#!/usr/bin/env python3
"""Cek teks persis Pasal 14 & Pasal 22 UU 18/2003 dan isi artikel biaya law firm (3566) untuk tautan internal."""
import base64, json, re, sys, urllib.request
WS = "/home/mantapman/.hermes/profiles/atun/workspace"
sys.path.insert(0, WS)
KUNCI = json.load(open(f"{WS}/.serper_token.json"))["key"]
H = {"X-API-KEY": KUNCI, "Content-Type": "application/json", "User-Agent": "Mozilla/5.0"}
for q in ["UU 18 tahun 2003 Pasal 14 advokat bebas mengeluarkan pendapat tidak dapat dituntut",
          "UU 18 tahun 2003 Pasal 21 advokat berhak memperoleh informasi dokumen"]:
    print("=" * 92); print("T:", q)
    body = json.dumps({"q": q, "gl": "id", "hl": "id", "num": 3}).encode()
    req = urllib.request.Request("https://google.serper.dev/search", data=body, headers=H, method="POST")
    try:
        with urllib.request.urlopen(req, timeout=60) as r:
            d = json.load(r)
        for it in d.get("organic", [])[:3]:
            print("  -", it.get("title")); print("   ", (it.get("snippet") or "")[:300])
    except Exception as e:
        print("  GAGAL:", e)

from cfg_tslaw import CFG
AUTH = base64.b64encode(f"{CFG['user']}:{CFG['pass']}".encode()).decode()
req = urllib.request.Request("https://tslaw.id/wp-json/wp/v2/posts/3566?context=edit",
                             headers={"Authorization": f"Basic {AUTH}", "User-Agent": "Mozilla/5.0"})
with urllib.request.urlopen(req, timeout=120) as r:
    p = json.load(r)
raw = p["content"]["raw"]
print("\n" + "=" * 92)
print("3566:", p["link"], "| kata:", len(re.sub(r"<[^>]+>", " ", raw).split()))
print("judul:", p["title"]["raw"])
for m in re.finditer(r"<h([23])[^>]*>(.*?)</h\1>", raw, flags=re.S):
    print(f"  h{m.group(1)}: {re.sub(r'<[^>]+>','',m.group(2)).strip()[:80]}")