Python: Synchronously (block until it's ready) request a GBIF download

gistfile1.py

# Quick and dirty gist to show how to request a GBIF download, block until it's ready then finally download it.
# (no need to monitor an email address, nor to install PyGBIF and all its dependencies. Only requests is needed)

# TODO: use download id as filename
# TODO: improve make_predicate function so it's much more flexible
from time import sleep

import requests

SLEEP_DURATION = 20


def make_predicate_dataset_key(
    dataset_key: str, username: str, notification_address: str
):
    v = {
        "creator": username,
        "notificationAddresses": [notification_address],
        "predicate": {"type": "equals", "key": "DATASET_KEY", "value": dataset_key},
    }

    return v


def test_blocking_download(
    dataset_key: str,
    username: str,
    password: str,
    notification_email: str,
    output_path: str,
):
    p = make_predicate_dataset_key(dataset_key, username, notification_email)

    print(f"Will trigger a download for datasetKey={dataset_key}")
    download_trigger = requests.post(
        "https://api.gbif.org/v1/occurrence/download/request",
        json=p,
        auth=(username, password),
    )
    download_id = download_trigger.text
    print(f"Download triggered, download_id is {download_id}")

    while True:
        print(f"(re)trying to get download {download_id}...")
        download_get = requests.get(
            f"https://api.gbif.org/v1/occurrence/download/request/{download_id}"
        )
        status = download_get.status_code

        if status != 404:  # 404: not ready yet
            if status == 200:
                print(f"Download is ready, getting it")
                with open(output_path, "wb") as f:
                    f.write(download_get.content)
            else:
                print(f"Status is {status}, why?")
                print(download_get)
            break

        sleep(SLEEP_DURATION)


if __name__ == "__main__":
    test_blocking_download(
        dataset_key="b7ee2a4d-8e10-410f-a951-a7f032678ffe",
        username="<YOUR_GBIF_USERNAME_HERE>",
        password="<YOUR_GBIF_PASSWORD_HERE>",
        notification_email="<YOUR_GBIF_EMAIL_HERE>",
        output_path="download.zip",
    )