import requests

def import_filtered_cpi():
    # URL for BLS CPI data
    url = "https://download.bls.gov/pub/time.series/cu/cu.dat..."
    # Set User-Agent to avoid 403 errors
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36"
    }

    # Fetch data
    try:
        response = requests.get(url, headers=headers)
        response.raise_for_status()  # Raise exception for non-200 status codes
    except requests.exceptions.RequestException as e:
        print(f"Error fetching data: {e}")
        return

    # Split data into rows
    data = response.text
    rows = data.strip().split("\n")

    # Map period to month (M01 -> 01, M02 -> 02, etc.)
    period_to_month = {
        "M01": "01", "M02": "02", "M03": "03", "M04": "04",
        "M05": "05", "M06": "06", "M07": "07", "M08": "08",
        "M09": "09", "M10": "10", "M11": "11", "M12": "12"
    }

    # Prepare output file
    output_file = "cpi_filtered_data.txt"

    # Filter rows and write to file
    with open(output_file, "w", encoding="utf-8") as f:
        # Write headers
        f.write("date\tvalue\n")

        # Filter for series_id = "CUUR0000SA0" and period != "M13"
        filtered_rows = []
        for row in rows[1:]:  # Skip header
            columns = row.split("\t")
            series_id = columns[0].strip()
            year = columns[1].strip()
            period = columns[2].strip()
            value = columns[3].strip()
            if series_id == "CUUR0000SA0" and period != "M13":
                # Convert period to month and format date as YYYY-MM-01
                if period in period_to_month:
                    date = f"{year}-{period_to_month[period]}-01"
                    filtered_rows.append([date, value])
                    f.write(f"{date}\t{value}\n")

    # Print summary
    print(f"Filtered {len(filtered_rows)} rows written to {output_file}")

if __name__ == "__main__":
    import_filtered_cpi()