app.py

import gradio as gr
import requests
from bs4 import BeautifulSoup
from gradio_client import Client
from urllib.parse import urljoin
#import pandas as pd
#from io import StringIO
import json
#import groq
import os

def list_of_clubs(ort):
    base_url = "https://vereine-in-deutschland.net"
    all_links_text = []
    initial_url = f"{base_url}/vereine/Bayern/{ort}"

    try:
        response = requests.get(initial_url)
        response.raise_for_status()
        soup = BeautifulSoup(response.content, 'html.parser')
        
        # Determine the last page
        link_element = soup.select_one('li.page-item:nth-child(8) > a:nth-child(1)')
        last_page = 10
        if link_element and 'href' in link_element.attrs:
            href = link_element['href']
            last_page = int(href.split('/')[-1])

        # Loop through all pages and collect links
        for page_number in range(1, last_page + 1):
            page_url = f"{base_url}/vereine/Bayern/{ort}/p/{page_number}"
            response = requests.get(page_url)
            response.raise_for_status()
            soup = BeautifulSoup(response.content, 'html.parser')
            target_div = soup.select_one('div.row-cols-1:nth-child(4)')

            if target_div:
                texts = [a.text for a in target_div.find_all('a', href=True)]
                all_links_text.extend(texts)
            else:
                print(f"Target div not found on page {page_number}")

    except Exception as e:
        return str(e), []

    all_links_text = all_links_text[0::2]
    return all_links_text

def process_ort(ort):
    links_text = list_of_clubs(ort)
    return links_text

# Create the Gradio interface
iface = gr.Interface(
    fn=process_ort,
    inputs=gr.Textbox(lines=1, placeholder="Ort eingeben..."),
    outputs=gr.Textbox(),
    title="vereine",
    description="VereineFinder"
)

# Launch the Gradio app
iface.launch()