aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2022-02-08 17:49:39 -0800
committerBryan Newbold <bnewbold@archive.org>2022-02-08 17:49:50 -0800
commit3a6fc1f1c26885fd7a44b13ee156fcdb61e6aadd (patch)
tree077afcd3c48553dbc65760db047b2e81ba080a73
parent067c97a59a4a8728add7b9e561082a5403be52e5 (diff)
downloadsandcrawler-3a6fc1f1c26885fd7a44b13ee156fcdb61e6aadd.tar.gz
sandcrawler-3a6fc1f1c26885fd7a44b13ee156fcdb61e6aadd.zip
more patch crawling
-rw-r--r--notes/ingest/2022-01-06_patch_crawl.md138
-rw-r--r--notes/ingest/2022-01-13_doi_crawl.md80
2 files changed, 209 insertions, 9 deletions
diff --git a/notes/ingest/2022-01-06_patch_crawl.md b/notes/ingest/2022-01-06_patch_crawl.md
index ffd6669..bc1d4d5 100644
--- a/notes/ingest/2022-01-06_patch_crawl.md
+++ b/notes/ingest/2022-01-06_patch_crawl.md
@@ -21,7 +21,7 @@ TODO: html-resource-no-capture (from error message? or do SPN requests separatel
Dump terminal URLs (will do ingest requests later, using similar command):
- COPY (
+ COPY (
SELECT ingest_file_result.terminal_url
-- SELECT row_to_json(ingest_request.*)
FROM ingest_request
@@ -154,3 +154,139 @@ TODO: filter out archive.org/www.archive.org
TODO: cleanup ingest request table in sandcrawler-db:
- remove filtered OAI-PMH prefixes
- remove any invalid `base_url` (?)
+
+## More Seedlist (2022-02-08)
+
+ 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 >= '2022-01-12'
+ 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'
+ OR 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_2022-02-08.rows.json';
+ ) TO '/srv/sandcrawler/tasks/patch_terminal_url.2022-02-08.txt';
+ => COPY 444764
+
+ cat patch_terminal_url.2022-02-08.txt \
+ | rg -v www.archive.org \
+ | rg '://' \
+ | rg -v '://10\.' \
+ | rg -v '://172\.' \
+ | rg -i '^http' \
+ | sort -u -S 4G \
+ | pv -l \
+ > patch_terminal_url.2022-02-08.uniq.txt
+ => 426k 0:00:04 [ 103k/s]
+
+ cut -f3 -d/ patch_terminal_url.2022-02-08.uniq.txt | sort | uniq -c | sort -nr | head -n25
+ 60123 www.degruyter.com
+ 59314 arxiv.org
+ 43674 zenodo.org
+ 17771 doi.org
+ 9501 linkinghub.elsevier.com
+ 9379 www.mdpi.com
+ 5691 opendata.uni-halle.de
+ 5578 scholarlypublishingcollective.org
+ 5451 era.library.ualberta.ca
+ 4982 www.cairn.info
+ 4306 www.taylorfrancis.com
+ 4189 papers.ssrn.com
+ 4157 apps.crossref.org
+ 4089 www.sciencedirect.com
+ 4033 mdpi-res.com
+ 3763 dlc.mpg.de
+ 3408 osf.io
+ 2603 www.frontiersin.org
+ 2594 watermark.silverchair.com
+ 2569 journals.lww.com
+ 1787 underline.io
+ 1680 archiviostorico.fondazione1563.it
+ 1658 www.jstage.jst.go.jp
+ 1611 cyberleninka.ru
+ 1535 www.schoeningh.de
+
+ cat patch_terminal_url.2022-02-08.txt | awk '{print "F+ " $1}' > patch_terminal_url.2022-02-08.schedule
+ => Done
+
+Copied to crawler svc206 and added to frontier.
diff --git a/notes/ingest/2022-01-13_doi_crawl.md b/notes/ingest/2022-01-13_doi_crawl.md
index 6f3b2c8..09a3b46 100644
--- a/notes/ingest/2022-01-13_doi_crawl.md
+++ b/notes/ingest/2022-01-13_doi_crawl.md
@@ -1,6 +1,8 @@
Could roll this in to current patch crawl instead of starting a new crawl from scratch.
