We Keep Coding

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 decode email from base64

hello iam using python script to fetch a message from a specific address mail seems everything work fine but i have a problem with the printable result is a base64 code.
i want to decode the result to get the decode message when do the final result with print, pls help!!
already thanks
the code used.
# Importing libraries
import imaplib, email
user = 'USER_EMAIL_ADDRESS'
password = 'USER_PASSWORD'
imap_url = 'imap.gmail.com'
# Function to get email content part i.e its body part
def get_body(msg):
if msg.is_multipart():
return get_body(msg.get_payload(0))
else:
return msg.get_payload(None, True)
# Function to search for a key value pair
def search(key, value, con):
result, data = con.search(None, key, '"{}"'.format(value))
return data
# Function to get the list of emails under this label
def get_emails(result_bytes):
msgs = [] # all the email data are pushed inside an array
for num in result_bytes[0].split():
typ, data = con.fetch(num, 'BODY.PEEK[1]')
msgs.append(data)
return msgs
# this is done to make SSL connnection with GMAIL
con = imaplib.IMAP4_SSL(imap_url)
# logging the user in
con.login(user, password)
# calling function to check for email under this label
con.select('Inbox')
# fetching emails from this user "tu**h*****1#gmail.com"
msgs = get_emails(search('FROM', 'MY_ANOTHER_GMAIL_ADDRESS', con))
# Uncomment this to see what actually comes as data
# print(msgs)
# Finding the required content from our msgs
# User can make custom changes in this part to
# fetch the required content he / she needs
# printing them by the order they are displayed in your gmail
for msg in msgs[::-1]:
for sent in msg:
if type(sent) is tuple:
# encoding set as utf-8
content = str(sent[1], 'utf-8')
data = str(content)
# Handling errors related to unicodenecode
try:
indexstart = data.find("ltr")
data2 = data[indexstart + 5: len(data)]
indexend = data2.find("</div>")
# printtng the required content which we need
# to extract from our email i.e our body
print(data2[0: indexend])
except UnicodeEncodeError as e:
pass
THE RESULT PRINTED
'''
aGVsbG8gd29yZCBpYW0gdGhlIG1lc3NhZ2UgZnJvbSBnbWFpbA==
'''

You could just use the base64 module to decode base64 encoded strings:
import base64
your_string="aGVsbG8gV29ybGQ==" # the base64 encoded string you need to decode
result = base64.b64decode(your_string.encode("utf8")).decode("utf8")
print(result)
Edit: encoding changed from ASCII to utf-8

If you need to find all encoded places (can be Subject, From, To email addresses with names), the code below might be useful. Given contentData is the entire email,
import re, base64
encodedParts=re.findall('(=\?(.+)\?B\?(.+)\?=)', contentData)
for part in encodedParts:
encodedPart = part[0]
charset = part[1]
encodedContent = part[2]
contentData = contentData.replace(encodedPart, base64.b64decode(encodedContent).decode(charset))

