A!leys Galerie

import requests
from bs4 import BeautifulSoup
import json
import time
from datetime import datetime
from rich.console import Console
from rich.table import Table
from rich.progress import Progress

# Konfiguration
TARGET_URL = "https://www.bbc.com/news"
OUTPUT_FILE = "scraped_data.json"
USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"

console = Console()

def fetch_page(url: str) -> str:
    """Fetch the HTML content of a page."""
    headers = {"User-Agent": USER_AGENT}
    response = requests.get(url, headers=headers)
    response.raise_for_status()
    return response.text

def parse_news(html: str) -> list:
    """Parse the news articles from the HTML."""
    soup = BeautifulSoup(html, "html.parser")
    articles = []
    
    # Find all article elements (this depends on the website's structure)
    # For BBC News, we can look for h3 elements within the main content
    for article in soup.find_all("h3"):
        title = article.get_text(strip=True)
        link = article.find("a")
        if link:
            articles.append({
                "title": title,
                "link": link.get("href"),
                "timestamp": datetime.now().strftime("%Y-%m-%d %H:%M:%S")
            })
    
    return articles

def save_to_json(data: list, filename: str):
    """Save the scraped data to a JSON file."""
    with open(filename, "w", encoding="utf-8") as f:
        json.dump(data, f, indent=4, ensure_ascii=False)

def main():
    """Main execution function."""
    console.print("[bold magenta]Neon Scraper v1.0[/bold magenta] - Starting...")
    
    try:
        with Progress() as progress:
            task = progress.add_task("[cyan]Fetching data...", total=1)
            html = fetch_page(TARGET_URL)
            progress.update(task, advance=1)
            
            progress.add_task("[green]Parsing articles...", total=1)
            articles = parse_news(html)
            progress.update(task, advance=1)
            
            progress.add_task("[yellow]Saving to JSON...", total=1)
            save_to_json(articles, OUTPUT_FILE)
            progress.update(task, advance=1)
            
        console.print(f"[bold green]Success![/bold green] Scraped {len(articles)} articles and saved to {OUTPUT_FILE}.")
        
        # Display the first 5 articles in a table
        table = Table(title="Latest News")
        table.add_column("Title", style="bold magenta")
        table.add_column("Link", style="dim")
        
        for article in articles[:5]:
            table.add_row(article["title"], article["link"])
            
        console.print(table)
        
    except Exception as e:
        console.print(f"[bold red]Error:[/bold red] {e}")

if __name__ == "__main__":
    main()