scraper.py

import requests
import shutil

divids = ['101', '102', '103', '104', '105', '106', '107', '108', '109', '111', '112', '113', '114', '115', '117',
          '118', '119', '120', '121', '122', '124', '125', '126', '127', '128', '130', '131', '132', '133', '134',
          '135', '136', '137', '138', '139', '140', '144', '145', '146', '148', '149', '150', '151', '152', '153',
          '155', '156', '157', '158', '159', '160', '161', '162', '163', '164', '165', '166', '167', '168', '169',
          '170', '171', '172', '173', '174', '175', '176', '177', '178', '179', '180', '182', '183', '185', '186',
          '187', '188', '189', '190', '191', '192', '193', '194', '195', '196', '197', '198', '199', '200', '201',
          '203', '204', '205', '207', '208', '209', '210', '211', '212', '213', '214', '215', '216', '217', '218',
          '219', '220', '221', '222', '223', '224', '225', '226', '227', '228', '229', '230', '231', '232', '233',
          '234', '235', '236', '237', '238', '239', '240', '242', '243', '244', '245', '246', '247', '248', '249',
          '250', '251', '252', '302', '304', '305', '306', '307', '309', '310', '311', '312', '315', '316', '317']
outfolder = "C:/temp/shapes/votes/"
for i in divids:
    csv = requests.get('http://vtr.aec.gov.au/Downloads/SenateDivisionFirstPrefsByPollingPlaceDownload-20499-{}.csv'.format(i), stream=True)
    with open(outfolder+i+'.csv', 'wb') as out_file:
        shutil.copyfileobj(csv.raw, out_file)
    del csv

who_voted_for.py

import csv
from collections import defaultdict, Counter
import pprint
from glob import glob

pp = pprint.PrettyPrinter(indent=4)


def div(x, y):
    if y == 0:
        return 0
    else:
        return x / y


def get_pct_of(d, party, divisions):
    return div(divisions[d][party], divisions[d]['total'])


party = "Pauline Hanson's One Nation"


def make_divisions(col, subdiv, fnames, partycol):
    divisions = defaultdict(Counter)
    for fname in fnames:
        with open(fname, 'r') as infile:
            infile.readline()
            csvReader = csv.DictReader(infile)
            for row in csvReader:
                division = row[subdiv]
                divisions[division]['total'] += float(row[col])
                divisions[division][row[partycol]] += float(row[col])
    return divisions


def by_electorate():
    divisions = make_divisions('TotalVotes', 'DivisionNm',
                               ['C:/Users/Jonathan/Downloads/SenateFirstPrefsByDivisionByVoteTypeDownload-20499.csv'],
                               'PartyName')
    print("Division,Percent")
    for i in sorted(divisions, key=lambda x: get_pct_of(x, party, divisions)):
        print("{0},{1:.2f}%".format(i, get_pct_of(i, party, divisions) * 100))


def by_polling_place():
    divisions = make_divisions('OrdinaryVotes',
                               'PollingPlaceNm',
                               glob('C:/temp/shapes/votes/*.csv'),
                               'PartyNm')
    print("Booth,Percent")
    for i in sorted(divisions, key=lambda x: get_pct_of(x, party, divisions)):
        print("{0},{1:.2f}%".format(i, get_pct_of(i, party, divisions) * 100))

if __name__ == "__main__":
    by_polling_place()

    # by_electorate()