.Transport(cache=zeep.cache.SqliteCache())
- client = zeep.Client(wsdl=data['source'], transport=transport)
+ transport.session.verify = False
+ client = zeep.Client(wsdl=station['source'], transport=transport)
remote_data = {}
- for elementCd in data['desired_data']:
+ # massage begin/end date format
+ begin_date_str = begin.strftime('%Y-%m-%d %H:%M:00')
+ end_date_str = end.strftime('%Y-%m-%d %H:%M:00')
+
+ for element_cd in station['desired_data']:
time_element = time.time()
- # get the last three hours of data for this elementCd
+ # get the last three hours of data for this elementCd/element_cd
tmp = client.service.getHourlyData(
- stationTriplets=[data['station_id']],
- elementCd=elementCd,
- ordinal=1,
- beginDate=begin,
- endDate=end)
+ stationTriplets=[station['station_id']],
+ elementCd=element_cd,
+ ordinal=1,
+ beginDate=begin_date_str,
+ endDate=end_date_str)
- LOG.info("Time to get elementCd '%s': %.3f sec" % (elementCd,
- time.time() - time_element))
+ LOG.info("Time to get NRCS elementCd '%s': %.3f sec", element_cd,
+ time.time() - time_element)
values = tmp[0]['values']
# so perhaps this decision will be re-evaluated in the future
if values:
ordered = sorted(values, key=lambda t: t['dateTime'], reverse=True)
- remote_data[elementCd] = ordered[0]['value']
+ remote_data[element_cd] = ordered[0]['value']
else:
- remote_data[elementCd] = None
+ remote_data[element_cd] = None
return remote_data
-def get_mesowest_data(begin, end, data):
+def get_mesowest_data(begin, end, station):
"""get the data we're after from the MesoWest/Synoptic API"""
remote_data = {}
end_date_str = end.strftime('%Y%m%d%H%M')
# construct final, completed API URL
- api_req_url = data['source'] + '&start=' + begin_date_str + '&end=' + end_date_str
+ api_req_url = station['source'] + '&start=' + begin_date_str + '&end=' + end_date_str
req = requests.get(api_req_url)
try:
try:
observations = json['STATION'][0]['OBSERVATIONS']
- except ValueError:
- LOG.error("Bad JSON in MesoWest response")
+ except KeyError as exc:
+ LOG.error("Unexpected JSON in MesoWest response: '%s'", exc)
+ sys.exit(1)
+ except IndexError as exc:
+ LOG.error("Unexpected JSON in MesoWest response: '%s'", exc)
+ try:
+ LOG.error("Detailed MesoWest response: '%s'",
+ json['SUMMARY']['RESPONSE_MESSAGE'])
+ except KeyError:
+ pass
+ sys.exit(1)
+ except ValueError as exc:
+ LOG.error("Bad JSON in MesoWest response: '%s'", exc)
sys.exit(1)
pos = len(observations['date_time']) - 1
- for elementCd in data['desired_data'].split(','):
+ for element_cd in station['desired_data'].split(','):
# sort and isolate the most recent, see note above in NRCS for how and
# why this is done
#
# irregularities
# we may not have the data at all
- key_name = elementCd + '_set_1'
+ key_name = element_cd + '_set_1'
+
if key_name in observations:
if observations[key_name][pos]:
- remote_data[elementCd] = observations[key_name][pos]
+ remote_data[element_cd] = observations[key_name][pos]
+
+ # mesowest by default provides wind_speed in m/s, but
+ # we specify 'english' units in the request; either way,
+ # we want mph
+ if element_cd in ('wind_speed', 'wind_gust'):
+ remote_data[element_cd] = kn_to_mph(remote_data[element_cd])
else:
- remote_data[elementCd] = None
