def get_url(querier, phrase):
# Setup query
query = SearchScholarQuery()
# Query title / phrase
query.set_phrase(phrase)
# Set title search only
query.set_scope(True)
# Result count
query.set_num_page_results(1)
try:
# Send query
querier.send_query(query)
articles = querier.articles
for art in articles:
url, _, _ = art.attrs['url']
url_pdf, _, _ = art.attrs['url_pdf']
return url
except:
return None
def get_results_for(title, author):
query = SearchScholarQuery()
query.set_author(author)
query.set_phrase(title)
query.set_num_page_results(1)
query.set_scope(True)
settings = ScholarSettings()
settings.set_citation_format(ScholarSettings.CITFORM_BIBTEX)
querier = ScholarQuerier()
querier.apply_settings(settings)
querier.send_query(query)
for art in querier.articles:
print art.as_citation();
bibtex_split = art.as_citation().split("\n")
reftype = bibtex_split[0][1:-1].split("{")[0].lower();
refid = bibtex_split[0][1:-1].split("{")[1].lower();
bibtex_split.remove(bibtex_split[0])
#print reftype + " " + refid + " " + str(bibtex_split)
thismodule = sys.modules[__name__]
while(True):
try:
features_of_type = getattr(thismodule, reftype).func_code.co_varnames[ 1: getattr(thismodule, reftype).func_code.co_argcount ]
break;
except AttributeError:
var = raw_input("Type " + reftype + " not recongised, please enter a known type: ");
reftype = var;
while (True):
arranged_name = []
arranged_value = []
for i in range(1, 10):
arranged_name.append(None)
arranged_value.append(None)
for line in bibtex_split:
if ( line.find("=") > -1 ):
stored_name = line.split("=")[0].strip()
stored_value = line.split("=")[1].strip();
stored_value = stored_value[1:-(len(stored_value)-stored_value.rfind("}"))]
if stored_name in features_of_type:
arranged_name[features_of_type.index(stored_name)] = stored_name
arranged_value[features_of_type.index(stored_name)] = stored_value
short_arranged_name = arranged_name[ 0 : arranged_name.index(None)];
short_arranged_value = arranged_value[ 0 : arranged_value.index(None)];
if len(short_arranged_name) == len(features_of_type):
return getattr(thismodule, reftype)(refid, *short_arranged_value).__getprintable__(True)
else:
for feature in features_of_type:
if ( feature not in arranged_name ):
var = raw_input(feature + " is not provided by the retrieved bibtex entry. Would you like to enter it now? (Y) or (N)");
if var == "Y":
var = raw_input("Enter value for " + feature + ": ");
bibtex_split.append(feature + " = {" + var + "}");
#input: full path to xlsx file containing article titles from scopus. Assumes that
#titles are first column in the sheet 'Qatar_Scopus'.
#output: csv file containing paper titles, citations, possibly free PDF link from web.
from openpyxl import load_workbook
import sys
from scholar import ScholarQuerier, ScholarSettings, SearchScholarQuery,onecsv
from time import sleep
import csv
querier = ScholarQuerier()
settings = ScholarSettings()
querier.apply_settings(settings)
query = SearchScholarQuery()
query.set_scope(True)
alldata=[]
counter=1
xlsxfile=sys.argv[1]
wb = load_workbook(xlsxfile, use_iterators=True)
print wb.get_sheet_names()
ws = wb.get_sheet_by_name('Qatar_Scopus')
for row in ws.iter_rows(row_offset=1):
if row[0].value is not None:
temp=[]
title=row[0].value.encode("utf-8")
query.set_phrase(title)
query.set_num_page_results(1)
querier.send_query(query)
x=onecsv(querier)
if (x!=None):
#cites =[]
#citation_list = [] # [year of pub]
with open('citations_counts_25307.csv', "w") as csv_file:
writer = csv.writer(csv_file, delimiter=',')
for k,v in df['Article Title'][25307:].iteritems():
# why is df['Article Title'] of type dict??
querier = ScholarQuerier()
settings = ScholarSettings()
settings.set_citation_format(ScholarSettings.CITFORM_BIBTEX)
querier.apply_settings(settings)
query = SearchScholarQuery()
query.set_phrase(v)
query.set_scope(True)
querier.send_query(query)
if querier.articles:
cites=querier.articles[0].__getitem__('num_citations')
citation_list=querier.articles[0].__getitem__('url_citations')
else:
cites=0
citation_list= ""
# json_results = []
# file_name = 'query_data/cites_for_article_'+str(k+1)+'.json'
# for art in querier.articles:
# json_results.append(
# {key: art.attrs[key][0] for key in art.attrs.keys()})
# with open(file_name, 'wb') as f:
# json.dump(json_results, f)