watch shanghai german consulate termin

terminwatch.py

#!/usr/bin/env python
#-*- coding: utf-8 -*-#
import smtplib, time, urllib2
from bs4 import BeautifulSoup
from email.mime.text import MIMEText

def mailme(message):
    msg = MIMEText(message)
    msg['Subject'] = 'German Consu Termin!'
    msg['From'] = 'fox@antares.metaphox.com'
    msg['To'] = '<targeemailaddress>'
    s = smtplib.SMTP('gmail-smtp-in.l.google.com')
    s.sendmail('fox@antares.metaphox.com', ['<targeemailaddress>'], msg.as_string())
    s.quit()

def tellme(message, direct=False):
    #print message
    mailme(message)

def watch():
    MONATE = ['06.2012', '07.2012']
    FAILTXT = [u'An diesem Tag k\xf6nnen keine Termine gebucht werden',
               u'An diesem Tag sind alle Termine belegt',
               u'An diesem Tag werden keine Termine angeboten',
               u'Termine f\xfcr diesen Tag k\xf6nnen nicht gebucht werden',
               u'All appointments for this date are already taken',
               u'On this date bookings are not possible',
               u'Appointments for this date cant be booked',
               u'For this date no appointments are offered']
    FAILTXT_DAY = [u'In diesem Zeitraum sind keine Termine frei',
                   u'No appointments available for this period']
    #BASEURL = 'https://service2.diplo.de/rktermin/extern/appointment_showMonth.do?locationCode=shan&realmId=96&categoryId=183&dateStr=01.{0}.{1}'
    #cate 183 is for "normal" termin, cate 460 is for the "special" ones
    BASEURL = "https://service2.diplo.de/rktermin/extern/appointment_showMonth.do?locationCode=shan&realmId=96&categoryId=460&dateStr=01.{0}.{1}"
    DATEURL = 'https://service2.diplo.de/rktermin/extern/appointment_showDay.do?locationCode=shan&realmId=96&categoryId=460&dateStr={0}.{1}.{2}'

    dates = []
    for mon in MONATE:
        mon_view_f = urllib2.urlopen( BASEURL.format( *mon.split('.') ) )
        soup = BeautifulSoup(mon_view_f.read())
        for each in soup.find_all('h4'):
            txt = each.find_parent('div').find_next_sibling('div').get_text().strip()
            #see if txt has any of FAILTXT, then reduce the result boolean list
            if not True in map(lambda x : x in txt, FAILTXT):
                print txt
                dates.append(each.get_text())

    if len(dates):
        days = [day.split(' ')[1] for day in dates]
        urls = [(day, DATEURL.format( *day.split('.') )) for day in days]
        links = []
        for day, url in urls:
            tellme('{0} -- {1}'.format(day, url))
"""
UNTESTED
# print "Opening %s" % url
day_view_f = urllib2.urlopen(url)
soup_day = BeautifulSoup(day_view_f.read())
idx = 1
for each in soup_day.find_all('h4'):
  anchortag = each.find_parent('div').find_next_sibling('div').find('a')
  if anchortag:
    tellme('{0} ({2}) https://service2.diplo.de/rktermin/{1}'.format(day, anchortag.get('href'), idx))
    idx += 1
"""

if __name__ == '__main__':
    cnt = 0
    error_cnt = 0
    tellme('terminwatch starts to run')
    while 1:
        try:
            watch()
        except urllib2.URLError:
            error_cnt += 1
            if error_cnt % 20 == 0:
                tellme('Termin watch is still running, %s times checked, %s errors occured.' % (cnt, error_cnt))
        cnt += 1
        if cnt % 480  == 0:
            tellme('Termin watch is still running, %s times checked so far, %s errors occured.' % (cnt, error_cnt))
        time.sleep(30)    

is it still alive?) cause i have tested but it doesn't work)