#!/usr/bin/env python3
"""Cek fakta tahap 4: PMK 111/2014 (izin konsultan pajak) + Tax Center UNAIR + IKPI Surabaya."""
import re, zlib, urllib.request, urllib.error

UA = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 Chrome/124 Safari/537.36"}


def get(u, n=3000000):
    try:
        r = urllib.request.Request(u, headers=UA)
        with urllib.request.urlopen(r, timeout=90) as x:
            return x.status, x.read(n)
    except urllib.error.HTTPError as e:
        return e.code, b""
    except Exception as e:
        return type(e).__name__, b""


def teks(b):
    t = b.decode("utf-8", "replace")
    t = re.sub(r"<(script|style)[^>]*>.*?</\1>", " ", t, flags=re.S | re.I)
    t = re.sub(r"<[^>]+>", " ", t)
    t = re.sub(r"&nbsp;?", " ", t).replace("&amp;", "&")
    return re.sub(r"\s+", " ", t).strip()


def pdf_text(b):
    hasil = []
    for c in re.findall(rb"stream\r?\n(.*?)endstream", b, re.S):
        try:
            d = zlib.decompress(c)
        except Exception:
            continue
        for m in re.finditer(rb"\[(.*?)\]\s*TJ", d, re.S):
            for s in re.finditer(rb"\(([^()\\]*)\)", m.group(1)):
                hasil.append(s.group(1).decode("latin-1", "replace"))
        for m in re.finditer(rb"\(([^()\\]{2,})\)", d):
            hasil.append(m.group(1).decode("latin-1", "replace"))
    return re.sub(r"\s+", " ", " ".join(hasil))


def potong(t, pat, sebelum=60, sesudah=800, maks=2):
    n = 0
    for m in re.finditer(pat, t, re.I):
        a, z = max(0, m.start() - sebelum), min(len(t), m.start() + sesudah)
        print(f"  >{t[a:z]}")
        n += 1
        if n >= maks:
            break
    if n == 0:
        print("  [TIDAK DITEMUKAN]", pat)


for url, label in [
    ("https://jdih.kemenkeu.go.id/api/download/5a00d249-d68c-427e-b688-0906eefa5ed0/PMK%20111%202014.pdf", "PMK 111/2014 jdih"),
    ("https://datacenter.ortax.org/ortax/aturan/show/15528", "PMK 111/2014 ortax"),
]:
    st, b = get(url)
    print(f"\n=== {label} -> HTTP {st} {len(b)}B")
    if st != 200 or not b:
        continue
    t = pdf_text(b) if b[:4] == b"%PDF" else teks(b)
    print("   teks", len(t), "| awal:", t[:200])
    for p in [r"Konsultan Pajak adalah", r"Izin Praktik", r"Pasal 4\b", r"Pasal 5\b", r"Kartu Izin Praktik"]:
        potong(t, p)
    if "Konsultan Pajak adalah" in t:
        open("/tmp/pmk111.txt", "w").write(t)
        break

print("\n=== Tax Center UNAIR / IKPI Surabaya (halaman resmi)")
for url in ["https://unair.ac.id/tag/tax-center/",
            "https://ikpi.or.id/articles/ikpi-surabaya",
            "https://www.pajak.go.id/id/alamat-kantor/kanwil-djp-jawa-timur-i-0"]:
    st, b = get(url)
    t = teks(b)
    print(f"\n  {url} -> HTTP {st} | {len(t)} char")
    for p in [r"Tax Center", r"Gedung", r"Jl\.", r"Jagir", r"Surabaya", r"sekretariat", r"Konsultan Pajak"]:
        potong(t, p, 80, 260, 1)