Get message and then send to another email using Gmail API with Python

I'm following the advice on this thread to set up bulk forwarding using Python. I'm trying to search for messages in the inbox with specific keywords, get the message IDs of those messages, and send those messages to a different person.
The search and getting IDs part works fine. Here's the code:
def search_message(service, user_id, search_string):
# initiate the list for returning
list_ids = []
# get the id of all messages that are in the search string
search_ids = service.users().messages().list(userId=user_id, q=search_string).execute()
# if there were no results, print warning and return empty string
try:
ids = search_ids['messages']
except KeyError:
print("WARNING: the search queried returned 0 results")
print("returning an empty string")
return ""
if len(ids)>1:
for msg_id in ids:
list_ids.append(msg_id['id'])
return(list_ids)
else:
list_ids.append(ids['id'])
return list_ids
It's when I try to send a message that things get hairy. I'm testing this on a single message ID at the moment, and here's what I've tried:
message_raw = service.users().messages().get(userId=user_id, id=msg_id,format='raw').execute()
message_full = service.users().messages().get(userId="me", id=msg_id, format="full", metadataHeaders=None).execute()
## get the subject line
msg_header = message_full['payload']['headers']
# this is a little faster then a loop
subj = [i['value'] for i in msg_header if i["name"]=="Subject"]
subject = subj[0]
msg_str = base64.urlsafe_b64decode(message_raw['raw'].encode('UTF-8'))
msg_bytes = email.message_from_bytes(msg_str)
# get content type for msg
content_type = msg_bytes.get_content_maintype()
if content_type == 'multipart':
# there will usually be 2 parts: the first will be the body as a raw string,
# the second will be the body as html
parts = msg_bytes.get_payload()
# return the encoded text
send_string = parts[0].get_payload()
# force utf-8 encoding on the string
send_string = send_string.encode('utf-8').decode('utf-8')
# now that we have the body in raw string, we will build a new mime object and
# send it via gmail
final_message = MIMEText(send_string)
# set send-to and subject line in the msg
final_message['to'] = to
final_message['subject'] = subject
final_message['from'] = 'tradethenewsapi#gmail.com'
# turn back into raw format and return
raw = base64.urlsafe_b64decode(final_message.as_bytes())
body = {'raw': raw}
However, when I go to send the actual email (as this thread suggests),
message_sent = (service.users().messages().send(userId='me', body=body).execute())
I keep getting this error
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x89 in position 1: invalid start byte
No matter what I do to search_string, it won't work and keeps giving me the unicode error.

How to get emails received from gmail python?

