Check Broken Links And SEO Basics Locally From Termux

pkg install -y python
python -m pip install beautifulsoup4
python - <<'PYCODE'
from pathlib import Path
from urllib.parse import unquote, urlsplit
from bs4 import BeautifulSoup

root = Path('.').resolve()
problems = []
for page in root.rglob('*.html'):
    soup = BeautifulSoup(page.read_text(encoding='utf-8', errors='replace'), 'html.parser')
    if not soup.title or not soup.title.get_text(strip=True):
        problems.append((page, 'missing <title>'))
    if not soup.find('meta', attrs={'name': 'description'}):
        problems.append((page, 'missing meta description'))
    if not soup.find('link', rel='canonical'):
        problems.append((page, 'missing canonical'))
    for tag, attr in [('a','href'),('img','src'),('script','src'),('link','href')]:
        for node in soup.find_all(tag):
            raw = (node.get(attr) or '').strip()
            if not raw or raw.startswith(('#','mailto:','tel:','data:','javascript:')):
                continue
            parsed = urlsplit(raw)
            if parsed.scheme or parsed.netloc:
                continue
            target = unquote(parsed.path)
            candidate = (root / target.lstrip('/')) if target.startswith('/') else (page.parent / target)
            if target.endswith('/'):
                candidate = candidate / 'index.html'
            if not candidate.resolve().exists():
                problems.append((page, f'broken {attr}: {raw}'))
for page, issue in problems:
    print(f'{page}: {issue}')
print(f'Problems: {len(problems)}')
PYCODE