+This file is misnamed; these are mostly non-DOI-specific small updates.
+
## KBART "almost complete" experimentation
Random 10 releases:
@@ -133,15 +135,12 @@ many of these are likely to crawl successfully.
| pv -l \
| gzip \
> /srv/fatcat/tasks/ingest_nonoa_doi.json.gz
- # Expecting 8255693 release objects in search queries
-
-## Seeds: not daily, but OA DOI
+ # re-running 2022-02-08 after this VM was upgraded
+ # Expecting 8321448 release objects in search queries
+ # TODO: in-progress
-There are a bunch of things we are no longer attempting daily, but should do
-heritrix crawls of periodically.
-
-TODO: maybe in daily crawling, should check container coverage and see if most URLs are bright, and if so do ingest? hrm
-TODO: What are they? zenodo.org?
+This is large enough that it will probably be a bulk ingest, and then probably
+a follow-up crawl.
## Seeds: HTML and XML links from HTML biblio
@@ -152,6 +151,71 @@ TODO: What are they? zenodo.org?
| gzip \
> ingest_file_result_fulltext_urls.2022-01-13.json.gz
+ # cut this off at some point? gzip is terminated weird
+
+ zcat ingest_file_result_fulltext_urls.2022-01-13.json.gz | wc -l
+ # gzip: ingest_file_result_fulltext_urls.2022-01-13.json.gz: unexpected end of file
+ # 2,538,433
+
+Prepare seedlists (to include in heritrix patch crawl):
+
+ zcat ingest_file_result_fulltext_urls.2022-01-13.json.gz \
+ | jq .html_biblio.xml_fulltext_url -r \
+ | rg '://' \
+ | sort -u -S 4G \
+ | pv -l \
+ | gzip \
+ > ingest_file_result_fulltext_urls.2022-01-13.xml_urls.txt.gz
+ # 1.24M 0:01:35 [12.9k/s]
+
+ zcat ingest_file_result_fulltext_urls.2022-01-13.json.gz \
+ | jq .html_biblio.html_fulltext_url -r \
+ | rg '://' \
+ | sort -u -S 4G \
+ | pv -l \
+ | gzip \
+ > ingest_file_result_fulltext_urls.2022-01-13.html_urls.txt.gz
+ # 549k 0:01:27 [6.31k/s]
+
+ zcat ingest_file_result_fulltext_urls.2022-01-13.xml_urls.txt.gz ingest_file_result_fulltext_urls.2022-01-13.html_urls.txt.gz \
+ | cut -f3 -d/ \
+ | sort -S 4G \
+ | uniq -c \
+ | sort -nr \
+ | head -n20
+
+ 534005 dlc.library.columbia.edu
+ 355319 www.degruyter.com
+ 196421 zenodo.org
+ 101450 serval.unil.ch
+ 100631 biblio.ugent.be
+ 47986 digi.ub.uni-heidelberg.de
+ 39187 www.emerald.com
+ 33195 www.cairn.info
+ 25703 boris.unibe.ch
+ 19516 journals.openedition.org
+ 15911 academic.oup.com
+ 11091 repository.dl.itc.u-tokyo.ac.jp
+ 9847 oxfordworldsclassics.com
+ 9698 www.thieme-connect.de
+ 9552 www.idunn.no
+ 9265 www.zora.uzh.ch
+ 8030 www.scielo.br
+ 6543 www.hanspub.org
+ 6229 asmedigitalcollection.asme.org
+ 5651 brill.com
+
+ zcat ingest_file_result_fulltext_urls.2022-01-13.xml_urls.txt.gz ingest_file_result_fulltext_urls.2022-01-13.html_urls.txt.gz \
+ | awk '{print "F+ " $1}' \
+ > ingest_file_result_fulltext_urls.2022-01-13.xml_and_html.schedule
+
+ wc -l ingest_file_result_fulltext_urls.2022-01-13.xml_and_html.schedule
+ 1785901 ingest_file_result_fulltext_urls.2022-01-13.xml_and_html.schedule
+
+Added to `JOURNALS-PATCH-CRAWL-2022-01`
+
## Seeds: most doi.org terminal non-success
Unless it is a 404, should retry.
+
+TODO: generate this list