Python Script to Audit Webpages for SEO & AI Readiness (No API Key Needed)

# simple_auditor.py
# Minimal, API-key-free webpage auditor with case-insensitive meta extraction.
# Change `url_to_audit` to target another page.

import re
import requests
from urllib.parse import urlparse
from bs4 import BeautifulSoup

# ====== Change this URL to audit another page ======
url_to_audit = "https://www.plus2net.com/python/pandas.php"

UA = "Mozilla/5.0 (compatible; AI-Ready-Auditor/1.1; +https://example.com)"
TIMEOUT = 30

def fetch_html(url: str) -> tuple[int, str]:
    r = requests.get(url, headers={"User-Agent": UA}, timeout=TIMEOUT)
    return r.status_code, r.text

def get_meta_by_name(soup: BeautifulSoup, meta_name: str):
    tag = soup.find("meta", attrs={"name": re.compile(re.escape(meta_name) + "$", re.I)})
    return (tag.get("content") or "").strip() if tag and tag.get("content") else None

def get_meta_by_property(soup: BeautifulSoup, prop_name: str):
    tag = soup.find("meta", attrs={"property": re.compile(re.escape(prop_name) + "$", re.I)})
    return (tag.get("content") or "").strip() if tag and tag.get("content") else None

def extract_schema_flags(json_ld_blocks: list[str]):
    j = "\n".join(json_ld_blocks)
    return "FAQPage" in j, "HowTo" in j, "VideoObject" in j

def analyze(url: str):
    status, html = fetch_html(url)
    soup = BeautifulSoup(html, "lxml")

    title = soup.title.string.strip() if soup.title and soup.title.string else None
    meta_description = get_meta_by_name(soup, "description") or get_meta_by_property(soup, "og:description")
    meta_keywords = get_meta_by_name(soup, "keywords")
    meta_viewport = get_meta_by_name(soup, "viewport")

    h1_tag = soup.find("h1")
    h1 = h1_tag.get_text(strip=True) if h1_tag else None

    canonical_tag = soup.find("link", rel=lambda v: v and v.lower() == "canonical")
    canonical_url = canonical_tag.get("href") if canonical_tag else None

    ga4_ids = list(sorted(set(re.findall("G-[A-Z0-9]{6,12}", html))))
    has_ga4 = bool(ga4_ids)

    og_tags = {
        t.get("property"): t.get("content")
        for t in soup.find_all("meta", attrs={"property": re.compile("^og:", re.I)})
        if t.get("property") and t.get("content")
    }

    imgs = soup.find_all("img")
    images_total = len(imgs)
    images_with_alt = sum(1 for i in imgs if (i.get("alt") or "").strip())
    images_alt_coverage_pct = round((images_with_alt / images_total * 100), 2) if images_total else 0.0

    parsed = urlparse(url)
    base_host = parsed.netloc
    internal_links, external_links = 0, 0
    for a in soup.find_all("a", href=True):
        p = urlparse(a.get("href"))
        if not p.netloc or p.netloc == "" or p.netloc == base_host:
            internal_links += 1
        else:
            external_links += 1

    json_ld_blocks = [t.get_text() for t in soup.find_all("script", type="application/ld+json")]
    has_faq_schema, has_howto_schema, has_video_schema = extract_schema_flags(json_ld_blocks)
    breadcrumbs_present = bool(soup.select('[itemtype*="BreadcrumbList" i], nav.breadcrumb, ol.breadcrumb'))

    root = f"{parsed.scheme}://{parsed.netloc}"
    sitemap_present = False
    try:
        rr = requests.get(f"{root}/robots.txt", headers={"User-Agent": UA}, timeout=10)
        if rr.ok and "sitemap" in rr.text.lower():
            sitemap_present = True
    except Exception:
        pass

    return {
        "url": url,
        "http_status": status,
        "title": title,
        "title_length": len(title) if title else None,
        "meta_description": meta_description,
        "meta_description_length": len(meta_description) if meta_description else None,
        "h1": h1,
        "canonical_url": canonical_url,
        "ga4_ids": ga4_ids,
        "images_total": images_total,
        "images_with_alt": images_with_alt,
        "images_alt_coverage_pct": images_alt_coverage_pct,
        "internal_links": internal_links,
        "external_links": external_links,
        "has_faq_schema": has_faq_schema,
        "has_howto_schema": has_howto_schema,
        "has_videoobject_schema": has_video_schema,
        "breadcrumbs_present": breadcrumbs_present,
        "sitemap_present": sitemap_present
    }

if __name__ == "__main__":
    report = analyze(url_to_audit)
    print(report)

# Change target URL for localhost site auditing
url_to_audit = "http://localhost/plus2net/python/pandas.php"

import requests
from urllib.parse import urlparse, urljoin
from bs4 import BeautifulSoup

url_to_audit = "https://www.plus2net.com/python/pandas.php"
response = requests.get(url_to_audit)
soup = BeautifulSoup(response.text, "html.parser")

parsed_base = urlparse(url_to_audit)
base_host = parsed_base.netloc

internal_links = []
external_links = []

for a in soup.find_all("a", href=True):
    href = a["href"].strip()
    if not href or href.startswith("#") or href.startswith("javascript:"):
        continue
    
    full_url = urljoin(url_to_audit, href)
    parsed_href = urlparse(full_url)
    
    if parsed_href.netloc == base_host:
        internal_links.append(full_url)
    else:
        external_links.append(full_url)

print("--- Internal Links ---")
for link in set(internal_links):
    print(link)

print("\n--- External Links ---")
for link in set(external_links):
    print(link)