Find download URLs for OPERA DISP products in ASF non-production archive by product version and frame id

find_opera_disp_products.py

import requests


def get_download_url(product: dict, protocol: str) -> str:
    if protocol not in ['https', 's3']:
        raise ValueError(f'Unknown protocol {protocol}; must be https or s3')

    for url in product['umm']['RelatedUrls']:
        if url['Type'].startswith('GET DATA') and url['URL'].startswith(protocol):
            return url['URL']
    raise ValueError(f'No download URL found for granule {product['umm']['GranuleUR']}')


def get_products(frame_id: int, product_version: str) -> list[dict]:
    # https://cmr.earthdata.nasa.gov/search/site/docs/search/api.html
    url = 'https://cmr.uat.earthdata.nasa.gov/search/granules.umm_json'
    params = {
        'short_name': 'OPERA_L3_DISP-S1_V1',
        'attribute[]': [
            f'float,PRODUCT_VERSION,{product_version}',
            f'int,FRAME_NUMBER,{frame_id}',
        ],
        'page_size': 2000,
    }
    headers = {}

    products = []
    while True:
        response = requests.get(url, params=params, headers=headers)
        response.raise_for_status()
        products.extend(response.json()['items'])
        if 'CMR-Search-After' not in response.headers:
            break
        headers['CMR-Search-After'] = response.headers['CMR-Search-After']
    return products


for product in get_products(frame_id=18904, product_version='0.9'):
    print(get_download_url(product, protocol='https'))