scraper.py

import requests
from bs4 import BeautifulSoup

def get_headings(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    headings = [h.get_text(strip=True) for h in soup.find_all(['h2', 'h3'])[:10]]
    return headings

def scrape_news(url, heading=None):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    articles = soup.find_all('article')[:6]
    news = []
    for art in articles:
        title = art.get_text(strip=True)
        link = art.find('a')['href'] if art.find('a') else url
        image = art.find('img')['src'] if art.find('img') else ''
        news.append({
            'title': title,
            'summary': f'Brief summary about {title[:40]}...',
            'link': link,
            'image': image
        })
    return news