check if links are broken, in the second run replace `TARGET_URL` with "https://gnusha.org/url"

link_checker.py

import re
import requests
from pathlib import Path
from concurrent.futures import ThreadPoolExecutor
from tqdm import tqdm

# Target URL to search for
TARGET_URL = "https://lists.linuxfoundation.org/pipermail"

def find_links_in_file(file_path):
    """Extract specific links from a markdown file."""
    with open(file_path, 'r', encoding='utf-8') as f:
        content = f.read()
    
    # Find all markdown links [text](url)
    links = re.findall(fr'\[([^\]]+)\]\(({TARGET_URL}[^)]+)\)', content)
    # Find all bare links
    bare_links = re.findall(fr'({TARGET_URL}\S+)', content)
    
    # Combine all found links (take URL from markdown links)
    all_links = [link[1] for link in links] + bare_links
    
    return list(set(all_links))  # Remove duplicates

def check_url(url):
    """Check if a URL is accessible."""
    try:
        response = requests.head(url, timeout=10, allow_redirects=True)
        if response.status_code == 405:  # If HEAD method not allowed, try GET
            response = requests.get(url, timeout=10)
        return url, response.status_code < 400, response.status_code
    except requests.RequestException as e:
        return url, False, str(e)

def main():
    # Get repository path from command line
    import argparse
    parser = argparse.ArgumentParser(description=f'Check links starting with {TARGET_URL}')
    parser.add_argument('repo_path', help='Path to the repository')
    args = parser.parse_args()
    
    repo_path = Path(args.repo_path)
    
    # Find all markdown files and collect links
    print(f"Finding links starting with {TARGET_URL}...")
    all_links = []
    for md_file in repo_path.rglob('*.md'):
        links = find_links_in_file(md_file)
        if links:
            print(f"\nFound in {md_file.relative_to(repo_path)}:")
            for link in links:
                print(f"  {link}")
            all_links.extend(links)
    
    if not all_links:
        print(f"\nNo links starting with {TARGET_URL} found.")
        return
    
    unique_links = list(set(all_links))
    print(f"\nChecking {len(unique_links)} unique links...")
    
    # Check all links in parallel
    with ThreadPoolExecutor(max_workers=5) as executor:
        results = list(tqdm(
            executor.map(check_url, unique_links),
            total=len(unique_links)
        ))
    
    # Print results
    print("\nResults:")
    print("========")
    
    print("\nBroken Links:")
    broken = False
    for url, is_working, status in results:
        if not is_working:
            broken = True
            print(f"❌ {url}")
            print(f"   Error: {status}")
    
    if not broken:
        print("No broken links found!")

if __name__ == '__main__':
    main()

Cool, thanks for double checking. check_url for most lists.linuxfoundation.org urls is unnecessary because you can just manually check that it's gone: https://lists.linuxfoundation.org/pipermail/bitcoin-dev which would indicate pipermail/bitcoin-dev/* will be 404 as well.