Here is my code:
import imaplib
from email.parser import HeaderParser
conn = imaplib.IMAP4_SSL('imap.gmail.com')
conn.login('example#gmail.com', 'password')
conn.select()
conn.search(None, 'ALL')
data = conn.fetch('1', '(BODY[HEADER])')
header_data = data[1][0][1]
newdata = header_data.decode('utf-8')
parser = HeaderParser()
msg = parser.parsestr(newdata)
print (msg.keys())
This prints out the keys(headers) : Mime-version, x-no-auto-attachment, received, date, messageID, subject, from. to, content type.
However there is 2 missing, which are X-GM-THRID and X-Gmail-Labels? Any ideas why and how can i solve this?
I don't think those are in the email header but extensions to the FETCH command:
conn.fetch('1', '(BODY[HEADER] X-GM-THRID X-GM-Labels)')
See Gmail's documentation.
Related
After 5 hours of trying, time to get some help. Sifted through all the stackoverflow questions related to this but couldn't find the answer.
The code is a gmail parser - works for most emails but some emails cause the UnicodeDecodeError. The problem is "raw_email.decode('utf-8')" but changing it (see comments) causes a different problem down below.
# Source: https://stackoverflow.com/questions/7314942/python-imaplib-to-get-gmail-inbox-subjects-titles-and-sender-name
import datetime
import time
import email
import imaplib
import mailbox
from vars import *
import re # to remove links from str
import string
EMAIL_ACCOUNT = 'gmail_login'
PASSWORD = 'gmail_psswd'
mail = imaplib.IMAP4_SSL('imap.gmail.com')
mail.login(EMAIL_ACCOUNT, PASSWORD)
mail.list()
mail.select('inbox')
result, data = mail.uid('search', None, "ALL") # (ALL/UNSEEN)
id_list = data[0].split()
email_rev = reversed(id_list) # Returns a type list.reverseiterator, which is not list
email_list = list(email_rev)
i = len(email_list)
todays_date = time.strftime("%m/%d/%Y")
for x in range(i):
latest_email_uid = email_list[x]
result, email_data = mail.uid('fetch', latest_email_uid, '(RFC822)')
raw_email = email_data[0][1] # Returns a byte
raw_email_str = raw_email.decode('utf-8') # Returns a str
#raw_email_str = base64.b64decode(raw_email_str1) # Tried this but didn't work.
#raw_email_str = raw_email.decode('utf-8', errors='ignore') # Tried this but caused a TypeError down where var subject is created because something there is expecting a str or byte-like
email_message = email.message_from_string(raw_email_str)
date_tuple = email.utils.parsedate_tz(email_message['Date'])
date_short = f'{date_tuple[1]}/{date_tuple[2]}/{date_tuple[0]}'
# Header Details
if date_short == '12/23/2019':
#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'])))
subject = str(email.header.make_header(email.header.decode_header(email_message['Subject'])))
#print(subject)
if email_from.find('restaurants#uber.com') != -1:
print('yay')
# Body details
if email_from.find('restaurants#uber.com') != -1 and subject.find('Payment Summary') != -1:
for part in email_message.walk():
if part.get_content_type() == "text/plain":
body = part.get_payload(decode=True)
body = body.decode("utf-8") # Convert byte to str
body = body.replace("\r\n", " ")
text = re.sub(r'\w+:\/{2}[\d\w-]+(\.[\d\w-]+)*(?:(?:\/[^\s/]*))*', '', body) # removes url links
text2 = text.translate(str.maketrans('', '', string.punctuation))
body_list = re.sub("[^\w]", " ", text2).split()
print(body_list)
print(date_short)
else:
continue
Here is an example how to retrieve and read mail parts with imapclient and the email.* modules from the python standard libs:
from imapclient import IMAPClient
import email
from email import policy
def walk_parts(part, level=0):
print(' ' * 4 * level + part.get_content_type())
# do something with part content (applies encoding by default)
# part.get_content()
if part.is_multipart():
for part in part.get_payload():
get_parts(part, level + 1)
# context manager ensures the session is cleaned up
with IMAPClient(host="your_mail_host") as client:
client.login('user', 'password')
# select some folder
client.select_folder('INBOX')
# do something with folder, e.g. search & grab unseen mails
messages = client.search('UNSEEN')
for uid, message_data in client.fetch(messages, 'RFC822').items():
email_message = email.message_from_bytes(
message_data[b'RFC822'], policy=policy.default)
print(uid, email_message.get('From'), email_message.get('Subject'))
# alternatively search for specific mails
msgs = client.search(['SUBJECT', 'some subject'])
#
# do something with a specific mail:
#
# fetch a single mail with UID 12345
raw_mails = client.fetch([12345], 'RFC822')
# parse the mail (very expensive for big mails with attachments!)
mail = email.message_from_bytes(
raw_mails[12345][b'RFC822'], policy=policy.default)
# Now you have a python object representation of the mail and can dig
# into it. Since a mail can be composed of several subparts we have
# to walk the subparts.
# walk all parts at once
for part in mail.walk():
# do something with that part
print(part.get_content_type())
# or recurse yourself into sub parts until you find the interesting part
walk_parts(mail)
See the docs for email.message.EmailMessage. There you find all needed bits to read into a mail message.
