Created
January 17, 2022 22:44
-
-
Save rafaelpezzuto/ae8456e29faff7bf026c3e873eabef19 to your computer and use it in GitHub Desktop.
Parse doaj dump
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import csv | |
import json | |
import os | |
DOAJ_DUMP_FILES = [f for f in os.listdir() if f.endswith('json')] # diretório com arquivos JSON do DOAJ DUMP | |
DOAJ_KEYS = ['publisher', 'doi', 'czu', 'pissn', 'issn', 'eissn', 'elocationid'] # chaves esperadas nos dados DOAJ | |
def extract_links(data): | |
links = data.get('bibjson', {}).get('link', []) | |
parsed_links = [l.get('url', '').lower() for l in links] | |
return '#'.join([l for l in parsed_links if l != '']) | |
def extract(data): | |
identifiers = data.get('bibjson', {}).get('identifier', []) | |
created_date = data.get('created_date') | |
last_updated = data.get('last_updated') | |
links = extract_links(data) | |
parsed_ids = {} | |
for i in identifiers: | |
id_type = i.get('type', '').lower() | |
id_value = i.get('id', '').lower() | |
if id_type != '': | |
parsed_ids[id_type] = id_value | |
return '|'.join([data['id']] + [parsed_ids.get(v, '') for v in sorted(DOAJ_KEYS)] + [links] + [created_date, last_updated]) | |
with open('doaj-dump-parsed.csv', 'w') as fout: | |
for f in DOAJ_DUMP_FILES: | |
fj = json.load(open(f)) | |
fout.write('|'.join(['doaj_id'] + sorted(DOAJ_KEYS) + ['links'] + ['created_date', 'last_updated']) + '\n') | |
for line in fj: | |
try: | |
fout.write(extract(line) + '\n') | |
except Exception as e: | |
print(line) | |
print(e) | |
continue |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment