app.py

import gradio as gr
import requests
import pandas as pd
import time
import os
import tempfile
import json
from datetime import datetime

# Function to query the GBIF API and download data
def download_gbif_data(species_name, country_code, max_results):
    base_url = "https://api.gbif.org/v1/occurrence/search"
    all_results = []
    offset = 0
    limit = 300
    status_message = ""
    metadata_file_path = None
    csv_file_path = None

    try:
        while offset < int(max_results):
            params = {
                "scientificName": species_name,
                "country": country_code,
                "limit": limit,
                "offset": offset,
            }
            response = requests.get(base_url, params=params)

            if response.status_code == 200:
                data = response.json()
                if "results" in data and data["results"]:
                    all_results.extend(data["results"])
                    status_message += f"Fetched {len(data['results'])} records for {species_name} (Offset: {offset}).\n"
                    print(f"Fetched {len(data['results'])} records for {species_name} (Offset: {offset}).")
                else:
                    status_message += f"No more data found for {species_name} at offset {offset}.\n"
                    print(f"No more data found for {species_name} at offset {offset}.")
                    break
            else:
                error_message = f"Failed to retrieve data for {species_name} at offset {offset}. HTTP Status Code: {response.status_code}"
                print(error_message)
                return f"Error: {error_message}", None, None

            offset += limit
            time.sleep(1)

        if all_results:
            df = pd.json_normalize(all_results)
            with tempfile.NamedTemporaryFile(suffix=".csv", delete=False) as tmp_file:
                csv_file_path = tmp_file.name
                df.to_csv(csv_file_path, index=False)
                print(f"Data for {species_name} saved to {csv_file_path}.")

            status_message += f"Data for {species_name} downloaded successfully!\n"
            # Generate Metadata
            metadata = {
                "speciesName": species_name,
                "countryCode": country_code,
                "maxResults": max_results,
                "downloadedTime": datetime.now().isoformat(),
                "gbif_url": f"https://www.gbif.org/occurrence/search?scientificName={species_name}&country={country_code}",
                "note": "Please cite GBIF as the original source of data."
            }

            with tempfile.NamedTemporaryFile(suffix=".json", mode="w", delete=False) as tmp_metadata_file:
                metadata_file_path = tmp_metadata_file.name
                json.dump(metadata, tmp_metadata_file, indent=2)
                print(f"Metadata saved to {metadata_file_path}")

            return status_message, csv_file_path, metadata_file_path

        else:
            return f"No data found for {species_name} in {country_code}.", None, None

    except Exception as e:
        error_message = f"An error occurred: {str(e)}"
        print(error_message)
        return error_message, None, None

# Clean Up Temporary File
def postprocess(status, csv_file_path, metadata_file_path):
    if csv_file_path:
        os.remove(csv_file_path)
        print(f"Removed temporary file: {csv_file_path}")
    if metadata_file_path:
        os.remove(metadata_file_path)
        print(f"Removed temporary file: {metadata_file_path}")
    return status, csv_file_path, metadata_file_path


# Wrap the download_gbif_data function to convert max_result to int
def download_gbif_data_wrapper(species_name, country_code, max_results):
    try:
        max_results = int(max_results)
    except ValueError:
        return "Error: Invalid value for Max Results. Please enter a valid integer.", None, None

    return download_gbif_data(species_name, country_code, max_results)



# Gradio Interface using gr.Blocks
with gr.Blocks(title="GBIF Data Downloader") as iface:
    gr.Markdown("Enter a species name, country code, and max results to download CSV data from GBIF")
    with gr.Row():
      species_name_input = gr.Textbox(label="Species Name", placeholder="e.g. Aconitum naviculare")
      country_code_input = gr.Textbox(label="Country Code", value="NP", placeholder="e.g. NP")
      max_results_input = gr.Textbox(label="Max Results", value="5000", placeholder="e.g. 5000")
    with gr.Row():
      download_button = gr.Button("Download Data")
    with gr.Row():
        output_status = gr.Textbox(label="Status")
        output_csv = gr.File(label="Download CSV")
        output_metadata = gr.File(label="Download Metadata")

    inputs = [species_name_input, country_code_input, max_results_input]
    outputs = [output_status, output_csv, output_metadata]

    def clear_inputs(): # Create a function to clear all inputs
      return [None, None, None]

    download_button.click(
        download_gbif_data_wrapper,
        inputs=inputs,
        outputs=outputs,
        postprocess = postprocess
    ).then(clear_inputs, None, inputs) # added the then() and clear_inputs

if __name__ == "__main__":
    iface.launch()