def main(author_name):
""" Print all publications as JSON to STDOUT """
data = {}
data['publications'] = []
author = scholarly.fill(next(scholarly.search_author(author_name)))
for pub in author['publications']:
pub_details = scholarly.fill(pub)['bib']
data['publications'].append({
'authors':
reformat_coauthors(pub_details['author'].split(' and ')),
'year':
pub_details.get('pub_year', ''),
'title':
pub_details.get('title', ''),
'journal':
pub_details.get('journal', ''),
'volume':
pub_details.get('volume', ''),
'issue':
pub_details.get('issue', ''),
'pages':
pub_details.get('pages', ''),
'citations':
pub.get('num_citations', 0),
'pub_url':
pub.get('pub_url', ''),
#'eprint_url': pub.get('pub_url', '') # seems to be same as pub_url
})
output_json(data)
def get_all_coauthors(author_name, min_year, max_year, max_coauthors,
include_no_year):
""" Get a set of all coauthors """
author = scholarly.fill(next(scholarly.search_author(author_name)))
all_coauthors = set()
for pub in author['publications']:
# Evaluate if publication year is indicated (if not, ignore depending
# on presence of --include_no_year flag)
if 'pub_year' in pub['bib']:
pub_year = int(pub['bib']['pub_year'])
elif include_no_year:
pub_year = max_year
else:
pub_year = min_year - 1
# Evaluate whether publication falls within indicated timerange
if min_year <= pub_year <= max_year:
coauthors = scholarly.fill(pub)['bib']['author'].split(' and ')
# Evaluate if number of coauthors meets optional threshold
if len(coauthors) <= max_coauthors:
[
all_coauthors.add(reformat_name(coauthor))
for coauthor in coauthors
]
return all_coauthors
def main(args):
gs_author = {}
gs_pubs = []
if not args.force:
gs_author = load('google_scholar_author.pkl') or {}
gs_pubs = load('google_scholar_publications.pkl') or []
gs_author = scholarly.search_author_id('SZR6mXsAAAAJ')
gs_author = scholarly.fill(gs_author)
save(gs_author, 'google_scholar_author.pkl')
current_pubs_ids = {p['author_pub_id'] for p in gs_pubs}
author_pubs_ids = {p['author_pub_id'] for p in gs_author['publications']}
new_pubs_ids = author_pubs_ids - current_pubs_ids
new_pubs = [
p for p in gs_author['publications']
if p['author_pub_id'] in new_pubs_ids
]
# TODO update based on info available on gs_author
for p in tqdm(new_pubs):
p = scholarly.fill(p)
gs_pubs.append(p)
save(gs_pubs, 'google_scholar_publications.pkl')
def find_bbe_coauthors(
name, institution="Caltech", start=2015, verbose=True):
search_query = scholarly.search_author(name + ", " + institution)
author = scholarly.fill(next(search_query))
coauthors = set()
for i, pub in enumerate(author['publications']):
# Make sure this is within the date range that we care about
try:
if int(pub['bib']['pub_year']) < start:
# Skip this entry
continue
elif verbose:
print(i, end=" ", flush=True)
except KeyError:
continue
# Get the full data
pub = scholarly.fill(pub)
for author in pub['bib']['author'].split("and"):
coauthors.add(author.strip())
print("")
return coauthors
def test_search_author_single_author(self):
query = 'Steven A. Cholewiak'
authors = [a for a in scholarly.search_author(query)]
self.assertGreaterEqual(len(authors), 1)
author = scholarly.fill(authors[0])
self.assertEqual(author['name'], u'Steven A. Cholewiak, PhD')
self.assertEqual(author['scholar_id'], u'4bahYMkAAAAJ')
pub = scholarly.fill(author['publications'][2])
self.assertEqual(pub['author_pub_id'], u'4bahYMkAAAAJ:LI9QrySNdTsC')
def scholarly_request(search_string: str) -> Dict:
'''This function takes a search keyword string and request information about the corresponding article
via scholarly'''
# Get all available information
search_query = scholarly.search_pubs(search_string)
article_info = next(search_query)
scholarly.fill(article_info)
article_dict = article_info['bib']
article_dict = normalize_scholarly_dict(article_dict)
article_dict = add_retrieval_information(article_dict, 'Scholarly',
'unstructured_ID', search_string)
return article_dict
def fetch_citations(author,
filesave="citations.json",
proxy="",
proxy_list=""):
""" Fetch citations from google scholar using scholarly """
if proxy != "":
print("Setting up proxy ", proxy)
scholarly.use_proxy(scholarly.SingleProxy(http=proxy, https=proxy))
if proxy_list != "":
lproxies = open(proxy_list, 'r').readlines()
def proxy_gen():
if proxy_gen.counter >= len(lproxies):
raise IndexError("We ran out of proxies...")
