MS Graph API Outlook Attachments to s3 bucket

Question

I'm attempting to pull email attachments from outlook and store them in an s3 bucket in aws. This is one of my first python projects, and its proving to be very difficult for me and is probably very messy code.

# see https://github.com/AzureAD/microsoft-authentication-library-for-python/blob/dev/sample/device_flow_sample.py
# This authenticates for first time login. 
# As long as you call acquire_token_silent before you invoke any graph APIs, the tokens will stay up to date. 
# The refresh token is good for 90 days, and automatically updates. Once you login, the tokens will 
# be updated and stored in the cache (and persisted to a file), and will stay alive more-or-less indefinitely 
# (there are some things that can invalidate it on the server side).
from __future__ import with_statement
import io
import sys
import json
import logging
import os
import tarfile
import atexit
from wsgiref import headers
import requests
import msal
import boto3
import base64
from botocore.exceptions import ClientError
import codecs

print('Starting...')

#   logging
logging.basicConfig(level=logging.DEBUG)  # Enable DEBUG log for entire script
logging.getLogger("msal").setLevel(logging.INFO)  # Optionally disable MSAL DEBUG logs

client=boto3.client('secretsmanager')

#   config
config = dict(
    authority = "https://login.microsoftonline.com/common",
    client_id = '123456',
    scope = ["Mail.ReadWrite"],
    username = 'username',
    cache_file = client.get_secret_value(SecretId="demo-ms-graph")['SecretBinary'],
    endpoint = 'https://graph.microsoft.com/v1.0/me/mailFolders/inbox/messages?$expand=attachments&$search="hasAttachments:true"'
)

#   cache
cache = msal.SerializableTokenCache()
if os.path.exists(config["cache_file"]):
    with tarfile.open('token.cache.tar.gz', "w:gz") as tar:
        tar.add(config["cache_file"])
bts = open('token.cache.tar.gz','rb').read()
print("Length before",len(bts))

#sec=client.update_secret(SecretId="demo-ms-graph", SecretBinary=bts)
sec=client.get_secret_value(SecretId="demo-ms-graph")['SecretBinary']
print("Length after",len(sec))

with tarfile.open(fileobj=io.BytesIO(sec), mode='r:gz') as t:
    d=t.extractfile('token.cache')

    #print file content
    print("File content",str(d.read()))

with tarfile.open(fileobj=io.BytesIO(sec), mode='r:gz') as t:
    d=t.extractfile('token.cache')
    
#   app
app = msal.PublicClientApplication(
    config["client_id"], authority=config["authority"],
    token_cache=cache)
print('Connecting to app..')

#   exists?
result = None
accounts = app.get_accounts()
if accounts:
    logging.info("found accounts in the app")
    for a in accounts:
        print(a)
        if a["username"] == config["username"]:
            result = app.acquire_token_silent(config["scope"], account=a)
            break

if result and "access_token" in result:
    # Calling graph using the access token
    graph_data = requests.get(  # Use token to call downstream service
        config["endpoint"],
        headers={'Authorization': 'Bearer ' + result['access_token']},).json()
    #print("Graph API call result: %s" % json.dumps(graph_data, indent=2))
else:
    print(result.get("error"))
    print(result.get("error_description"))
    print(result.get("correlation_id"))  # You may need this when reporting a bug

main = 'https://graph.microsoft.com/v1.0/me/mailFolders/inbox/messages?$expand=attachments&$search="hasAttachments:true"'

response = requests.get(main, headers={'Authorization': 'Bearer ' + result['access_token']})
if response.status_code != 200:
    raise Exception(response.json())

response_json = response.json()

print('Starting upload...')

emails = response_json['value']

s3 = boto3.client('s3')
bucket ='demo-email-app'

for email in emails:
    email_id = email['id']
    subject = email['subject']
    if email['hasAttachments']:
        print(subject)
        attachments = email['attachments']
        for attachment in attachments:
            name = attachment['name']
            fileContent = json.dumps(email, indent=2)
            s3.put_object(Bucket=bucket, Key=name.replace('.', '_') + '.json', Body=fileContent.encode('UTF-8'))
        print('Upload Complete')
        #download_email_attachments(email_id, headers)

print('All uploads complete')

My secret is stored as binary in secrets manager, and it seems to be able to pull the secret and prints it fine. I'm running into an error in the # exists? section with "AttributeError: 'NoneType' object has no attribute 'get'"

Am I approaching this in the wrong way? I have the token stored in secretsmanager, and am trying to retrieve it for msal to use and authenticate my user to the MS Graph API so I can pull attachments from the Outlook account and store those in an s3 bucket.

MS Graph API Outlook Attachments to s3 bucket

0 Answers