Easy Web Scraping

This is a little script I use to email myself the latest Reality Check comic from a cron job.

#!/usr/bin/python
# Send new "Reality Check" image in email

from urllib import urlopen
import re
from smtplib import SMTP
from email.MIMEImage import MIMEImage
from email.MIMEMultipart import MIMEMultipart
from time import ctime

# My email
MYMAIL = "miki.tebeka@gmail.com"
# Find email image name
find_image = re.compile("reality\d+\.gif", re.M).search
BASE_URL = "http://www.unitedmedia.com/comics/reality"

def send_new():
    '''Send new image in email'''
    # Find
    im = find_image(urlopen(BASE_URL).read())
    if not im:
        raise ValueError("error: can't find image file in web page")
    image = im.group()

    # Full image URL
    url = BASE_URL + "/archive/images/" + image
    # Read image data
    image_data = urlopen(url).read()

    # Send it in email
    msg = MIMEMultipart()
    msg["Subject"] = "Reality check for %s " % ctime()
    msg["To"] = MYMAIL
    msg["From"] = MYMAIL
    att = MIMEImage(image_data)
    att.add_header("Content-Disposition", "attachment", filename=image)
    msg.attach(att)

    s = SMTP("my-mail-host")
    s.sendmail(MYMAIL, [MYMAIL], msg.as_string())
    s.close()

if __name__ == "__main__":
    try:
        send_new()
    except Exception, e:
        raise SystemExit("error: %s" % e)