+ remote_data[element_cd] = None
else:
- remote_data[elementCd] = None
+ remote_data[element_cd] = None
return remote_data
+def switch_units_to_metric(data_map, mapping):
+ """replace units with metric counterparts"""
+
+ # NOTE: to update this, use the fmap<->final_data mapping laid out
+ # in setup_infoex_fields_mapping ()
+ data_map[mapping['tempMaxHourUnit']] = 'C'
+ data_map[mapping['tempMinHourUnit']] = 'C'
+ data_map[mapping['tempPresUnit']] = 'C'
+ data_map[mapping['precipitationGaugeUnit']] = 'mm'
+ data_map[mapping['hsUnit']] = 'cm'
+ data_map[mapping['windSpeedUnit']] = 'm/s'
+ data_map[mapping['windGustSpeedNumUnit']] = 'm/s'
+ data_map[mapping['dewPointUnit']] = 'C'
+ data_map[mapping['hn24AutoUnit']] = 'cm'
+ data_map[mapping['hstAutoUnit']] = 'cm'
+
+ return data_map
+
+def convert_nrcs_units_to_metric(element_cd, value):
+ """convert NRCS values from English to metric"""
+ if element_cd == 'TOBS':
+ value = f_to_c(value)
+ elif element_cd == 'SNWD':
+ value = in_to_cm(value)
+ elif element_cd == 'PREC':
+ value = in_to_mm(value)
+ return value
+
# CSV operations
def write_local_csv(path_to_file, data):
"""Write the specified CSV file to disk"""
- with open(path_to_file, 'w') as f:
+ with open(path_to_file, 'w') as file_object:
# The requirement is that empty values are represented in the CSV
# file as "", csv.QUOTE_NONNUMERIC achieves that
- LOG.debug("writing CSV file '%s'" % (path_to_file))
- writer = csv.writer(f, quoting=csv.QUOTE_NONNUMERIC)
+ LOG.debug("writing CSV file '%s'", path_to_file)
+ writer = csv.writer(file_object, quoting=csv.QUOTE_NONNUMERIC)
writer.writerow(data)
- f.close()
+ file_object.close()
return True
def upload_csv(path_to_file, infoex_data):
"""Upload the specified CSV file to InfoEx FTP and remove the file"""
with open(path_to_file, 'rb') as file_object:
- LOG.debug("uploading FTP file '%s'" % (infoex_data['host']))
+ LOG.debug("uploading FTP file '%s'", infoex_data['host'])
ftp = FTP(infoex_data['host'], infoex_data['uuid'],
infoex_data['api_key'])
ftp.storlines('STOR ' + path_to_file, file_object)
file_object.close()
os.remove(path_to_file)
+# other miscellaneous routines
+def setup_time_values(station):
+ """establish time bounds of data request(s)"""
+
+ # default timezone to UTC (for MesoWest)
+ tz = pytz.utc
+
+ # but for NRCS, use the config-specified timezone
+ if station['provider'] == 'nrcs':
+ tz = station['tz']
+
+ # floor time to nearest hour
+ date_time = datetime.datetime.now(tz=tz)
+ end_date = date_time - datetime.timedelta(minutes=date_time.minute % 60,
+ seconds=date_time.second,
+ microseconds=date_time.microsecond)
+ begin_date = end_date - datetime.timedelta(hours=3)
+ return (begin_date, end_date)
+
+def f_to_c(f):
+ """convert Fahrenheit to Celsius"""
+ return (float(f) - 32) * 5.0/9.0
+
+def in_to_cm(inches):
+ """convert inches to centimetrs"""
+ return float(inches) * 2.54
+
+def in_to_mm(inches):
+ """convert inches to millimeters"""
+ return (float(inches) * 2.54) * 10.0
+
+def ms_to_mph(ms):
+ """convert meters per second to miles per hour"""
+ return ms * 2.236936
+
+def kn_to_mph(kn):
+ """convert knots to miles per hour"""
+ return kn * 1.150779
+
if __name__ == "__main__":
sys.exit(main())
wylark / infoex-autowx.git / blobdiff