Termin catcher

termin_catcher.py

#!/usr/bin/python2
# -*- coding: utf-8 -*-

import BeautifulSoup
import urllib
import re
from time import sleep
import webbrowser
import sys


SLEEP = 30


def main(url):
    days_prev = []

    while True:

        html = BeautifulSoup.BeautifulSoup(urllib.urlopen(url))
        months = html.findAll('div',
                              {'class': 'calendar-month-table span6'})

        days = []
        for m in months:
            days += [x.a['href'] for x in m.findAll('td',
                     {'class': 'buchbar '})]

        print 'Found {0} days with termins'.format(len(days))

        if not days:                                                                                    
            print 'No termins are avaliable in your timerange. Skipping sanity check..' 
        elif not days_prev:
            print '''TEST: I will open an earliest termin now.
Please check your browser in {0} seconds'''.format(SLEEP)
            days.pop(0)
            days_prev = days

        new_termins = set(days) - set(days_prev)
        if new_termins:
            for t in new_termins:
                webbrowser.open_new('''http://service.berlin.de/
terminvereinbarung/termin/{0}'''.format(t))
            days_prev = days

        sleep(SLEEP)


if __name__ == '__main__':

    if len(sys.argv) < 2:
        url = raw_input('Enter termin url (http://service.berlin.de/...): ')
    else:
        url = sys.argv[1]
    main(url)