I want to get the last 10 received gmails with python.
Currently I have this code but it only returns a limited number of emails and it manipulates pop3 directly, which makes it unnecessary long.
Source of the code: https://www.code-learner.com/python-use-pop3-to-read-email-example/
import poplib
import smtplib, ssl
def guess_charset(msg):
# get charset from message object.
charset = msg.get_charset()
# if can not get charset
if charset is None:
# get message header content-type value and retrieve the charset from the value.
content_type = msg.get('Content-Type', '').lower()
pos = content_type.find('charset=')
if pos >= 0:
charset = content_type[pos + 8:].strip()
return charset
def decode_str(s):
value, charset = decode_header(s)[0]
if charset:
value = value.decode(charset)
return value
# variable indent_number is used to decide number of indent of each level in the mail multiple bory part.
def print_info(msg, indent_number=0):
if indent_number == 0:
# loop to retrieve from, to, subject from email header.
for header in ['From', 'To', 'Subject']:
# get header value
value = msg.get(header, '')
if value:
# for subject header.
if header=='Subject':
# decode the subject value
value = decode_str(value)
# for from and to header.
else:
# parse email address
hdr, addr = parseaddr(value)
# decode the name value.
name = decode_str(hdr)
value = u'%s <%s>' % (name, addr)
print('%s%s: %s' % (' ' * indent_number, header, value))
# if message has multiple part.
if (msg.is_multipart()):
# get multiple parts from message body.
parts = msg.get_payload()
# loop for each part
for n, part in enumerate(parts):
print('%spart %s' % (' ' * indent_number, n))
print('%s--------------------' % (' ' * indent_number))
# print multiple part information by invoke print_info function recursively.
print_info(part, indent_number + 1)
# if not multiple part.
else:
# get message content mime type
content_type = msg.get_content_type()
# if plain text or html content type.
if content_type=='text/plain' or content_type=='text/html':
# get email content
content = msg.get_payload(decode=True)
# get content string charset
charset = guess_charset(msg)
# decode the content with charset if provided.
if charset:
content = content.decode(charset)
print('%sText: %s' % (' ' * indent_number, content + '...'))
else:
print('%sAttachment: %s' % (' ' * indent_number, content_type))
# input email address, password and pop3 server domain or ip address
email = 'yourgmail#gmail.com'
password = 'yourpassword'
# connect to pop3 server:
server = poplib.POP3_SSL('pop.gmail.com')
# open debug switch to print debug information between client and pop3 server.
server.set_debuglevel(1)
# get pop3 server welcome message.
pop3_server_welcome_msg = server.getwelcome().decode('utf-8')
# print out the pop3 server welcome message.
print(server.getwelcome().decode('utf-8'))
# user account authentication
server.user(email)
server.pass_(password)
# stat() function return email count and occupied disk size
print('Messages: %s. Size: %s' % server.stat())
# list() function return all email list
resp, mails, octets = server.list()
print(mails)
# retrieve the newest email index number
#index = len(mails)
index = 3
# server.retr function can get the contents of the email with index variable value index number.
resp, lines, octets = server.retr(index)
# lines stores each line of the original text of the message
# so that you can get the original text of the entire message use the join function and lines variable.
msg_content = b'\r\n'.join(lines).decode('utf-8')
# now parse out the email object.
from email.parser import Parser
from email.header import decode_header
from email.utils import parseaddr
import poplib
# parse the email content to a message object.
msg = Parser().parsestr(msg_content)
print(len(msg_content))
# get email from, to, subject attribute value.
email_from = msg.get('From')
email_to = msg.get('To')
email_subject = msg.get('Subject')
print('From ' + email_from)
print('To ' + email_to)
print('Subject ' + email_subject)
for part in msg.walk():
if part.get_content_type():
body = part.get_payload(decode=True)
print_info(msg, len(msg))
# delete the email from pop3 server directly by email index.
# server.dele(index)
# close pop3 server connection.
server.quit()
I also tried this code but it didn't work:
import imaplib, email, base64
def fetch_messages(username, password):
messages = []
conn = imaplib.IMAP4_SSL("imap.gmail.com", 993)
conn.login(username, password)
conn.select()
typ, data = conn.uid('search', None, 'ALL')
for num in data[0].split():
typ, msg_data = conn.uid('fetch', num, '(RFC822)')
for response_part in msg_data:
if isinstance(response_part, tuple):
messages.append(email.message_from_string(response_part[1]))
typ, response = conn.store(num, '+FLAGS', r'(\Seen)')
return messages
and this also didn't work for me...
import poplib
from email import parser
pop_conn = poplib.POP3_SSL('pop.gmail.com')
pop_conn.user('#gmail.com')
pop_conn.pass_('password')
messages = [pop_conn.retr(i) for i in range(1, len(pop_conn.list()[1]) + 1)]
# Concat message pieces:
messages = ["\n".join(mssg[1]) for mssg in messages]
#Parse message intom an email object:
messages = [parser.Parser().parsestr(mssg) for mssg in messages]
for message in messages:
print(message['subject'])
print(message['body'])

I managed to solve it, the only issue is that it marks as read every unread email, here is the code I used:
import imaplib
mail = imaplib.IMAP4_SSL('imap.gmail.com')
email = input('Email: ')
password = input('Password: ')
mail.login(email+'#gmail.com', password)
mail.list()
# Out: list of "folders" aka labels in gmail.
mail.select("inbox") # connect to inbox.
result, data = mail.search(None, "ALL")
ids = data[0] # data is a list.
id_list = ids.split() # ids is a space separated string
latest_email_id = id_list[-1] # get the latest
# fetch the email body (RFC822) for the given ID
result, data = mail.fetch(latest_email_id, "(RFC822)")
raw_email = data[0][1] # here's the body, which is raw text of the whole email
# including headers and alternate payloads
import email
email_message = email.message_from_string(str(raw_email))
print (email_message['To'])
print (email.utils.parseaddr(email_message['From'])) # for parsing "Yuji Tomita" <yuji#grovemade.com>
print (email_message.items()) # print all headers
# note that if you want to get text content (body) and the email contains
# multiple payloads (plaintext/ html), you must parse each message separately.
# use something like the following: (taken from a stackoverflow post)
def get_first_text_block(self, email_message_instance):
maintype = email_message_instance.get_content_maintype()
if maintype == 'multipart':
for part in email_message_instance.get_payload():
if part.get_content_maintype() == 'text':
return part.get_payload()
elif maintype == 'text':
return email_message_instance.get_payload()

