From 4e85415cca420bf043061572589833d74a93d5de Mon Sep 17 00:00:00 2001 From: Alan Orth Date: Thu, 12 Jul 2018 09:00:08 +0300 Subject: [PATCH] Update notes for 2018-07-12 --- content/posts/2018-07.md | 2 +- docs/2018-07/index.html | 6 +++--- docs/robots.txt | 2 +- docs/sitemap.xml | 20 ++++++++++---------- 4 files changed, 15 insertions(+), 15 deletions(-) diff --git a/content/posts/2018-07.md b/content/posts/2018-07.md index 404c41aef..31e975949 100644 --- a/content/posts/2018-07.md +++ b/content/posts/2018-07.md @@ -309,7 +309,7 @@ $ grep -c -E 'session_id=[A-Z0-9]{32}:ip_addr=95.108.181.88' dspace.log.2018-07- 993 GET /search-filter 804 GET /browse # zcat --force /var/log/nginx/*.log /var/log/nginx/*.log.1 | grep -E "Pcore-HTTP" | grep robots -208.110.72.10 - - [12/Jul/2018:00:22:28 +0000] "GET /robots.txt HTTP/1.1" 200 1301 "https://cgspace.cgiar.org/robots.txt" "Pcore-HTTP/v0.44.0 +208.110.72.10 - - [12/Jul/2018:00:22:28 +0000] "GET /robots.txt HTTP/1.1" 200 1301 "https://cgspace.cgiar.org/robots.txt" "Pcore-HTTP/v0.44.0" ``` - So this bot is just like Baiduspider, and I need to add it to the nginx rate limiting diff --git a/docs/2018-07/index.html b/docs/2018-07/index.html index 2ddf4c474..087330b7b 100644 --- a/docs/2018-07/index.html +++ b/docs/2018-07/index.html @@ -30,7 +30,7 @@ There is insufficient memory for the Java Runtime Environment to continue. - + @@ -73,7 +73,7 @@ There is insufficient memory for the Java Runtime Environment to continue. "url": "https://alanorth.github.io/cgspace-notes/2018-07/", "wordCount": "2079", "datePublished": "2018-07-01T12:56:54+03:00", - "dateModified": "2018-07-11T16:55:30+03:00", + "dateModified": "2018-07-12T08:35:39+03:00", "author": { "@type": "Person", "name": "Alan Orth" @@ -487,7 +487,7 @@ org.apache.solr.client.solrj.SolrServerException: IOException occured when talki 993 GET /search-filter 804 GET /browse # zcat --force /var/log/nginx/*.log /var/log/nginx/*.log.1 | grep -E "Pcore-HTTP" | grep robots -208.110.72.10 - - [12/Jul/2018:00:22:28 +0000] "GET /robots.txt HTTP/1.1" 200 1301 "https://cgspace.cgiar.org/robots.txt" "Pcore-HTTP/v0.44.0 +208.110.72.10 - - [12/Jul/2018:00:22:28 +0000] "GET /robots.txt HTTP/1.1" 200 1301 "https://cgspace.cgiar.org/robots.txt" "Pcore-HTTP/v0.44.0"