We Keep Coding

How do I implement the imaplib search function?

import imaplib
import email
from email.header import decode_header
import webbrowser
import os
# account credentials
username = "example#stack.com"
password = "exapleforstack"
imap_server = "imap.one.com"
def clean(text):
# clean text for creating a folder
return "".join(c if c.isalnum() else "_" for c in text)
# create an IMAP4 class with SSL
imap = imaplib.IMAP4_SSL(imap_server)
# authenticate
imap.login(username, password)
status, messages = imap.select("INBOX")
imap.search(None, 'SUBJECT', '"exampleforstack"')
# number of top emails to fetch
N = 3
# total number of emails
messages = int(messages[0])
for i in range(messages, messages-N, -1):
# fetch the email message by ID
res, msg = imap.fetch(str(i), "(RFC822)")
for response in msg:
if isinstance(response, tuple):
# parse a bytes email into a message object
msg = email.message_from_bytes(response[1])
# decode the email subject
subject, encoding = decode_header(msg["Subject"])[0]
if isinstance(subject, bytes):
# if it's a bytes, decode to str
subject = subject.decode(encoding)
# decode email sender
From, encoding = decode_header(msg.get("From"))[0]
if isinstance(From, bytes):
From = From.decode(encoding)
print("Subject:", subject)
print("From:", From)
# if the email message is multipart
if msg.is_multipart():
# iterate over email parts
for part in msg.walk():
# extract content type of email
content_type = part.get_content_type()
content_disposition = str(part.get("Content-Disposition"))
try:
# get the email body
body = part.get_payload(decode=True).decode()
except:
pass
if content_type == "text/plain" and "attachment" not in content_disposition:
# print text/plain emails and skip attachments
print(body)
elif "attachment" in content_disposition:
# download attachment
filename = part.get_filename()
if filename:
folder_name = clean(subject)
if not os.path.isdir(folder_name):
# make a folder for this email (named after the subject)
os.mkdir(folder_name)
filepath = os.path.join(folder_name, filename)
# download attachment and save it
open(filepath, "wb").write(part.get_payload(decode=True))
else:
# extract content type of email
content_type = msg.get_content_type()
# get the email body
body = msg.get_payload(decode=True).decode()
if content_type == "text/plain":
# print only text email parts
print(body)
if content_type == "text/html":
# if it's HTML, create a new HTML file and open it in browser
folder_name = clean(subject)
if not os.path.isdir(folder_name):
# make a folder for this email (named after the subject)
os.mkdir(folder_name)
filename = "index.html"
filepath = os.path.join(folder_name, filename)
# write the file
open(filepath, "w").write(body)
# open in the default browser
webbrowser.open(filepath)
print("="*100)
# close the connection and logout
imap.close()
imap.logout()
I tried using the search method a couple different ways, like:
res, msg = imap.search(None, 'SUBJECT', "example")
and
res, msg = imap.search(None, 'SUBJECT, "example"')
but my code just gives an error and automatically fetches the most recent 3.
I've tried replacing the line:
res, msg = imap.fetch(str(i), "(RFC822)")
with
res, msg = imap.search(None, 'SUBJECT', '"example"')
but the program returns nothing at all.
how would I go about implementing the search I got this code from pythoncode and altered its credentials.
But I'm not sure why I can't implement the search function.

