Mercurial > repos > iuc > ncbi_eutils_esummary
view ecitmatch.py @ 7:82e10809842f draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ncbi_entrez_eutils commit dc7c7e808d6482dd32f6bc0d9c14ac83007ca425"
author | iuc |
---|---|
date | Sat, 27 Nov 2021 09:51:18 +0000 |
parents | 254f40d3ae2b |
children |
line wrap: on
line source
#!/usr/bin/env python import argparse import eutils if __name__ == '__main__': parser = argparse.ArgumentParser(description='ECitMatch', epilog='') parser.add_argument('--file', type=argparse.FileType('r'), help='Tabular file containing citations to search') parser.add_argument('--key', nargs='*', help='Citation Key') parser.add_argument('--journal_title', nargs='*', help='Journal Title') parser.add_argument('--year', nargs='*', help='Year') parser.add_argument('--volume', nargs='*', help='Volume') parser.add_argument('--first_page', nargs='*', help='First Page') parser.add_argument('--author_name', nargs='*', help='Author name') parser.add_argument('--version', action='version', version=eutils.Client.getVersion(), help='Version (reports Biopython version)') # Emails parser.add_argument('--user_email', help="User email") parser.add_argument('--admin_email', help="Admin email") args = parser.parse_args() c = eutils.Client(user_email=args.user_email, admin_email=args.admin_email) citations = [] if args.file is None: for key, journal, year, volume, first_page, author_name in \ zip(args.key, args.journal_title, args.year, args.volume, args.first_page, args.author_name): citations.append({ 'key': key, 'journal': journal, 'year': year, 'volume': volume, 'first_page': first_page, 'author_name': author_name, }) else: for line in args.file: line = line.strip() if not line.startswith('#'): tmp = line.split('\t') try: citations.append({ 'journal': tmp[0], 'year': tmp[1], 'volume': tmp[2], 'first_page': tmp[3], 'author_name': tmp[4], 'key': tmp[5], }) except KeyError: print("Could not parse line: %s" % line) payload = { 'db': 'pubmed', 'bdata': citations } results = c.citmatch(**payload) # We get data back as pipe separated, so just replace those with tabs print(results.replace('|', '\t'))