import os
import re
import json

ROOT = r"C:\Users\Bodia\OneDrive\Робочий стіл\myipnow-main"
REPORT = "faq_schema_validation_report.txt"

def extract_faq_content(html):
    """Detect visible FAQ pairs from accordion HTML."""
    q_pattern = r'<div class="faq-question">(.*?)</div>'
    a_pattern = r'<div class="faq-answer">(.*?)</div>'

    questions = re.findall(q_pattern, html, flags=re.DOTALL)
    answers = re.findall(a_pattern, html, flags=re.DOTALL)

    faqs = []
    for i in range(min(len(questions), len(answers))):
        q = re.sub(r"&lt;.*?&gt;", "", questions[i]).strip()
        a = re.sub(r"&lt;.*?&gt;", "", answers[i]).strip()
        faqs.append((q, a))

    return faqs


def extract_schema_faq(html):
    """Detect FAQ inside JSON-LD blocks."""
    schemas = re.findall(r'<script type="application/ld\+json">(.*?)</script>', html, re.DOTALL)
    faq_list = []

    for schema in schemas:
        try:
            data = json.loads(schema)

            # support graph-style schemas
            if "@graph" in data:
                for entry in data["@graph"]:
                    if entry.get("@type") in ["FAQPage", "Question"]:
                        if entry.get("mainEntity"):
                            for faq in entry["mainEntity"]:
                                if faq.get("@type") == "Question":
                                    q = faq.get("name", "").strip()
                                    a = faq.get("acceptedAnswer", {}).get("text", "").strip()
                                    faq_list.append((q, a))
            elif data.get("@type") == "FAQPage":
                for faq in data.get("mainEntity", []):
                    if faq.get("@type") == "Question":
                        q = faq.get("name", "").strip()
                        a = faq.get("acceptedAnswer", {}).get("text", "").strip()
                        faq_list.append((q, a))
        except:
            pass

    return faq_list


def run():
    report = []

    for root, _, files in os.walk(ROOT):
        for file in files:
            if not file.endswith(".html"):
                continue

            path = os.path.join(root, file)
            rel = os.path.relpath(path, ROOT).replace("\\", "/")

            with open(path, "r", encoding="utf-8", errors="ignore") as f:
                html = f.read()

            visible_faq = extract_faq_content(html)
            schema_faq = extract_schema_faq(html)

            status = []

            if visible_faq and not schema_faq:
                status.append("❌ FAQ visible but NOT in schema")

            elif schema_faq and not visible_faq:
                status.append("⚠ Schema contains FAQ but no visible FAQ (Google may remove rich result)")

            elif visible_faq and schema_faq:
                if len(visible_faq) == len(schema_faq):
                    status.append("✔ FAQ schema matches visible content count")
                else:
                    status.append(f"⚠ FAQ mismatch — schema({len(schema_faq)}) vs content({len(visible_faq)})")

            else:
                status.append("— No FAQ present (expected for legal/about pages)")

            report.append(f"""
━━━━━━━━━━━━━━━━━━━━━━━━━━
📄 FILE: {rel}
━━━━━━━━━━━━━━━━━━━━━━━━━━
Visible FAQ count: {len(visible_faq)}
Schema FAQ count: {len(schema_faq)}
Status: {'; '.join(status)}
""")

    with open(REPORT, "w", encoding="utf-8") as f:
        f.write("\n".join(report))

    print(f"✅ DONE — Report saved as {REPORT}")


if __name__ == "__main__":
    run()