Find Broken Image References Across a Website in Python

import requests
from urllib.parse import urljoin, urlparse
from bs4 import BeautifulSoup
from concurrent.futures import ThreadPoolExecutor, as_completed

def find_all_links(base_url, max_pages=50):
    visited, to_visit = set(), {base_url}
    while to_visit and len(visited) < max_pages:
        url = to_visit.pop()
        if url in visited:
            continue
        visited.add(url)
        try:
            resp = requests.get(url, timeout=10)
            if 'text/html' not in resp.headers.get('Content-Type', ''):
                continue
            soup = BeautifulSoup(resp.text, 'html.parser')
            for tag in soup.find_all(['img', 'source']):
                src = tag.get('src') or tag.get('srcset', '').split()[0]
                if src:
                    full_url = urljoin(url, src)
                    if full_url.startswith(base_url.rstrip('/')):
                        yield full_url
            for a in soup.find_all('a', href=True):
                full_url = urljoin(url, a['href'])
                if full_url.startswith(base_url.rstrip('/')) and full_url not in visited:
                    to_visit.add(full_url)
        except requests.RequestException:
            pass

def check_images(base_url):
    image_urls = set(find_all_links(base_url))
    broken = []
    with ThreadPoolExecutor(max_workers=10) as executor:
        futures = {executor.submit(requests.head, url, timeout=5): url for url in image_urls}
        for future in as_completed(futures):
            url = futures[future]
            try:
                resp = future.result()
                if resp.status_code >= 400:
                    broken.append((url, resp.status_code))
            except requests.RequestException:
                broken.append((url, 'Connection error'))
    broken.sort(key=lambda x: x[1] if isinstance(x[1], int) else 999)
    return broken

if __name__ == '__main__':
    site = 'https://example.com'
    broken_images = check_images(site)
    for url, status in broken_images:
        print(f'{status} {url}')