Fetch a particular unseen email and print only those emails

To elaborate the question I have a code that searches for UNSEEN emails and stores the ID to a variable.
status, messages = mail.select('Inbox')
messages = int(messages[0])
_, new_mails = mail.search(None, '(UNSEEN)')
recent_mails = len(new_mails[0].split())
print("Total Messages that is New:" , recent_mails)
print(new_mails)
and it prints this:
Total Messages that is New: 2
[b'389 393']
What I want to do is the use these numbers to fetch it's contents like subject, who sent it and the body of the email. Is it possible to this implementation?
I have a previous code that fetches the first and beyond emails by indicating on how emails it will go to using the variable
N code follows:
N = 0
for i in range(messages, messages-N, -1):
# fetch the email message by ID
res, msg = mail.fetch(str(i), "(RFC822)")
for response in msg:
if isinstance(response, tuple):
# parse a bytes email into a message object
msg = email.message_from_bytes(response[1])
# decode the email subject
pre_subject, encoding = decode_header(msg["Subject"])[0]
subject = pre_subject.upper()
if isinstance(subject, bytes):
# if it's a bytes, decode to str
subject = subject.decode(encoding)
# decode email sender
From, encoding = decode_header(msg.get("From"))[0]
if isinstance(From, bytes):
From = From.decode(encoding)
print("Subject:", pre_subject)
print("From:", From)
# if the email message is multipart
if msg.is_multipart():
# iterate over email parts
for part in msg.walk():
# extract content type of email
content_type = part.get_content_type()
content_disposition = str(part.get("Content-Disposition"))
try:
# get the email body
body = part.get_payload(decode=True).decode()
except:
pass
if content_type == "text/plain" and "attachment" not in content_disposition:
# print text/plain emails and skip attachments
print(body)
plain = body
elif "attachment" in content_disposition:
# download attachment
filename = part.get_filename()
if filename:
folder_name = clean(subject)
if not os.path.isdir(folder_name):
# make a folder for this email (named after the subject)
os.mkdir(folder_name)
filepath = os.path.join(folder_name, filename)
# download attachment and save it
open(filepath, "wb").write(part.get_payload(decode=True))
else:
# extract content type of email
content_type = msg.get_content_type()
# get the email body
body = msg.get_payload(decode=True).decode()
if content_type == "text/plain":
# print only text email parts
print(body)
plain = body
print("="*100)

Finally for hours of experimenting I successfully implemented it.
Basically the ID I fetched on UNSEEN emails is converted to string from byte and then pass those number lists to the loop
gmail_host = 'imap.gmail.com'
mail = imaplib.IMAP4_SSL(gmail_host)
mail.login(EMAIL_ADDRESS,EMAIL_PASSWORD)
mail.list()
status, messages = mail.select('Inbox')
messages = int(messages[0])
_, raw_mails = mail.search(None, '(UNSEEN)')
recent_mails = len(raw_mails[0].split())
splited = str(raw_mails[0], 'utf-8')
new_emails = splited.split()
print("Total Messages that is New:" , recent_mails)
print(new_emails)
Output:
['378', '390']
And changed my for loop to this
for i in new_emails:

Python Sending E-Mail with Umlauts

I want to create a program in python that receives every new unread email from one of my email accounts to another email account.
So far I got everything set up. Unfortunately I have really big issues with umlauts (ä,ö,ü). For some reason I con not make it to work properly.
Here is my code:
# -*- coding: utf-8 -*-
import os, sys
import imaplib
import email
import smtplib
from email.mime.multipart import MIMEMultipart
servername = 'SERVERNAME'
username='USERNAME'
password='PASSWORD'
mail = imaplib.IMAP4_SSL(servername)
(retcode, capabilities) = mail.login(username,password)
mail.list()
mail.select('inbox')
server_smtp = smtplib.SMTP_SSL('SMTP')
n=0
(retcode, messages) = mail.search(None, '(UNSEEN)')
if retcode == 'OK':
for num in messages[0].split() :
n=n+1
typ, data = mail.fetch(num,'(RFC822)')
for response_part in data:
if isinstance(response_part, tuple):
original = email.message_from_string(response_part[1])
print original['From']
typ, data = mail.store(num,'+FLAGS','\\Seen')
body = ""
if original.is_multipart():
for part in original.walk():
ctype = part.get_content_type()
cdispo = str(part.get('Content-Disposition'))
if ctype == 'text/plain' and 'attachment' not in cdispo:
body = part.get_payload(decode=True) # decode
break
else:
body = original.get_payload(decode=True)
body = body.encode('UTF-8')
body = str(body)
print(body)
body = "Betreff: " + str(original['Subject']) + "\n\n\n" + body.encode('UTF-8')
SUBJECT = original['From']
server_smtp.login(username, password)
msg = 'Subject: {}\n\n{}'.format(SUBJECT, body.decode('UTF-8'))
server_smtp.sendmail(username, 'TARGET', msg)
For example: if I want to send this message: "ÄäÖöÜü&ß" I will receive this: "������������&��
���"
Do you know what I am doing wrong?
I would really appreciate your help!

