#!/usr/bin/env python3
"""TSLaw: pastikan arsip penulis yang dimatikan sudah ber-noindex."""
import re, urllib.request

UA = {"User-Agent": "Mozilla/5.0"}
for u in ("https://www.tslaw.id/author/mantapman/", "https://www.tslaw.id/?s=hukum",
          "https://www.tslaw.id/feed/", "https://www.tslaw.id/pengacara-gugat-cerai-surabaya/"):
    h = urllib.request.urlopen(urllib.request.Request(u, headers=UA), timeout=60).read().decode("utf-8", "replace")
    robots = re.search(r'<meta name="robots" content="([^"]*)"', h)
    canon = re.search(r'<link rel="canonical" href="([^"]*)"', h)
    print(f"  {u.replace('https://www.tslaw.id', '') or '/'}")
    print(f"     robots meta : {robots.group(1) if robots else '(tidak ada)'}")
    print(f"     canonical   : {canon.group(1) if canon else '-'}")