Gmail API Fundamentals

Gmail Cleanup — Gmail API Fundamentals

Gmail Cleanup — Practical Scripting

Course 1 · Chapter 3 · Gmail API Fundamentals

📧 Gmail API Fundamentals

Now that you have credentials and configuration set up, it's time to connect to Gmail and start querying emails. This chapter teaches the Gmail API structure, how to authenticate, query emails, and parse the responses.

🔌 Connecting to Gmail

from google.auth.transport.requests import Request
from google.oauth2.credentials import Credentials
from google_auth_oauthlib.flow import InstalledAppFlow
from googleapiclient.discovery import build

def get_gmail_service():
    """Authenticate and return Gmail service."""
    SCOPES = ['https://www.googleapis.com/auth/gmail.modify']

    creds = None

    # Load existing token if available
    try:
        creds = Credentials.from_authorized_user_file('token.json', SCOPES)
    except:
        pass

    # If no valid credentials, perform OAuth flow
    if not creds or not creds.valid:
        if creds and creds.expired and creds.refresh_token:
            creds.refresh(Request())
        else:
            flow = InstalledAppFlow.from_client_secrets_file(
                'credentials.json', SCOPES
            )
            creds = flow.run_local_server(port=0)

        # Save token for next time
        with open('token.json', 'w') as token:
            token.write(creds.to_json())

    return build('gmail', 'v1', credentials=creds)
        

🔍 Querying Emails

Gmail Search Syntax

Query	Meaning
`before:2020/01/01`	Emails before January 1, 2020
`from:sender@example.com`	Emails from specific sender
`filename:pdf`	Emails with PDF attachments
`size:>10M`	Emails larger than 10MB
`has:attachment`	Emails with attachments

Query Example

def find_old_emails(service, days_old: int) -> list:
    """Find emails older than N days."""
    from datetime import datetime, timedelta

    cutoff_date = (datetime.now() - timedelta(days=days_old)).strftime('%Y/%m/%d')
    query = f"before:{cutoff_date}"

    try:
        results = service.users().messages().list(
            userId='me',
            q=query,
            maxResults=10
        ).execute()

        messages = results.get('messages', [])
        print(f"✅ Found {len(messages)} emails older than {days_old} days")
        return messages

    except Exception as e:
        print(f"❌ Error: {e}")
        return []
        

📨 Parsing Email Details

def get_email_details(service, message_id: str) -> dict:
    """Get details about a single email."""
    try:
        message = service.users().messages().get(
            userId='me',
            id=message_id
        ).execute()

        headers = message['payload']['headers']
        subject = next(h['value'] for h in headers if h['name'] == 'Subject')
        sender = next(h['value'] for h in headers if h['name'] == 'From')
        date_str = next(h['value'] for h in headers if h['name'] == 'Date')

        size = int(message.get('sizeEstimate', 0))

        return {
            'id': message_id,
            'subject': subject,
            'from': sender,
            'date': date_str,
            'size_bytes': size,
            'size_mb': size / 1024 / 1024
        }

    except Exception as e:
        print(f"❌ Error: {e}")
        return None
        