#!/usr/bin/env python3
"""Ambil utuh skrip mencurigakan di halaman DAS dan cari petunjuk di dalamnya."""
import re, urllib.request

URL = "https://dasindonesia.com/merawat-sistem-pendingin-mesin-radiator-cairan/"
UA = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/124.0 Safari/537.36"}
t = urllib.request.urlopen(urllib.request.Request(URL, headers=UA), timeout=60).read().decode("utf-8", "replace")

skrip = re.findall(r"<script(?![^>]*src)[^>]*>(.*?)</script>", t, re.S)
print(f"skrip sebaris: {len(skrip)}\n")
for i, s in enumerate(skrip, 1):
    isi = re.sub(r"\s+", " ", s).strip()
    if not isi:
        continue
    tanda = "⚠" if re.search(r"referrer|_b4a7b|atob|fromCharCode|decodeURIComponent|eval", isi) else " "
    print(f"{tanda} #{i} ({len(isi)} char): {isi[:120]}")
    if tanda == "⚠":
        print(f"     UTUH: {isi[:1200]}")
        # cari domain/url di dalam
        urls = sorted(set(re.findall(r"https?://[a-z0-9./\-_?=&%]+", isi, re.I)))
        domains = sorted(set(re.findall(r"['\"]([a-z0-9-]+\.[a-z]{2,6})['\"]", isi, re.I)))
        if urls:
            print(f"     URL di dalam skrip: {urls[:6]}")
        if domains:
            print(f"     domain di dalam skrip: {domains[:10]}")
        print(f"     baris ke berapa di HTML: {t.find(s[:60])}")