From 9d81dc3176fdbd4a35b53484784b2a8b0e5276ea Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Mon, 5 Nov 2018 17:45:39 +0200
Subject: [PATCH] Update notes for 2018-11-05

---
 content/posts/2018-11.md |  9 +++++++++
 docs/2018-11/index.html  | 16 +++++++++++++---
 docs/sitemap.xml         | 10 +++++-----
 3 files changed, 27 insertions(+), 8 deletions(-)

diff --git a/content/posts/2018-11.md b/content/posts/2018-11.md
index 127196b38..801643063 100644
--- a/content/posts/2018-11.md
+++ b/content/posts/2018-11.md
@@ -232,5 +232,14 @@ $ grep -c -E 'session_id=[A-Z0-9]{32}:ip_addr=2a03:2880:11ff' dspace.log.2018-11
 
 - I added the "most-popular" pages to the list that return `X-Robots-Tag: none` to try to inform bots not to index or follow those pages
 - Also, I implemented an nginx rate limit of twelve requests per minute on all dynamic pages... I figure a human user might legitimately request one every five seconds
+- I wrote a small Python script [add-dc-rights.py](https://gist.github.com/alanorth/4ff81d5f65613814a66cb6f84fdf1fc5) to add usage rights (`dc.rights`) to CGSpace items based on the CSV Hector gave me from MARLO:
+
+```
+$ ./add-dc-rights.py -i /tmp/marlo.csv -db dspace -u dspace -p 'fuuu'
+```
+
+- The file `marlo.csv` was cleaned up and formatted in Open Refine
+- 165 of the items in their 2017 data are from CGSpace!
+- I will add the data to CGSpace this week
 
 <!-- vim: set sw=2 ts=2: -->
diff --git a/docs/2018-11/index.html b/docs/2018-11/index.html
index 3174f1e8a..2e21f5487 100644
--- a/docs/2018-11/index.html
+++ b/docs/2018-11/index.html
@@ -23,7 +23,7 @@ Today these are the top 10 IPs:
 " />
 <meta property="og:type" content="article" />
 <meta property="og:url" content="https://alanorth.github.io/cgspace-notes/2018-11/" /><meta property="article:published_time" content="2018-11-01T16:41:30&#43;02:00"/>
-<meta property="article:modified_time" content="2018-11-04T12:18:52&#43;02:00"/>
+<meta property="article:modified_time" content="2018-11-04T22:45:00&#43;02:00"/>
 
 <meta name="twitter:card" content="summary"/>
 <meta name="twitter:title" content="November, 2018"/>
@@ -52,9 +52,9 @@ Today these are the top 10 IPs:
   "@type": "BlogPosting",
   "headline": "November, 2018",
   "url": "https://alanorth.github.io/cgspace-notes/2018-11/",
-  "wordCount": "992",
+  "wordCount": "1057",
   "datePublished": "2018-11-01T16:41:30&#43;02:00",
-  "dateModified": "2018-11-04T12:18:52&#43;02:00",
+  "dateModified": "2018-11-04T22:45:00&#43;02:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -368,6 +368,16 @@ Today these are the top 10 IPs:
 <ul>
 <li>I added the &ldquo;most-popular&rdquo; pages to the list that return <code>X-Robots-Tag: none</code> to try to inform bots not to index or follow those pages</li>
 <li>Also, I implemented an nginx rate limit of twelve requests per minute on all dynamic pages&hellip; I figure a human user might legitimately request one every five seconds</li>
+<li>I wrote a small Python script <a href="https://gist.github.com/alanorth/4ff81d5f65613814a66cb6f84fdf1fc5">add-dc-rights.py</a> to add usage rights (<code>dc.rights</code>) to CGSpace items based on the CSV Hector gave me from MARLO:</li>
+</ul>
+
+<pre><code>$ ./add-dc-rights.py -i /tmp/marlo.csv -db dspace -u dspace -p 'fuuu'
+</code></pre>
+
+<ul>
+<li>The file <code>marlo.csv</code> was cleaned up and formatted in Open Refine</li>
+<li>165 of the items in their 2017 data are from CGSpace!</li>
+<li>I will add the data to CGSpace this week</li>
 </ul>
 
 <!-- vim: set sw=2 ts=2: -->
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index fee4bd7fd..b12d8ddcc 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -4,7 +4,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2018-11/</loc>
-    <lastmod>2018-11-04T12:18:52+02:00</lastmod>
+    <lastmod>2018-11-04T22:45:00+02:00</lastmod>
   </url>
   
   <url>
@@ -194,7 +194,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2018-11-04T12:18:52+02:00</lastmod>
+    <lastmod>2018-11-04T22:45:00+02:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -205,7 +205,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2018-11-04T12:18:52+02:00</lastmod>
+    <lastmod>2018-11-04T22:45:00+02:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -217,13 +217,13 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/posts/</loc>
-    <lastmod>2018-11-04T12:18:52+02:00</lastmod>
+    <lastmod>2018-11-04T22:45:00+02:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2018-11-04T12:18:52+02:00</lastmod>
+    <lastmod>2018-11-04T22:45:00+02:00</lastmod>
     <priority>0</priority>
   </url>