def semantic_scholar_alias(NAME):
"""
inputs a URL that's full of publication orientated links, preferably the
authors scholar page.
"""
author_results = []
aliases = None
dois, coauthors, titles, visit_urls = author_to_urls(NAME)
inv_alias_dict = {}
velocity = {}
for d in dois:
paper = sch.paper(d, timeout=32)
if "authors" in paper.keys():
all_coauthors = paper["authors"]
for co_name in all_coauthors:
key = co_name["name"]
if (NAME.split(" ")[0] in key.split(" ")[0]
or key.split(" ")[0] in NAME.split(" ")[0]
or NAME.split(" ")[-1] in key.split(" ")[-1]):
author = sch.author(co_name["authorId"], timeout=32)
if "aliases" in author.keys():
aliases = author["aliases"]
return aliases
def fetch_semantic_author(ssID, fillpapers=True):
''' Queries semantic scholar for a given author
Also fills all papers if fillpapers is True (a bit slower)'''
author = sch.author(ssID, timeout=2)
if fillpapers:
filledpapers = fetch_semantic_papers(author)
author['filledpapers'] = filledpapers
return author
def get_all_papers():
"""Determine the ids of all relevant research papers."""
neumann = 143993045
valenzuela = 143990000
li = 144000000
grant = 144100000
kemper = 144122431
authorIds = [neumann, valenzuela, li, grant, kemper]
paperIds = []
for authorId in authorIds:
author = ss.author(authorId)
papers = []
if author != {}:
papers = author['papers']
for paper in papers:
paperId = paper['paperId']
paperIds.append(paperId)
return paperIds
def papercollector(id, year):
author = sch.author(id)
paper = author["papers"]
collectedpapers = []
for p in paper:
if p["year"] == year:
a = sch.paper(p["paperId"])["abstract"]
# print(a)
try:
lan = detect(a)
# print(lan)
if lan == 'en':
p["abstract"] = a
collectedpapers.append(p)
except TypeError:
collectedpapers.append(p)
print(collectedpapers)
return collectedpapers
def test_author():
data = sch.author(2262347)
assert data['name'] == 'Alan M. Turing'
def test_author(self):
data = sch.author(2262347, timeout=5)
self.assertEqual(data['name'], 'A. Turing')
def loop(_id, _papers):
papers = sch.author(_id, timeout=2)
for paper in papers['papers']:
_papers.append(paper['paperId'])
_papers = sorted(list(dict.fromkeys(_papers))) # de-duplicate and sort
variable declarations
count: ID for every paper
numbers_of_papers: for numbers of papers that the user want to view
MAX: number of documents the author has written
author: select an author in the semantic scholar database
name: author name
file: the csv file
CSVstring: string to write to the CSV file
auth_name_file: name of the file, compose of iD and author name
team: group of people who worked on the same document
"""
print("inserisci l'id dell'autore che si vuole analizzare")
print("esempio: Turing 2262347")
iD_auth = input()
author = sch.author(iD_auth)
try:
MAX = int(len(author['papers']))
pass
except KeyError:
print("Numero autore non valido: " + iD_auth)
print("Il programma verrà interrotto...")
time.sleep(2)
exit()
print("quanti documenti scientifici vuoi analizzare?")
print("documenti totali di questo autore: " + str(MAX))
numbers_of_papers = int(input())
if (numbers_of_papers < 0 or numbers_of_papers > MAX):
print("Numero non valido, verranno analizzati tutti i documenti")
numbers_of_papers = MAX