Archive the pages in your sheet to S3 every month

import boto3
from datetime import date
from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from clickruntime import on_trigger, credentials, http, notify

SHEET_ID = "your-spreadsheet-id"
REGION, BUCKET = "us-east-1", "northwind-files"

def aws(service):
    return boto3.client(service, region_name=REGION, aws_access_key_id=credentials.secret("AWS_ACCESS_KEY_ID"),
                        aws_secret_access_key=credentials.secret("AWS_SECRET_ACCESS_KEY"))

@on_trigger
def run(event):
    sheets, s3, today = build("sheets", "v4", credentials=Credentials(credentials.connection("google", "work")), cache_discovery=False).spreadsheets(), aws("s3"), date.today().isoformat()
    urls = [r[0] for r in sheets.values().get(spreadsheetId=SHEET_ID, range="Legal Pages!A2:A").execute().get("values", []) if r]
    paths = []
    for url in urls:
        try:
            r = http.get(url, timeout=30)
            key = f"archive/{today}/{url.split('//', 1)[-1].replace('/', '_')}.html"
            s3.put_object(Bucket=BUCKET, Key=key, Body=r.content, ContentType="text/html")
            paths.append([f"s3://{BUCKET}/{key}"])
        except Exception as e:
            paths.append([f"failed: {e.__class__.__name__}"])
    sheets.values().update(spreadsheetId=SHEET_ID, range=f"Legal Pages!B2:B{len(urls) + 1}", valueInputOption="RAW", body={"values": paths}).execute()
    ok = sum(p[0].startswith("s3://") for p in paths)
    notify.slack(f"Archived {ok} of {len(urls)} pages to s3://{BUCKET}/archive/{today}/", channel="#legal")
    return {"archived": ok, "total": len(urls)}