rafaelpezzuto

import requests.exceptions as r_exceptions
import urllib3.exceptions as u_exceptions

from articlemeta.client import RestfulClient
from datetime import datetime, timedelta
from sickle import Sickle
from sickle.oaiexceptions import NoRecordsMatch


URL_STATIC_PDF_FILES = 'http://%s/static_pdf_files.txt'

rafaelpezzuto

rafaelpezzuto

rafaelpezzuto

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):

rafaelpezzuto

import csv
import json
import os

PATH_ISSNS = 'issns.txt'
PATH_DOAJ_DUMP_PARSED = 'doaj-dump-parsed.csv'

issns = set([i.strip() for i in open(PATH_ISSNS)])
scielo_doaj_docs = []

rafaelpezzuto

import urllib.parse

PATH_SCL_DOAJ_DOCS = 'scl-doaj-docs.csv'
PATH_SCL_PIDS_DOIS = 'scl-pids-dois.csv'
PATH_SCL_PIDS_DOAJ_LAST = 'scl-doaj-docs-jan-22.csv'
PATH_ISSNS = 'issns.txt'

scl_doaj_docs = [i.strip().split('|') for i in open(PATH_SCL_DOAJ_DOCS)]
scl_pids_dois = [i.strip().split(',') for i in open(PATH_SCL_PIDS_DOIS)]
issns = set([i.strip().upper() for i in open(PATH_ISSNS)])

rafaelpezzuto

rafaelpezzuto

rafaelpezzuto

rafaelpezzuto