I am trying to save attachments of my outlook account emails to a local directory and the code was working perfectly till now, it starts showing error and I am not able to get this through. Can anybody please help with this?
TimeoutError: [WinError 10060] A connection attempt failed because the connected party did not properly respond after a period of time, or established connection failed because connected host has failed to respond
Here is the code.
from classes.logfile import logger
from classes.config_ini import Config
import email
import imaplib
import email.mime.multipart
import os
import pandas as pd
import datetime
# This class is useful of fetching data from outlook emails by providing a subject line with files
class Outlook(Config):
def __init__(self):
super(Outlook, self).__init__()
self.username = None
self.password = None
self.imap = None
self.subject = None
self.file_name = None
self.s = None
self.att_path = "No attachment found"
def subject_line(self):
subject_read = pd.read_csv(self.section_value[0] + 'outlookEmails.csv')
subject = subject_read.iloc[:, :]
self.s = subject
self.subject = subject.iloc[:, 1]
self.file_name = subject.iloc[:, 0]
def close_connection(self):
return self.imap.close()
def login(self, username, password):
# IMAP Settings
self.username = username
self.password = password
print("signing in")
while True:
# Connect to the server
try:
self.imap = imaplib.IMAP4_SSL("outlook.office365.com", port=993)
r, d = self.imap.login(username, password)
assert r == 'OK', 'login failed'
print(" > Sign as ", d)
except imaplib.IMAP4.error:
print(" > Sign In ...")
continue
break
def inbox(self):
# selecting the inbox
typ, data = self.imap.select("Inbox")
print(typ, data)
num_msgs = int(data[0])
print('There are {} messages in INBOX'.format(num_msgs))
return self.imap.select("Inbox")
def email_check(self, download_folder):
# fetch the email body (RFC822) for the given ID
try:
for i, j in zip(self.subject, self.file_name):
print('Subject {}'.format(i))
# typ, msg_ids = self.imap.uid('search', None, 'SUBJECT {}'.format(i))
typ, msg_ids = self.imap.uid('search', None, '(SUBJECT "{}")'.format(i))
inbox_item_list = msg_ids[0].split()
most_recent = inbox_item_list[-1]
print(most_recent)
if typ == "OK":
ret, data = self.imap.uid('fetch', most_recent, '(RFC822)')
raw_data = data[0][1]
# converts byte literal to string removing b''
raw_data_string = raw_data.decode('utf-8')
msg = email.message_from_string(raw_data_string)
# downloading attachments
# print(msg)
print('Subject:' + msg['Subject'])
for part in msg.walk():
if part.get_content_maintype() == 'multipart':
continue
if part.get('Content-Disposition') is None:
continue
filename = part.get_filename()
print("filename:" + filename)
filename = j
# if there is no filename, we create one with a counter to avoid duplicates
self.att_path = os.path.join(download_folder, filename)
# Check if its already there
# if not os.path.isfile(self.att_path):
fp = open(self.att_path, 'wb')
fp.write(part.get_payload(decode=True))
fp.close()
except (imaplib.IMAP4.error, TypeError) as e:
logger.error(str(e))
pass
# moving files to particular folder
# folders = [d for d in os.listdir(download_folder) if os.path.isdir(d)]
# files = [f for f in os.listdir(download_folder) if os.path.isfile(f)]
# for d in folders:
# for f in files:
# if d in f:
# new_loc =
def main(self):
self.subject_line()
self.login('XXX', 'XXX')
self.inbox()
logger.info('start downloading emails at ' + str(datetime.datetime.now().strftime("%Y-%m-%d %H:%M")))
self.email_check(self.section_value[1])
self.close_connection()
logger.info('Emails Downloaded ' + str(datetime.datetime.now().strftime("%Y-%m-%d %H:%M")))
if __name__ == "__main__":
obj = Outlook()
obj.main()
Can somebody help me with this?
Related
I am trying to download csv file in my email attachment using this link : Download a csv file from gmail using python
It doesn't show any error and The program says 'Process finished with exit code 0' but it doesn't download any attachments either. I tried to print some variables but it doesn't get print.
Is it a gmail issue or is there anything wrong with the code?
import getpass
import imaplib
import os
import sys
userName = 'abc#gmail.com'
passwd = 'password'
directory = 'c:/users/pictures'
detach_dir = '.'
if 'DataFiles' not in os.listdir(detach_dir):
os.mkdir('DataFiles')
imapSession = imaplib.IMAP4_SSL('imap.gmail.com')
typ, accountDetails = imapSession.login(userName, passwd)
print(typ)
if typ != 'OK':
print ('Not able to sign in!')
raise()
imapSession.select('[Gmail]/All Mail')
typ, data = imapSession.search(None, 'ALL')
print(typ)
if typ != 'OK':
print ('Error searching Inbox.')
raise ()
for msgId in data[0].split():
typ, messageParts = imapSession.fetch(msgId, '(RFC822)')
print(typ)
if typ != 'OK':
print ('Error fetching mail.')
raise ()
emailBody = messageParts[0][1]
emailBody = emailBody.decode('utf-8')
mail = email.message_from_string(emailBody)
for part in mail.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(detach_dir, 'DataFiles', fileName)
if not os.path.isfile(filePath) :
print (fileName)
fp = open(filePath, 'wb')
fp.write(part.get_payload(decode=True))
print('file written')
fp.close()
imapSession.close()
imapSession.logout()
print ('Done')
The script I wrote:1) connects to my work Outlook email. The script reads my username and password from a text file which is found in the variable TextFilePath. 2) Looks for attachments based upon a searchterm I choose that would be in the Subject of the email (here, it's "special_search_term_in_email"). 3) Downloads the attachments to a specific folder titled 'DownloadFolderPath'.
The goal for this script is to run everyday and connect to my email and download 4 attachments that will be sent to me everyday. The issue is that the script will sometimes download all 4 attachments, but then sometimes will only download 3 of 4 attachments and then won't even terminate. Appreciate the help.
import email
import imaplib
import os
import datetime
import csv
# these 3 variables you need to set to run the code
mail_server = "imap-mail.outlook.com"
TextFilePath = "C:/Users/FakeName/PycharmProjects/imaplib_script/unpw.txt"
LogFilePath = 'C:/Users/FakeName/PycharmProjects/imaplib_script/downloaded_attachments/logfile.csv'
DownloadFolderPath = 'C:/Users/FakeName/PycharmProjects/imaplib_script/downloaded_attachments/'
# below read_input_return_list function reads input from a text file and returns a list
def read_input_return_list():
textunpw = open(TextFilePath, "r")
lines = textunpw.readlines()
username = lines[0].strip('\n')
password = lines[1]
textunpw.close()
return [username, password]
read_input_variable = read_input_return_list()
username = read_input_variable[0]
password = read_input_variable[1]
script_ran_time=datetime.datetime.today().strftime('%c')
mail = imaplib.IMAP4_SSL(mail_server)
mail.login(username, password)
print("{0} Connecting to mailbox via IMAP...".format(datetime.datetime.today().strftime("%Y-%m-%d %H:%M:%S")))
mail.select()
type, data = mail.search(None, '(SUBJECT "special_search_term_in_email")')
total_count = 0
with open(LogFilePath,newline='', encoding='utf-8', mode='a') as csv_file:
writer = csv.writer(csv_file, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
for num in data[0].split():
type, data = mail.fetch(num, '(RFC822)')
raw_email = data[0][1]
raw_email_string = raw_email.decode('utf-8')
email_message = email.message_from_string(raw_email_string)
for part in email_message.walk():
if part.get_content_maintype() == 'multipart':
for part1 in part.walk():
c_type = part.get_content_type()
c_disp0 = str(part.get('Content-Disposition'))
# skip any text/plain (txt) attachments
if c_type == 'text/plain' and 'attachment' not in c_disp0:
body = part1.get_payload(decode=True)
break
attachment = part.get_filename()
if bool(attachment):
filePath = os.path.join(DownloadFolderPath, attachment)
if os.path.isfile(filePath):
filename, file_extension = os.path.splitext(filePath)
FileDownloadAndWriteTime = '__' + datetime.datetime.today().strftime('%m_%d_%Y %H_%M_%S')
new_fname = "{}_{}{}".format(filename, FileDownloadAndWriteTime, file_extension)
while os.path.exists(new_fname):
new_fname = "{}_{}{}".format(filename, FileDownloadAndWriteTime, file_extension)
filePath = new_fname
filepathopen = open(filePath, 'wb')
filepathopen.write(part.get_payload(decode=True))
FileDownloadAndWriteTime = datetime.datetime.today().strftime('%m_%d_%Y %H_%M_%S')
total_count += 1
writer.writerow([filePath,FileDownloadAndWriteTime, script_ran_time])
filepathopen.close()
print('Download file attachment name: ', attachment)
print("Total count of downloaded documents: ", total_count)
mail.close()
I can't pinpoint what's wrong but try adopting this code here: https://gist.github.com/cdunklau/9001357
It worked for me.
