python imaplib to get gmail inbox subjects titles and sender name

I'm using pythons imaplib to connect to my gmail account. I want to retrieve the top 15 messages (unread or read, it doesn't matter) and display just the subjects and sender name (or address) but don't know how to display the contents of the inbox.

Here is my code so far (successful connection)

import imaplib

mail = imaplib.IMAP4_SSL('imap.gmail.com')
mail.login('mygmail@gmail.com', 'somecrazypassword')
mail.list()
mail.select('inbox')

#need to add some stuff in here

mail.logout()

I believe this should be simple enough, I'm just not familiar enough with the commands for the imaplib library. Any help would be must appreciated...

UPDATE thanks to Julian I can iterate through each message and retrieve the entire contents with:

typ, data = mail.search(None, 'ALL')
for num in data[0].split():
   typ, data = mail.fetch(num, '(RFC822)')
   print 'Message %s\n%s\n' % (num, data[0][1])
mail.close()

but I'm wanting just the subject and the sender. Is there a imaplib command for these items or will I have to parse the entire contents of data[0][1] for the text: Subject, and Sender?

UPDATE OK, got the subject and sender part working but the iteration (1, 15) is done by desc order apparently showing me the oldest messages first. How can I change this? I tried doing this:

for i in range( len(data[0])-15, len(data[0]) ):
     print data

but that just gives me None for all 15 iterations... any ideas? I've also tried mail.sort('REVERSE DATE', 'UTF-8', 'ALL') but gmail doesnt support the .sort() function

UPDATE Figured out a way to do it:

#....^other code is the same as a开发者_C百科bove except need to import email module
mail.select('inbox')
typ, data = mail.search(None, 'ALL')
ids = data[0]
id_list = ids.split()
#get the most recent email id
latest_email_id = int( id_list[-1] )

#iterate through 15 messages in decending order starting with latest_email_id
#the '-1' dictates reverse looping order
for i in range( latest_email_id, latest_email_id-15, -1 ):
   typ, data = mail.fetch( i, '(RFC822)' )

   for response_part in data:
      if isinstance(response_part, tuple):
          msg = email.message_from_string(response_part[1])
          varSubject = msg['subject']
          varFrom = msg['from']

   #remove the brackets around the sender email address
   varFrom = varFrom.replace('<', '')
   varFrom = varFrom.replace('>', '')

   #add ellipsis (...) if subject length is greater than 35 characters
   if len( varSubject ) > 35:
      varSubject = varSubject[0:32] + '...'

   print '[' + varFrom.split()[-1] + '] ' + varSubject

this gives me the most recent 15 message subject and sender address in decending order as requested! Thanks to all who helped!

    c.select('INBOX', readonly=True)

    for i in range(1, 30):
        typ, msg_data = c.fetch(str(i), '(RFC822)')
        for response_part in msg_data:
            if isinstance(response_part, tuple):
                msg = email.message_from_string(response_part[1])
                for header in [ 'subject', 'to', 'from' ]:
                    print '%-8s: %s' % (header.upper(), msg[header])

This should give you an idea on how to retrieve the subject and from?

This was my solution to get the useful bits of information from emails:

import datetime
import email
import imaplib
import mailbox


EMAIL_ACCOUNT = "your@gmail.com"
PASSWORD = "your password"

mail = imaplib.IMAP4_SSL('imap.gmail.com')
mail.login(EMAIL_ACCOUNT, PASSWORD)
mail.list()
mail.select('inbox')
result, data = mail.uid('search', None, "UNSEEN") # (ALL/UNSEEN)
i = len(data[0].split())

for x in range(i):
    latest_email_uid = data[0].split()[x]
    result, email_data = mail.uid('fetch', latest_email_uid, '(RFC822)')
    # result, email_data = conn.store(num,'-FLAGS','\\Seen') 
    # this might work to set flag to seen, if it doesn't already
    raw_email = email_data[0][1]
    raw_email_string = raw_email.decode('utf-8')
    email_message = email.message_from_string(raw_email_string)

    # Header Details
    date_tuple = email.utils.parsedate_tz(email_message['Date'])
    if date_tuple:
        local_date = datetime.datetime.fromtimestamp(email.utils.mktime_tz(date_tuple))
        local_message_date = "%s" %(str(local_date.strftime("%a, %d %b %Y %H:%M:%S")))
    email_from = str(email.header.make_header(email.header.decode_header(email_message['From'])))
    email_to = str(email.header.make_header(email.header.decode_header(email_message['To'])))
    subject = str(email.header.make_header(email.header.decode_header(email_message['Subject'])))

    # Body details
    for part in email_message.walk():
        if part.get_content_type() == "text/plain":
            body = part.get_payload(decode=True)
            file_name = "email_" + str(x) + ".txt"
            output_file = open(file_name, 'w')
            output_file.write("From: %s\nTo: %s\nDate: %s\nSubject: %s\n\nBody: \n\n%s" %(email_from, email_to,local_message_date, subject, body.decode('utf-8')))
            output_file.close()
        else:
            continue

