#!/usr/bin/python

import sys
import imaplib
import getpass
import email
import datetime
import re
from bs4 import BeautifulSoup

password = open('password','r').read().strip()

'''

urlregex = re.compile(
    r'(?:http|ftp)s?://' # http:// or https://
    r'(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+(?:[A-Z]{2,6}\.?|[A-Z0-9-]{2,}\.?)|' #domain...
    r'localhost|' #localhost...
    r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})' # ...or ip
    r'(?::\d+)?' # optional port
    r'(?:/?|[/?]\S+)', re.IGNORECASE)'''
urlregex = re.compile("(?P<url>https?://[^\s]+)")

def isValidUrl(url):
    if urlregex.match(url) is not None:
        #print re.compile('.*\.(.*)$').match(url).group(1)
        return True;
    return False

def getlinks(page):
    match = urlregex.match(page)
    if match is None:
        return []
    else:
        return match.groups()
    '''soup = BeautifulSoup(page,'html.parser')
    links = soup.findAll('a',href=True)
    output = []
    print links
    for l in links:
        if isValidUrl(l['href']):
            output.append(l['href'])
    return output'''

def process_mailbox(M):
  rv, data = M.search(None, "ALL")
  if rv != 'OK':
      print "No messages found!"
      return
  count = 0
  for num in data[0].split():
      #rv, data = M.fetch(num, '(RFC822)')
      rv, data = M.fetch(num, '(BODY[1])')
      if rv != 'OK':
          print "ERROR getting message", num
          return

      msg = email.message_from_string(data[0][1])
      msg = str(str(msg).decode('quopri').replace('\n',' ').replace('\r',' '))
      print 'MESSAGE: '
      print msg
      #htmlregex = re.compile(r'<!DOCTYPE.*<\/html>')
      #msg = msg[msg.find('<!DOCTYPE'):(msg.find('</html>')+7)]
      print 'LINKS: '
      #msg = msg.decode('quopri')
      print getlinks(msg)
      count += 1
      if count > 5:
        break
      '''print 'Message %s: %s' % (num, msg['Subject'])
      print 'Raw Date:', msg['Date']
      date_tuple = email.utils.parsedate_tz(msg['Date'])
      if date_tuple:
          local_date = datetime.datetime.fromtimestamp(
              email.utils.mktime_tz(date_tuple))
          print "Local Date:", \
              local_date.strftime("%a, %d %b %Y %H:%M:%S")'''

MAIL_SERVERS = {'gmail': 'imap.gmail.com',
                'yahoo': 'imap.mail.yahoo.com',
                'aol': 'imap.aol.com'}

M = imaplib.IMAP4_SSL(MAIL_SERVERS['yahoo'])
try:
    M.login('npipitone1234@yahoo.com', password)
except imaplib.IMAP4.error:
    print "LOGIN FAILED!!! "
    # ... exit or deal with failure...

rv, mailboxes = M.list()
if rv == 'OK':
    print "Mailboxes:"
    print mailboxes

rv, data = M.select("INBOX")
if rv == 'OK':
    print "Processing mailbox...\n"
    process_mailbox(M) # ... do something with emails, see below ...
    M.close()
M.logout()