diff options
Diffstat (limited to 'notes/petabox_ia_metadata.txt')
| -rw-r--r-- | notes/petabox_ia_metadata.txt | 56 |
1 files changed, 56 insertions, 0 deletions
diff --git a/notes/petabox_ia_metadata.txt b/notes/petabox_ia_metadata.txt new file mode 100644 index 0000000..f46ea61 --- /dev/null +++ b/notes/petabox_ia_metadata.txt @@ -0,0 +1,56 @@ + +Ran in aitio:/schnell/iamine-journals in December 2018. + +Output uploaded to https://archive.org/details/ia-petabox-journal-metadata-2018 + +Commands: + + # didn't work! + #ia-mine --search collection:journals --itemlist > journals.20181218.itemlist + + # fetched manually via metamgr, using prefix matches + cat metamgr-* > metamgr-journals-loose.20181218.items + + ia-mine metamgr-journals-loose.20181218.items > journals.20181218.json + + export LC_ALL=C + cat journals-ia.20181218.json | jq 'select(.files) | .files[] | select(.format == "Text PDF") | .sha1' -r | sort -S 4G -u > journals-ia.20181218.pdf-sha1.tsv + +Size/results: + + bnewbold@ia601101$ wc -l journals-ia.20181218.json metamgr-journals-loose.20181218.items + 2043877 journals-ia.20181218.json + 2044362 metamgr-journals-loose.20181218.items + + # missed about 500; meh + + -rw-rw-r-- 1 bnewbold bnewbold 9.5G Dec 19 23:26 journals-ia.20181218.json + + bnewbold@ia601101$ wc -l journals-ia.20181218.pdf-sha1.tsv + 1748645 journals-ia.20181218.pdf-sha1.tsv + +## June 2019 Ingest + + bnewbold@ia601101$ pwd + /schnell/iamine-journals + + zcat journals-ia.20181218.json.gz | rg '"identifier": "arxiv-' > arxiv.json + zcat journals-ia.20181218.json.gz | rg '"identifier": "jstor-' > jstor.json + zcat journals-ia.20181218.json.gz | rg '"identifier": "paper-doi-10_' > paper-doi.json + zcat journals-ia.20181218.json.gz | rg '"identifier": "pubmed-PMC' > pmc.json + + cat arxiv.json | ./ia_pdf_match.py > arxiv.match.json + cat jstor.json | ./ia_pdf_match.py > jstor.match.json + cat paper-doi.json | ./ia_pdf_match.py > paper-doi.match.json + cat pmc.json | ./ia_pdf_match.py > pmc.match.json + + bnewbold@ia601101$ wc -l arxiv.*json jstor.*json paper-doi.*json pmc.*json + 1076012 arxiv.json + 740970 arxiv.match.json + 451204 jstor.json + 451204 jstor.match.json + 77838 paper-doi.json + 23736 paper-doi.match.json + 209787 pmc.json + 189093 pmc.match.json + |