Spaces:
Sleeping
Sleeping
File size: 1,918 Bytes
1a172fd 7a4ee36 1a172fd 7a4ee36 d748d51 1a172fd 7a4ee36 1a172fd 7a4ee36 c53abd7 7a4ee36 1a172fd c53abd7 1a172fd 7a4ee36 7df5f02 7a4ee36 1a172fd c53abd7 1a172fd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 |
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() |