aboutsummaryrefslogtreecommitdiffstats
path: root/notes
diff options
context:
space:
mode:
Diffstat (limited to 'notes')
-rw-r--r--notes/ingest/2021-08_mag.md124
1 files changed, 124 insertions, 0 deletions
diff --git a/notes/ingest/2021-08_mag.md b/notes/ingest/2021-08_mag.md
index 5bab4f0..5f92196 100644
--- a/notes/ingest/2021-08_mag.md
+++ b/notes/ingest/2021-08_mag.md
@@ -274,3 +274,127 @@ And actually dump seedlist(s):
4593238 /srv/sandcrawler/tasks/mag_seedlist_2021-08-11.base_url.txt
4632911 /srv/sandcrawler/tasks/mag_seedlist_2021-08-11.combined.txt
3294710 /srv/sandcrawler/tasks/mag_seedlist_2021-08-11.terminal_url.txt
+
+## Post-Crawl Bulk Re-Ingest
+
+Got about 1.8 million new PDFs from crawl, and a sizable fraction of dupes (by
+hash, URL agnostic).
+
+Enqueue for buik re-ingest:
+
+ cat /srv/sandcrawler/tasks/mag_ingest_request_2021-08-11.ingest_request.json | rg -v "\\\\" | jq . -c | kafkacat -P -b wbgrp-svc263.us.archive.org -t sandcrawler-prod.ingest-file-requests-bulk -p -1
+ => Thu 19 Aug 2021 09:10:59 PM UTC
+
+
+## Post-Ingest Stats
+
+Just the new stuff (compare against above for delta):
+
+ SELECT ingest_file_result.status, COUNT(*)
+ FROM ingest_request
+ LEFT JOIN ingest_file_result
+ ON ingest_file_result.ingest_type = ingest_request.ingest_type
+ AND ingest_file_result.base_url = ingest_request.base_url
+ WHERE
+ ingest_request.ingest_type = 'pdf'
+ AND ingest_request.link_source = 'mag'
+ AND ingest_request.base_url NOT LIKE '%journals.sagepub.com%'
+ AND ingest_request.base_url NOT LIKE '%pubs.acs.org%'
+ AND ingest_request.base_url NOT LIKE '%ahajournals.org%'
+ AND ingest_request.base_url NOT LIKE '%www.journal.csj.jp%'
+ AND ingest_request.base_url NOT LIKE '%aip.scitation.org%'
+ AND ingest_request.base_url NOT LIKE '%academic.oup.com%'
+ AND ingest_request.base_url NOT LIKE '%tandfonline.com%'
+ AND ingest_request.base_url NOT LIKE '%researchgate.net%'
+ AND ingest_request.base_url NOT LIKE '%muse.jhu.edu%'
+ AND ingest_request.base_url NOT LIKE '%omicsonline.org%'
+ AND ingest_request.base_url NOT LIKE '%link.springer.com%'
+ AND ingest_request.base_url NOT LIKE '%ieeexplore.ieee.org%'
+ AND ingest_request.created > '2021-06-01'
+ GROUP BY status
+ ORDER BY COUNT DESC
+ LIMIT 20;
+
+ status | count
+ -------------------------+---------
+ success | 7748241 89.2%
+ no-capture | 429688 4.9%
+ redirect-loop | 172831 2.0%
+ terminal-bad-status | 94029 1.1%
+ no-pdf-link | 86437 1.0%
+ blocked-cookie | 67903 0.8%
+ link-loop | 50622
+ wrong-mimetype | 21064
+ null-body | 6650
+ cdx-error | 3313
+ wayback-error | 2630
+ gateway-timeout | 399
+ petabox-error | 268
+ wayback-content-error | 170
+ not-found | 130
+ read-timeout | 128
+ | 109
+ invalid-host-resolution | 63
+ bad-redirect | 39
+ spn2-error | 20
+ (20 rows)
+
+New success due to crawl (new batch only): 7748241 - 1957844 = 5,790,397
+
+Overall success of new batch: 7748241. / 8686315 = 89.2%
+
+And combined (old and new) status again:
+
+ SELECT ingest_file_result.status, COUNT(*)
+ FROM ingest_request
+ LEFT JOIN ingest_file_result
+ ON ingest_file_result.ingest_type = ingest_request.ingest_type
+ AND ingest_file_result.base_url = ingest_request.base_url
+ WHERE
+ ingest_request.ingest_type = 'pdf'
+ AND ingest_request.link_source = 'mag'
+ AND ingest_request.base_url NOT LIKE '%journals.sagepub.com%'
+ AND ingest_request.base_url NOT LIKE '%pubs.acs.org%'
+ AND ingest_request.base_url NOT LIKE '%ahajournals.org%'
+ AND ingest_request.base_url NOT LIKE '%www.journal.csj.jp%'
+ AND ingest_request.base_url NOT LIKE '%aip.scitation.org%'
+ AND ingest_request.base_url NOT LIKE '%academic.oup.com%'
+ AND ingest_request.base_url NOT LIKE '%tandfonline.com%'
+ AND ingest_request.base_url NOT LIKE '%researchgate.net%'
+ AND ingest_request.base_url NOT LIKE '%muse.jhu.edu%'
+ AND ingest_request.base_url NOT LIKE '%omicsonline.org%'
+ AND ingest_request.base_url NOT LIKE '%link.springer.com%'
+ AND ingest_request.base_url NOT LIKE '%ieeexplore.ieee.org%'
+ -- AND ingest_request.created > '2021-06-01'
+ GROUP BY status
+ ORDER BY COUNT DESC
+ LIMIT 20;
+
+ status | count
+ -------------------------------------+----------
+ success | 31990062
+ redirect-loop | 1704717
+ no-capture | 1263462
+ link-loop | 1218280
+ blocked-cookie | 1213838
+ no-pdf-link | 1096664
+ terminal-bad-status | 960070
+ gateway-timeout | 202190
+ wrong-mimetype | 86557
+ invalid-host-resolution | 37262
+ null-body | 15443
+ wayback-error | 12839
+ cdx-error | 4047
+ spn2-error | 1731
+ spn2-error:job-failed | 962
+ petabox-error | 463
+ wayback-content-error | 379
+ spn2-error:invalid-url-syntax | 336
+ spn2-error:soft-time-limit-exceeded | 203
+ | 175
+ (20 rows)
+
+New success total: 31990062 - 26123975 = 5,866,087
+
+A full 1,263,462 no-capture that could be attempted... though many of those may
+be excluded for a specific reason.