Mining Mailinator 2, Web Scraping Public Email

#Original Author: http://www.malos-ojos.com/?p=445
#Much Thanks!
#Forked from: http://cl.ly/3Jo7
#updated by gremlin 13 MAR 2013
#recognizing, no error handling, ungraceful parsing. Have fun!

import urllib
import re
import string
import csv

words = []
mails = []
counter = 0

outWriter = csv.writer(open('data.csv', 'wb'), delimiter=',')
file = open('words.txt', 'r')

for line in file:
    words.append(line)
    counter += 1

print "\n"
print "imported %i word(s)" % counter
counter = 0

for word in words:
    o = urllib.FancyURLopener({})
    c = o.open("http://www.mailinator.com/rss.jsp?email=%s" % word)
    s = c.read()

    r = re.findall('item\srdf:about=\"(.*)">', s)

    for item in r:
        n = string.replace(item, 'amp;', '')
        #Experimental View
        #n = string.replace(n, 'displayemail', 'displayemail1')
        x = re.findall('@([^&]*)', n) #remove mail domain ex. '@mailinator.com'
        y = '@' + x[0]
        n = string.replace(n, y, '')
        mails.append(n)
        counter += 1

print "mined %i e-mail(s)" % counter
counter = 0

for item in mails:
    print item
    o = urllib.FancyURLopener({})
    c = o.open(item)
    s = c.read()

    t = re.search('<td\sclass=\"label\">To\:<\/td>\s*<td\sclass=\"data\"\swidth\=\"300px\">(.*)\s*<\/td>', s)
    f = re.search('<td\sclass=\"label\">From\:<\/td>\s*<td\sclass=\"data\">(.*)\s*<\/td>', s)
    j = re.search('<td\sclass=\"label\">Subject\:<\/td>\s*<td\sclass=\"data\">(.*)\s*<\/td>', s)

    if t and f and j:
        outWriter.writerow([t.group(1), f.group(1), j.group(1), item])
        counter += 3

print "wrote %i pieces of data to csv" % counter
print "\n"
file.close()