# scraper.py import requests from bs4 import BeautifulSoup from urllib.parse import urljoin def scrape_url(url): """Fetch text + image URLs from webpage.""" try: res = requests.get(url, timeout=10) res.raise_for_status() soup = BeautifulSoup(res.text, 'html.parser') # get text text = soup.get_text(separator='\n', strip=True) # get image URLs (absolute) images = [] for img in soup.find_all('img'): src = img.get('src') if src: images.append(urljoin(url, src)) return text, images except Exception as e: return f"[Error scraping {url}: {e}]", []