use 'ISO 8859-1' instead of 'utf-8'
I had the same issue And after a lot of research I realized that I simply need to use, message_from_bytes function from email rather than using message_from_string
so for your code simply replace:
raw_email_str = raw_email.decode('utf-8')
email_message = email.message_from_string(raw_email_str)
to
email_message = email.message_from_bytes(raw_email)
should work like a charm :)
I am using the csv library to pull data to into an email body. I am pulling certain columns from the csv for the body. I am using a junk gmail account to test. I'm just confused on how to use the for loop. If I'm correct, you need a for loop to read the rows then a for loop to email out. I did read Reading and Writing CSV Files but was uncertain how to implement it with smtplib.
import csv, smtplib, ssl
message = """Subject: Your Title
{supervisor} {title} {start}"""
from_address = "test#gmail.com"
password = input("Type your password and press enter: ")
context = ssl.create_default_context()
with smtplib.SMTP_SSL("smtp.gmail.com", 465, context=context) as server:
server.login(from_address, password)
with open('test.csv','rb') as file:
reader = csv.reader(file, delimiter=',')
next(reader)
#start = []
#title = []
#supervisor = []
for row in reader:
title = row[3]
start = row[0]
supervisor = row[4]
for supervisor, title, start in reader:
server.sendmail(
from_address,
Email,
message.format(supervisor=supervisor, start=start, title=title)
)
print('Emails were sent successfully!')
CSV File:
StartDate,Employee Name,PC,Title,Supervisor Name,email
12/9/2019,Katti M. Ricke,289,Recruiter,Courtney Clark,test#gmail.com
Probably if you use pandas for to handle the csv could be more easy ..for install pandas just pip install pandas
import pandas as pd
import io
import smtplib, ssl
from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart
# read csv using pandas and then convert the csv to html string ....this code later will add into body
str_io = io.StringIO()
df = pd.read_csv('test.csv')
df.to_html(buf=str_io)
table_html = str_io.getvalue()
print(table_html)
sender_email = "mymail#gmail.com"
receiver_email = "anothermail#gmail.com"
password = "mypass"
message = MIMEMultipart("alternative")
message["Subject"] = "Subject: Your Title"
message["From"] = sender_email
message["To"] = receiver_email
text = """\
Subject: Your Title"""
html = """\
<html>
<body>
<p>{table_html}</p>
</body>
</html>
""".format(table_html=table_html)
part1 = MIMEText(text, "plain")
part2 = MIMEText(html, "html")
message.attach(part1)
message.attach(part2)
# Send email
context = ssl.create_default_context()
with smtplib.SMTP_SSL("smtp.gmail.com", 465, context=context) as server:
server.login(sender_email, password)
server.sendmail(
sender_email, receiver_email, message.as_string()
)
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!
this is my actula code :
import poplib, sys, re, threading, time, Queue
from email import parser
Mailbox = poplib.POP3(pop3, '110')
Mailbox.user(username)
Mailbox.pass_(password)
numMessages = len(Mailbox.list()[1])
for i in range(numMessages):
fullemail = ''
fullemail = '\n'.join([msg for msg in Mailbox.retr(i+1)[1]])
msg = parser.Parser().parsestr(fullemail)
for part in msg.walk():
print part.get_payload(decode=True)
print part.get_payload(decode=True) print body of email, how i can print header of email ?
the method items() of email.message.Message/email.message.EmailMessage object may be useful:
for t in msg.items():
print(t)
t is a tuple like this (key,value).
Here is my code:
import imaplib
from email.parser import HeaderParser
conn = imaplib.IMAP4_SSL('imap.gmail.com')
conn.login('example#gmail.com', 'password')
conn.select()
conn.search(None, 'ALL')
data = conn.fetch('1', '(BODY[HEADER])')
header_data = data[1][0][1]
parser = HeaderParser()
msg = parser.parsestr(header_data)
From this i get the error message:
TypeError: initial_value must be str or none, not bytes
Im using python 3 which apparently automatically decodes. So why am i still getting this error message?
You can try:
header_data = data[1][0][1].decode('utf-8')
I would suggest do this,(Python 3)
typ, data = conn.fetch('1', '(RFC822)') # will read the first email
email_content = data[0][1]
msg = email.message_from_bytes(email_content) # this needs to be corrected in your case
emailDate = msg["Date"]
emaiSubject = msg["Subject"]
You probably want to use a BytesHeaderParser in this case.