import json, re
docs = json.load(open('/tmp/repliz_dump_hc63.json'))
posts = json.load(open('/tmp/ss_posts_hc63.json'))
LI = "6a334c49c5ff4ce3a32259c9"
URLRE = re.compile(r"https?://[^\s\"'<>)\]]*studiosoft\.id[^\s\"'<>)\]]*")

def slugs(d):
    out = set()
    for m in (d.get('medias') or []):
        for u in URLRE.findall(m.get('url') or ''):
            if 'openclaw-img' not in u:
                out.add(u.rstrip('/').split('/')[-1].lower())
    for f in ('description', 'title', 'topic'):
        for u in URLRE.findall(d.get(f) or ''):
            if 'openclaw-img' not in u:
                out.add(u.rstrip('/').split('/')[-1].lower())
    return out

idx = {}
for d in docs:
    if d.get('accountId') != LI:
        continue
    for s in slugs(d):
        idx.setdefault(s, []).append((d.get('scheduleAt', '')[:16], (d.get('status') or '').lower()))
print("30 post terbaru vs jadwal LI (semua status):")
for p in posts:
    s = p['slug']
    ev = sorted(idx.get(s, []))
    pend = [e for e in ev if e[1] in ('pending', 'scheduled', 'draft')]
    print("  %-60s n=%-3d pending=%s last=%s" % (s[:60], len(ev), pend[:2] if pend else '-', ev[-1] if ev else 'BELUM'))