proxy = lproxies[proxy_gen.counter]
if not proxy.startswith("http"):
proxy = "http://" + proxy
proxy_gen.counter += 1
return proxy
proxy_gen.counter = 0
scholarly.use_proxy(proxy_gen)
print("Looking up " + author)
search = scholarly.search_author(author)
author = scholarly.fill(next(search))
publications = []
for i, pub in enumerate(author['publications']):
cites = pub['num_citations'] # often this gets messed up upon .fill()
if "pub_year" in pub['bib']:
pubyear = pub['bib'][
"pub_year"] # also this gets messed up upon .fill()
pub = scholarly.fill(pub)
pub['bib']["pub_year"] = pubyear
else:
pub = scholarly.fill(pub)
if not "pub_year" in pub.bib:
# skip publications that really don't have a year,
# they probably are crap that was picked up by the search robot
continue
pub['num_citations'] = cites
print("Fetching: " + str(i) + "/" + str(len(author['publications'])) +
": " + pub['bib']["title"] + " (" + str(pub['bib']["pub_year"]) +
")")
pub['bib'].pop("abstract", None)
pub.pop("source", None)
publications.append(pub)
f = open(filesave, "w")
f.write(json.dumps(publications))
f.close()
def quick_fetch_author(name):
search_query = scholarly.search_author(name)
author = scholarly.fill(next(search_query),
sections=['publications', 'coauthors'])
iterator = 0
data = {}
publications = []
coauthors = []
for auth in author['coauthors']:
coauthors.append(auth['name'])
for pub in author['publications']:
pub_info = {}
make_attribute(pub_info, 'title', pub, 'bib')
make_attribute(pub_info, 'num_citations', pub, 'plain')
make_attribute(pub_info, 'pub_year', pub, 'bib')
pub_info['_id'] = iterator
iterator += 1
publications.append(pub_info)
make_attribute(data, 'name', author, 'plain')
make_attribute(data, 'coauthors', coauthors, 'obj')
make_attribute(data, 'affiliation', author, 'plain')
make_attribute(data, 'email_domain', author, 'plain')
make_attribute(data, 'interests', author, 'plain')
make_attribute(data, 'citedby', author, 'plain')
make_attribute(data, 'number_of_publications', len(publications), 'obj')
make_attribute(data, 'publications', publications, 'obj')
return data
def extract_coauthors_by_id(author_id):
"""
extracts the co-authors of the currently existing authors in the dataset
"""
# create the output file
author = scholarly.search_author_id(author_id)
filled_coauthors = scholarly.fill(author, ['coauthors'])
coauthors_list = filled_coauthors['coauthors']
for author in coauthors_list:
filled_author = scholarly.fill(author, ['indices'])
register_coauthering(author_id, filled_author['scholar_id'])
print(filled_author)
mydict = filled_author_to_dict(filled_author)
write_author(mydict, AUTHORS_CSV_FILE_OUTPUT_COAUTHORS)
def add_publications(self, request):
owner_id = self.request.user.id
owner = get_object_or_404(User, pk=owner_id)
Publication.objects.filter(
owner=owner
).delete()
author_id = request.GET.get('author_id', None)
author_basic = scholarly.search_author_id(author_id)
author = scholarly.fill(author_basic)
data = {}
for publication in author['publications'][:25]:
publication_info = publication['bib']
if 'title' in publication_info:
data['title'] = publication_info['title']
if 'pub_year' in publication_info:
data['publication_year'] = publication_info['pub_year']
if 'author_pub_id' in publication:
elem = publication['author_pub_id'].split(':')
base_link = "https://scholar.google.com/citations?user={}" + \
"#d=gs_md_cita-d&u=%2Fcitations%3Fview_op%3D" +\
"view_citation%26user%3D{}%26citation_for_view%3D{}%3A{}"
data['link'] = base_link.format(
elem[0], elem[0], elem[0], elem[1])
if 'num_citations' in publication:
data['citation_number'] = publication['num_citations']
data['owner'] = owner_id
serializer = PublicationSerializer(data=data)
serializer.is_valid(raise_exception=True)
Publication.objects.create(
**serializer.validated_data)
return Response(status=status.HTTP_201_CREATED)
def get_schoolar_data(author_name,
cache_folder="scholarly",
affiliation='UBC'):
output_folder = os.path.join(os.path.dirname(os.path.realpath(__file__)),
"..", "resources", cache_folder)
cached = os.path.join(output_folder, format_author(author_name))
from_cache = False
final_data = []
