Brexit Results Scraper: Gets current voting status.

euref.py

#!/usr/bin/env python

import re
import urllib2
import bs4

BASE_URL = 'http://www.bbc.co.uk/news/politics/eu_referendum/results/local/'
VOTES = re.compile(r'[0-9]+(?:,[0-9]+)*')

def get_urls():
    return [BASE_URL + chr(x) for x in range(97, 123)]

TOTAL_LEAVE = 0
TOTAL_REMAIN = 0

print '## Format: [place] | [leave votes] | [remain votes]'
print ''

for url in get_urls():
    try:
        content = urllib2.urlopen(url).read()
        soup = bs4.BeautifulSoup(content, 'html.parser')
        results = soup.find_all('div', class_='eu-ref-result-bar')
        for result in results:
            name = result.find('h3').get_text()
            leave = result.find('div', class_='eu-ref-result-bar__party--leave')
            remain = result.find('div', class_='eu-ref-result-bar__party--remain')
            lvotes = leave.find('div', class_='eu-ref-result-bar__votes').get_text().strip()
            rvotes = remain.find('div', class_='eu-ref-result-bar__votes').get_text().strip()
            lv = VOTES.search(lvotes)
            if lv:
                lvotes = lv.group(0)
                TOTAL_LEAVE += int(lvotes.replace(',', ''))
            rv = VOTES.search(rvotes)
            if rv:
                rvotes = rv.group(0)
                TOTAL_REMAIN += int(rvotes.replace(',', ''))
            print name.strip(), '|', lvotes, '|', rvotes
    except urllib2.HTTPError:
        pass

def prettify(n):
    if n < 1000:
        return str(n)
    return prettify(n // 1000) + ',' + '%03d' % (n % 1000)

print ''
print 'Total Votes |', prettify(TOTAL_LEAVE), '|', prettify(TOTAL_REMAIN)