From c4a2cf6713e69b77f55f8352165acc1868df0c45 Mon Sep 17 00:00:00 2001 From: Dan Helfman Date: Wed, 2 Jan 2008 03:27:31 +0000 Subject: [PATCH] Prevent web crawlers from spidering the "download as html" version of a notebook. --- static/html/robots.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/static/html/robots.txt b/static/html/robots.txt index 8c4f43e..b79cb91 100644 --- a/static/html/robots.txt +++ b/static/html/robots.txt @@ -1,6 +1,7 @@ # prevent bots from signing up for demo accounts User-agent: * Disallow: /users/demo +Disallow: /notebooks/download_html/ # this crawler is completely broken and requests many invalid URLs User-agent: panscient.com