Spaces:
Running
Running
| import gradio as gr | |
| import requests | |
| from bs4 import BeautifulSoup | |
| from urllib.parse import urljoin | |
| def parse_links_and_content(ort): | |
| base_url = "https://vereine-in-deutschland.net" | |
| # Konstruiere die vollständige URL | |
| url = f"{base_url}/vereine/Bayern/{ort}" | |
| try: | |
| # Senden der Anfrage an die URL | |
| response = requests.get(url) | |
| response.raise_for_status() # Überprüfen, ob die Anfrage erfolgreich war | |
| # Parse the HTML content using BeautifulSoup | |
| soup = BeautifulSoup(response.content, 'html.parser') | |
| # Finde das Element mit dem CSS-Selektor | |
| target_div = soup.select_one('div.row-cols-1:nth-child(4)') | |
| if target_div: | |
| # Extrahiere alle Links aus dem Element und füge die Base URL hinzu | |
| links = [urljoin(base_url, a['href']) for a in target_div.find_all('a', href=True)] | |
| # Extrahiere den HTML-Code des Elements | |
| html_code = str(target_div) | |
| return html_code, links | |
| else: | |
| return "Target div not found", [] | |
| except Exception as e: | |
| return str(e), [] | |
| def scrape_links(links): | |
| results = [] | |
| for link in links: | |
| try: | |
| # Senden der Anfrage an die URL | |
| response = requests.get(link) | |
| response.raise_for_status() # Überprüfen, ob die Anfrage erfolgreich war | |
| # Parse the HTML content using BeautifulSoup | |
| soup = BeautifulSoup(response.content, 'html.parser') | |
| # Extrahiere den gewünschten Inhalt (hier als Beispiel der Titel der Seite) | |
| content = soup.title.string if soup.title else "No title found" | |
| results.append((link, content)) | |
| except Exception as e: | |
| results.append((link, str(e))) | |
| return results | |
| # Erstelle die Gradio-Schnittstelle | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# Vereine in Bayern Parser") | |
| ort_input = gr.Textbox(label="Ort", placeholder="Gib den Namen des Ortes ein") | |
| html_output = gr.Code(label="HTML-Code des Elements", language="html") | |
| links_output = gr.JSON(label="Gefundene Links") | |
| content_output = gr.JSON(label="Inhalt der Links") | |
| def process_ort(ort): | |
| html_code, links = parse_links_and_content(ort) | |
| scraped_content = scrape_links(links) | |
| return html_code, links, scraped_content | |
| # Button zum Starten der Parsung | |
| button = gr.Button("Parse und Scrape") | |
| # Verbinde den Button mit der Funktion | |
| button.click(fn=process_ort, inputs=ort_input, outputs=[html_output, links_output, content_output]) | |
| # Starte die Gradio-Anwendung | |
| demo.launch() |