Redirect chain: come ho ridotto 3 hop a 1 e migliorato il crawl budget

verifica redirect chain

# Mostra tutti i redirect nella catena
curl -sI -L http://www.tuosito.com/ | grep -i "HTTP/\|location"

# Output atteso (catena con problemi):
# HTTP/1.1 301 Moved Permanently
# location: https://www.tuosito.com/
# HTTP/2 301
# location: https://tuosito.com/
# HTTP/2 200

# Output ideale (un solo hop):
# HTTP/1.1 301 Moved Permanently
# location: https://tuosito.com/
# HTTP/2 200

_redirects — fix completo

# Fix redirect chain: www → non-www in un hop diretto
# Il ! forza il redirect anche se esiste già una regola di matching
https://www.smartweb-media.com/* https://smartweb-media.com/:splat 301!

# Altri redirect del sito (invariati)
/index-en.html /en/ 301
/blog-en.html /en/blog.html 301
# ... ecc.

verifica post-fix

# Test 1: http www (era il caso problematico)
curl -sI -L http://www.smartweb-media.com/ | grep -i "HTTP/\|location"
# Risultato atteso:
# HTTP/1.1 301
# location: https://smartweb-media.com/
# HTTP/2 200

# Test 2: https www
curl -sI -L https://www.smartweb-media.com/ | grep -i "HTTP/\|location"
# Risultato atteso:
# HTTP/2 301
# location: https://smartweb-media.com/
# HTTP/2 200

# Test 3: http non-www (deve funzionare ancora)
curl -sI -L http://smartweb-media.com/ | grep -i "HTTP/\|location"
# Risultato atteso:
# HTTP/1.1 301
# location: https://smartweb-media.com/
# HTTP/2 200

# Test 4: path specifico preservato?
curl -sI http://www.smartweb-media.com/blog/articolo.html | grep "location"
# Risultato atteso:
# location: https://smartweb-media.com/blog/articolo.html

.htaccess

RewriteEngine On

# Redirect tutto http → https (incluso www)
RewriteCond %{HTTPS} off
RewriteRule ^ https://%{HTTP_HOST}%{REQUEST_URI} [R=301,L]

# Redirect www → non-www (solo su https)
RewriteCond %{HTTPS} on
RewriteCond %{HTTP_HOST} ^www\.(.+)$ [NC]
RewriteRule ^ https://%1%{REQUEST_URI} [R=301,L]

.htaccess — singolo hop

RewriteEngine On

# Caso 1: http + www → https + non-www (singolo hop)
RewriteCond %{HTTPS} off
RewriteCond %{HTTP_HOST} ^www\.(.+)$ [NC]
RewriteRule ^ https://%1%{REQUEST_URI} [R=301,L]

# Caso 2: http + non-www → https + non-www
RewriteCond %{HTTPS} off
RewriteCond %{HTTP_HOST} ^(?!www\.)(.+)$ [NC]
RewriteRule ^ https://%1%{REQUEST_URI} [R=301,L]

# Caso 3: https + www → https + non-www
RewriteCond %{HTTPS} on
RewriteCond %{HTTP_HOST} ^www\.(.+)$ [NC]
RewriteRule ^ https://%1%{REQUEST_URI} [R=301,L]

nginx.conf

# Server block per http (entrambe le versioni)
server {
    listen 80;
    server_name www.tuosito.com tuosito.com;
    # Redirect tutto http → https non-www in un hop
    return 301 https://tuosito.com$request_uri;
}

# Server block per https www
server {
    listen 443 ssl;
    server_name www.tuosito.com;
    # Redirect https www → https non-www
    return 301 https://tuosito.com$request_uri;
}

# Server block principale
server {
    listen 443 ssl;
    server_name tuosito.com;
    # ... configurazione normale
}

check_redirects.py

import requests
import xml.etree.ElementTree as ET
from urllib.parse import urlparse

def get_redirect_chain(url, max_hops=10):
    """Segue tutti i redirect e restituisce la catena completa."""
    chain = []
    current_url = url
    session = requests.Session()
    session.max_redirects = max_hops

    for i in range(max_hops):
        try:
            resp = session.head(current_url, allow_redirects=False,
                               timeout=10, headers={'User-Agent': 'Mozilla/5.0'})
            chain.append({'url': current_url, 'status': resp.status_code})

            if resp.status_code in (301, 302, 307, 308):
                location = resp.headers.get('Location', '')
                if not location:
                    break
                # Gestisci URL relativi
                if location.startswith('/'):
                    parsed = urlparse(current_url)
                    location = f"{parsed.scheme}://{parsed.netloc}{location}"
                current_url = location
            else:
                break
        except Exception as e:
            chain.append({'url': current_url, 'status': f'ERR: {e}'})
            break

    return chain

def audit_sitemap_redirects(sitemap_url):
    """Controlla redirect chain per ogni URL nella sitemap."""
    resp = requests.get(sitemap_url, timeout=10)
    root = ET.fromstring(resp.content)
    ns = {'sm': 'http://www.sitemaps.org/schemas/sitemap/0.9'}
    urls = [loc.text for loc in root.findall('.//sm:loc', ns)]

    print(f"Audit redirect chain su {len(urls)} URL dalla sitemap\n")
    problems = []

    for url in urls:
        chain = get_redirect_chain(url)
        hops = len(chain) - 1  # -1 perché l'ultimo è la destinazione finale

        if hops > 1:
            problems.append({'url': url, 'hops': hops, 'chain': chain})
            print(f"⚠️  {hops} hop: {url}")
            for step in chain:
                print(f"     → {step['status']} {step['url']}")
        elif hops == 1:
            final = chain[-1]['url']
            if final != url:
                print(f"✅  1 hop OK: {url} → {final}")
        else:
            print(f"✅  Diretto: {url}")

    print(f"\n{'='*60}")
    print(f"Problemi trovati: {len(problems)} URL con redirect chain multipla")
    return problems

# Uso
if __name__ == '__main__':
    problems = audit_sitemap_redirects('https://smartweb-media.com/sitemap.xml')