User-agent: Scrapy Allow: / User-agent: * # On empêche l'indexation des dossiers sensibles Disallow: /wp-admin Disallow: /wp-includes Disallow: /wp-content/plugins Disallow: /wp-content/cache Disallow: /wp-content/themes Disallow: /trackback Disallow: /feed Disallow: /comments Disallow: /category/*/* Disallow: */trackback Disallow: */feed Disallow: */comments Disallow: /*.pdf$ # On désindexe tous les URL ayant des paramètres (duplication de contenu) Disallow: /*?* Disallow: /*? # On désindexe la page de connexion (contenu inutile) Disallow: /wp-login.php # disable duggmirror by Digg User-agent: duggmirror Disallow: / # allow google image bot to search all images User-agent: Googlebot-Image Disallow: /wp-includes/ Allow: /* # On autorise l'indexation des images Allow: /wp-content/uploads # Autoriser Google Image User-agent: Googlebot-Image Disallow: Allow: /* # Autoriser Google AdSense User-agent: Mediapartners-Google* Disallow: Allow: /* # On indique au spider le lien vers notre sitemap Sitemap: http://allolemonde.fr/sitemapindex.xml