Email Extraction

Sangeetha112 · ‎01-14-2025

Hi , Hope you are doing well. I was trying to extract a specific email attachment from the outlook, and inject into the dbfs loaction, but something went wrong. Could you please help. I am hereby giving the code whcih I used.

import imaplib

import email

import os

from email.header import decode_header

from email.utils import parseaddr

import base64

IMAP_SERVER = "outlook.office365.com"

IMAP_PORT = 993

EMAIL_ACCOUNT = "------------"

PASSWORD =

try:

mail = imaplib.IMAP4_SSL(IMAP_SERVER, IMAP_PORT)

mail.login(EMAIL_ACCOUNT, PASSWORD)

mail.select("inbox")

status, messages = mail.search(None, '(SUBJECT "API_Files")')

email_ids = messages[0].split()

for email_id in email_ids:

status, msg_data = mail.fetch(email_id, "(RFC822)")

for response_part in msg_data:

if isinstance(response_part, tuple😞

msg = email.message_from_bytes(response_part[1])

subject, encoding = decode_header(msg["Subject"])[0]

if isinstance(subject, bytes😞

subject = subject.decode(encoding if encoding else "utf-8")

from_ = msg.get("From")

from_email = parseaddr(from_)[1]

if msg.is_multipart():

for part in msg.walk():

content_type = part.get_content_type()

content_disposition = str(part.get("Content-Disposition"))

if "attachment" in content_disposition:

filename = part.get_filename()

if filename:

filepath = f"dbfs:/tmp{filename}"

with open(filepath, "wb") as f:

f.write(part.get_payload(decode=True))

print(f"Attachment saved to {filepath}")

else:

pass

mail.logout()

except imaplib.IMAP4.error as e:

print(f"IMAP error: {e}")