[Python] Gmail message shows actual upload date after import via Python script and not the...

the following Python script should import eml files which are located within a specific folder and assign a pre-defined label. In general the script is working and doing its job.

There is just one small problem, instead of the timestamp form the eml, in the Gmail interface I see the timestamp from the import. This way emails are not blended into the timeline correctly.

Is it possible to adjust the "Received:" date to the date from the eml as it was originally?

I thought I tackled this already by setting the "internalDate".

import os
import base64
import email
import json
import imaplib
from google.oauth2.credentials import Credentials
from google_auth_oauthlib.flow import InstalledAppFlow
from googleapiclient.discovery import build
from datetime import datetime

# Gmail API settings
SCOPES = ['https://www.googleapis.com/auth/gmail.modify']
CLIENT_SECRET_FILE = 'credentials.json'
GMAIL_USER = 'user@gmail.com'

# Label to use in Gmail (e.g., "backup")
GMAIL_LABEL = 'backup'

# Directory containing your local .eml files
LOCAL_EML_DIR = './eml/'

# Define a function to get a Gmail API service
def get_gmail_service():
creds = None
# The file token.json stores the user's access and refresh tokens.
if os.path.exists('token.json'):
creds = Credentials.from_authorized_user_file('token.json', SCOPES)
if not creds or not creds.valid:
flow = InstalledAppFlow.from_client_secrets_file(CLIENT_SECRET_FILE, SCOPES)
creds = flow.run_local_server(port=0)
# Save the credentials for the next run
with open('token.json', 'w') as token:
token.write(creds.to_json())
service = build('gmail', 'v1', credentials=creds)
return service

def get_label_id(service, label_name):
results = service.users().labels().list(userId=GMAIL_USER).execute()
labels = results.get('labels', [])

for label in labels:
if label['name'] == label_name:
return label['id']

return None

# Upload local .eml files to Gmail using the Gmail API
def upload_eml_files_to_gmail(service, label_name, eml_dir):
label_id = get_label_id(service, label_name) # Get the label ID by name
if not label_id:
print(f"Label '{label_name}' not found in Gmail.")
return

for filename in os.listdir(eml_dir):
if filename.endswith('.eml'):
eml_path = os.path.join(eml_dir, filename)

# Read the .eml file
with open(eml_path, 'rb') as eml_file:
eml_data = eml_file.read()

# Extract the INTERNALDATE from the EML file
eml_message = email.message_from_bytes(eml_data)
internaldate = eml_message.get('Date')

# Convert internaldate to Unix timestamp and then to an integer
internaldate = datetime.strptime(internaldate, '%a, %d %b %Y %H:%M:%S %z').timestamp()
internaldate = int(internaldate)

# Create a message with the eml file content and internalDate
message = base64.urlsafe_b64encode(eml_data).decode('utf-8')

message = {
'raw': message,
'internalDate': str(internaldate),
'labelIds': [label_id] # Assign the label to the message
}

# Upload the message to Gmail with the specified label
service.users().messages().insert(userId=GMAIL_USER, body=message).execute()

# Main function to run the script
def main():
service = get_gmail_service() # Authenticate with Gmail API
upload_eml_files_to_gmail(service, GMAIL_LABEL, LOCAL_EML_DIR) # Upload .eml files to Gmail

if __name__ == '__main__':
main()



Original time stamp:

Gmail time stamp (shows the upload time):

Message header in Gmail (shows both time stamps):

Continue reading...