https://developers.google.com/gmail/api/quickstart/python is the preferred way:
from gmail.gmail import gmail_auth, ListThreadsMatchingQuery
service = gmail_auth()
threads = ListThreadsMatchingQuery(service, query=query)
where:
def ListThreadsMatchingQuery(service, user_id='me', query=''):
"""List all Threads of the user's mailbox matching the query.
Args:
service: Authorized Gmail API service instance.
user_id: User's email address. The special value "me"
can be used to indicate the authenticated user.
query: String used to filter messages returned.
Eg.- 'label:UNREAD' for unread messages only.
Returns:
List of threads that match the criteria of the query. Note that the returned
list contains Thread IDs, you must use get with the appropriate
ID to get the details for a Thread.
"""
try:
response = service.users().threads().list(userId=user_id, q=query).execute()
threads = []
if 'threads' in response:
threads.extend(response['threads'])
while 'nextPageToken' in response:
page_token = response['nextPageToken']
response = service.users().threads().list(userId=user_id, q=query,
pageToken=page_token).execute()
threads.extend(response['threads'])
return threads
except errors.HttpError as error:
raise error

You should try easyimap lib to get a list of e-mails, I'm not sure if works with pop3.
Code example:
import easyimap
host = 'imap.gmail.com'
user = 'you#example.com'
password = 'secret'
mailbox = 'INBOX.subfolder'
imapper = easyimap.connect(host, user, password, mailbox)
email_quantity = 10
emails_from_your_mailbox = imapper.listids(limit=email_quantity)
imapper.quit()

How do I know the "From" of an email? (Using IMAP)

In this case I am downloading plain text from an email with a criteria,
but how do I know the #gmail.com adress who sent it.
I am using Python 3.5.4
import imaplib
import email
mail = imaplib.IMAP4_SSL('imap.gmail.com')
#imaplib module implements connection based on IMAPv4 protocol
mail.login('myemail', 'mypassword')
mail.list() # Lists all labels in GMail
mail.select('inbox') # Connected to inbox.
result, data = mail.uid('search', None, '(HEADER Subject "[News]")')
#search and return uids instead
i = len(data[0].split()) # data[0] is a space separate string
for x in range(i):
latest_email_uid = data[0].split()[x] # unique ids wrt label selected
result, email_data = mail.uid('fetch', latest_email_uid, '(RFC822)')
# fetch the email body (RFC822) for the given ID
raw_email = email_data[0][1]
#From = email.utils.parseaddr(email_data['From'])
#continue inside the same for loop as above
raw_email_string = raw_email.decode('utf-8')
# converts byte literal to string removing b''
email_message = email.message_from_string(raw_email_string)
#this will loop through all the available multiparts in mail
for part in email_message.walk():
if part.get_content_type() == "text/plain": # ignore attachments/html
enter code here`body = part.get_payload(decode=True)
save_string = str("Llave de amigo" + str(x) + str("a"))
# location on disk
myfile = open(save_string, 'a')
myfile.write(body.decode('utf-8'))
# body is again a byte literal
myfile.close()

This is perhaps not obvious from the documentation (assuming Python 2.7), but the email_message object acts like a dict, by implementing the __getitem__ function. Since you fetched and parsed the entirety of the message, you should be able to access it simply as:
email_message['from']
Note, this gives you a raw representation of the header, which is probably okay in a lot of cases.
You may then want to use email.utils.parseaddr to break it into constituent parts:
realname, addr = email.utils.parseaddr(email_message['from')).
email.utils.getaddresses might be useful if you then parse To or Cc headers with more than one recipient.
If you need to deal with internationalized headers in older versions of Python, email.header.decode_header and email.header.make_header can be used.
In Python3.6, this has changed significantly, and should be more straightforward.