#!/usr/bin/env python3
import json, re
from urllib.parse import urlparse


def norm(u):
    u = u.strip().rstrip(").,;\"'")
    p = urlparse(u)
    return f"{p.netloc.lower().replace('www.', '')}{p.path.rstrip('/').lower()}"


cands = [
    "https://www.tslaw.id/pengacara-surat-wasiat/",
    "https://dasindonesia.com/bengkel-spesialis-overhaul-mobil-surabaya-kapan-dibutuhkan/",
    "https://www.theskincodeclinic.com/panduan-memilih-dokter-kulit-krian/",
]
targets = {norm(c): c for c in cands}
docs = json.load(open('/tmp/repliz_all_20260930.json'))
found = {k: [] for k in targets}
for d in docs:
    for m in re.findall(r'https?://[^\s"\'\\]+', json.dumps(d, ensure_ascii=False)):
        n = norm(m)
        if n in targets:
            found[n].append((d.get('_id'), d.get('status'), d.get('scheduleAt')))
for k, c in targets.items():
    print(("DIPAKAI" if found[k] else "FRESH  "), c, found[k][:3])

log = json.load(open('log_threads_harian.json'))
s = json.dumps(log)
for u in ['pengacara-surat-wasiat', 'bengkel-spesialis-overhaul-mobil-surabaya', 'panduan-memilih-dokter-kulit-krian']:
    print(u, u in s)