in src/utils/data.py [0:0]
def get_account_data(s3_url: str):
"""Gets a XLS from the provided s3_url and returns a dict of account info. """
if 's3://' not in s3_url:
raise ValueError(f's3_url was set to {s3_url} and did not include s3://')
s3_path = s3_url.split('/', 3) # Max split of 3 means object key will be a single item even if it has "/"
bucket_name = s3_path[2]
object_key = s3_path[3]
if not (bool(bucket_name) and bool(object_key)):
raise ValueError(f'bucket_name or object_key is either None or Empty')
if not re.search(r'^\S+.xls$', object_key):
raise Exception("File format not supported, Only '.xsl' format is supported as of now.")
xls = get_s3_data(bucket_name, object_key)
account_data = process_xls(xls)
return account_data