def process(document):
scholar = ScholarQuerier()
query = SearchScholarQuery()
# save cookie at first paper
global save_cookie
if save_cookie:
query.set_phrase("quantum theory")
scholar.send_query(query)
scholar.save_cookies()
save_cookie = False
query.set_phrase(document.title)
scholar.send_query(query)
scholar_articles = scholar.articles
if len(scholar_articles) == 0:
return None
title_match_ratio = \
difflib.SequenceMatcher(None, document.title, scholar_articles[0]['title']).ratio()
if title_match_ratio < min_title_match_ratio:
return None
old_tags = document.tags
citation_tag = ncitations_to_tag(scholar_articles[0]['num_citations'])
new_tags = update_tags(old_tags, [(tag_pattern, citation_tag)])
new_tags.append(str(scholar_articles[0]['num_citations']))
document.update(tags=new_tags)
return scholar_articles[0]['num_citations']
def papers_by_query_api(request):
if request.method == 'GET':
phrase = request.GET.get('phrase', '')
if not phrase:
return HttpResponseBadRequest()
query = SearchScholarQuery()
query.set_phrase(phrase)
querier = ScholarQuerier()
querier.send_query(query)
papers = querier.articles
if not papers:
result = {
'papers': [{
'title': '',
'id': 0,
'url': '',
'excerpt': ''
}]
}
else:
result = {
'papers': [{
'title': papers[0]['title'],
'id': papers[0]['cluster_id'],
'url': papers[0]['url'],
'excerpt': papers[0]['excerpt']
}]
}
return JsonResponse(result)
else:
return HttpResponseBadRequest()
def getPublications(author):
print author
querier = ScholarQuerier()
settings = ScholarSettings()
querier.apply_settings(settings)
query = SearchScholarQuery()
query.set_author(author)
querier.send_query(query)
#scholar.csv(querier)
scholar.txt(querier, with_globals=False)
def getRelatedPublications(author):
print author
settings = ScholarSettings() #adjust scholar settings
querier = ScholarQuerier(
) #Instance of ScholarQuerier() conducts a search on Google Scholar
querier.apply_settings(
settings
) #applies settings as provided by the instance of ScholarSettings()
query = SearchScholarQuery()
query.set_author(author)
querier.send_query(query)
print querier.articles
def getResult(query):
querier = ScholarQuerier()
citations = 0
url_citations = ""
clusterID = ""
try:
querier.send_query(query)
print querier.articles[0].attrs['cluster_id']
citations = querier.articles[0].attrs['num_citations'][0]
url_citations = querier.articles[0].attrs['url_citations'][0]
clusterID = querier.articles[0].attrs['cluster_id'][0]
except:
pass
return citations, url_citations, clusterID
def literature_search(query_terms, type='full_name'):
"""
perform a google scholar query with given terms
"""
querier = ScholarQuerier()
settings = ScholarSettings()
config = ScholarConf()
settings.set_citation_format(ScholarSettings.CITFORM_BIBTEX)
querier.apply_settings(settings)
query = SearchScholarQuery()
papers = []
for item in query_terms.values:
repo_id = item[0]
if type !='full_name':
repo_name = item[1]
phrase = item[2]
keywords = item[3]
start_year = item[4]
if keywords:
if ',' not in keywords:
keywords = keywords + ','
query.set_words_some(keywords)
query.set_words(repo_name)
query.set_phrase(phrase)
phrase_text = repo_name + ', ' + phrase
else:
phrase = item[1]
start_year = item[2]
query.set_phrase(phrase) # commontk/CTK, meoyo/AIPS
phrase_text = phrase
print('search papers for {} ...'.format(phrase_text))
query.set_timeframe(start_year)
querier.send_query(query)
articles = querier.articles
if len(articles)==0:
continue
results = process_arts(config, item[0], phrase_text, articles)
papers = papers + results
time_delay = random.randrange(1,10)
time.sleep(time_delay)
return papers
def search(bot, update, args):
search_command = ' '.join(args)
bot.send_message(chat_id=update.message.chat_id, text="You searched for: " + search_command)
querier = ScholarQuerier()
query = SearchScholarQuery()
query.set_words(args)
querier.send_query(query)
articles = querier.articles
message = ""
bot.send_message(chat_id=update.message.chat_id, text="Number of results: " + str(len(articles)))
index = 0
for article in articles:
bot.send_message(chat_id=update.message.chat_id, text=str(index+1)+". " + article.attrs['title'][0])
def getPublications_Title(title):
querier = ScholarQuerier()
settings = ScholarSettings()
querier.apply_settings(settings)
query = SearchScholarQuery()
publications = []
query.set_words(title)
querier.send_query(query)
related_list = scholar.json(querier)
if related_list:
print "No of related publications found : ",
print len(related_list)
for item in related_list:
#print item.keys()
#item["relatedTitle"] = title[0]
publications.append(item)
#time.sleep(random.randrange(10, 40, 2));
#time.sleep(60);
return publications
def query_scholar_for_papers(author, searchstring):
querier = ScholarQuerier()
settings = ScholarSettings()
settings.set_citation_format(settings.CITFORM_BIBTEX)
settings.set_per_page_results(5)
querier.apply_settings(settings)
query = SearchScholarQuery()
query.set_author(author)
query.set_phrase(searchstring)
querier.send_query(query)
return_str = ''
if len(querier.articles) > 0:
return_str += querier.articles[0].as_citation() + '\n'
else:
return_str = 'Ooopsie. No results. Maybe we ran over the request limit?'