I updated the find_attachments method like this:
def find_attachments(message):
"""
Return a tuple of parsed content-disposition dict, message object
for each attachment found.
"""
found = []
for part in message.walk():
if 'content-disposition' not in part:
continue
cdisp = part['content-disposition'].split(';')
cdisp = [x.strip() for x in cdisp]
if cdisp[0].lower() != 'attachment':
continue
parsed = {}
for kv in cdisp[1:]:
try:
key, val = kv.split('=')
if val.startswith('"'):
val = val.strip('"')
elif val.startswith("'"):
val = val.strip("'")
parsed[key] = val
except Exception as e:
parsed['filename']=kv.replace('filename=','')
found+=list(parsed.values())
return found
I would really appreciate if someone can help me with this issue.
I have implemented the below code to read "unread emails from gmail inbox". I need to print "To", "From", "Subject", "Body" and "save attachments in a specified location"
I have 2 issues here.
If there is any email with attachments, it gives the error Body: [<email.message.Message object at 0x026D1050>, <email.message.Message object at 0x02776B70>]. It will print all the required things and saves attachments but DOESN'T print the body.
This works fine if no attachment is included.
If there is an email body with any styling in it like "bold/italic/underline/colour...etc", it doesn't print as it is.
Example : Python is printed as Python=C2=A0i= and sometimes different styling is seperated by "*".
def get_body(email_message):
for payload in email_message.get_payload():
# print('Body:\t', payload.get_payload())
break
return(payload.get_payload())
def read_email(server,uname,pwd):
username = uname
password = pwd
mail = imaplib.IMAP4_SSL(server)
mail.login(username, password)
mail.select("inbox")
try:
result, data = mail.uid('search', None, '(UNSEEN)')
inbox_item_list = data[0].split()
most_recent = inbox_item_list[-1]
result2, email_data = mail.uid('fetch', most_recent, '(RFC822)')
raw_email = email_data[0][1].decode("UTF-8")
email_message = email.message_from_string(raw_email)
for part in email_message.walk():
if part.get_content_maintype() == 'multipart':
continue
if part.get('Content-Disposition') is None:
continue
filename = part.get_filename()
att_path = os.path.join(location, filename)
if not os.path.isfile(att_path):
fp = open(att_path, 'wb')
fp.write(part.get_payload(decode=True))
fp.close()
print('Downloaded file:', filename)
if email_message.is_multipart():
for payload in email_message.get_payload():
print('To:\t\t', email_message['To'])
print('From:\t', email_message['From'])
print('Subject:', email_message['Subject'])
print('Date:\t',email_message['Date'])
print('Body:\t', get_body(email_message))
break
else:
print('Nothing'])
except IndexError:
print("No new email")
while True:
read_email("imap.gmail.com", "s#gmail.com", "spassword")
time.sleep(10)
Many thanks
I new to python and this is the complete working code I have done to read unseen emails. You can print the elements according to your requirements. It works for gmail and office 365. This script runs for every 10 seconds. This might also work for other email providers by passing the credentials. Hope this helps.
