From 6b40f3b54efabb740e825ba3d94b5695c2b98ede Mon Sep 17 00:00:00 2001
From: pdp8 <pdp8@pdp8.info>
Date: Mon, 4 Mar 2024 13:42:04 +0100
Subject: disallow AI bots in robots.txt, mail.rb title,  valid rss

---
 rss.rb | 37 ++++++++++++++++++++++++++++++-------
 1 file changed, 30 insertions(+), 7 deletions(-)

(limited to 'rss.rb')

diff --git a/rss.rb b/rss.rb
index 554d45c..eb163d4 100755
--- a/rss.rb
+++ b/rss.rb
@@ -1,43 +1,66 @@
 #!/usr/bin/env ruby
 require 'date'
+require 'json'
+
 MEDIA = '/srv/media/'
+SOCIAL = '/srv/social/outbox/object/note/'
 WWW = '/srv/www/pdp8-test/'
+
 items = []
 %w[music videos].each do |cat|
   Dir[File.join(MEDIA, cat, '*')].each do |dir|
+    next unless File.basename(dir).match(/^\d/)
+
     date = File.basename(dir).split('_')[0]
-    updated = Date.parse(date) # .strftime('%Y-%m-%d')
+    updated = Date.parse(date)
     items << {
       title: File.basename(dir).split('_')[1..-1].join(' '),
       link: File.join('https://pdp8.info', cat + '.html#' + date),
       guid: File.join('https://pdp8.info', cat + '.html#' + date),
-      description: File.read(File.join(dir, 'README')).chomp.sub(/^\n/, '').sub("\n\n", "\n"),
+      description: '<![CDATA[' + File.read(File.join(dir, 'README')).chomp.sub(/^\n/, '').sub("\n\n", "\n") + ']]>',
       pubDate: updated.httpdate
-      # 'dc:date' => updated.rfc3339
     }
   end
 end
+
+# duplication of music/video posts?
+# Dir[File.join(SOCIAL, '*.json')].each do |json|
+#   note = JSON.parse(File.read(json))
+#   next unless note['attributedTo'] == 'https://social.pdp8.info/pdp8' and note['to'].include?('https://www.w3.org/ns/activitystreams#Public')
+#
+#   # TODO: add enclosures for attachments
+#   # tags
+#   items << {
+#     title: note['published'],
+#     link: 'https://pdp8.info/social/create.html#' + note['published'],
+#     guid: note['id'],
+#     description: '<![CDATA[' + note['content'] + ']]>',
+#     pubDate: Date.parse(note['published']).httpdate
+#   }
+# end
+
 date = Dir[File.join(MEDIA, 'pictures', '*.jpeg')].last.split('_')[0]
-updated = Date.parse(date) # .strftime('%Y%m%d')
+updated = Date.parse(date)
 items << {
   title: 'pictures',
   link: 'https://pdp8.info/pictures.html',
   guid: 'https://pdp8.info/pictures.html',
   pubDate: updated.httpdate
-  # 'dc:date' => updated.rfc3339
 }
 
 xml = ['<?xml version="1.0" encoding="UTF-8"?>
 <rss version="2.0"
   xmlns:content="http://purl.org/rss/1.0/modules/content/"
+  xmlns:atom="http://www.w3.org/2005/Atom">
   <channel>
     <title>pdp8</title>
     <link>https://pdp8.info</link>
     <description>music, pictures and videos</description>
-    <language>en</language>']
+    <language>en</language>
+    <atom:link href="https://pdp8.info/rss.xml" rel="self" type="application/rss+xml" /> ']
+
 date = DateTime.now
 xml << "    <pubDate>#{date.httpdate}</pubDate>"
-# xml << "    <dc:date>#{date.rfc3339}</dc:date>"
 
 items.sort_by { |i| i['pubDate'] }.each do |item|
   xml << '    <item>'
-- 
cgit v1.2.3