def getYears(self,file,label):
paperYear=dict()
counter=0
with open(file) as f:
reader = csv.reader(f)
for row in reader:
print counter
counter+=1
papername=row[1]
try:
content=dblp.search(papername)
if content==None:
time.sleep(20)
content=dblp.search(papername)
if content.empty: continue
except:
time.sleep(180)
content=dblp.search(papername)
if content==None:
time.sleep(20)
content=dblp.search(papername)
if content.empty: continue
paperYear[row[0]]=content
if counter%200==0:
pickle.dump(paperYear, open('notmatchedpaperyear_'+label+'.dat', "wb"), True)
def search_dblp(title):
"""Given a paper title, attempt to search for it on DBLP.
If @title does not match anything, we iteratively loosen our search
constraints by dropping the last word of the title until results are found.
"""
title = title.replace("{", "").replace("}", "")
results = dblp.search([title])
if results.empty:
return search_dblp(" ".join(title.split(" ")[:-1]))
return results
print(". \tNumber of Publications: ", end="")
print(len(clusterList[i]))
sortedList = sorted(clusterList[i], key = getKey)
for j in range(0, len(clusterList[i])):
#clusterList[i][j].print_val()
sortedList[j].print_val()
print("--------------------------------------------------------------------------------------------------")
pubList = []
search_input = input("Please enter the name of the researcher (case - insensitive): ")
authors = dblp.search(search_input)
if len(authors) == 0:
print("No matching results found")
exit()
print("Please select one of the below researchers: (Wait till input is not asked for)")
for i in range(0, len(authors)):
author = authors[i]
print(str(i+1) + ". " + author.name)
print("number of publications = " + str(len(author.publications)))
print("-----------------------------------------")
opt_intput = input("Type 1 for affiliation timeline. Type 2 for clusterization.\n")
if opt_intput == "1":
auth_index = input('Please select one of the Author Index: ')
i = int(auth_index) - 1
import dblp, requests
search_string = input('Enter author name for search: ')
search_results = dblp.search(search_string)
if (search_results.empty):
print("No results...\nExitting...")
exit(1)
print(f'Index\tType\tAuthor Names\tYear')
for index, val in search_results.iterrows():
print(f'{index}\t{val.Type}\t{val.Authors}\t{val.Title}\t{val.Year}')
print('\n\t\t---------------------------------\n')
option = int(input('Enter index of the record to get data: '))
record = search_results.loc[option]
request = requests.get(record.Link)
print(request.status_code)
print(request.text)
def _main():
g = nx.Graph()
authors = dblp.search('Cosmin Bonchis')
cosmin = authors[0]
authors1 = dblp.search('Stefan Balint')
stefanb = authors1[0]
authors2 = dblp.search('Adrian Craciun')
adrian = authors2[0]
authors3 = dblp.search('Roxana Dogaru')
roxana = authors3[0]
authors4 = dblp.search('Teodor-Florin Fortis')
teodor = authors4[0]
authors5 = dblp.search('Marc Frincu')
marc = authors5[0]
authors6 = dblp.search('Victoria Iordan')
victoria = authors6[0]
authors7 = dblp.search('Gabriel Istrate')
gabriel = authors7[0]
authors8 = dblp.search('Ciprian Jichici')
ciprianj = authors8[0]
authors9 = dblp.search('Gabriel Iuhasz')
iuhasz = authors9[0]
authors10 = dblp.search('Eva Kaslik')
eva = authors10[0]
authors11 = dblp.search('Mircea Marin')
mircea = authors11[0]
authors12 = dblp.search('Flavia Micota')
flavia = authors12[0]
authors13 = dblp.search('Cristina Mindruta')
cristina = authors13[0]
authors14 = dblp.search('Stefan Maruster')
stefanm = authors14[0]
authors15 = dblp.search('Marian Neagul')
marian = authors15[0]
authors16 = dblp.search('Viorel Negru')
viorel = authors16[0]
authors17 = dblp.search('Dana Petcu')
dana = authors17[0]
authors18 = dblp.search('Daniel Pop')