if not os.path.isfile(cached):
try:
# Retrieve the author's data, fill-in, and print
search_query = scholarly.search_author(
f'{author_name} {affiliation}')
author = scholarly.fill(next(search_query))
# Print the titles of the author's publications
titles = [pub['bib']['title'] for pub in author['publications']]
final_data = []
for title in titles:
logger.info("Processing " + Fore.YELLOW + title +
Style.RESET_ALL)
ret = get_publication(title)
retries = 0
while not ret['success'] and retries < MAX_RETRIES_ON_ERROR:
retries += 1
msg = "Error while querying CrossRef API ({}), retrying ({})...".format(
ret["exception"], retries)
logger.info(Fore.RED + msg + Style.RESET_ALL)
ret = get_publication(title)
sleep(3)
if ret['success']:
ret['original_title'] = title
final_data.append(ret)
else:
logger.info(Fore.RED + '> Failed' + Style.RESET_ALL)
final_data = list(
filter(lambda k: k['result']['similarity'] >= 0.7, final_data))
final_data = sorted(final_data,
key=lambda k: k['result']['similarity'],
reverse=True)
with open(cached, 'w') as fo:
json.dump(final_data, fo, indent=4, sort_keys=True)
except StopIteration:
logger.info(Fore.RED + 'no more schoolar data available' +
Style.RESET_ALL)
with open(cached, 'w') as fo:
json.dump(final_data, fo, indent=4, sort_keys=True)
except Exception as ex:
logger.exception(str(ex))
else:
with open(cached, 'r') as fo:
final_data = json.load(fo)
from_cache = True
return final_data, from_cache
def test_search_pubs_filling_publication_contents(self):
'''
This process checks the process of filling a publication that is derived
from the search publication snippets.
'''
query = 'Creating correct blur and its effect on accommodation'
results = scholarly.search_pubs(query)
pubs = [p for p in results]
self.assertGreaterEqual(len(pubs), 1)
f = scholarly.fill(pubs[0])
self.assertTrue(
f['bib']['author'] ==
u'Cholewiak, Steven A and Love, Gordon D and Banks, Martin S')
self.assertTrue(
f['author_id'] == ['4bahYMkAAAAJ', '3xJXtlwAAAAJ', 'Smr99uEAAAAJ'])
self.assertTrue(f['bib']['journal'] == u'Journal of vision')
self.assertTrue(f['bib']['number'] == '9')
self.assertTrue(f['bib']['pages'] == u'1--1')
self.assertTrue(
f['bib']['publisher'] ==
u'The Association for Research in Vision and Ophthalmology')
self.assertTrue(
f['bib']['title'] ==
u'Creating correct blur and its effect on accommodation')
self.assertTrue(
f['pub_url'] ==
u'https://jov.arvojournals.org/article.aspx?articleid=2701817')
self.assertTrue(f['bib']['volume'] == '18')
self.assertTrue(f['bib']['pub_year'] == u'2018')
def _add_or_update_academic(google_scholar_id, user_id):
user = User.query.get(user_id)
current_app.logger.info(f'Adding or Updating Academic: {google_scholar_id} as user {user}')
Entrez.email = user.email
resp = scholarly.fill(scholarly.search_author_id(google_scholar_id), sections=['indices'])
if resp:
a = Academic.query.filter(Academic.google_scholar_id == google_scholar_id).one_or_none()
if a is None:
a = Academic(google_scholar_id=google_scholar_id)
a.name=resp['name']
a.affiliation=resp['affiliation']
a.cited_by=resp['citedby']
a.h_index=resp['hindex']
a.i10_index=resp['i10index']
a.last_update_date=datetime.utcnow()
a.is_updating = True
db.session.add(a)
db.session.commit()
_update_publications(a)
a = Academic.query.filter(Academic.google_scholar_id == google_scholar_id).one()
a.is_updating = False
db.session.add(a)
db.session.commit()
current_app.logger.info(f'Adding or Updating Academic Completed: {google_scholar_id}')
def fetch_publication_from_id(name, id):
search_query = scholarly.search_author(name)
pub = scholarly.fill(next(search_query), sections=['publications'])
scholarly.fill(pub['publications'][id])
result = pub['publications'][id]
data = {}
make_attribute(data, 'title', result, 'bib')
make_attribute(data, 'author', result, 'bib')
make_attribute(data, 'pub_year', result, 'bib')
make_attribute(data, 'abstract', result, 'bib')
make_attribute(data, 'journal', result, 'bib')
make_attribute(data, 'number', result, 'bib')
make_attribute(data, 'pages', result, 'bib')
make_attribute(data, 'publisher', result, 'bib')
make_attribute(data, 'volume', result, 'bib')
