Fetch publications given an ORCID and turn them into a markdown-formatted publication list

orcid_to_publications_markdown.sh

#!/bin/bash

# dependencies: jq, grep, sed, tr, curl, and perl URI::Escape (or replace url_encode function)
set -e
orcid="0000-0002-3512-7146"
# name to match when bolding in author list, should be abbreviated as in
# "Given Names Last" -> "G. N. Last"
match_name="C. Daniels"

# whether to output as a numbered list instead of unordered (i.e. bullet points)
output_numbered_list=true

function url_encode {
    # note: requires `perl-uri` on arch linux
    perl -MURI::Escape -e 'print uri_escape($ARGV[0]);' "${1?"Missing argument"}"
}

function echoerr {
    echo "$@" 1>&2
}

function get_dois_from {
    jq -r "
    # get the DOI for a ORCID group entry
    def group_doi:
        .groupId as \$gid |
        .externalIdentifiers | map(
            # we are only looking for DOIs here
            select(
                .externalIdentifierType.value == \"doi\" and 
                .relationship.value == \"self\"
            ) | 
            # actual DOI string (e.g., '10.1021/acsnano.9b05817')
            .externalIdentifierId.value
        ) | 
        if length == 0 then
            error(\"Missing DOI for ORCID entry [groupId = \(\$gid)]. Please edit works.json and try again.\")
        elif length > 1 then
            error(\"More than one DOI for ORCID entry [groupId = \(\$gid)]. Please edit works.json and try again.\")
        else
            .[0]
        end;

    # just get the associated DOI for each group entry
    .groups[] | group_doi
    " "${1?"missing input json file argument"}"
}

if [ -f "works.json" ]; then
    echoerr "Reusing existing works.json for ORCID $orcid"
else
    echoerr "Fetching works.json for ORCID $orcid"
    # get works in order of latest-oldest
    curl "https://orcid.org/$orcid/worksPage.json?offset=0&sort=date&sortAsc=false" \
        -H 'Accept: application/json, text/plain, */*' \
        -H "Referer: https://orcid.org/$orcid" \
        > works.json
fi

# get dois
echoerr "Getting DOIs from works.json"
get_dois_from works.json > works.txt
echoerr "Got $(wc -l < works.txt) DOIs from works.json"

# get data from crossref
echoerr "Getting info from crossref for each DOI"
while IFS="" read -r doi; do
    # url encode because /'s
    url_doi=$(url_encode "$doi")
    # output filenames
    xref_json="doi-$url_doi.json"
    xref_bib="doi-$url_doi.bib"
    
    if [ -f "$xref_json" ] && [ -f "$xref_bib" ]; then
        echoerr "  $doi already processed, skipping"
        continue
    fi
    
    echoerr "  Processing $doi"
    curl "https://api.crossref.org/v1/works/$url_doi" > "$xref_json"
    sleep 0.25
    curl "https://search.crossref.org/citation?format=bibtex&doi=$url_doi" > "$xref_bib"
    sleep 0.75
done < works.txt


# build markdown publication file...very hackily since this is taking too much time
echoerr "Building publications.md"
pub_idx=0
while IFS="" read -r doi; do
    echoerr "  Processing $doi"
    pub_idx=$(( pub_idx + 1 ))
    url_doi=$(url_encode "$doi")
    xref_json="doi-$url_doi.json"
    xref_bib="doi-$url_doi.bib"

    authors=$(
        jq -r --arg name "$match_name" '
            def abbreviate:
                split(" ") | map(.[:1] + ".") | join(" ");
            
            .message.author | map(
                "\(.given | abbreviate) \(.family)" |
                # bold name in author list if it matches
                if . == $name then
                    "**\(.)**"
                else
                    .
                end
            ) | join(", ")' "$xref_json"
    )
    title=$(jq -r '.message.title[0]' "$xref_json")
    journal=$(jq -r '.message | .["container-title"][0]' "$xref_json")
    year=$(grep 'year = ' "$xref_bib" | tr -d -c '[0-9]')
    volume=$(grep 'volume = ' "$xref_bib" | sed -e 's/^.*{//' -e 's/}.*$//')
    pages=$(grep 'pages = ' "$xref_bib" | sed -e 's/^.*{//' -e 's/}.*$//')

    markdown="$authors, _${title}_, $journal"
    if [ ! -z "$volume" ]; then markdown+=" $volume"; fi
    markdown+=", "
    if [ ! -z "$pages" ]; then markdown+="$pages "; fi
    markdown+="[$doi](https://doi.org/$url_doi)"
    if [ ! -z "$year" ]; then markdown+=" ($year)"; fi
    markdown+="."

