Get a weekly Drive cleanup report in Slack

from collections import defaultdict
from datetime import datetime, timedelta, timezone
from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from clickruntime import on_trigger, credentials, notify

@on_trigger
def run(event):
    drive = build("drive", "v3", credentials=Credentials(credentials.connection("google", "work")), cache_discovery=False)
    now = datetime.now(timezone.utc)
    files, token = [], None
    while True:
        page = drive.files().list(q="trashed=false and mimeType!='application/vnd.google-apps.folder'", pageToken=token,
                                  fields="nextPageToken,files(name,md5Checksum,modifiedTime)", pageSize=1000).execute()
        files += page.get("files", [])
        token = page.get("nextPageToken")
        if not token:
            break
    by_sum = defaultdict(list)
    for f in files:
        if f.get("md5Checksum"):
            by_sum[f["md5Checksum"]].append(f["name"])
    dups = [names for names in by_sum.values() if len(names) > 1]
    age = lambda f: now - datetime.fromisoformat(f["modifiedTime"].replace("Z", "+00:00"))
    backups = [f["name"] for f in files if "backup" in f["name"].lower() and age(f) > timedelta(days=7)]
    stale = [f["name"] for f in files if age(f) > timedelta(days=365)]
    notify.slack(f"Drive report: {len(dups)} duplicate sets, {len(backups)} old backups, {len(stale)} files untouched for a year.\n"
                 + "\n".join(" = ".join(d) for d in dups[:20]), channel="#it")
    return {"duplicates": len(dups), "backups": len(backups), "stale": len(stale)}