app.py

import pandas as pd
import re
import gradio as gr

# Constants
CORE_STARS_CSV_PATH = "core_stars.csv"
OUTPUT_CORE_STARS_TXT_PATH = "core_stars.txt"
APP_DESCRIPTION = """
With love by @espejelomar!

Upload a CSV file, pinpointing the column with users' Telegram IDs. The program then reviews this data and produces a new CSV file. In this file, a `1` in the `is_in_core_stars` column confirms that the person is a member of Core Stars.

It is 100% certain that if an individual appears in your Excel file and is in the Core Stars group then they will have a 1 in the `is_in_core_stars` column, however there is a low probability (less than 5%) that they will have a 0 and I know part of Core Stars. This happens because the person incorrectly typed their Telegram ID in the form. For example, these are cases that have already happened:

1. They wrote O instead of 0.
2. They changed their Telegram ID after filling out the form.
"""

# Normalize Telegram IDs
def normalize_id(telegram_id):
    telegram_id = str(telegram_id).lower().strip()
    if telegram_id.startswith("https://t.me/"):
        telegram_id = telegram_id.replace("https://t.me/", "")
    telegram_id = telegram_id.lstrip("@")
    telegram_id = re.sub(r"[^a-zA-Z0-9_]", "", telegram_id)
    return telegram_id

# Create core_stars.txt
def create_core_stars_txt(csv_path, output_path, column_name="Telegram Handle"):
    df = pd.read_csv(csv_path)
    normalized_ids = df[column_name].apply(normalize_id).unique()
    with open(output_path, "w") as file:
        for id in normalized_ids:
            file.write(id + "\n")

# Read core_stars_ids
def read_core_stars_ids(file_path):
    with open(file_path, "r") as file:
        return [normalize_id(line) for line in file]

# Process uploaded CSV and return updated CSV
def process_csv(uploaded_csv, column_name):
    # create_core_stars_txt(CORE_STARS_CSV_PATH, OUTPUT_CORE_STARS_TXT_PATH)
    core_stars_ids = read_core_stars_ids(OUTPUT_CORE_STARS_TXT_PATH)
    
    df = pd.read_csv(uploaded_csv)
    df[column_name] = df[column_name].apply(normalize_id)
    df["is_in_core_stars"] = df[column_name].apply(
        lambda id: 1 if id in core_stars_ids else 0
    )
    cols = ["is_in_core_stars"] + [
        col for col in df.columns if col != "is_in_core_stars"
    ]
    df = df[cols]
    
    # Save to a temporary file and return
    output_file = "updated_file.csv"
    df.to_csv(output_file, index=False)
    return output_file

# Set up Gradio interface
iface = gr.Interface(
    fn=process_csv,
    inputs=[
        gr.File(label="Upload CSV File"),
        gr.Textbox(label="Enter Column Name for Telegram ID")
    ],
    outputs=gr.File(label="Download Updated CSV"),
    title="Telegram Core Stars Membership Checker",
    description=APP_DESCRIPTION
)

iface.launch()

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