def doi_article(ref, user=None):
article_array = []
fetch = PubMedFetcher()
for doi in Reference.doi(ref):
article = fetch.article_by_doi(doi)
article_array.append(article)
return article
def doi_article(ref, user=None):
article_array = []
fetch = PubMedFetcher()
for doi in Reference.doi(ref):
article = fetch.article_by_doi(doi)
article_array.append(article)
return article
def get_info_by_DOI(DOI: str) -> Dict:
'''This function takes a DOI str, requests information about the corresponding
article via metapub or crossref and checks if all necessary information has been retrieved.'''
article_dict = {}
fetch = PubMedFetcher()
try:
article = fetch.article_by_doi(DOI)
# Save information in Dict
for info in dir(article):
if info[0] != '_':
article_dict[info] = eval('article.' + info)
# Add data retrieval info to the dict
article_dict = add_retrieval_information(article_dict, 'MetaPub',
'DOI', DOI)
except MetaPubError:
# If it does not work via Metapub, do it via Crossref Api
# If there is a timeout, try again (5 times)
for _ in range(5):
try:
works = Works()
article_dict = works.doi(DOI)
break
except:
pass
#article_dict = normalize_crossref_dict(article_dict)
# Add data retrieval info to the dict
#if contains_minimal_information(article_dict):
article_dict = add_retrieval_information(article_dict, 'Crossref',
'DOI', DOI)
return article_dict
def fetch_pubmed(pub_id, id_type = "pmid"):
"""
Fetches and formats pub data from
pubmed
"""
pm = PubMedFetcher()
if id_type == 'doi':
try:
result = pm.article_by_doi(pub_id)
except (AttributeError, MetaPubError, EutilsNCBIError):
return None
elif id_type == "pmid":
try:
result = pm.article_by_pmid(pub_id)
except (AttributeError, InvalidPMID, EutilsNCBIError):
return None
elif id_type == "pmc":
try:
result = pm.article_by_pmcid('PMC' + str(pub_id))
except (AttributeError, MetaPubError, EutilsNCBIError):
return None
result = result.to_dict()
# Set link using DOI
if result.get('doi'):
result['url'] = "http://dx.doi.org/" + result.get('doi')
else:
result['url'] = result.get('url')
# Provide PDF if possible
if result.get('pmc'):
result['pdf_url'] = f"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC{result['pmc']}/pdf"
out = {"pub_title": result.get('title'),
"pub_authors": result.get('authors'),
"pub_abstract": result.get('abstract'),
"pub_doi": result.get('doi'),
"pub_pmid": result.get('pmid'),
"pub_pmc": pub_id if id_type == 'pmc' else None,
"pub_url": result.get('url'),
"pub_pdf_url": result.get('pdf_url') or 'searching',
"pub_journal": result.get('journal'),
"pub_date": result['history'].get('pubmed')}
return out
def search(entry):
fetch = PubMedFetcher()
try:
article = fetch.article_by_pmid(entry['pmid'])
except:
try:
article = fetch.article_by_pmcid(entry['pmcid'])
except:
try:
article = fetch.article_by_doi(entry['doi'])
except:
try:
pmids = fetch.pmids_for_citation(authors=entry['author'], journal=entry['journal'], year=entry['year'], volume=entry['volume'])
# pmids2 = fetch.pmids_for_query(entry['title'])
article = fetch.article_by_pmid(pmids[0])
except:
return None
return article
def handle(self, *args, **options):
csvfile = "pmids.csv"
with open(csvfile, 'rU') as f:
reader = csv.reader(f)
count = 0
for row in reader:
pmid = self.get_pmid(row)
if count == 0:
count += 1
continue #skip first header row
if Publication.objects.filter(pmid=pmid).count() > 0:
count += 1
continue
if count == 3000: break
ref_id = row[0]
ref_type = row[1]
year = row[3]
article_title = row[4]
secondary_author = row[5]
journal_title = row[6]
place_published = row[7]
publisher = row[8]
volume = row[9]
issue = row[10]
pages = row[11]
date = row[12] #bad data in csv, don't use...
alt_journal = row[13]
doi = self.get_doi(row)
print doi
#pmid_from_ref = row[15]
#pmid_from_updates = row[16]
abstract = row[17]
url = row[18]
file_attachments = row[19]
author_address_from_pubmed = row[20] #empty column
figure = row[21]
cis_acc = row[22]
access_date = row[23]
luminex_product = row[24]
db_name = row[25]
db_provider = row[26]
language = row[27]
reprint_author_name = row[28]
blank = row[29]
reprint_author_email = row[30]
ecopy = row[39]
paper_type = row[40]
species = row[41]
assay = row[42]
sample_type = row[43] #this is the article title...
whos_kit = row[44]
misc = row[45]
application = row[46]
market_segment = row[47]
subsidiary_author = row[48]
custom_6 = row[49]
issn = row[51]
pub = Publication(
title=sample_type,
pmid=pmid,
doi=doi,
abstract=abstract,
)
fresh_data = None
if len(pmid) < 1:
fetch = PubMedFetcher()
try:
fresh_data = fetch.article_by_doi(doi)
fresh_data = fresh_data.to_dict()
except:
pass
else:
pub.pmid = fresh_data['pmid']
pub.save()
self.add_cis_tags(pub, row)
authors = self.get_authors(row)
for author in authors:
pub.authors.add(author)
lab = self.get_lab(row)
if lab:
for author in authors:
author.labs.add(lab)
pub.labs.add(lab)
count += 1