From d998a59fdaa3e9b0cf5f1ff3871387c20a20b27b Mon Sep 17 00:00:00 2001 From: Michael Fabian 'Xaymar' Dirks Date: Sat, 7 Sep 2024 13:55:17 +0200 Subject: [PATCH] Add robots and fix up sitemap. --- robots.txt | 11 +++++++++++ sitemap.xml | 9 +++++---- 2 files changed, 16 insertions(+), 4 deletions(-) diff --git a/robots.txt b/robots.txt index 3567238..7d4dfbf 100644 --- a/robots.txt +++ b/robots.txt @@ -1,4 +1,11 @@ +--- +layout: null +sitemap: + exclude: true +--- + User-agent: * +Sitemap: {{ "/robots.txt" | absolute_url }} Disallow: /assets/ Disallow: /feed/ Disallow: /feed.xml @@ -13,12 +20,14 @@ User-agent: Applebot User-agent: Applebot-Extended User-agent: Bytespider User-agent: CCBot +User-agent: ChatGPT User-agent: ChatGPT-User User-agent: Claude-Web User-agent: ClaudeBot User-agent: Diffbot User-agent: FacebookBot User-agent: FriendlyCrawler +User-agent: GPT User-agent: GPTBot User-agent: Google-Extended User-agent: GoogleOther @@ -29,7 +38,9 @@ User-agent: ICC-Crawler User-agent: ImagesiftBot User-agent: Meta-ExternalAgent User-agent: Meta-ExternalFetcher +User-agent: OpenAI User-agent: OAI-SearchBot +User-agent: OAI-Bot User-agent: PerplexityBot User-agent: PetalBot User-agent: Scrapy diff --git a/sitemap.xml b/sitemap.xml index a21c296..e7ee701 100644 --- a/sitemap.xml +++ b/sitemap.xml @@ -3,13 +3,13 @@ layout: null sitemap: exclude: true --- - +{% capture var %} {% for post in site.posts %} {% unless post.published == false %} - {{ site.url }}{{ post.url }} + {{ site.url | xml_encode }}{{ post.url | xml_encode }} {% if post.sitemap.lastmod %} {{ post.sitemap.lastmod | date: "%Y-%m-%d" }} {% elsif post.date %} @@ -41,7 +41,7 @@ sitemap: {% endfor %} {% unless skip == true or page.sitemap.exclude == true %} - {{ site.url }}{{ page.url | remove: "index.html" }} + {{ site.url | xml_encode }}{{ page.url | remove: "index.html" | xml_encode }} {% if page.sitemap.lastmod %} {{ page.sitemap.lastmod | date: "%Y-%m-%d" }} {% elsif page.date %} @@ -62,4 +62,5 @@ sitemap: {% endunless %} {% endfor %} - \ No newline at end of file + +{% endcapture %}{{ var | normalize_whitespace }}