get_ERA5_waves.py

import os
import datetime
import cdsapi #Setup as per https://cds.climate.copernicus.eu/how-to-api
import pandas as pd

dates = pd.date_range(datetime.date(2006,1,1),datetime.date(2023,12,1),freq='MS')

dates = dates[::-1]  # reverse order to start downloading from the most recent data

client = cdsapi.Client()
download_folder = '/storage/shared/oceanparcels/output_data/data_Michael/ERA5/waves_NECCTON'
name_ = 'ERA5_global_waves_monthly_'

for date_ in dates:

  file_str = os.path.join(download_folder, name_ + str(date_.date()) + '.nc')

  dataset = 'reanalysis-era5-single-levels'
  request = {
    'product_type': ['reanalysis'],
    'variable': ['mean_wave_period','peak_wave_period','u_component_stokes_drift','v_component_stokes_drift'],
    'year': str(date_.year),
    'month': '%2.2i' %date_.month,
    'day': [
                      '01', '02', '03',
                      '04', '05', '06',
                      '07', '08', '09',
                      '10', '11', '12',
                      '13', '14', '15',
                      '16', '17', '18',
                      '19', '20', '21',
                      '22', '23', '24',
                      '25', '26', '27',
                      '28', '29', '30',
                      '31',
                  ],
                  "time": [ # Take 6 hourly data to reduce load on CDS
                        "00:00",
                        "06:00",
                        "12:00",
                        "18:00"
                    ],
    'data_format': 'netcdf',
  }
  target = file_str
  client.retrieve(dataset, request, target)
  print(file_str, "retrieved.")