Parses event details out from the Hay Festival website

Haymaker.py

from bs4 import BeautifulSoup
import json
import requests
import HTMLParser

class FestivalEvent(object):
    pass

def cleanText(txt):
    return txt.strip().replace(u'\u2013', '-').replace(u'\u2019', '\'')

def parsePage(url):

    html = requests.get(url).text

    try:
        soup = BeautifulSoup(html)

        for div in soup.find_all("div","event"):
            fe = FestivalEvent()
            fe.event_title = cleanText(div.h2.a.text) # HACK - gets around bad char in HTML
            if (div.h3):
                fe.event_subtitle = cleanText(div.h3.text)
            if len(div.find_all("p")) > 1:
                fe.event_blurb = cleanText(div.find_all("p")[1].text) # big assumption made here that the second <p> is the blurb!!!
            if (div.find("span",{"class","variantprice"})):
                fe.event_price = cleanText(div.find("span",{"class","variantprice"}).text)
            else :
                fe.event_price = "Sold out / Price unavailable"
            fe.event_url = "https://www.hayfestival.com/" + div.h2.a['href']
            fe.event_number = cleanText(div.find("span",{"class","event-number"}).text)
            fe.event_venue = cleanText(div.find("span",{"class","event-venue"}).text)
            fe.event_time = cleanText(div.find("span",{"class","event-time"}).text)
            yield fe

    except HTMLParser.HTMLParseError, e:
        print "Unable to parse \"" + url + "\""
        print e

url2 = "http://e2.truffler.net/[...]" #TODO: use your Truffler.net account details

for i in range(1,39):

    print "Parsing page " + str(i)
    url = "https://www.hayfestival.com/m-57-hay-festival-2012.aspx?pagenum=%s" % str(i)
    
    for event in parsePage(url):
        event_json = json.dumps(event.__dict__)
        print "%(num)s: %(date)s :\"%(title)s\" (%(venue)s)" %  {
            "num":event.event_number, 
            "date":event.event_time, 
            "title":event.event_title,
            "venue":event.event_venue 
            }
        response = requests.post(url2, data=event_json)
        if (response.status_code > 299):
            print response.text

NB before commenting on this, please bear in mind that it is, by design, a massive hack.