app.py

import gradio as gr
import requests
from bs4 import BeautifulSoup
import urllib.parse

def fetch_website(url):
    try:
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0 Safari/537.36"
        }
        response = requests.get(url, headers=headers, timeout=10)
        response.raise_for_status()
        
        soup = BeautifulSoup(response.text, 'html.parser')
        title = soup.title.string if soup.title else "No Title"
        
        # Extract links from page
        base_url = urllib.parse.urljoin(url, '/')
        links = [
            urllib.parse.urljoin(base_url, a.get('href'))
            for a in soup.find_all('a', href=True)
        ]
        
        return {
            "title": title,
            "url": url,
            "status_code": response.status_code,
            "content_preview": response.text[:1000],  # First 1000 chars
            "links": "\n".join(links[:20])  # Show up to 20 links
        }
    except Exception as e:
        return {
            "title": "Error",
            "url": "",
            "status_code": 500,
            "content_preview": str(e),
            "links": ""
        }

# UI Definition
with gr.Blocks(theme="default") as demo:
    gr.Markdown("# 🌐 Proxy Website Surfer\nEnter a URL to fetch its contents through this HuggingFace-powered proxy.")
    
    with gr.Row():
        url_input = gr.Textbox(label="Enter URL", placeholder="https://example.com") 
    
    submit_btn = gr.Button("Fetch Site")
    
    with gr.Row():
        title_output = gr.Textbox(label="Page Title")
        status_output = gr.Number(label="HTTP Status Code")
    
    content_output = gr.Textbox(label="Content Preview (first 1000 characters)", lines=10)
    link_output = gr.Textbox(label="Extracted Links", lines=15)

    def wrapper(url):
        result = fetch_website(url)
        return (
            result["title"],
            result["status_code"],
            result["content_preview"],
            result["links"]
        )

    submit_btn.click(
        fn=wrapper,
        inputs=url_input,
        outputs=[title_output, status_output, content_output, link_output]
    )

demo.launch()