#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""Ambil blok ISI artikel TSC dari script artikel -> teks biasa untuk sumber slide feed."""
import re, sys, html

src = sys.argv[1] if len(sys.argv) > 1 else "tsc_artikel_bekas_jerawat_cekung.py"
s = open(f"/home/mantapman/.hermes/profiles/atun/workspace/{src}").read()
m = re.search(r'ISI\s*=\s*"""(.+?)"""', s, re.S)
body = m.group(1)
out = []
for block in re.findall(r"<(h2|h3|p)>(.*?)</\1>", body, re.S):
    tag, txt = block
    txt = re.sub(r"<[^>]+>", "", txt)
    txt = html.unescape(re.sub(r"\s+", " ", txt)).strip()
    if not txt:
        continue
    out.append(f"[{tag.upper()}] {txt}")
open("/tmp/tsc_artikel.txt", "w").write("\n\n".join(out))
print("\n\n".join(out))