    markdown=$(sed 's/--/–/g' <<< "$markdown")
    if [ "$output_numbered_list" = true ]; then
        echo "$pub_idx. $markdown"
    else
        echo "* $markdown"
    fi
done < works.txt > publications.md
echoerr "Done"

Output looks something like this:

1. J. Overbeck, G. Borin Barin, C. Daniels, M. L. Perrin, L. Liang, O. Braun, R. Darawish, B. Burkhardt, T. Dumslaff, X. Wang, A. Narita, K. Müllen, V. Meunier, R. Fasel, M. Calame, P. Ruffieux, Optimized Substrates and Measurement Approaches for Raman Spectroscopy of Graphene Nanoribbons, physica status solidi (b), 1900343 10.1002/pssb.201900343 (2019).
2. J. Overbeck, G. B. Barin, C. Daniels, M. L. Perrin, O. Braun, Q. Sun, R. Darawish, M. De Luca, X. Wang, T. Dumslaff, A. Narita, K. Müllen, P. Ruffieux, V. Meunier, R. Fasel, M. Calame, A Universal Length-Dependent Vibrational Mode in Graphene Nanoribbons, ACS Nano, 10.1021/acsnano.9b05817 (2019).
3. D. Liu, C. Daniels, V. Meunier, A. G. Every, D. Tománek, In-plane breathing and shear modes in low-dimensional nanostructures, Carbon 157, 364–370 10.1016/j.carbon.2019.10.041 (2020).
4. C. Sánchez‐Sánchez, T. Dienel, A. Nicolaï, N. Kharche, L. Liang, C. Daniels, V. Meunier, J. Liu, X. Feng, K. Müllen, J. R. Sánchez‐Valencia, O. Gröning, P. Ruffieux, R. Fasel, On‐Surface Synthesis and Characterization of Acene‐Based Nanoribbons Incorporating Four‐Membered Rings, Chemistry – A European Journal 25, 12074–12082 10.1002/chem.201901410 (2019).
5. N. W. Hackney, D. Tristant, A. Cupo, C. Daniels, V. Meunier, Shell model extension to the valence force field: application to single-layer black phosphorus, Physical Chemistry Chemical Physics 21, 322–328 10.1039/c8cp05923c (2019).
6. O. Gröning, S. Wang, X. Yao, C. A. Pignedoli, G. Borin Barin, C. Daniels, A. Cupo, V. Meunier, X. Feng, A. Narita, K. Müllen, P. Ruffieux, R. Fasel, Engineering of robust topological quantum phases in graphene nanoribbons, Nature 560, 209–213 10.1038/s41586-018-0375-9 (2018).
7. J. Owens, C. Daniels, A. Nicolaï, H. Terrones, V. Meunier, Structural, energetic, and electronic properties of gyroidal graphene nanostructures, Carbon 96, 998–1007 10.1016/j.carbon.2015.10.042 (2016).
8. C. Daniels, A. Horning, A. Phillips, D. V. P. Massote, L. Liang, Z. Bullard, B. G. Sumpter, V. Meunier, Elastic, plastic, and fracture mechanisms in graphene materials, Journal of Physics: Condensed Matter 27, 373002 10.1088/0953-8984/27/37/373002 (2015).
9. Z. J. Qi, C. Daniels, S. J. Hong, Y. W. Park, V. Meunier, M. Drndić, A. T. C. Johnson, Electronic Transport of Recrystallized Freestanding Graphene Nanoribbons, ACS Nano 9, 3510–3520 10.1021/nn507452g (2015).
10. A. Nicolaï, J. Monti, C. Daniels, V. Meunier, Electrolyte Diffusion in Gyroidal Nanoporous Carbon, The Journal of Physical Chemistry C 119, 2896–2903 10.1021/jp511919d (2015).
11. C. Daniels, Z. Bullard, E. C. Girão, V. Meunier, Emergent magnetism in irradiated graphene nanostructures, Carbon 78, 196–203 10.1016/j.carbon.2014.06.072 (2014).
12. Z. Bullard, E. Costa Girão, C. Daniels, B. G. Sumpter, V. Meunier, Quantifying energetics of topological frustration in carbon nanostructures, Physical Review B 89, 10.1103/physrevb.89.245425 (2014).