Quick-and-dirty script that notifies you by mail when a webpage of interest changes

updatedyet.py

import cPickle
import urllib2
import hashlib
from datetime import datetime
import smtplib
from email.mime.text import MIMEText

PICKLE_FILE = '/home/justin/tools/updatedyet.pkl'
MAIL_ON_CHANGE = ['[email protected]']
MAIL_FROM = '[email protected]'
URLS_OF_INTEREST = [
    'http://store.apple.com/nl/browse/home/shop_iphone/family/iphone',
    'http://vwees.net/justin/test.html'
]

def fetch_and_hash_content(url):
    try:
        contents = urllib2.urlopen(url).read()
    except:
        return None

    hash = hashlib.sha1(contents)
    return hash.hexdigest()


def notify_of_change(url, prev_hash, prev_date, curr_hash, curr_date):
    message = MIMEText('Contents of %s changed.\n\nPreviously (%s): %s\nNow (%s):'\
        ' %s' % (url, prev_date, prev_hash, curr_date, curr_hash))
    message['Subject'] = 'updatedyet.py: contents of %s changed' % url
    message['From'] = MAIL_FROM

    for mailaddress in MAIL_ON_CHANGE:
        message['To'] = mailaddress
        s = smtplib.SMTP('localhost')
        s.sendmail(MAIL_FROM, [mailaddress], message.as_string())
        s.quit()


def load_pickle(pickle_location=PICKLE_FILE):
    try:
        pickle = cPickle.load(open(pickle_location, 'r'))
    except:
        pickle = {}

    return pickle


def save_pickle(obj, pickle_location=PICKLE_FILE):
    cPickle.dump(obj, open(pickle_location, 'w'))


def check_if_updated(urls=URLS_OF_INTEREST):
    prev_hashes = load_pickle()

    for url in urls:
        current_time = datetime.utcnow()
        current_hash = fetch_and_hash_content(url)

        if not current_hash:
            continue

        if url not in prev_hashes:
            prev_hashes[url] = []
        else:
            prev_sample = prev_hashes[url][-1]
            if prev_sample[1] != current_hash:
                notify_of_change(url, prev_sample[1], prev_sample[0],\
                    current_hash, current_time)

        prev_hashes[url].append((current_time, current_hash))

    save_pickle(prev_hashes)

if __name__ == '__main__':
    check_if_updated()