Replace body message of an email using python

I created a class in python that will send emails via one of my private servers. It works but I'm wondering if there is a method to replace an existing email body message with a new one?
Emailer Class
class Emailer:
def __init__(self, subj=None, message=None, toAddr=None, attachment=None, image=None):
# initialize email inputs
self.msg = email.MIMEMultipart.MIMEMultipart()
self.cidNum = 0
self.message = []
if message is not None:
self.addToMessage(message,image)
# set the subject of the email if there is one specified
self.subj = []
if subj is not None:
self.setSubject(subj)
# set the body of the email and any attachements specified
self.attachment = []
if attachment is not None:
self.addAtachment(attachment)
# set the recipient list
self.toAddr = []
if toAddr is not None:
self.addRecipient(toAddr)
def addAttachment(self,attachment):
logger.debug("Adding attachement to email")
# loop through list of attachments and add them to the email
if attachment is not None:
if type(attachment) is not list:
attachment = [attachment]
for f in attachment:
part = email.MIMEBase.MIMEBase('application',"octet-stream")
part.set_payload( open(f,"rb").read() )
encoders.encode_base64(part)
part.add_header('Content-Disposition', 'attachment; filename="{0}"'.format(os.path.basename(f)))
self.msg.attach(part)
def addToMessage(self,message,image=None):
logger.debug("Adding to email message. Content: [%s]" % message)
# add the plain text message
self.message.append(message)
# add embedded images to message
if image is not None:
if type(image) is not list:
image = [image]
for i in image:
msgText = email.MIMEText.MIMEText('<br><img src="cid:image%s"><br>' % self.cidNum, 'html')
self.msg.attach(msgText)
fp = open(i, 'rb')
img = email.MIMEImage.MIMEImage(fp.read())
fp.close()
img.add_header('Content-ID','<image%s>' % self.cidNum)
self.msg.attach(img)
self.cidNum += 1
# method to set the subject of the email
def setSubject(self,subj):
self.msg['Subject'] = subj
# method to add recipients to the email
def addRecipient(self, toAddr):
# loop through recipient list
for x in toAddr:
self.msg['To'] = x
# method to configure server settings: the server host/port and the senders login info
def configure(self, serverLogin, serverPassword, fromAddr, toAddr, serverHost='myserver', serverPort=465):
self.server=smtplib.SMTP_SSL(serverHost,serverPort)
self.server.set_debuglevel(True)
# self.server.ehlo()
# self.server.ehlo()
self.server.login(serverLogin, serverPassword) #login to senders email
self.fromAddr = fromAddr
self.toAddr = toAddr
# method to send the email
def send(self):
logger.debug("Sending email!")
msgText = email.MIMEText.MIMEText("\n".join(self.message))
self.msg.attach(msgText)
print "Sending email to %s " % self.toAddr
text = self.msg.as_string() #conver the message contents to string format
try:
self.server.sendmail(self.fromAddr, self.toAddr, text) #send the email
except Exception as e:
logger.error(e)
Currently, the addToMessage() method is what adds text to the body of the email. If addToMessage() had already been called but I wanted to replace that body text with new text, is there a way?

If addToMessage() had already been called but I wanted to replace that body text with new text, is there a way?
Yes. If you are always replacing the last entry added to self.message, you can reference this element with self.message[-1] since it is a list. If you want to replace a specific element, you can search for it with the index() method.
Example #1: Replace Last Written Text in Body
def replace_last_written_body_text(new_text):
if len(self.message) > 0:
self.message[-1] = new_text
Example #2: Replace Specified Text in Body
def replace_specified_body_text(text_to_replace, new_text):
index_of_text_to_replace = self.message.index(text_to_replace)
if index_of_text_to_replace is not None:
self.message[index_of_text_to_replace] = new_text
else:
logger.warning("Cannot replace non-existent body text")

If addToMessage has been called just once, then:
message is a list, and its first element is the body text, so you just need to replace that element with the new text:
def replace_body(self, new_text):
if len(self.message) > 0:
self.message[0] = new_text
else:
self.message = [new_text]
I haven't tested that, but it should work. Make sure you write some unit tests for this project!
EDIT:
if addToMessage has been called multiple times, then the new replace function could replace the entire text, or just part of it. If you want to replace all of it, then just replace message, like the part after else above: self.message = [new_text]. Otherwise, you're going to have to find the element you need to replace, like #BobDylan is doing in his answer.

Downloading multiple attachments using imaplib

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.