From 2837cd34b0da501a7c69616e2befc08d26ced809 Mon Sep 17 00:00:00 2001 From: Alan Orth Date: Sat, 6 Apr 2019 12:01:09 +0300 Subject: [PATCH] Update notes for 2019-04-06 --- content/posts/2019-04.md | 10 ++++++++++ docs/2019-04/index.html | 17 ++++++++++++++--- docs/sitemap.xml | 10 +++++----- 3 files changed, 29 insertions(+), 8 deletions(-) diff --git a/content/posts/2019-04.md b/content/posts/2019-04.md index 4cd0fbb13..0744e9702 100644 --- a/content/posts/2019-04.md +++ b/content/posts/2019-04.md @@ -155,6 +155,16 @@ GET /handle/10568/72970/discover?filtertype_0=type&filtertype_1=author&filter_re 22077 /handle/10568/72970/discover ``` +- Yesterday they made 43,000 requests and we actually blocked most of them: + +``` +# zcat --force /var/log/nginx/access.log /var/log/nginx/access.log.1 /var/log/nginx/access.log.2.gz | grep "05/Apr/2019" | grep 45.5.184.72 | grep -oE '/handle/[0-9]+/[0-9]+/discover' | sort | uniq -c + 43631 /handle/10568/72970/discover +# zcat --force /var/log/nginx/access.log /var/log/nginx/access.log.1 /var/log/nginx/access.log.2.gz | grep "05/Apr/2019" | grep 45.5.184.72 | grep -E '/handle/[0-9]+/[0-9]+/discover' | awk '{print $9}' | sort | uniq -c + 142 200 + 43489 503 +``` + - I need to find a contact at CIAT to tell them to use the REST API rather than crawling Discover - Maria from Bioversity recommended that we use the phrase "AGROVOC subject" instead of "Subject" in Listings and Reports - I made a pull request to update this and merged it to the `5_x-prod` branch ([#418](https://github.com/ilri/DSpace/pull/418)) diff --git a/docs/2019-04/index.html b/docs/2019-04/index.html index 9bc721731..07233f090 100644 --- a/docs/2019-04/index.html +++ b/docs/2019-04/index.html @@ -38,7 +38,7 @@ $ ./delete-metadata-values.py -i /tmp/2019-02-21-delete-1-region.csv -db dspace - + @@ -81,9 +81,9 @@ $ ./delete-metadata-values.py -i /tmp/2019-02-21-delete-1-region.csv -db dspace "@type": "BlogPosting", "headline": "April, 2019", "url": "https://alanorth.github.io/cgspace-notes/2019-04/", - "wordCount": "980", + "wordCount": "1044", "datePublished": "2019-04-01T09:00:43+03:00", - "dateModified": "2019-04-05T23:07:30+03:00", + "dateModified": "2019-04-06T11:47:45+03:00", "author": { "@type": "Person", "name": "Alan Orth" @@ -338,6 +338,17 @@ $ ./delete-metadata-values.py -i /tmp/2019-02-21-delete-1-region.csv -db dspace 22077 /handle/10568/72970/discover + + +
# zcat --force /var/log/nginx/access.log /var/log/nginx/access.log.1 /var/log/nginx/access.log.2.gz | grep "05/Apr/2019" | grep 45.5.184.72 | grep -oE '/handle/[0-9]+/[0-9]+/discover' | sort | uniq -c 
+  43631 /handle/10568/72970/discover
+# zcat --force /var/log/nginx/access.log /var/log/nginx/access.log.1 /var/log/nginx/access.log.2.gz | grep "05/Apr/2019" | grep 45.5.184.72 | grep -E '/handle/[0-9]+/[0-9]+/discover' | awk '{print $9}' | sort | uniq -c 
+    142 200
+  43489 503
+
+