For those looking for how to check mail and parse the headers, this is what I used:

def parse_header(str_after, checkli_name, mailbox) :
    #typ, data = m.search(None,'SENTON', str_after)
    print mailbox
    m.SELECT(mailbox)
    date = (datetime.date.today() - datetime.timedelta(1)).strftime("%d-%b-%Y")
    #date = (datetime.date.today().strftime("%d-%b-%Y"))
    #date = "23-Jul-2012"

    print date
    result, data = m.uid('search', None, '(SENTON %s)' % date)
    print data

    doneli = []
    for latest_email_uid in data[0].split():
        print latest_email_uid
        result, data = m.uid('fetch', latest_email_uid, '(RFC822)')
        raw_email = data[0][1]

        import email
        email_message = email.message_from_string(raw_email)
        print email_message['To']
        print email_message['Subject']
        print email.utils.parseaddr(email_message['From'])
        print email_message.items() # print all headers

I was looking for a ready made simple script to list last inbox via IMAP without sorting through all messages. The information here is useful, though DIY and misses some aspects. First, IMAP4.select returns message count. Second, subject header decoding isn't straightforward.

#! /usr/bin/env python
# -*- coding: utf-8 -*-


import imaplib
import email
from email.header import decode_header
import HTMLParser


# to unescape xml entities
_parser = HTMLParser.HTMLParser()

def decodeHeader(value):
  if value.startswith('"=?'):
    value = value.replace('"', '')

  value, encoding = decode_header(value)[0]
  if encoding:
    value = value.decode(encoding)

  return _parser.unescape(value)

def listLastInbox(top = 4):
  mailbox = imaplib.IMAP4_SSL('imap.gmail.com')
  mailbox.login('mygmail@gmail.com', 'somecrazypassword')

  selected = mailbox.select('INBOX')
  assert selected[0] == 'OK'
  messageCount = int(selected[1][0])

  for i in range(messageCount, messageCount - top, -1):
    reponse = mailbox.fetch(str(i), '(RFC822)')[1]
    for part in reponse:
      if isinstance(part, tuple):
        message = email.message_from_string(part[1])
        yield {h: decodeHeader(message[h]) for h in ('subject', 'from', 'date')}

  mailbox.logout()


if __name__ == '__main__':
  for message in listLastInbox():
    print '-' * 40
    for h, v in message.items():
      print u'{0:8s}: {1}'.format(h.upper(), v)

BODY gets almost everything and marks the message as read. BODY[<parts>] gets just those parts. BODY.PEEK[<parts>] gets the same parts, but doesn't mark the message read. <parts> can be HEADER or TEXT or HEADER.FIELDS (<list of fields>) or HEADER.FIELDS.NOT (<list of fields>)

This is what I use: typ, data = connection.fetch(message_num_s, b'(BODY.PEEK[HEADER.FIELDS (SUBJECT FROM)])')

`

def safe_encode(seq):
    if seq not in (list,tuple):
        seq = [seq]
    for i in seq:
        if isinstance(i, (int,float)):
            yield str(i).encode()
        elif isinstance(i, str):
            yield i.encode()
        elif isinstance(i, bytes):
            yield i
        else:
            raise ValueError

def fetch_fields(connection, message_num, field_s):
    """Fetch just the fields we care about. Parse them into a dict"""
    if isinstance(field_s, (list,tuple)):
        field_s = b' '.join(safe_encode(field_s))
    else:
        field_s = tuple(safe_encode(field_s))[0]

    message_num = tuple(safe_encode(message_num))[0]

    typ, data = connection.fetch(message_num, b'(BODY.PEEK[HEADER.FIELDS (%s)])'%(field_s.upper()))
    if typ != 'OK':
        return typ, data  #change this to an exception if you'd rather

    items={}
    lastkey = None
    for line in data[0][1].splitlines():
        if b':' in line:
            lastkey, value = line.strip().split(b':', 1)
            lastkey = lastkey.capitalize()
            #not all servers capitalize the same, and some just leave it
            #as however it arrived from some other mail server.

            items[lastkey]=value
        else:
            #subject was so long it ran onto the next line, luckily it didn't have a ':' in it so its easy to recognize.
            items[lastkey]+=line
            #print(items[lastkey])
    return typ, items
`

You drop it into your code example: by replacing the call to 'mail.fetch()' with fetch_fields(mail, i, 'SUBJECT FROM') or fetch_fields(mail, i, ('SUBJECT' 'FROM'))

Adding to all the above answers.

import imaplib
import base64
import os
import email

if __name__ == '__main__':
    email_user = "email@domain.com"
    email_pass = "********"
    mail = imaplib.IMAP4_SSL("hostname", 993)
    mail.login(email_user, email_pass)
    mail.select()
    type, data = mail.search(None, 'ALL')
    mail_ids = data[0].decode('utf-8')
    id_list = mail_ids.split()
    mail.select('INBOX', readonly=True)
    for i in id_list:
        typ, msg_data = mail.fetch(str(i), '(RFC822)')
        for response_part in msg_data:
            if isinstance(response_part, tuple):
                msg = email.message_from_bytes(response_part[1])
                print(msg['from']+"\t"+msg['subject'])

This will give you the email's from and subject name.