Get all PLOS PMCIDs from PMC using Entrez

plos_pmc.py

import requests
import time

def get_all_pmc_dois(retstart=0, retmax=80000, count=None):
    """Query the entrez database to get a comprehensive list of all PMCIDs associated with all PLOS journals,
    individually included in the search url.
    See https://www.ncbi.nlm.nih.gov/books/NBK25499/#chapter4.ESearch for more info on search parameters
    :return: the full list of PMCIDs in PMC for PLOS articles
    """
    pmc_allplos_query_url = ('https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pmc&term='
                             '(((((("PLoS+ONE"[Journal])+OR+"PLoS+Genetics"[Journal])+OR+"PLoS+Pathogens"[Journal])'
                             'OR+"PLoS+Neglected+Tropical+Diseases"[Journal])+OR+"PLoS+Computational+Biology"[Journal])'
                             'OR+"PLoS+Biology"[Journal])+OR+"PLoS+Medicine"[Journal]+OR+"plos+currents"[Journal]'
                             '&retmode=json&tool=corpustest&email=name@domain.com')

    pmcidlist = []
    r = requests.get(pmc_allplos_query_url).json()
    if count is None:
        count = int(r['esearchresult']['count'])
        print(count, "articles found in PMC")
    while retstart < count:
        query = pmc_allplos_query_url + '&retstart={}&retmax={}'.format(retstart, retmax)
        r = requests.get(query).json()
        idlist = r['esearchresult']['idlist']
        for id in idlist:
            pmcidlist.append('PMC' + id)
        retstart += retmax
        time.sleep(1)
    pmcidlist = sorted(list(set(pmcidlist)))

    print(len(pmcidlist), "articles retrieved")
    return pmcidlist

if __name__ == '__main__':
    pmcidlist = get_all_pmc_dois()