#!/usr/bin/env python3
"""Tampilkan HTML asli di sekitar penyebutan domain lama supaya jelas bentuknya."""
import base64, json, re, urllib.request

A = base64.b64encode(b"bambangbot:q26r RePo BVy6 pwU2 F3z7 ouyl").decode()
H = {"Authorization": f"Basic {A}", "User-Agent": "Mozilla/5.0"}
TARGET = {2857: ["creativism.id"], 3474: ["lenteraweb"], 3642: ["creativism.id"],
          3368: ["papdisurabaya"], 3558: ["?"], 2962: ["?"]}

for pid, doms in TARGET.items():
    try:
        d = json.loads(urllib.request.urlopen(urllib.request.Request(
            f"https://studiosoft.id/wp-json/wp/v2/posts/{pid}?context=edit&_fields=content,slug",
            headers=H), timeout=120).read())
    except Exception as e:
        print(f"#{pid} gagal: {e}")
        continue
    isi = d["content"]["raw"]
    print(f"\n########## #{pid} {d['slug'][:60]} ({len(isi)} char)")
    for dom in doms:
        if dom == "?":
            continue
        for mo in re.finditer(r".{0,140}" + re.escape(dom) + r".{0,140}", isi, re.I):
            print(f"   [{dom}] {mo.group(0)[:300]}")
    # cek juga anchor aneh: <a> tanpa href atau href kosong
    for mo in re.finditer(r'<a(?![^>]*href)[^>]*>.{0,60}', isi):
        print(f"   [a tanpa href] {mo.group(0)[:130]}")