diff --git a/content/posts/2019-05.md b/content/posts/2019-05.md index a6a2653ca..b253c258d 100644 --- a/content/posts/2019-05.md +++ b/content/posts/2019-05.md @@ -322,11 +322,21 @@ UPDATE metadatavalue SET text_lang='es_ES' WHERE resource_type_id=2 AND metadata - So this was definitely an attack of some sort... only God knows why - I noticed a few new bots that don't use the word "bot" in their user agent and therefore don't match Tomcat's Crawler Session Manager Valve: - `Blackboard Safeassign` + - `Unpaywall` ## 2019-05-12 +- I see that the Unpaywall bot is resonsible for a few thousand XMLUI sessions every day (IP addresses come from nginx access.log): + +``` +$ cat dspace.log.2019-05-11 | grep -E 'ip_addr=(100.26.206.188|100.27.19.233|107.22.98.199|174.129.156.41|18.205.243.110|18.205.245.200|18.207.176.164|18.207.209.186|18.212.126.89|18.212.5.59|18.213.4.150|18.232.120.6|18.234.180.224|18.234.81.13|3.208.23.222|34.201.121.183|34.201.241.214|34.201.39.122|34.203.188.39|34.207.197.154|34.207.232.63|34.207.91.147|34.224.86.47|34.227.205.181|34.228.220.218|34.229.223.120|35.171.160.166|35.175.175.202|3.80.201.39|3.81.120.70|3.81.43.53|3.84.152.19|3.85.113.253|3.85.237.139|3.85.56.100|3.87.23.95|3.87.248.240|3.87.250.3|3.87.62.129|3.88.13.9|3.88.57.237|3.89.71.15|3.90.17.242|3.90.68.247|3.91.44.91|3.92.138.47|3.94.250.180|52.200.78.128|52.201.223.200|52.90.114.186|52.90.48.73|54.145.91.243|54.160.246.228|54.165.66.180|54.166.219.216|54.166.238.172|54.167.89.152|54.174.94.223|54.196.18.211|54.198.234.175|54.208.8.172|54.224.146.147|54.234.169.91|54.235.29.216|54.237.196.147|54.242.68.231|54.82.6.96|54.87.12.181|54.89.217.141|54.89.234.182|54.90.81.216|54.91.104.162)' | grep -E 'session_id=[A-Z0-9]{32}' | sort | uniq | wc -l +2206 +``` + +- I added "Unpaywall" to the list of bots in the Tomcat Crawler Session Manager Valve - Set up nginx to use TLS and proxy pass to NodeJS on the AReS development server (linode20) - Run all system updates on linode20 and reboot it - Also, there is 10 to 20% CPU steal on that VM, so I will ask Linode to move it to another host +- Commit changes to the `resolve-addresses.py` script to add proper CSV output support diff --git a/docs/2019-05/index.html b/docs/2019-05/index.html index 4e8d814d2..596535604 100644 --- a/docs/2019-05/index.html +++ b/docs/2019-05/index.html @@ -28,7 +28,7 @@ But after this I tried to delete the item from the XMLUI and it is still present - + @@ -61,9 +61,9 @@ But after this I tried to delete the item from the XMLUI and it is still present "@type": "BlogPosting", "headline": "May, 2019", "url": "https:\/\/alanorth.github.io\/cgspace-notes\/2019-05\/", - "wordCount": "2254", + "wordCount": "2323", "datePublished": "2019-05-01T07:37:43\x2b03:00", - "dateModified": "2019-05-10T17:27:11\x2b03:00", + "dateModified": "2019-05-12T10:39:10\x2b03:00", "author": { "@type": "Person", "name": "Alan Orth" @@ -518,15 +518,28 @@ UPDATE metadatavalue SET text_lang='es_ES' WHERE resource_type_id=2 AND metadata

2019-05-12

diff --git a/docs/sitemap.xml b/docs/sitemap.xml index 0ffbde08a..3c24adcb2 100644 --- a/docs/sitemap.xml +++ b/docs/sitemap.xml @@ -4,30 +4,30 @@ https://alanorth.github.io/cgspace-notes/ - 2019-05-10T17:27:11+03:00 + 2019-05-12T10:39:10+03:00 0 https://alanorth.github.io/cgspace-notes/2019-05/ - 2019-05-10T17:27:11+03:00 + 2019-05-12T10:39:10+03:00 https://alanorth.github.io/cgspace-notes/tags/notes/ - 2019-05-10T17:27:11+03:00 + 2019-05-12T10:39:10+03:00 0 https://alanorth.github.io/cgspace-notes/posts/ - 2019-05-10T17:27:11+03:00 + 2019-05-12T10:39:10+03:00 0 https://alanorth.github.io/cgspace-notes/tags/ - 2019-05-10T17:27:11+03:00 + 2019-05-12T10:39:10+03:00 0