i want to downloap PJ from an email so i write this code
import imaplib, email, os
from time import sleep
user='my_email'
password = 'secret'
imap_url = 'Outlook.office365.com'
con = imaplib.IMAP4_SSL(imap_url)
con.login(user,password)
def get_attachments(msg):
for part in msg.walk():
if part.get_content_maintype()=='multipart':
continue
if part.get('Content-Disposition') is None:
continue
fileName = part.get_filename()
if bool(fileName):
filePath = os.path.join(attachment_dir, fileName)
with open(filePath,'wb') as f:
f.write(part.get_payload(decode=True))
attachment_dir = "D:/TOUT/DATANALYSE/email_python/attachement/"
never_stop = True
while never_stop:
last_email_id = search('FROM', "kvaccarin#datanalyse.fr", con)[0].split()[-1]
typ, data = con.fetch(last_email_id, '(RFC822)')
msg = email.message_from_bytes(data[0][1])
get_attachments(msg)
time.sleep(12*60*60)
this code works when i run on Jupyter but when i want to run this code with Sublime Texte i have this error:
NameError: name 'search' is not defined
This fonction search() is not the fonction from re but it's the fonction from IMAP
Someone know how to fix it?
It's the beginning of the answers... but it's something!
Thanks to Max, I understand the error on the first Question, So to fix it I define a new function search_data():
def search_data(key,value,con):
result, data = con.search(None,key,'"{}"'.format(value))
return data
and when I run the same code with the use of this function like that:
import imaplib, email, os
from time import sleep
user='my_email'
password = 'secret'
imap_url = 'Outlook.office365.com'
con = imaplib.IMAP4_SSL(imap_url)
con.login(user,password)
def get_attachments(msg):
for part in msg.walk():
if part.get_content_maintype()=='multipart':
continue
if part.get('Content-Disposition') is None:
continue
fileName = part.get_filename()
if bool(fileName):
filePath = os.path.join(attachment_dir, fileName)
with open(filePath,'wb') as f:
f.write(part.get_payload(decode=True))
def search_data(key,value,con):
result, data = con.search(None,key,'"{}"'.format(value))
return data
attachment_dir = "D:/TOUT/DATANALYSE/email_python/attachement/"
never_stop = True
while never_stop:
last_email_id = search_data('FROM', "kvaccarin#datanalyse.fr", con)[0].split()[-1]
typ, data = con.fetch(last_email_id, '(RFC822)')
msg = email.message_from_bytes(data[0][1])
get_attachments(msg)
time.sleep(12*60*60)
there still have an error:
error: command SEARCH illegal in state AUTH, only allowed in states SELECTED
I know it's the beginning of the answer but it perhaps helps to have the entire answer!
So I've been trying to make a code to print my Gmail inbox onto a website. I want to further develop this to only contain certain data from the email and write it onto a database. However, it does not seem to me that there is anything wrong with the code, but the localhost:8080 (The port I'm using) does not load at all. The browser has the loading icon when trying to access the page, but it does not load, even after hours. Command line does not respond with any errors. I also have the GMAIL imap settings correctly, and I have tried it with Outlooks email as well. Here is the code:
import webapp2
import smtplib
import time
import imaplib
import email
class ReadMail(webapp2.RequestHandler):
def get(self):
mail = imaplib.IMAP4('xxx#gmail.com',993)
mail.login('email#gmail.com','password')
type, data = mail.search(None, 'ALL')
mail_ids = data[0]
id_list = mail_ids.split()
first_email_id = int(id_list[0])
latest_email_id = int(id_list[-1])
for i in range(latest_email_id,first_email_id, -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])
email_subject = msg['subject']
email_from = msg['from']
self.response.headers["Content-Type"] = "text/plain"
self.response.write("From:" + email_from)
self.response.write("Subject:" + email_subject)
routes = [('/', ReadMail),]
app = webapp2.WSGIApplication(routes, debug=True)
App.yml is correctly setup as well. This code works with something really simple, such as only containing a print "this". Hopefully someone can help with my problem, thanks in advance!