import email
import imaplib
import os
import html2text
import time
detach_dir = 'locationWhereYouWantToSaveYourAttachments'
def get_body(email_message):
for payload in email_message.get_payload():
break
return payload.get_payload()
def two_way_email(server,uname,pwd):
username = uname
password = pwd
mail = imaplib.IMAP4_SSL(server)
mail.login(username, password)
mail.select("inbox")
try:
result, data = mail.uid('search', None, '(UNSEEN)')
inbox_item_list = data[0].split()
most_recent = inbox_item_list[-1]
result2, email_data = mail.uid('fetch', most_recent, '(RFC822)')
raw_email = email_data[0][1].decode("UTF-8")
email_message = email.message_from_string(raw_email)
for part in email_message.walk():
if part.get_content_maintype() == 'multipart':
continue
if part.get('Content-Disposition') is None:
continue
filename = part.get_filename()
att_path = os.path.join(detach_dir, filename)
if not os.path.isfile(att_path):
fp = open(att_path, 'wb')
fp.write(part.get_payload(decode=True))
fp.close()
print('Downloaded file:', filename)
if email_message.is_multipart():
for payload in email_message.get_payload():
print('To:\t\t', email_message['To'])
print('From:\t', email_message['From'])
print('Subject:', email_message['Subject'])
print('Date:\t',email_message['Date'])
for part in email_message.walk():
if (part.get_content_type() == 'text/plain') and (part.get('Content-Disposition') is None):
print('Body:\t',part.get_payload())
break
else:
print('To:\t\t', email_message['To'])
print('From:\t', email_message['From'])
print('Subject:', email_message['Subject'])
print('Date:\t', email_message['Date'])
print('Thread-Index:\t', email_message['Thread-Index'])
text = f"{email_message.get_payload(decode=True)}"
html = text.replace("b'", "")
h = html2text.HTML2Text()
h.ignore_links = True
output = (h.handle(f'''{html}''').replace("\\r\\n", ""))
output = output.replace("'", "")
print(output)
except IndexError:
print("No new email")
while True:
two_way_email("outlook.office365.com", "yourOffice365EmailAddressHere", "yourpassword")
two_way_email("imap.gmail.com", "yourGmailAddressHere", "yourPassword")
time.sleep(10)
from imap_tools import MailBox, A
with MailBox('imap.mail.com').login('test#mail.com', 'pwd') as mailbox:
for msg in mailbox.fetch(A(seen=False)):
body = msg.text or msg.html
print(msg.subject, msg.from_, msg.to, len(body))
for att in msg.attachments:
print(att.filename, len(att.payload))
https://github.com/ikvk/imap_tools
I am lib author.
More examples: https://github.com/ikvk/imap_tools/blob/master/examples/idle.py#L19
I have this code, and it seems to be able to log into the Gmail and view the emails (Unread email become marked as read). However, there is no downloading occurring, and I'm not sure why. Any ideas on how to make this happen?
import email
import getpass, imaplib
import os
import sys
detach_dir = '.'
if 'attachments' not in os.listdir(detach_dir):
os.mkdir('attachments')
userName = input('Enter your GMail username:')
passwd = getpass.getpass('Enter your password: ')
imapSession = imaplib.IMAP4_SSL('imap.gmail.com')
typ, accountDetails = imapSession.login(userName, passwd)
if typ != 'OK':
print ('Not able to sign in!')
raise
imapSession.select('Inbox')
typ, data = imapSession.search(None, 'ALL')
if typ != 'OK':
print ('Error searching Inbox.')
raise
# Iterating over all emails
for msgId in data[0].split(): typ, messageParts = imapSession.fetch(msgId,
'(RFC822)')
if typ != 'OK':
print ('Error fetching mail.')
