Sitemap che Google indicizza davvero: quello che le guide non dicono

check_indexing.py

from google.oauth2 import service_account
from googleapiclient.discovery import build
import requests
import xml.etree.ElementTree as ET

SCOPES   = ['https://www.googleapis.com/auth/webmasters.readonly']
KEY_FILE = 'service-account.json'
SITE_URL = 'https://smartweb-media.com/'

def get_service():
    creds = service_account.Credentials.from_service_account_file(
        KEY_FILE, scopes=SCOPES)
    return build('searchconsole', 'v1', credentials=creds)

def get_sitemap_urls(sitemap_url):
    """Legge tutti gli URL dalla sitemap XML."""
    resp = requests.get(sitemap_url, timeout=10)
    root = ET.fromstring(resp.content)
    ns = {'sm': 'http://www.sitemaps.org/schemas/sitemap/0.9'}
    return [loc.text for loc in root.findall('.//sm:loc', ns)]

def check_url_indexing(service, url, site_url):
    """Controlla lo stato di indicizzazione di un URL specifico."""
    try:
        result = service.urlInspection().index().inspect(
            body={'inspectionUrl': url, 'siteUrl': site_url}
        ).execute()

        idx = result.get('inspectionResult', {}).get('indexStatusResult', {})
        return {
            'url': url,
            'verdict': idx.get('verdict', 'UNKNOWN'),
            'coverage': idx.get('coverageState', 'UNKNOWN'),
            'last_crawl': idx.get('lastCrawlTime', 'N/A')[:10] if idx.get('lastCrawlTime') else 'N/A',
            'canonical_gsc': idx.get('googleCanonical', ''),
            'canonical_declared': idx.get('userCanonical', ''),
            'referring_urls': idx.get('referringUrls', [])
        }
    except Exception as e:
        return {'url': url, 'verdict': 'ERROR', 'coverage': str(e)}

def audit_indexing(sitemap_url=f"{SITE_URL}sitemap.xml"):
    """Verifica lo stato di indicizzazione di ogni URL nella sitemap."""
    service = get_service()
    urls = get_sitemap_urls(sitemap_url)

    print(f"Controllo indicizzazione per {len(urls)} URL\n{'='*60}")
    results = {'indexed': [], 'issues': [], 'errors': []}

    for url in urls:
        status = check_url_indexing(service, url, SITE_URL)
        path = url.replace(SITE_URL.rstrip('/'), '') or '/'

        if status['verdict'] == 'PASS':
            print(f"  ✅ {path:<50} {status['coverage']}")
            print(f"     Ultimo crawl: {status['last_crawl']}")
            results['indexed'].append(status)
        elif status['verdict'] == 'NEUTRAL':
            print(f"  ⚠️  {path:<50} {status['coverage']}")
            if status['canonical_gsc'] != status['canonical_declared']:
                print(f"     Google canonical: {status['canonical_gsc']}")
                print(f"     Tuo canonical:    {status['canonical_declared']}")
            results['issues'].append(status)
        elif status['verdict'] == 'FAIL':
            print(f"  ❌ {path:<50} {status['coverage']}")
            results['errors'].append(status)
        else:
            print(f"  ?  {path:<50} {status['verdict']}")

    print(f"\n{'='*60}")
    print(f"RIEPILOGO:")
    print(f"  ✅ Indicizzate:  {len(results['indexed'])}")
    print(f"  ⚠️  Con problemi: {len(results['issues'])}")
    print(f"  ❌ Errori:       {len(results['errors'])}")

    return results

if __name__ == '__main__':
    audit_indexing()

sitemap.xml — formato corretto

<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
  <url>
    <loc>https://smartweb-media.com/</loc>
    <lastmod>2026-03-30</lastmod>
    <changefreq>weekly</changefreq>
    <priority>1.0</priority>
  </url>
  <url>
    <loc>https://smartweb-media.com/blog/seo-audit-con-claude-pipeline.html</loc>
    <lastmod>2026-03-02</lastmod>
    <changefreq>monthly</changefreq>
    <priority>0.8</priority>
  </url>
</urlset>