#!/usr/bin/env python3
"""Cek format FAQ #3904 + scan klaim IELTS/TOEFL di seluruh konten LEIT."""
import base64, json, re, urllib.request

SITE = "https://www.leitsurabaya.com"
AUTH = base64.b64encode(b"bambangbot:zibd dLIV xY8x onP9 39qL hiNr").decode()


def api(p):
    r = urllib.request.Request(SITE + p, headers={"Authorization": f"Basic {AUTH}", "User-Agent": "Mozilla/5.0"})
    return json.loads(urllib.request.urlopen(r, timeout=240).read())


raw = api("/wp-json/wp/v2/posts/3904?context=edit&_fields=content,title")["content"]["raw"]
i = raw.lower().find("faq")
print("=== #3904 area FAQ ===")
print(raw[max(0, i - 100):i + 900] if i > 0 else "tidak ada 'faq'")

print("\n=== klaim TOEFL / IELTS di seluruh artikel ===")
posts = api("/wp-json/wp/v2/posts?per_page=100&context=edit&_fields=id,title,content")
for p in posts:
    c = p["content"]["raw"]
    hits = []
    for m in re.finditer(r"[^<>]{0,90}(?:IELTS|TOEFL)[^<>]{0,90}", c):
        t = re.sub(r"\s+", " ", m.group(0)).strip()
        if t:
            hits.append(t)
    if hits:
        print(f"\n#{p['id']} {p['title']['rendered'][:60]}  ({len(hits)} sebutan)")
        for h in hits[:4]:
            print("   •", h[:150])