## fdex database pull ##
# Request only what you need, transport only what is necessary, and cache what you can.
# fdex_db_pull.py
# Python translation by ChatGPT

import requests
import pandas as pd
from datetime import datetime
import string

# -------------------------------
# Setup
# -------------------------------

# Current date formatting (equivalent to strftime in R)
theDate = datetime.now().strftime("%d_%b_%Y")

# Alphabet vector
alphabet_vector = list(string.ascii_lowercase)

# Base API URL
fd_api_base_url = "https://fdex.org/services/api/query.php?qText="

# -------------------------------
# Functions
# -------------------------------

def get_fd_record(endpoint, query_text):
    url = f"{fd_api_base_url}{query_text}&qField={endpoint}"
    try:
        response = requests.get(url, timeout=10)
        response.raise_for_status()
        return response.json()
    except Exception:
        return None

# -------------------------------
# Main Code
# -------------------------------

# Column names
the_colnames = [
    "taxon", "authors", "mbNumber", "otherID", "rank", "rankCode",
    "taxonomicStatus", "currentTaxon", "currentMbNumber",
    "currentOtherID", "currentStatus", "parentTaxon",
    "parentMbNumber", "parentOtherID", "recordSource",
    "taxonomicAgreement"
]

# Initialize empty DataFrame
fdex_data_frame = pd.DataFrame(columns=the_colnames)

# Loop through alphabet combinations
for i, first_letter_lower in enumerate(alphabet_vector):
    for j, second_letter in enumerate(alphabet_vector):
        first_letter = first_letter_lower.upper()
        combined_letters = first_letter + second_letter

        print(f"Processing genera starting: '{combined_letters}' for i = {i+1} and j = {j+1}")

        query = f"{combined_letters}%25"
        fdex_data = get_fd_record("taxon", query)

        if fdex_data:
            temp_df = pd.DataFrame(fdex_data)
            fdex_data_frame = pd.concat([fdex_data_frame, temp_df], ignore_index=True)

# Filter for "Index Fungorum"
fdex_data_frame = fdex_data_frame[
    fdex_data_frame["recordSource"] == "Index Fungorum"
]

# Save to CSV
output_file = f"{theDate}_fdex_db.csv"
fdex_data_frame.to_csv(output_file, index=False)

print(f"Data saved to {output_file}")