I am developing a Gmail extracting app and using Gmail API to fetch mail from server. the problem lies in the fact that fetch time for mails is too large even though I used threading in back end framework. now I am going to implement one feature which will suggest user opting for bulk download that "once your download is ready, we will mail you" but for that i want to run download.py mentioned below in app tree in background and once the fetch is over it will get terminated. And in the very bottom of the code i want to mail user that their download is ready but its not working though i have defined the mail server in settings.py .
download.py
import httplib2, base64
from stripogram import html2text
from oauth2client.django_orm import Storage
from apiclient.discovery import build
from oauth2client import client
from django.contrib.auth.models import User
from .models import CredentialsModel
from django.conf import settings
from rest_framework.views import APIView
from rest_framework.response import Response
from rest_framework import authentication, permissions
from gextracto import models
from gextracto.models import UserData
from django.core.mail import EmailMessage
from django.core import mail
connection = mail.get_connection()
class ListMails(APIView):
"""
Gets a list of a specified number mail ids for a particular label
Extracts the email in the form of plain/text
The API returns all the extracted mails
"""
authentication_classes = (authentication.SessionAuthentication,)
permission_classes = (permissions.IsAuthenticated,)
def extract_headers(self, message):
"""
Extract the headers for a single mail and returns it
{To, From, Subject}
"""
needed_fields = ('From', 'To', 'Subject')
return {i['name']:i['value'] for i in message['payload']['headers'] if i['name'] in needed_fields}
def get_message_body(self, message):
"""
Get the body of an email
Recursively look for the body for different mimetypes
Returns the body as text/plain
"""
if 'payload' in message:
return self.get_message_body(message['payload'])
elif 'parts' in message:
return self.get_message_body(message['parts'][0])
else:
data = base64.urlsafe_b64decode(message['body']['data'].encode('ASCII'))
markdown_data = html2text(data)#.decode('utf-8', "replace")
data = data.replace("\n", "<br/>")
# return {markdown, html}
return {'markdown':unicode( markdown_data,"ISO-8859-1"), 'html':unicode(data,"ISO-8859-1")} if markdown_data else {'html':unicode(data,"ISO-8859-1")}
def message_content_html(self, userId, message_id, service):
"""
Make queries to get the content for a mail given its message id
Returns all the content
"""
content = {'id':message_id}
# try
message = service.users().messages().get(userId=userId, id=message_id).execute()
mimetype = message['payload']['mimeType']
if mimetype == 'text/html':
return {}
#
else:
body = self.get_message_body(message)
if body == "":
body = "<empty message>"
headers = self.extract_headers(message)
content['body'] = body
content.update(headers)
return content
def collect_mails(self, user, messages, service):
"""
Collect the content for all the mails currently downloaded
"""
all_messages = []
try:
for message in messages:
content = self.message_content_html(user.username, message['id'], service)
if content:
all_messages.append(content)
return all_messages
# return empty list if no messages were downloaded
except KeyError:
return []
def get(self, request, format=None):
"""
Handles the GET request to get all the mails for a label
Paginages through the GAPI content if required
API returns all the messages
{To, From, Subject, body}
"""
user = request.user
storage = Storage(CredentialsModel, 'id', user, 'credential')
credentials = storage.get()
http_auth = credentials.authorize(httplib2.Http())
service = build('gmail', 'v1', http=http_auth)
user_Id = user.username
label_id = request.GET['label']
# try
# call Google API with a request to get a list of all the labels
response = service.users().messages().list(userId=user_Id, labelIds=label_id, maxResults=100).execute()
all_messages = self.collect_mails(user, response['messages'], service)
if not all_messages:
return Response([])
else:
if 'nextPageToken' in response:
page_token_flag = True
# request more more mails if the download limit has not yet been satisfied
while(page_token_flag):
response = service.users().messages().list(userId=user_Id, pageToken=response['nextPageToken'], maxResults=100).execute()
all_messages.append(self.collect_mails(user, response['messages'], service))
print(all_messages)
#for x in range(0,len(all_messages)):
#b=all_messages[10]
#instance= UserData(user_id=user ,label=label_id, sender = b['From'] , subject=b['Subject'] , body=b['body'])
#instance.save()
page_token_flag = 'nextPageToken' in response
##
for x in range(0,len(all_messages)):
b=all_messages[10]
instance= UserData(user_id=user ,label=label_id, sender = b['From'] , subject=b['Subject'] , body=b['body'])
instance.save()
print ("Hi i am here!!!")
email = EmailMessage('Your Download Ready!', 'http://127.0.0.1:8000/admin/gextracto/userdata/', to=[user], connection=connection)
email.send()
connection.close()
return Response(all_messages)
Please tell me the way to run it in background. if need any other info please do ask. Thanks
Don't know the exact requirements but I'll think about Celery to run background tasks. This approach allows to manage all post-script activities in native Django manner.
Also you can think about running the Django script using cron (as manage.py command) - but it can lead to some limitations.
What about sending emails failure - believe, you don't need to close connection after sending email. Usually I use send_mail()/send_mass_mail() functions - please, check their code to get an idea.