make_attribute(data, 'num_citations', result, 'plain')
return data
def fetch_scholar_author(gsID, fill=True):
''' Queries google scholar for a given author
Also fills all stats if fill is True (a bit slower)'''
author = scholarly.search_author_id(gsID)
if fill:
author = scholarly.fill(
author, sections=['publications', 'basics', 'indices', 'counts'])
return author
def get_papers_for_author(author_id):
'''
Gets and registers the papers of an author
'''
print("getting paper for author " + author_id)
author = scholarly.search_author_id(author_id)
filled_publications = scholarly.fill(author, ['publications'])
publications_list = filled_publications['publications']
nbpubs_counter = 0
for publication in publications_list:
filled_publication = scholarly.fill(publication)
mydict = tiny_publication_to_dict(filled_publication)
write_publication(mydict, PUBLICATIONS_CSV_FILE_OUTPUT)
nbpubs_counter += 1
print("nbpubs_counter =====>")
print(nbpubs_counter)
if nbpubs_counter > NB_MAX_PAPERS_PER_AUTHOR:
break
def main(args):
print('Querying Google Scholar ...')
author = scholarly.search_author_id('SZR6mXsAAAAJ')
author = scholarly.fill(author, sections=['publications'])
pubs = map(_parse, author['publications'])
cites = {x[0]: x[1] for x in pubs if x[1] > 0}
# jsonp = 'cites = {};'.format()
jsonp = json.dumps(cites)
with open(args.output, 'w') as out:
out.write(jsonp)
def register_authors_from_generator(author_generator):
"""
This method goes throught the author generator and gets all
the authors and registre them in the authors dataset
"""
# create the file
open(AUTHORS_CSV_FILE_OUTPUT, 'w')
while True:
author = next(author_generator)
filled_author = scholarly.fill(author, ['indices'])
mydict = filled_author_to_dict(filled_author)
write_author(mydict, AUTHORS_CSV_FILE_OUTPUT)
def save_csv():
_file = open("output.csv", "w+")
search_query = scholarly.search_author("Mayken Espinoza-Andaluz")
author = scholarly.fill(next(search_query))
_file.write("title|authors|year|abstract\n")
for pub in author["publications"]:
title = pub["bib"]["title"]
year = pub["bib"]["pub_year"]
abstract = pub["bib"]["title"]
_file.write(f"{title}|{authors}|{year}|{abstract}\n")
_file.close()
def get_author(author,university=""):
url_part = "https://scholar.google.co.in/citations?user="******", "+university if university!='' else ''))
try:
authorResult = next(authorSearch)
except:
return "Not Found"
authorRaw = scholarly.fill(authorResult,sections=['basics','indices','publications'])
authorDetails = {'name':authorRaw['name'],'affiliation':authorRaw['affiliation'],'email_domain':authorRaw['email_domain'],'interests':authorRaw['interests']
,'publications':len(authorRaw['publications']),'citedby':authorRaw['citedby'],'hindex':authorRaw['hindex'],'i10index':authorRaw['i10index']
,'gscholar_url':url_part+authorRaw['scholar_id']}
return authorDetails
def composeTweet(authorName, authorHandles_dic, pubTitle, pub):
pub = scholarly.fill(pub)
pubURL = pub['pub_url']
if 'pub_year' in pub['bib'].keys():
if pub['bib']['pub_year'] == str(currentYear):
if authorName in authorHandles_dic.keys():
tweet = '[' + authorName + ']' + ' just published a new paper: "' + pubTitle + '"\n' + pubURL + '\n' + authorHandles_dic[authorName]
return pubURL, tweet
else:
tweet = '[' + authorName + ']' + ' just published a new paper: "' + pubTitle + '"\n' + pubURL
return pubURL, tweet
return None, None
def get_publications_sch(author_name):
# This block is useful for debugging and development
# reset=False
# if reset:
# search_query = scholarly.search_author('Nathan Pemberton')
# author = scholarly.fill(next(search_query))
# with open('author.pickle', 'wb') as f:
# pickle.dump(author, f)
#
# pubs = [ scholarly.fill(p) for p in author['publications'] ]
# with open('pubs.pickle', 'wb') as f:
# pickle.dump(pubs, f)
# else:
# with open('author.pickle', 'rb') as f:
# author = pickle.load(f)
# with open('pubs.pickle', 'rb') as f:
# pubs = pickle.load(f)
search_query = scholarly.search_author('Nathan Pemberton')
author = scholarly.fill(next(search_query))
pubs = [scholarly.fill(p) for p in author['publications']]
for pub in pubs:
bib = pub['bib']
