import html, re, urllib.request
h = urllib.request.urlopen(urllib.request.Request("https://www.tslaw.id/", headers={"User-Agent": "Mozilla/5.0"}), timeout=120).read().decode("utf-8", "replace")
bersih = lambda x: html.unescape(re.sub(r"<[^>]+>", "", x)).strip()
print("H1 :", [bersih(x)[:70] for x in re.findall(r"<h1[^>]*>(.*?)</h1>", h, re.S)])
print("H2 :", [bersih(x)[:58] for x in re.findall(r"<h2[^>]*>(.*?)</h2>", h, re.S)])
print("H3 :", [bersih(x)[:48] for x in re.findall(r"<h3[^>]*>(.*?)</h3>", h, re.S)][:8])
print("schema FAQ:", "ada" if "FAQPage" in h else "tidak ada")