From 7f30c43cd4955d596ebc51a56aea7996b1005e47 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Wed, 1 Apr 2020 15:26:12 -0700 Subject: update missing notes and commands --- notes/missing_2020-03-20.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'notes') diff --git a/notes/missing_2020-03-20.md b/notes/missing_2020-03-20.md index 2576a8e..4eaaa4e 100644 --- a/notes/missing_2020-03-20.md +++ b/notes/missing_2020-03-20.md @@ -290,11 +290,11 @@ Interesting sites to crawl or translate: cat missing_doi_status.tsv | rg '404$' | cut -f1 > unregistered_doi.tsv - cat missing_doi_status.tsv | rg '302$' | cut -f1 | parallel http --json get "https://api.crossref.org/v1/works/http://dx.doi.org/{}" | jq .message -c | pv -l > missing_doi_crossref.json + cat missing_doi_status.tsv | rg '302$' | cut -f1 | parallel -j1 'http --json get "https://api.crossref.org/v1/works/http://dx.doi.org/{}" mailto==webservices@archive.org' | rg '^\{' | jq .message -c | pv -l > missing_doi_crossref.json mkdir -p pubmed - cat missing_pmcid.tsv | parallel -j1 'http get "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id={}&rettype=pubmed" > pubmed/{}.xml' cat missing_pmid.tsv | parallel -j1 'http get "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id={}&rettype=pubmed" > pubmed/{}.xml' + cat missing_pmcid.tsv | parallel -j1 'http get "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pmc&id={}&rettype=pubmed" > pubmed/{}.xml' cat pubmed/*.xml | rg -v '^<\?xml version' | rg -v '^' | rg -v '^' > pubmed_combined.xml -- cgit v1.2.3