bib['ENTRYTYPE'] = 'article'
bib['ID'] = pub['author_pub_id']
bib['url'] = pub['eprint_url']
if 'pub_year' in bib:
bib['year'] = bib['pub_year']
special_cases(pub)
normalize_journal(pub)
pubs.sort(key=sort_by_year, reverse=True)
with open(BIBPATH, 'w') as f:
f.write('@preamble{"{"name" : "' + author_name + '"}"}\n')
for p in pubs:
f.write(scholarly.bibtex(p))
f.write('\n')
def download_citations():
# Retrieve the author's data, fill-in, and print
# search_query = scholarly.search_author(NAME)
search_query = scholarly.search_author_id(AUTHOR_ID)
# author = scholarly.fill(next(search_query))
author = scholarly.fill(search_query)
print(author)
# Print the titles of the author's publications
print([pub['bib']['title'] for pub in author['publications']])
# Take a closer look at the first publication
# pub = scholarly.fill(author['publications'][1])
# print(pub)
independent_citations = []
for pub in author['publications'][:]:
res_dict = {}
time.sleep(random.randint(WAIT, WAIT * 2))
pub = scholarly.fill(pub)
res_dict["title"] = pub['bib']["title"]
res_dict["year"] = pub['bib']["pub_year"]
print(pub['bib']["title"])
res_dict["author"] = [name.strip() for name in pub['bib']["author"].split("and")]
time.sleep(random.randint(WAIT, WAIT * 2))
cited_this = scholarly.citedby(pub)
if cited_this:
res_dict['cited_this'] = [{"author": citation['bib']["author"], "title": citation['bib']["title"]} for
citation
in
cited_this]
indep_citations = print_citations(res_dict)
res_dict['independent_citations'] = indep_citations
independent_citations.append(
{"title": res_dict["title"], "author": res_dict["author"], 'independent_citations': indep_citations})
save_json(res_dict['title'], res_dict)
else:
break
save_json("independent_citations.json", independent_citations)
def author_to_affiliations(NAME):
try:
with open('affilations.p', 'rb') as f:
affiliations = pickle.load(f)
for k, v in affiliations.items():
if type(v) is type(list()):
affiliations[k] = v[0]['name']
except:
pass
response = requests.get("https://dissem.in/api/search/?authors=" +
str(NAME))
author_papers = response.json()
visit_urls = []
coauthors = []
titles = []
affiliations = {}
orcids = {}
for p in author_papers["papers"]:
coauthors_ = p["authors"]
records = p["records"][0]
if "doi" in records.keys():
visit_urls.append(records["doi"])
doi_to_author_affil_list = crossref_commons.retrieval.get_publication_as_json(
records["doi"])
for al in doi_to_author_affil_list["author"]:
key = al['given'] + str(" ") + al['family']
#if key not in affiliations.keys():
if len(al['affiliation']):
affiliations[key] = al['affiliation'][0]['name']
if "ORCID" in al.keys():
orcids[key] = al["ORCID"]
#if not len(al['affiliation']):
search_query = list(scholarly.search_author(key))
#sq = search_query[0]
if len(search_query):
sq = search_query[0]
res_author_search = scholarly.fill(sq)
afil = res_author_search['affiliation']
#if "university" in afil or "state" in afil or "universidad" in afil or "college" in afil or "school" in afil:
if len(al['affiliation']):
#if al['affiliation'] in res_author_search['affiliation']:
print(al['affiliation'],
res_author_search['affiliation'])
affiliations[key] = res_author_search['affiliation']
#print(affiliations[key],key)
#print(affiliations)
with open('affilations.p', 'wb') as f:
pickle.dump(affiliations, f)
return affiliations
def busca_publicaciones(lista):
listapub = []
for row in lista:
print(row)
search_query = scholarly.search_author(row)
author = scholarly.fill(next(search_query))
for index in range(len(author['publications'])):
pub = scholarly.fill(author['publications'][index])
print(pub['bib'])
try:
listapub.append({
'investigador': row,
'year': pub['bib']['pub_year'],
'title': pub['bib']['title'],
'author': pub['bib']['author'],
'journal': pub['bib']['journal']
})
except:
pass
print(listapub)
return listapub
def test_search_pubs_citedby(self):
"""
Testing that when we retrieve the list of publications that cite
a publication, the number of citing publication is the same as
the number of papers that are returned. We use a publication
with a small number of citations, so that the test runs quickly.
