#!/usr/bin/env python3
"""TSLaw: cek efek penonaktifan arsip penulis + status robots.txt terpasang atau belum."""
import re, urllib.request, urllib.error

UA = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 Chrome/124 Safari/537.36"}


def ambil(u):
    try:
        r = urllib.request.urlopen(urllib.request.Request(u, headers=UA), timeout=60)
        return r.status, r.read().decode("utf-8", "replace"), dict(r.headers)
    except urllib.error.HTTPError as e:
        return e.code, "", {}
    except Exception as e:
        return 0, str(e)[:80], {}


print("=== 1. robots.txt sekarang (sudah diganti atau belum?) ===")
st, isi, h = ambil("https://www.tslaw.id/robots.txt")
print(f"   HTTP {st} | {len(isi)} char | cf={h.get('cf-cache-status')}")
for b in isi.splitlines()[:12]:
    print("     ", b)
sudah_diganti = "wp-admin" in isi or "Disallow: /feed/" in isi
print(f"   → robots.txt kustom sudah terpasang: {'YA' if sudah_diganti else 'BELUM (masih bawaan Yoast)'}")

print("\n=== 2. sitemap index setelah arsip penulis dimatikan ===")
st, isi, _ = ambil("https://www.tslaw.id/sitemap_index.xml")
for m in re.findall(r"<loc>([^<]+)</loc>", isi):
    print(f"     {m}")
print(f"   author-sitemap masih ada: {'YA' if 'author-sitemap' in isi else 'tidak'}")

print("\n=== 3. arsip penulis & halaman terkait ===")
for u in ("/author/mantapman/", "/author/", "/feed/", "/?s=hukum"):
    st, isi, _ = ambil(f"https://www.tslaw.id{u}")
    judul = re.search(r"<title>(.*?)</title>", isi, re.S) if isi else None
    print(f"   {st} | {u:<22} {judul.group(1)[:52] if judul else ''}")

print("\n=== 4. cek cepat sitemap artikel & halaman ===")
for u in ("/post-sitemap.xml", "/page-sitemap.xml"):
    st, isi, _ = ambil(f"https://www.tslaw.id{u}")
    print(f"   {st} | {u:<20} {len(re.findall(r'<loc>', isi))} entri")