Programmatic batch downloads

import operator
import pathlib
import time
import databento as db

# First, create a historical client
client = db.Historical("$YOUR_API_KEY")

# Next, we will submit a batch job
new_job = client.batch.submit_job(
    dataset="GLBX.MDP3",
    start="2022-12-12T00:00:00",
    end="2022-12-17T00:00:00",
    symbols="OZN.OPT",
    schema="trades",
    split_duration="day",
    stype_in="parent",
)

# Retrieve the new job ID
new_job_id: str = new_job["id"]

# Now, we have to wait for our batch job to complete
while True:
    done_jobs = list(map(operator.itemgetter("id"), client.batch.list_jobs("done")))
    if new_job_id in done_jobs:
        break  # Exit the loop to continue
    time.sleep(1.0)

# Once complete, we will download the files
downloaded_files = client.batch.download(
    job_id=new_job_id,
    output_dir=pathlib.Path.cwd(),
)

# Finally, we can load the data into a DBNStore for analysis
for file in sorted(downloaded_files):
    if file.name.endswith(".dbn.zst"):
        data = db.DBNStore.from_file(file)

        # Convert the data to a pandas.DataFrame
        df = data.to_df()
        print(f"{file.name} contains {len(df):,d} records")

glbx-mdp3-20221212.trades.dbn.zst contains 1,662 records
glbx-mdp3-20221213.trades.dbn.zst contains 3,511 records
glbx-mdp3-20221214.trades.dbn.zst contains 2,544 records
glbx-mdp3-20221215.trades.dbn.zst contains 2,460 records
glbx-mdp3-20221216.trades.dbn.zst contains 2,191 records