raise
emailBody = messageParts[0][1]
mail = email.message_from_string(emailBody)
for part in mail.walk():
if part.get_content_maintype() == 'multipart':
# print part.as_string()
continue
if part.get('Content-Disposition') is None:
# print part.as_string()
continue
fileName = part.get_filename()
if bool(fileName):
filePath = os.path.join(detach_dir, 'attachments', fileName)
if not os.path.isfile(filePath) :
print (fileName)
fp = open(filePath, 'wb')
fp.write(part.get_payload(decode=True))
fp.close()
imapSession.close()
imapSession.logout()
I was working with similar code and I had the same problem. In order to solve it, I changed
mail = email.message_from_string(emailBody)
to
mail = email.message_from_bytes(emailBody)
which worked for me.
Hope it helps!
How can I download multiple attachments from a single mail using imaplib?
Let's say I have an e-mail and that e-mail contains 4 attachments. How can I download all of those attachments? The code below only downloads a single attachment from an e-mail.
detach_dir = 'c:/downloads'
m = imaplib.IMAP4_SSL("imap.gmail.com")
m.login('hello#gmail.com','3323434')
m.select("[Gmail]/All Mail")
resp, items = m.search(None, "(UNSEEN)")
items = items[0].split()
for emailid in items:
resp, data = m.fetch(emailid, "(RFC822)")
email_body = data[0][1]
mail = email.message_from_string(email_body)
temp = m.store(emailid,'+FLAGS', '\\Seen')
m.expunge()
if mail.get_content_maintype() != 'multipart':
continue
print "["+mail["From"]+"] :" + mail["Subject"]
for part in mail.walk():
if part.get_content_maintype() == 'multipart':
continue
if part.get('Content-Disposition') is None:
continue
filename = part.get_filename()
att_path = os.path.join(detach_dir, filename)
if not os.path.isfile(att_path) :
fp = open(att_path, 'wb')
fp.write(part.get_payload(decode=True))
fp.close()
return HttpResponse('check folder')
For any future python travellers.
Here is a class that downloads any attachment found for an email and saves it to a specific location.
import email
import imaplib
import os
class FetchEmail():
connection = None
error = None
def __init__(self, mail_server, username, password):
self.connection = imaplib.IMAP4_SSL(mail_server)
self.connection.login(username, password)
self.connection.select(readonly=False) # so we can mark mails as read
def close_connection(self):
"""
Close the connection to the IMAP server
"""
self.connection.close()
def save_attachment(self, msg, download_folder="/tmp"):
"""
Given a message, save its attachments to the specified
download folder (default is /tmp)
return: file path to attachment
"""
att_path = "No attachment found."
for part in msg.walk():
if part.get_content_maintype() == 'multipart':
continue
if part.get('Content-Disposition') is None:
continue
filename = part.get_filename()
att_path = os.path.join(download_folder, filename)
if not os.path.isfile(att_path):
fp = open(att_path, 'wb')
fp.write(part.get_payload(decode=True))
fp.close()
return att_path
def fetch_unread_messages(self):
"""
Retrieve unread messages
"""
emails = []
(result, messages) = self.connection.search(None, 'UnSeen')
if result == "OK":
for message in messages[0].split(' '):
try:
ret, data = self.connection.fetch(message,'(RFC822)')
except:
print "No new emails to read."
self.close_connection()
exit()
msg = email.message_from_bytes(data[0][1])
if isinstance(msg, str) == False:
emails.append(msg)
response, data = self.connection.store(message, '+FLAGS','\\Seen')
return emails
self.error = "Failed to retreive emails."
return emails
def parse_email_address(self, email_address):
"""
Helper function to parse out the email address from the message
return: tuple (name, address). Eg. ('John Doe', 'jdoe#example.com')
"""
return email.utils.parseaddr(email_address)
I reworked the code, breaking it up into functions. I use PEEK so I don't change the UNREAD status of the email messages.
