Environmental Health Preston get postcodes

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import functools
import json
import re
from urlparse import urljoin

import requests
from requests import async
import lxml.html

import requests_cache
# Because I don't want to bother about persistence or explicitly saved state :)
# https://github.com/reclosedev/requests-cache
requests_cache.configure('env_health')


BASE_URL = 'http://www.environmentalhealthpreston.co.uk/'


def main():
    # Get 'moreinfo' urls from Zarino Zappia's scrapper https://scraperwiki.com/scrapers/environmental_health_preston/
    r = requests.get('https://api.scraperwiki.com/api/1.0/datastore/sqlite?format=jsonlist&name=environmental_health_preston&query=select%20url%20from%20%60eateries%60')
    urls = [url[0] for url in json.loads(r.text)['data']]
    results = {}

    def process_page(url_key, response):
        doc = lxml.html.fromstring(response.content)
        text = doc.xpath('//div[@class="content-text-sidebar"]//p[1]')[0].text_content()
        results[url_key] = retrieve_postcode(text)

    rs = [async.get(urljoin(BASE_URL, url),
                    hooks={'response': functools.partial(process_page, url)})
          for url in urls]
    async.map(rs, size=10)
    print json.dumps(results)


def retrieve_postcode(text):
    # credits: http://regexlib.com/REDetails.aspx?regexp_id=260&AspxAutoDetectCookieSupport=1
    m = re.search(r'([A-PR-UWYZ0-9][A-HK-Y0-9][AEHMNPRTVXY0-9]?[ABEHMNPRVWXY0-9]? {1,2}[0-9][ABD-HJLN-UW-Z]{2}|GIR 0AA)', text)
    if m:
        return m.group(0)
    return ''

if __name__ == '__main__':
    main()