return return_str
def process(document):
scholar = ScholarQuerier()
query = SearchScholarQuery()
query.set_phrase(document.title)
scholar.send_query(query)
scholar_articles = scholar.articles
if len(scholar_articles) == 0:
return None
title_match_ratio = \
difflib.SequenceMatcher(None, document.title, scholar_articles[0]['title']).ratio()
if title_match_ratio < min_title_match_ratio:
return None
old_tags = document.tags
citation_tag = ncitations_to_tag(scholar_articles[0]['num_citations'])
new_tags = update_tags(old_tags, [(tag_pattern, citation_tag)])
document.update(tags=new_tags)
return scholar_articles[0]['num_citations']
def blocked():
print "Test if blocked...."
#time.sleep(random.randrange(10, 40, 2));
time.sleep(60)
publications = []
querier = ScholarQuerier()
settings = ScholarSettings()
querier.apply_settings(settings)
query = SearchScholarQuery()
query.set_author("Ryan Baker")
querier.send_query(query)
related_list = scholar.json(querier)
if related_list:
print "Block Test : No of related publications found : ",
print len(related_list)
for item in related_list:
publications.append(item)
if len(publications) == 0:
return True
else:
return False
def getPublications(authors):
print authors
querier = ScholarQuerier()
settings = ScholarSettings()
querier.apply_settings(settings)
query = SearchScholarQuery()
publications = []
for author in authors:
if len(author) > 0:
print "Using Author : ",
print author
query.set_author(author)
querier.send_query(query)
related_list = scholar.json(querier)
if related_list:
print "No of related publications found : ",
print len(related_list)
for item in related_list:
#print item.keys()
#item["relatedAuthor"] = author
publications.append(item)
#time.sleep(random.randrange(10, 40, 2));
time.sleep(20)
return publications
def cites_api(request):
if request.method == 'GET':
paper_id = request.GET.get('paper_id', 0)
page = request.GET.get('page', None)
if not paper_id or page is None:
return HttpResponseBadRequest()
query = CitesScholarQuery(paper_id, page)
querier = ScholarQuerier()
querier.send_query(query)
papers = querier.articles
cites = []
for paper in papers:
if not paper['cluster_id']:
continue
cites.append({
'title': paper['title'],
'id': paper['cluster_id'],
'url': paper['url']
})
return JsonResponse({'paper_id': paper_id, 'cites': cites})
else:
return HttpResponseBadRequest()
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import logging
import yapbib.biblist as biblist
from scholar import ScholarQuerier
from . import db
q = ScholarQuerier()
COMMON_FIELDS = ('id', 'title', 'year', 'author', 'url', 'citation_count',
'version_count', 'citation_url', 'version_url', 'related_url')
class Article(object):
@staticmethod
def from_db(d):
if d is None:
return None
a = Article()
for name in COMMON_FIELDS:
assert hasattr(d, name), name
setattr(a, name, getattr(d, name))
return a
@property
def complete(self):
"""Whether article has complete information."""
for key in COMMON_FIELDS:
if not hasattr(self, key) or getattr(self, key) is None:
return False
from string import ascii_lowercase
import re
from pybtex.database import parse_bytes, parse_file
from scholar import ScholarQuerier, ScholarSettings, SearchScholarQuery
DST = Path(__file__).absolute().parents[1] / 'publications.bib'
IGNORE = """
vo2014cytotoxicity
takeilnatriureticpeptideisolatedfromeelbrain
matchintemporal
brodbeck2018transformation
""".split()
ACRONYMS = ['EEG', 'MEG', 'MRI']
querier = ScholarQuerier()
settings = ScholarSettings()
settings.set_citation_format(ScholarSettings.CITFORM_BIBTEX)
querier.apply_settings(settings)
query = SearchScholarQuery()
query.set_phrase("eelbrain")
query.set_timeframe(2012, None)
query.set_include_patents(False)
bib = parse_file(DST, 'bibtex')
start = 0
while True:
querier.send_query(query)
if len(querier.articles) == 0:
break
# extract articles