era5_google_cloud.py

from pathlib import Path

import requests


BASE_URL = "https://storage.googleapis.com/gcp-public-data-arco-era5/raw/date-variable-single_level"
DATA_DIR = Path("data")

VARIABLE = "total_precipitation"
YEAR = 2010
MONTH = 7

for day in range(1, calendar.monthrange(YEAR, MONTH)[1] + 1):
    
    url = f"{BASE_URL}/{YEAR}/{MONTH:02}/{day:02}/{VARIABLE}/surface.nc"
    output_dir = DATA_DIR / VARIABLE / f"{YEAR:04}" / f"{MONTH:02}"
    output_dir.mkdir(parents=True, exist_ok=True)
    fp = output_dir / f"{VARIABLE}_{YEAR}{MONTH:02}{day:02}.nc"

    with requests.get(url, stream=True) as r:
        with open(fp, "wb") as f:
            for chunk in r.iter_content(chunk_size=1024**2):
                if chunk:
                    f.write(chunk)