aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2022-03-02 17:09:44 -0800
committerBryan Newbold <bnewbold@archive.org>2022-03-02 17:09:44 -0800
commit4aa53c730f5fe9e0a5249d10d0b6ac0ff3c0db7c (patch)
tree250aa23b05a40363e67b1fed481f13c62b53410f
parent70de6d7e49bde4372962b7d5487d13f2d278f298 (diff)
downloadsandcrawler-4aa53c730f5fe9e0a5249d10d0b6ac0ff3c0db7c.tar.gz
sandcrawler-4aa53c730f5fe9e0a5249d10d0b6ac0ff3c0db7c.zip
2022 patch crawl bulk ingest notes
-rw-r--r--notes/ingest/2022-01-06_patch_crawl.md106
1 files changed, 106 insertions, 0 deletions
diff --git a/notes/ingest/2022-01-06_patch_crawl.md b/notes/ingest/2022-01-06_patch_crawl.md
index bc1d4d5..941519f 100644
--- a/notes/ingest/2022-01-06_patch_crawl.md
+++ b/notes/ingest/2022-01-06_patch_crawl.md
@@ -290,3 +290,109 @@ TODO: cleanup ingest request table in sandcrawler-db:
=> Done
Copied to crawler svc206 and added to frontier.
+
+
+## Bulk Ingest Requests (2022-02-28)
+
+Note that we are skipping OAI-PMH here, because we just did a separate ingest
+for those.
+
+This is going to dump many duplicate lines (same `base_url`, multiple
+requests), but that is fine. Expecting something like 7 million rows.
+
+ COPY (
+ -- SELECT ingest_file_result.terminal_url
+ SELECT row_to_json(ingest_request.*)
+ 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'
+ OR ingest_request.ingest_type = 'html'
+ )
+ AND ingest_file_result.updated <= '2022-02-08'
+ AND (
+ ingest_file_result.status = 'no-capture'
+ OR ingest_file_result.status = 'cdx-error'
+ OR ingest_file_result.status = 'wayback-error'
+ OR ingest_file_result.status = 'wayback-content-error'
+ OR ingest_file_result.status = 'petabox-error'
+ OR ingest_file_result.status = 'spn2-cdx-lookup-failure'
+ OR ingest_file_result.status = 'gateway-timeout'
+ OR (
+ ingest_file_result.status = 'terminal-bad-status'
+ AND (
+ ingest_file_result.terminal_status_code = 429
+ OR ingest_file_result.terminal_status_code = 500
+ OR ingest_file_result.terminal_status_code = 502
+ OR ingest_file_result.terminal_status_code = 503
+ )
+ )
+ )
+ AND (
+ -- ingest_request.link_source = 'oai'
+ ingest_request.link_source = 'doi'
+ OR ingest_request.link_source = 'arxiv'
+ OR ingest_request.link_source = 'doaj'
+ OR ingest_request.link_source = 'unpaywall'
+ OR ingest_request.link_source = 'pmc'
+ )
+
+ AND ingest_request.link_source_id NOT LIKE 'oai:kb.dk:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:bdr.oai.bsb-muenchen.de:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:hispana.mcu.es:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:bnf.fr:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:ukm.si:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:biodiversitylibrary.org:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:hsp.org:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:repec:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:n/a:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:quod.lib.umich.edu:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:americanae.aecid.es:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:www.irgrid.ac.cn:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:espace.library.uq.edu:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:edoc.mpg.de:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:bibliotecadigital.jcyl.es:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:repository.erciyes.edu.tr:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:krm.or.kr:%'
+ AND ingest_request.link_source_id NOT LIKE 'oai:hypotheses.org:%'
+
+ AND ingest_file_result.terminal_url NOT LIKE '%mdz-nbn-resolving.de%'
+ AND ingest_file_result.terminal_url NOT LIKE '%edoc.mpg.de%'
+ AND ingest_file_result.terminal_url NOT LIKE '%doaj.org%'
+ AND ingest_file_result.terminal_url NOT LIKE '%orcid.org%'
+ AND ingest_file_result.terminal_url NOT LIKE '%gateway.isiknowledge.com%'
+ -- AND ingest_file_result.terminal_url NOT LIKE '%europmc.org%'
+ -- AND ingest_file_result.terminal_url NOT LIKE '%arxiv.org%'
+ -- AND ingest_file_result.terminal_url NOT LIKE 'https://doi.org/10.%'
+
+ AND ingest_file_result.terminal_url NOT LIKE '%journals.sagepub.com%'
+ AND ingest_file_result.terminal_url NOT LIKE '%pubs.acs.org%'
+ AND ingest_file_result.terminal_url NOT LIKE '%ahajournals.org%'
+ AND ingest_file_result.terminal_url NOT LIKE '%www.journal.csj.jp%'
+ AND ingest_file_result.terminal_url NOT LIKE '%aip.scitation.org%'
+ AND ingest_file_result.terminal_url NOT LIKE '%academic.oup.com%'
+ AND ingest_file_result.terminal_url NOT LIKE '%tandfonline.com%'
+ AND ingest_file_result.terminal_url NOT LIKE '%researchgate.net%'
+ AND ingest_file_result.terminal_url NOT LIKE '%muse.jhu.edu%'
+ AND ingest_file_result.terminal_url NOT LIKE '%omicsonline.org%'
+ AND ingest_file_result.terminal_url NOT LIKE '%link.springer.com%'
+ AND ingest_file_result.terminal_url NOT LIKE '%ieeexplore.ieee.org%'
+
+ -- AND ingest_file_result.terminal_url NOT LIKE '%zenodo.org%'
+ AND ingest_file_result.terminal_url NOT LIKE '%t2r2.star.titech.ac.jp%'
+ AND ingest_file_result.terminal_url NOT LIKE '%www.google.com%'
+ -- AND ingest_file_result.terminal_url NOT LIKE '%figshare.com%'
+ -- AND ingest_file_result.terminal_url NOT LIKE '%springernature.figshare.com%'
+ AND ingest_file_result.terminal_url NOT LIKE '%www.archive.org%'
+ ) TO '/srv/sandcrawler/tasks/patch_ingest_request_2022-02-28.rows.json';
+ # COPY 3053219
+
+ ./scripts/ingestrequest_row2json.py /srv/sandcrawler/tasks/patch_ingest_request_2022-02-28.rows.json | pv -l | shuf > /srv/sandcrawler/tasks/patch_ingest_request_2022-02-28.ingest_request.json
+ => DONE
+
+ cat /srv/sandcrawler/tasks/patch_ingest_request_2022-02-28.ingest_request.json | rg -v "\\\\" | jq . -c | kafkacat -P -b wbgrp-svc263.us.archive.org -t sandcrawler-prod.ingest-file-requests-bulk -p -1
+ => DONE
+