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

Solution 1:

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

    for i inrange(1, 30):
        typ, msg_data = c.fetch(str(i), '(RFC822)')
        for response_part in msg_data:
            ifisinstance(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?

Solution 2:

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())

forx 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 detailsfor 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

Solution 3:

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"printdate
    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

Solution 4:

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()

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

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

  return _parser.unescape(value)

deflistLastInbox(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 inrange(messageCount, messageCount - top, -1):
    reponse = mailbox.fetch(str(i), '(RFC822)')[1]
    for part in reponse:
      ifisinstance(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'-' * 40for h, v in message.items():
      printu'{0:8s}: {1}'.format(h.upper(), v)

Solution 5:

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:
            ifisinstance(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.