Check What Google AI Mode Can Quote From a Local Business Website: A Small Python Audit

import json
import re
from html.parser import HTMLParser

BOOKING_WORDS = ("book", "booking", "appointment", "reserve", "reservation", "schedule", "order online")
HOURS_RE = re.compile(r"\b(mon|tue|wed|thu|fri|sat|sun)[a-z]*\b.{0,40}?\d{1,2}(:\d{2})?\s*(am|pm)", re.I)
PHONE_RE = re.compile(r"(\+?\d[\d\s-]{8,}\d)")
EMERGENCY_RE = re.compile(r"\b24\s*[/x]\s*7\b|\b24 hours\b|\bemergency\b", re.I)


class PageScan(HTMLParser):
    def __init__(self):
        super().__init__()
        self.text = []
        self.links = []
        self.jsonld = []
        self._in_jsonld = False
        self._skip = 0

    def handle_starttag(self, tag, attrs):
        a = dict(attrs)
        if tag == "script" and a.get("type") == "application/ld+json":
            self._in_jsonld = True
        elif tag in ("script", "style"):
            self._skip += 1
        elif tag == "a":
            self.links.append((a.get("href") or "", ""))

    def handle_endtag(self, tag):
        if tag == "script" and self._in_jsonld:
            self._in_jsonld = False
        elif tag in ("script", "style") and self._skip:
            self._skip -= 1

    def handle_data(self, data):
        if self._in_jsonld:
            self.jsonld.append(data)
        elif not self._skip:
            self.text.append(data)
            if self.links and self.links[-1][1] == "":
                href, _ = self.links[-1]
                self.links[-1] = (href, data.strip())


def schema_types(blocks):
    types = set()
    for raw in blocks:
        try:
            data = json.loads(raw)
        except json.JSONDecodeError:
            continue
        items = data if isinstance(data, list) else data.get("@graph", [data])
        for item in items:
            t = item.get("@type")
            types.update(t if isinstance(t, list) else [t])
    return {t for t in types if t}


def audit(html: str) -> dict:
    p = PageScan()
    p.feed(html)
    text = " ".join(p.text)
    types = schema_types(p.jsonld)
    booking = [h for h, label in p.links
               if any(w in (h + " " + label).lower() for w in BOOKING_WORDS)]
    return {
        "local_business_schema": any(t.endswith("Business") or t in {"Restaurant", "Electrician", "Plumber"} for t in types),
        "hours_on_page": bool(HOURS_RE.search(text)),
        "phone_on_page": bool(PHONE_RE.search(text)) or any(h.startswith("tel:") for h, _ in p.links),
        "booking_link": bool(booking),
        "emergency_or_24x7": bool(EMERGENCY_RE.search(text)),
    }


def score(result: dict) -> int:
    return sum(result.values())

thin_site = """<html><body><h1>Sharma Electricals</h1>
<p>Welcome to our website. We are the best.</p></body></html>"""

useful_site = """<html><head>
<script type="application/ld+json">
{"@context": "https://schema.org", "@type": "Electrician", "name": "Sharma Electricals",
 "telephone": "+91 98765 43210", "areaServed": ["Vijay Nagar", "Palasia"]}
</script></head><body>
<h1>Electrician in Vijay Nagar and Palasia</h1>
<p>House wiring, MCB and DB repair, inverter points. 24/7 emergency calls.</p>
<p>Open Monday to Saturday, 9 am to 8 pm.</p>
<a href="tel:+919876543210">Call +91 98765 43210</a>
<a href="/book">Book a visit</a>
</body></html>"""

for name, html in (("thin_site", thin_site), ("useful_site", useful_site)):
    r = audit(html)
    print(name, score(r), "/ 5", r)

thin_site 0 / 5 {'local_business_schema': False, 'hours_on_page': False, 'phone_on_page': False, 'booking_link': False, 'emergency_or_24x7': False}
useful_site 5 / 5 {'local_business_schema': True, 'hours_on_page': True, 'phone_on_page': True, 'booking_link': True, 'emergency_or_24x7': True}