get_nanpa_npa.py

import requests
import csv
from io import StringIO
from collections import defaultdict
from pprint import pformat

npa_report = 'http://www.nationalnanpa.com/nanp1/npa_report.csv'
out_file = 'phone_iso3166/nanpa.py'

r = requests.get(npa_report)
r.raise_for_status()
csvdata = StringIO(r.text)
csvdata.readline()  # Read header
csvdata.readline()  # Read header
npareader = csv.reader(csvdata, delimiter=',', quotechar='"')

npamap = StringIO()
npamap.write('# Generated by get_npna_npa.py\n')
npamap.write('# Based on http://nationalnanpa.com/reports/reports_npa.html\n\n')
npamap.write('npa = \\\n')

npadict = defaultdict(lambda: defaultdict(dict))


for row in npareader:
    try:
        # Get column 0 and 9, according to field definitions:
        #   http://www.nanpa.com/area_codes/AreaCodeDatabaseDefinitions.xls
        npa = row[0]
        assigned = row[5]
        use = row[7]
        location = row[8]
        country = row[9]
        if country == 'US':
            if location == 'USVI':
                country = 'VI'
            elif location == 'PUERTO RICO':
                country = 'PR'
            elif len(location) == 2:
                country = 'US'
            elif not location and assigned == 'No':
                country = 'US'  # For NPAs reserved to US, just say US
            elif not location and use == 'N':
                country = 'US'  # For US non-geographic codes, just say US
            elif npa == '670':
                # Fix Commonwealth of the Northern Mariana Islands (CNMI)
                country = 'MP'  # For some reason CNMI don't get a location
            else:
                print('Unknown location {} in US with NPA {}'
                      .format(location, npa))
        elif country == 'CANADA':
            country = 'CA'
        elif country == 'BAHAMAS':
            country = 'BS'
        elif country == 'BARBADOS':
            country = 'BB'
        elif country == 'ANGUILLA':
            country = 'AI'
        elif country == 'ANTIGUA/BARBUDA':
            country = 'AG'
        elif country == 'BRITISH VIRGIN ISLANDS':
            country = 'VG'
        elif country == 'CAYMAN ISLANDS':
            country = 'KY'
        elif country == 'GRENADA':
            country = 'GD'
        elif country == 'BERMUDA':
            country = 'BM'
        elif country == 'TURKS & CAICOS ISLANDS':
            country = 'TC'
        elif country == 'JAMAICA':
            country = 'JM'
        elif country == 'MONTSERRAT':
            country = 'MS'
        elif country == 'SINT MAARTEN':
            country = 'SX'
        elif country == 'ST. LUCIA':
            country = 'LC'
        elif country == 'DOMINICA':
            country = 'DM'
        elif country == 'ST. VINCENT & GRENADINES':
            country = 'VC'
        elif country == 'DOMINICAN REPUBLIC':
            country = 'DO'
        elif country == 'TRINIDAD AND TOBAGO':
            country = 'TT'
        elif country == 'ST. KITTS AND NEVIS':
            country = 'KN'
        elif country:
            print('Unknown NPA country: {} with NPA {}'.format(country, npa))

        if country:
            n0, n1, n2 = map(int, str(npa))
            npadict[n0][n1][n2] = country

    except IndexError:
        pass

npamap.write(pformat({k: dict(v) for k, v in npadict.items()}))
with open(out_file, 'w') as f:
    f.write(npamap.getvalue() + '\n')
print('Wrote ' + out_file)