How to use scholarly - 10 common examples
To help you get started, we’ve selected a few scholarly examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
chintu619 / citation-sorted-arxiv-slack-bot / arXiv_bot.py View on Github 
def getAuthorCitations(author):
# print(author)
# check if author has initials in name
author_name_without_initials = author.split(' ')[0] + ' ' + author.split(' ')[-1]
if author != author_name_without_initials:
flag_authorHasInitialsInName = True
else: flag_authorHasInitialsInName = False
search_query = scholarly.search_author(author)
try: # check if author is listed in google scholar
author_stats = next(search_query)
try: # if multiple people exist with same name, skip author
next(search_query); author_count = 2
except: author_count = 1
except:
author_count = 0
# if author is uniquely identified in scholar, get citation count
if author_count == 1:
try: author_citation_count = author_stats.citedby
except: author_citation_count = 0
elif (author_count == 0) and flag_authorHasInitialsInName:
author_citation_count = getAuthorCitations(author_name_without_initials)
else:
author_citation_count = 0def getAuthorCitations(author):
# print(author)
# check if author has initials in name
author_name_without_initials = author.split(' ')[0] + ' ' + author.split(' ')[-1]
if author != author_name_without_initials:
flag_authorHasInitialsInName = True
else: flag_authorHasInitialsInName = False
search_query = scholarly.search_author(author)
try: # check if author is listed in google scholar
author_stats = next(search_query)
try: # if multiple people exist with same name, skip author
next(search_query); author_count = 2
except: author_count = 1
except:
author_count = 0
# if author is uniquely identified in scholar, get citation count
if author_count == 1:
try: author_citation_count = author_stats.citedby
except: author_citation_count = 0
elif (author_count == 0) and flag_authorHasInitialsInName:
author_citation_count = getAuthorCitations(author_name_without_initials)
else:
author_citation_count = 0def query_scholar_for_author_profile(author):
try:
_author = next(scholarly.search_author(author))
except:
return "Ooopsie. Maybe we ran over the request limit?"
if _author == None:
return "Did not find a profile for %s" % author
resp_str = ""
resp_str += (_author.name + "\n")
resp_str += (_author.affiliation + "\n")
for interest in _author.interests:
resp_str += (interest + ' - ')
resp_str += "\n"
resp_str += ("https://scholar.google.ch/citations?user=" + _author.id)
return resp_strdef get_author(author_name):
# Retrieve the author's data, fill-in, and print
search_query = scholarly.search_author(author_name)
author = next(search_query).fill()
return authordef scholarly_query(authors, title):
"""
Query Google Scholar database.
Args:
authors (list): a list of strings for up the first authors last names.
title (str): the title of the article.
Returns:
A record (dict) of the bibtex entry obtained from Google Scholar.
"""
query = ' '.join(authors) + ' ' + title
search_query = scholarly.search_pubs_query(query)
try:
res = next(search_query)
except StopIteration:
return None
res.fill()
if 'abstract' in res.bib:
del res.bib['abstract']
# Post-process title
res.bib['title'] = re.sub('\\.*$', '', res.bib['title'])
print('S: ' + nomenclature.gen_filename(res.bib))
return res.bibdef fetch_bibtex_by_fulltext_scholar(txt, assess_results=True):
import scholarly
scholarly._get_page = _get_page_fast # remove waiting time
logger.debug(txt)
search_query = scholarly.search_pubs_query(txt)
# get the most likely match of the first results
results = list(search_query)
if len(results) > 1 and assess_results:
maxscore = 0
result = results[0]
for res in results:
score = _scholar_score(txt, res.bib)
if score > maxscore:
maxscore = score
result = res
else:
result = results[0]
# use url_scholarbib to get bibtex from google
if getattr(result, 'url_scholarbib', ''):def get_citations_url_scholarbibs_by_publication_title(publication_title):
bibtex_refs = []
search_query = scholarly.search_pubs_query(publication_title)
try:
pub = next(search_query).fill()
# pub = pub.fill()
citations = list(pub.get_citedby())
# citation = get_citatations()
print('{} citatations for {}'.format(len(citations), pub.bib['title']))
for citation in citations:
bibtex_refs.append(citation.url_scholarbib)
return bibtex_refs
except:
print('Can\'t find "{}"!'.format(publication_title))
return []# get the most likely match of the first results
results = list(search_query)
if len(results) > 1 and assess_results:
maxscore = 0
result = results[0]
for res in results:
score = _scholar_score(txt, res.bib)
if score > maxscore:
maxscore = score
result = res
else:
result = results[0]
# use url_scholarbib to get bibtex from google
if getattr(result, 'url_scholarbib', ''):
bibtex = scholarly._get_page(result.url_scholarbib).strip()
else:
raise NotImplementedError('no bibtex import linke. Make crossref request using title?')
return bibtexdef fetch_bibtex_by_fulltext_scholar(txt, assess_results=True):
import scholarly
scholarly._get_page = _get_page_fast # remove waiting time
logger.debug(txt)
search_query = scholarly.search_pubs_query(txt)
# get the most likely match of the first results
results = list(search_query)
if len(results) > 1 and assess_results:
maxscore = 0
result = results[0]
for res in results:
score = _scholar_score(txt, res.bib)
if score > maxscore:
maxscore = score
result = res
else:
result = results[0]def _search_scholar_soup(soup):
"""Generator that returns Publication objects from the search page"""
while True:
for row in soup.find_all('div', 'gs_or'):
yield Publication(row, 'scholar')
if soup.find(class_='gs_ico gs_ico_nav_next'):
url = soup.find(class_='gs_ico gs_ico_nav_next').parent['href']
soup = _get_soup(_HOST+url)
else:
breakscholarly
Simple access to Google Scholar authors and citations
