--- title: Email importer keywords: fastai sidebar: home_sidebar nb_path: "nbs/importers.GmailImporter.ipynb" ---
This importers fetches your emails and accounts over IMAP, it uses the python built-in imap client and some convenience functions for easier usage, batching and importing to the pod. This importer requires you to login with your email address and an app password. It is tested on gmail, but should work for other IMAP-servers.
{% include note.html content='The recommended usage for Gmail is to enable two-factor authentication. In this case, make sure you allow SMTP-connections and set an application password (explained in the same link)' %}
The EmailImporter
communicates with email providers over imap. We created a convenience class around pythons imaplib , called the ImapClient
that lets you list your mailboxes, retriev your mails and get their content.
class Account(Item):
def __init__(self, dateAccessed=None, dateCreated=None, dateModified=None, deleted=None,
externalId=None, itemDescription=None, starred=None, version=None, id=None, importJson=None,
handle=None, displayName=None, service=None, itemType=None, avatarUrl=None, changelog=None,
label=None, genericAttribute=None, measure=None, sharedWith=None, belongsTo=None, price=None,
location=None, organization=None, owner=None):
super().__init__(dateAccessed=dateAccessed, dateCreated=dateCreated, dateModified=dateModified,
deleted=deleted, externalId=externalId, itemDescription=itemDescription, starred=starred,
version=version, id=id, importJson=importJson, changelog=changelog, label=label,
genericAttribute=genericAttribute, measure=measure, sharedWith=sharedWith)
self.handle = handle
self.displayName = displayName
self.service = service
self.itemType = itemType
self.avatarUrl = avatarUrl
self.belongsTo = belongsTo if belongsTo is not None else []
self.price = price if price is not None else []
self.location = location if location is not None else []
self.organization = organization if organization is not None else []
self.owner = owner if owner is not None else []
The email importer has the following parameters
pod_client = PodClient()
assert pod_client.add_to_schema(EmailMessage(externalId="x", subject="x", dateSent=2, content="x"))
assert pod_client.add_to_schema(MessageChannel(externalId="x"))
assert pod_client.add_to_schema(Person(externalId="x", firstName="x"))
assert pod_client.add_to_schema(Account(externalId="x"))
def get_gmail_creds():
return read_file(HOME_DIR / '.memri' / 'credentials_gmail.txt').split("\n")[:2]
imap_user, imap_pw = get_gmail_creds()
importer = EmailImporter.from_data()
importer_run = ImporterRun(username=imap_user, password=imap_pw)
importer.run(importer_run=importer_run, pod_client=pod_client)
importer.set_imap_client(None, imap_user, imap_pw)
mail_ids = importer.imap_client.get_all_mail_ids()
assert len(mail_ids) > 0
all_mails = importer.get_mails(mail_ids[:int(10)],
importer_run=None,
pod_client=pod_client)
assert len(all_mails) > 0
for x in all_mails: assert isinstance(x, EmailMessage)
all_accounts = get_unique_accounts(all_mails)
assert len(all_accounts) > 0
test = b"""\
Message-id: 1234\r
From: user1 <a@gmail.com>\r
To: user1 <b@gmail.com>\r
Reply-to: user1 <c@gmail.com>\r
Subject: the subject\r
Date: Mon, 04 May 2020 00:37:44 -0700\r
This is content"""
email_importer = EmailImporter()
mail_item = email_importer.create_item_from_mail(test, 'message_channel_id')
assert mail_item.externalId == '1234'
assert mail_item.sender[0].externalId == 'a@gmail.com'
assert mail_item.receiver[0].externalId == 'b@gmail.com'
assert mail_item.replyTo[0].externalId == 'c@gmail.com'
assert mail_item.subject == 'the subject'
assert mail_item.content == 'This is content'
assert mail_item.dateSent == email_importer.get_timestamp_from_message(email.message_from_bytes(test))
assert mail_item.messageChannel[0].externalId == 'message_channel_id'
email_importer = EmailImporter()
message = email.message.EmailMessage()
message.set_content('aa')
message.add_attachment(b'bb', maintype='image', subtype='jpeg', filename='sample.jpg')
message.add_attachment(b'cc', maintype='image', subtype='jpeg', filename='sample2.jpg')
content = email_importer.get_content(message)
attachments = email_importer.get_attachments(message)
assert content == 'aa\n'
assert attachments[0].get_content() == b'bb'
assert attachments[1].get_content() == b'cc'
Not implemented