RSCVD Fatcat Fuzzycat Lookup

rscvd_fatcat_check.py

#!/usr/bin/env/python3
"""
To run this script you need the 'fuzzycat' and 'elasticsearch' pip packages
installed (eg, 'pip install fuzzycat')
"""

import sys
import csv
import json
import elasticsearch
from fuzzycat.simple import closest_fuzzy_biblio_match
from fuzzycat.matching import public_api


def first_ia_access(release):
    for f in (release.files or []):
        for u in (f.urls or []):
            if "://web.archive.org/" in u.url or "://archive.org/" in u.url:
                return u.url
    for w in (release.webcaptures or []):
        for u in w.archive_urls:
            if "://web.archive.org/" in u.url:
                return u.url
    return None

def run(tsv_input):
    api = public_api("https://api.fatcat.wiki/v0")
    es_client = elasticsearch.Elasticsearch("https://search.fatcat.wiki:443")
    reader = csv.DictReader(tsv_input, delimiter="\t")

    for row in reader:
        doi = row.get('DOI') or None
        if doi and not doi.startswith('10.'):
            doi = None
        match = closest_fuzzy_biblio_match(
            es_client=es_client,
            biblio=dict(
                title=row.get('Article') or None,
                journal=row.get('Journal') or None,
                first_author=row.get('Author Name') or None,
                year=row.get('Publication Year') or None,
                volume=row.get('Volume / Edition') or None,
                issue=row.get('Issue') or None,
                pages=row.get('Pages') or None,
                doi=doi,
                pmid=row.get('pmid') or None,
                pcmid=row.get('pmcid') or None,
            )
        )
        if match:
            row['fuzzycat_status'] = match.status.name
            if match.release:
                match.release = api.get_release(match.release.ident, expand="container,files,webcaptures")
                row['fatcat_url'] = f"https://fatcat.wiki/release/{match.release.ident}"
                row['ia_access_url'] = first_ia_access(match.release)
                if match.release.container and match.release.container.extra:
                    #print(match.release.container.extra.get('ia'), file=sys.stderr)
                    row['ia_any_sim'] = bool((match.release.container.extra.get('ia') or {}).get('sim'))
                else:
                    row['ia_any_sim'] = False
        else:
            row['fuzzycat_status'] = "NONE"
        print(json.dumps(row))

if __name__ == "__main__":
    if len(sys.argv) != 2:
        print("Expect a single argument: RSCVD TSV file (exported from google sheets")
        sys.exit(-1)
    with open(sys.argv[1], "r") as tsv_input:
        run(tsv_input)