The 'Machine-learned epidemiology' paper had 11 citations as of
June 1, 2020.
"""
query = 'Machine-learned epidemiology: real-time detection of foodborne illness at scale'
pubs = [p for p in scholarly.search_pubs(query)]
self.assertGreaterEqual(len(pubs), 1)
filled = scholarly.fill(pubs[0])
cites = [c for c in scholarly.citedby(filled)]
self.assertEqual(len(cites), filled['num_citations'])
def get_author_statistics(name):
OUT = np.zeros((1, ), dtype=my_dtype)
search_query = scholarly.search_author(name) #
author = scholarly.fill(next(search_query))
for s in statistics[:6]:
OUT[s] = author[s]
for year in YEARS:
yearstr = "cit%s" % (year)
try:
OUT[yearstr] = author['cites_per_year'][year]
except:
pass
return OUT
from scholarly import scholarly
author = scholarly.search_author_id('V4ycRTQAAAAJ')
pubs = scholarly.fill(author)
pub = pubs['publications'][0]['bib']['title']
query = next(scholarly.search_pubs(pub)) # depois de algumas chamadas, o Google bloqueia...
bib = scholarly.bibtex(query)
print(bib)
#query = scholarly.search_pubs("A density-based algorithm for discovering clusters in large spatial databases with noise")
#pub = next(query)
#print(pub)
#print(scholarly.bibtex(pub))
# Add new author and populate previous pubs into pubfile
from scholarly import scholarly
newAuthors = ['Jerome Buhl', 'Steven Strogatz'] # Replace Me
with open('authors.csv', 'a') as authorFile:
for newAuthor in newAuthors:
authorFile.write(newAuthor + '\n')
search_query = scholarly.search_author(newAuthor)
author = scholarly.fill(next(search_query))
pubIDs = []
for pub in author['publications']:
authPubID = pub['author_pub_id']
iColon = authPubID.find(':')
pubID = authPubID[iColon + 1:]
pubIDs.append(pubID)
with open('pubs.csv', 'a') as pubFile:
for pubID in pubIDs:
pubFile.write(pubID + '\n')
from scholarly import scholarly as schl
import pandas as pd
import requests
labull = schl.search_author_id('Lszt1B4AAAAJ')
schl.pprint(labull)
# pubs associated w labull
auth = schl.fill(labull, sections=['publications', 'indices'], sortby='year')
# fill pub info
pub_info = [
schl.fill(pub, sections=['bib', 'pub_url']) for pub in auth['publications']
]
# co-authors
pub_auth = [pub['bib']['author'] for pub in pub_info]
pub_surnames = []
for auth_list in pub_auth:
sn = [auth.split()[-1] for auth in auth_list.split(' and ')]
sn[sn.index('Bull')] = '**Bull**'
pub_surnames.append(sn)
# journal
# pub_jnl = [pub['bib'].get('journal') for pub in pub_info]
# pub info string
publ_entry = [
', '.join(pub_surnames[pp]) + ' ' + # author surnames
'[' + pub['bib']['title'] + ']' + '(' + pub.get('pub_url') + ')' +
' ' + # title w links
'(' + str(pub['bib']['pub_year']) + ')' # yr