I'm posting my take on the problem, similar to #John, but I use only functions instead of classes:
import imaplib
import email
# Connect to an IMAP server
def connect(server, user, password):
m = imaplib.IMAP4_SSL(server)
m.login(user, password)
m.select()
return m
# Download all attachment files for a given email
def downloaAttachmentsInEmail(m, emailid, outputdir):
resp, data = m.fetch(emailid, "(BODY.PEEK[])")
email_body = data[0][1]
mail = email.message_from_string(email_body)
if mail.get_content_maintype() != 'multipart':
return
for part in mail.walk():
if part.get_content_maintype() != 'multipart' and part.get('Content-Disposition') is not None:
open(outputdir + '/' + part.get_filename(), 'wb').write(part.get_payload(decode=True))
# Download all the attachment files for all emails in the inbox.
def downloadAllAttachmentsInInbox(server, user, password, outputdir):
m = connect(server, user, password)
resp, items = m.search(None, "(ALL)")
items = items[0].split()
for emailid in items:
downloaAttachmentsInEmail(m, emailid, outputdir)
You code appears okay except for the return (perhaps a typo?) right after the fp.close():
...
fp.write(part.get_payload(decode=True))
fp.close()
return HttpResponse('check folder')
After saving the first attachment it returns from the function. Comment out that line and see if it fixes your issue.
You may use imap_tools package:
https://pypi.org/project/imap-tools/
from imap_tools import MailBox
with MailBox('imap.mail.com').login('test#mail.com', 'password', 'INBOX') as mailbox:
for message in mailbox.fetch():
for att in message.attachments: # list: [Attachment objects]
att.filename # str: 'cat.jpg'
att.content_type # str: 'image/jpeg'
att.payload # bytes: b'\xff\xd8\xff\xe0\'
* You can try following function to get mail attachment
def create_message_attachment(self,msg_str):
count = 1
body = ''
content_id = ''
for part in msg_str.walk():
file_name_gl = None
mptype = part.get_content_maintype()
file_name_gl = part.get_filename()
if mptype == "multipart":
continue
elif mptype == "text":
if not file_name_gl: continue
elif mptype == "image":
content_id = part.get('Content-ID')
if not file_name_gl:
file_name_gl = 'image_' + str(count) + '.' + part.get_content_subtype()
count = count + 1
body = part.get_payload(decode = True)
if type(body) <> type(None) :
body = body.strip()
if body <> "":
body = base64.encodestring(body)
#sashoalm 's code worked for me with a minor change:
change mail = email.message_from_string(email_body) in downloaAttachmentsInEmail to mail = email.message_from_bytes(email_body)
I was getting an error when trying to read bytes (the attachment) as a string. Now it works perfectly for me.
Heres a full example of the code:
server = 'outlook.office365.com'
user = 'YOUR USERNAME'
password = 'YOUR PASSWORD'
outputdir = 'DIRECTORY THAT YOU WANT FILES DOWNLOADED TO'
subject = 'Data Exports' #subject line of the emails you want to download attachments from
def connect(server, user, password):
m = imaplib.IMAP4_SSL(server)
m.login(user, password)
m.select()
return m
def downloaAttachmentsInEmail(m, emailid, outputdir):
resp, data = m.fetch(emailid, "(BODY.PEEK[])")
email_body = data[0][1]
mail = email.message_from_bytes(email_body)
if mail.get_content_maintype() != 'multipart':
return
for part in mail.walk():
if part.get_content_maintype() != 'multipart' and part.get('Content-Disposition') is not None:
open(outputdir + '/' + part.get_filename(), 'wb').write(part.get_payload(decode=True))
#download attachments from all emails with a specified subject line
def downloadAttachments(subject):
m = connect(server, user, password)
m.select("Inbox")
typ, msgs = m.search(None, '(SUBJECT "' + subject + '")')
msgs = msgs[0].split()
for emailid in msgs:
downloaAttachmentsInEmail(m, emailid, outputdir)
downloadAttachments(subject)
import re
def get_valid_filename(s):
s = str(s).strip().replace(' ', '_')
return re.sub(r'(?u)[^-\w.]', '', s)
fileName = get_valid_filename(part.get_filename())
Clean up the file name if it contains invalid characters. e.g: : on Windows.