Daily report

[icaoberg]

This is it call @shirey . It nothing but a wrapper around

def daily() -> pd.DataFrame:
    now = datetime.now()
    report_output_directory = "daily-report"
    report_output_filename = (
        f'{report_output_directory}/{str(now.strftime("%Y%m%d"))}.tsv'
    )

    if Path(report_output_filename).exists():
        df = pd.read_csv(report_output_filename, sep="\t")
        return df
    else:
        url = "https://ingest.api.hubmapconsortium.org/datasets/data-status"  # The URL to get the data from
        try:
            response = requests.get(url)  # Send a request to the URL to get the data
            response.raise_for_status()  # Check if the request was successful (no errors)
            json_data = response.json()  # Convert the response to JSON format

            # Ensure 'data' key exists in the JSON
            if "data" in json_data:  # Check if the JSON contains the key 'data'
                df = pd.DataFrame(
                    json_data["data"]
                )  # Create a DataFrame using the data under 'data' key
            else:
                raise KeyError(
                    "'data' key not found in the JSON response"
                )  # Raise an error if 'data' key is missing
        except (
            ValueError,
            KeyError,
        ) as e:  # Catch errors related to value or missing keys
            print(f"Error loading data: {e}")  # Print the error message
            return pd.DataFrame()  # Return an empty DataFrame if there is an error
        except (
            requests.RequestException
        ) as e:  # Catch errors related to the request itself
            print(f"Request failed: {e}")  # Print the error message
            return pd.DataFrame()  # Return an empty DataFrame if the request fails

        if not Path(report_output_directory).exists():
            Path(report_output_directory).mkdir()

        try:
            df.to_csv(report_output_filename, sep="\t", index=False)
        except:
            print(f"Unable to save dataframe to {report_output_filename}.")

        hive_directory = "/hive/hubmap/bdbags/reports/"
        report_output_backup_file = (
            f'{hive_directory}/{str(now.strftime("%Y%m%d"))}.tsv'
        )

        symlink = "/hive/hubmap/bdbags/reports/today.tsv"
        if Path(symlink).exists():
            Path(symlink).unlink()
            Path(symlink).symlink_to(report_output_backup_file)

        return df