#!/usr/bin/python

import csv
import email
import getopt
import os
import sys
import time
from imaplib import *

# Sample usage:
# ./search_queries.py --passfile=[FILENAME] \
#                     --username=[USERNAME] \
#                     --host=[DOMAIN] \
#                     --outfile=[FILENAME]

EMAIL_SUBJECT = 'Analytics asirap.net' 
IMAP_MB = "INBOX"
IMAP_HOST = ""
IMAP_PASS = ""
IMAP_USER = ""
OUTFILE = ""

# Retrieve server, username, and password to authenticate to the IMAP server.
try:
  opts, args = getopt.getopt(sys.argv[1:], 'p:u:h:o',
                             ["passfile=", "username=", "host=", "outfile="])
except getopt.GetoptError, err:
  print str(err)
  sys.exit(2)
for o, a in opts:
  if o == "--passfile":
    f = open(os.path.expanduser(a))
    IMAP_PASS = f.read().strip()
    f.close()
  elif o == "--username":
    IMAP_USER = a
  elif o == "--host":
    IMAP_HOST = a
  elif o == "--outfile":
    OUTFILE = a
  else:
    assert False, "Unknown option"

# Connect to your IMAP server.
server = IMAP4_SSL(IMAP_HOST)
server.login(IMAP_USER, IMAP_PASS)
mboxes = server.list()[1]
inbox = server.select(IMAP_MB)

# Find any Analytics reports in your mailbox.
typ, data = server.search(None, 'SUBJECT', EMAIL_SUBJECT)
msg_nums = [int(i) for i in data[0].split()]

# Process the most recent Analytics report, naively the one that matches with 
# the highest message id.
typ, data = server.fetch(str(max(msg_nums)), '(RFC822)')
msg = email.message_from_string(data[0][1])
date = msg['Date'] or time.strftime("%Y-%m-%d")
dtime = email.Utils.parsedate_tz(date)
date = time.strftime('%Y-%m-%d', dtime[:9])    

# Iterate over all message parts and find, read, and decode the report
# attachment.
for part in msg.walk():
  if part.get_content_type() == "application/octet-stream":
    decoded = part.get_payload(decode=1)

# Create a CSV reader from our CSV string.
reader = csv.reader(decoded.split(os.linesep))
lines = []
for r in reader:
  lines.append(r)
  
queries = []
for i in range(len(lines)):
  elems = lines[i]
  if len(elems) != 2:
    continue
  # ['Keyword', 'Entrances'] is where the queries start in our CSV file
  if elems[0] == 'Keyword' and elems[1] == 'Entrances':
    # The first query is always unset for me, so I skip over it.
    # The last query is just a demarc line, so I also skip that.
    queries = lines[i+2:len(lines)-1]
    break

# Personalize your formatting however...
f = open(OUTFILE, 'w')
for k in queries:
  f.write("%s... %s<br>" % (k[0], k[1]))