So after a while I got it working by making my own WSGI application file instead of using the webapp2. There are still some issues such as the message being formatted wrong, but this is my code now:
from pyramid.config import Configurator
from pyramid.response import Response
import email, getpass, imaplib, os, re
import sys
detach_dir = "C:\OTHERS\CS\PYTHONPROJECTS"
def imaptest(request):
m = imaplib.IMAP4_SSL("imap.gmail.com")
m.login("testi.protokolla#gmail.com", "testiprotokolla221")
m.select("INBOX")
resp, items = m.search(None, '(FROM "vallu.toivonen96#gmail.com")')
items = items [0].split()
my_msg = []
msg_cnt = 0
break_ = False
for emailid in items[::1]:
resp, data = m.fetch(emailid, "(RFC822)")
if ( break_ ):
break
for response_part in data:
if isinstance(response_part, tuple):
msg = email.message_from_string(response_part[1])
varSubject = msg['subject']
varDate = msg['date']
if varSubject[0] == '$':
r, d = m.fetch(emailid, "(UID BODY[TEXT])")
ymd = email.utils.parsedate(varDate)[0:3]
my_msg.append([ email.message_from_string(d[0][1]), ymd])
msg_cnt += 1
# Print as HTML
return Response(
'Content-Type': 'text/html'
"Your latest Email:" + str(msg)
)
config = Configurator()
config.add_route('imaptest', '/imaptest')
config.add_view(imaptest, route_name='imaptest')
app = config.make_wsgi_app()
Below is the code that is supposed to read my Gmail account.
import smtplib
import time
import imaplib
import email
from reportlab.pdfgen import canvas
ORG_EMAIL = '#gmail.com'
FROM_EMAIL = 'amitesh.sahay#gmail.com'
FROM_PWD = '<my_password>'
SMTP_SERVER = 'imap.gmail.com'
SMTP_PORT = 993
# -------------------------------------------------
#
# Utility to read email from Gmail Using Python
#
# ------------------------------------------------
def read_email_from_gmail():
try:
mail = imaplib.IMAP4_SSL(SMTP_SERVER)
mail.login(FROM_EMAIL,FROM_PWD)
mail.select('inbox')
type1, data = mail.search(None, 'ALL')
mail_ids = data[0]
id_list = mail_ids.split()
first_email_id = int(id_list[0])
latest_email_id = int(id_list[-1])
for i in range(latest_email_id,first_email_id, -1):
type1, data = mail.fetch(i, '(RFC822)' )
for response_part in data:
if isinstance(response_part, tuple):
msg = email.message_from_string(response_part[1])
email_subject = msg['subject']
email_from = msg['from']
print('From : ' + email_from + '\n')
print('Subject : ' + email_subject + '\n')
except ValueError:
print("Oops! That was no valid mailbox. Try again...")
When I execute the code, it runs without throwing any error, but it's not giving any output as well. I am using python 3.6 and Installed all the python package that comes inbuilt within PyCharm. Is there anything that somebody can point out which could be a probable issue?
Please let me know if any further details are required.
I have a Python script to move messages with a certain subject. The messages get marked as read and I don't want them to be marked as read. What part of the script marks them as read and how do I make it not mark as read?
Also, I'm not too sure what I am doing yet, so if there is any redundant code or errors please let me know.
import getpass
from Crypto.Hash import MD5
import sys
import imaplib
import email
import re
password = getpass.getpass()
match = "redacted"
username = "redacted"
dest = "000"
pattern_uid = re.compile('\d+ \(UID (?P<uid>\d+)\)')
def md5(message):
hash = MD5.new()
hash.update(message)
return hash.hexdigest()
md5 = md5(password)
if md5 == match:
pass
else:
print "Mismatch"
sys.exit()
M = imaplib.IMAP4_SSL("mail.redacted.com", 993)
M.login(username, password)
M.select()
typ, data = M.search(None, 'ALL')
M.select('Inbox')
msgs = M.search(None, 'ALL')[1]
num_messages = len(msgs[0].split())
num_messages += 1
def parse_uid(data):
match = pattern_uid.match(data)
return match.group('uid')
for i in range(1, num_messages):
try:
typ, msg_data = M.fetch(str(i), '(RFC822)')
except:
pass
for response_part in msg_data:
if isinstance(response_part, tuple):
UID = M.fetch(str(i),'UID')
UID = UID[1]
try:
UID = parse_uid(UID[0])
except:
pass
msg = email.message_from_string(response_part[1])
for header in [ 'subject' ]:
if msg[header] == "Redacted":
result = M.uid('COPY', UID, dest)
if result[0] == 'OK':
mov, data = M.uid('STORE', UID, '+FLAGS', '(\Deleted)')
M.expunge()
M.close()
M.logout()
typ, msg_data = M.fetch(str(i), '(RFC822)')
Fetching a message body marks it as read. You'll want to use BODY.PEEK[].
Although, I don't know why you're fetching the whole message just to copy it. Why don't you just fetch the headers? Use BODY.PEEK[HEADERS].
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 above 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.