batchload.py

def main(data, context, dataset='test_dataset_dev', table='beer'):
    print('Event ID: {}'.format(context.event_id))
    print('Event type: {}'.format(context.event_type))
    print('Importing required modules.')

    from google.cloud import bigquery

    print('This is the data: {}'.format(data))

    input_bucket_name = data['bucket']
    source_file = data['name']
    uri = 'gs://{}/{}'.format(input_bucket_name, source_file)

    print('Getting the data from bucket "{}"'.format(uri))

    client = bigquery.Client()
    dataset_ref = client.dataset(dataset)

    job_config = bigquery.LoadJobConfig()
    job_config.autodetect = True
    job_config.schema_update_options = [bigquery.SchemaUpdateOption.ALLOW_FIELD_ADDITION]

    job_config.source_format = bigquery.SourceFormat.CSV
    job_config.write_disposition = bigquery.WriteDisposition.WRITE_APPEND

    load_job = client.load_table_from_uri(uri, dataset_ref.table(table), job_config=job_config)

    print('Starting job {}'.format(load_job.job_id))

    load_job.result()
    print('Job finished.')

    destination_table = client.get_table(dataset_ref.table(table))
    print('Loaded {} rows.'.format(destination_table.num_rows))

    print('File imported successfully.')