get_right_name(authors18, 'Daniel Pop')
pop = authors18[0]
authors19 = dblp.search('Horia Popa')
horia = authors19[0]
authors20 = dblp.search('Ciprian Pungila')
ciprianp = authors20[0]
authors21 = dblp.search('Monica Tirea')
monica = authors21[0]
authors22 = dblp.search('Daniela Zaharie')
daniela = authors22[0]
authors23 = dblp.search('Calin Sandru')
calin = authors23[0]
g.add_edge(stefanb.name, eva.name, weight=6)
g.add_edge(stefanb.name, teodor.name, weight=4)
g.add_edge(cosmin.name, gabriel.name, weight=6)
g.add_edge(cosmin.name, dana.name, weight=1)
g.add_edge(adrian.name, gabriel.name, weight=4)
g.add_edge(adrian.name, mircea.name, weight=2)
g.add_edge(roxana.name, flavia.name, weight=1)
g.add_edge(roxana.name, daniela.name, weight=1)
g.add_edge(teodor.name, viorel.name, weight=14)
g.add_edge(teodor.name, pop.name, weight=2)
g.add_edge(teodor.name, cristina.name, weight=3)
g.add_edge(marc.name, dana.name, weight=16)
g.add_edge(marc.name, marian.name, weight=4)
g.add_edge(marc.name, daniela.name, weight=3)
g.add_edge(victoria.name, dana.name, weight=2)
g.add_edge(gabriel.name, mircea.name, weight=3)
g.add_edge(ciprianj.name, pop.name, weight=1)
g.add_edge(ciprianj.name, viorel.name, weight=1)
g.add_edge(iuhasz.name, dana.name, weight=1)
g.add_edge(iuhasz.name, viorel.name, weight=6)
g.add_edge(iuhasz.name, daniela.name, weight=1)
g.add_edge(iuhasz.name, monica.name, weight=1)
g.add_edge(eva.name, dana.name, weight=1)
g.add_edge(flavia.name, daniela.name, weight=1)
g.add_edge(cristina.name, viorel.name, weight=2)
g.add_edge(cristina.name, calin.name, weight=2)
g.add_edge(cristina.name, dana.name, weight=1)
g.add_edge(stefanm.name, viorel.name, weight=1)
g.add_edge(marian.name, dana.name, weight=11)
g.add_edge(marian.name, calin.name, weight=2)
g.add_edge(marian.name, daniela.name, weight=2)
g.add_edge(marian.name, pop.name, weight=1)
g.add_edge(viorel.name, ciprianp.name, weight=5)
g.add_edge(viorel.name, daniela.name, weight=17)
g.add_edge(viorel.name, calin.name, weight=6)
g.add_edge(viorel.name, pop.name, weight=9)
g.add_edge(viorel.name, monica.name, weight=9)
g.add_edge(viorel.name, dana.name, weight=10)
g.add_edge(viorel.name, horia.name, weight=8)
g.add_edge(dana.name, calin.name, weight=4)
g.add_edge(dana.name, daniela.name, weight=15)
g.add_edge(dana.name, pop.name, weight=1)
g.add_edge(dana.name, horia.name, weight=1)
g.add_edge(pop.name, daniela.name, weight=1)
g.add_edge(pop.name, calin.name, weight=2)
g.add_edge(pop.name, horia.name, weight=2)
g.add_edge(horia.name, daniela.name, weight=1)
pos = nx.circular_layout(g)
edge_labels = {(u, v): d['weight'] for u, v, d in g.edges(data=True)}
nx.draw_networkx_nodes(g,
pos,
node_size=1600,
node_color='white',
node_alpha=0.2,
node_text_size=6,
edge_color='blue',
edge_alpha=0.2,
edge_tickness=1,
edge_text_pos=0.2,
text_font='sans-serif')
nx.draw_networkx_edges(g, pos)
nx.draw_networkx_labels(g, pos)
nx.draw_networkx_edge_labels(g, pos, edge_labels=edge_labels)
plt.title("Professors Graph")
plt.axis('off')
plt.savefig('output.png')
plt.show()
# http://www.informatik.uni-trier.de/~ley/db/
import dblp
authors = dblp.search('Gregor von Laszewski')
for author in authors:
print author.name
authors = dblp.search('Laszewski')
for author in authors:
print author.name
no_matched_author = []
no_pub_list = []
notes_count = 0
for eachLine in fp.readlines():
emailId, firstName, lastName = eachLine.split(',')
name = firstName + " " + lastName.strip()
file_name = firstName + "_" + lastName.strip()
if name == '' or name == ' ':
print emailId
no_name += 1
no_name_list.append(emailId)
else:
try:
authors = dblp.search(name)
except Exception as e:
sleep(2)
authors = dblp.search(name)
if authors:
if len(authors) > 1:
print "More than one authors found! "
more_than_one += 1
author_disambiguation[name] = []
author = None
for ath in authors:
author_disambiguation[name].append(ath.name)
if name.lower() == ath.name.lower():
author = ath
if not author:
no_matched_author.append(name)
# -*- coding: utf-8 -*-
"""
Created on Fri Jun 7 23:57:13 2019
@author: Markus Borg
"""
import dblp
authors = dblp.search('markus borg')
markus = authors[0]
print("Publications: ", len(markus.publications))
for p in markus.publications:
print(p.citations)
# for inside use only:
while True:
try:
for node_in_file in nodes_by_lines:
name_to_find = node_in_file.split(',')[1].replace('_', ' ')
id_of_searched = int(node_in_file.split(',')[0])
print(name_to_find)
print(id_of_searched)
print(list_of_nodes_to_add)
print(list_of_edges_to_add)
# skip on passed ids
if id_of_searched < position:
continue
options = dblp.search(name_to_find)
chosen_publisher_index = choose_name(name_to_find, options)
print(chosen_publisher_index)
if chosen_publisher_index != -1:
publisher = dblp.search(
name_to_find)[chosen_publisher_index]
# run on every publications and adding it to "nodes_by_lines"
for article in publisher.publications:
authors_of_article = article.authors
print(authors_of_article)
for author in authors_of_article:
author = unidecode(author.lower())
if author != unidecode(publisher.name.lower()):
author_splitted = author.split(' ')
# normalizing names
normalized_author = ""
# coding: utf-8
# In[38]:
import dblp
authors = dblp.search('alessandro bozzon')
paper23=authors.iloc[23]
# In[2]:
url=paper23.Link
# In[3]:
import urllib
import os
webFile = urllib.urlopen(url)
pdfFile = open(url.split('/')[-1], 'w')
print pdfFile
pdfFile.write(webFile.read())
webFile.close()
pdfFile.close()
def _main():
g = nx.Graph()
authors = dblp.search('Cosmin Bonchis')
cosmin=authors[0]
authors1 = dblp.search('Stefan Balint')
stefanb=authors1[0]
authors2 = dblp.search('Adrian Craciun')
adrian=authors2[0]
authors3 = dblp.search('Roxana Dogaru')
roxana=authors3[0]
authors4 = dblp.search('Teodor-Florin Fortis')
teodor=authors4[0]
authors5 = dblp.search('Marc Frincu')
marc=authors5[0]
authors6 = dblp.search('Victoria Iordan')
victoria=authors6[0]
authors7 = dblp.search('Gabriel Istrate')
gabriel=authors7[0]
authors8 = dblp.search('Ciprian Jichici')
ciprianj=authors8[0]
authors9 = dblp.search('Gabriel Iuhasz')
iuhasz=authors9[0]
authors10 = dblp.search('Eva Kaslik')
eva=authors10[0]
authors11 = dblp.search('Mircea Marin')
mircea=authors11[0]
authors12 = dblp.search('Flavia Micota')
flavia=authors12[0]
authors13 = dblp.search('Cristina Mindruta')
cristina=authors13[0]
authors14 = dblp.search('Stefan Maruster')
stefanm=authors14[0]
authors15 = dblp.search('Marian Neagul')
marian=authors15[0]
authors16 = dblp.search('Viorel Negru')
viorel=authors16[0]
authors17 = dblp.search('Dana Petcu')
dana=authors17[0]
authors18 = dblp.search('Daniel Pop')
get_right_name(authors18,'Daniel Pop')
pop=authors18[0]
authors19 = dblp.search('Horia Popa')
horia=authors19[0]
authors20 = dblp.search('Ciprian Pungila')
ciprianp=authors20[0]
authors21 = dblp.search('Monica Tirea')
monica=authors21[0]
authors22 = dblp.search('Daniela Zaharie')
daniela=authors22[0]
authors23 = dblp.search('Calin Sandru')
calin=authors23[0]
g.add_edge(stefanb.name, eva.name, weight=6 )
g.add_edge(stefanb.name, teodor.name, weight=4 )
g.add_edge(cosmin.name, gabriel.name, weight=6)
g.add_edge(cosmin.name, dana.name, weight=1)
g.add_edge(adrian.name, gabriel.name, weight=4)
g.add_edge(adrian.name, mircea.name, weight=2)
g.add_edge(roxana.name, flavia.name, weight=1)
g.add_edge(roxana.name, daniela.name, weight=1)
g.add_edge(teodor.name, viorel.name, weight=14)
g.add_edge(teodor.name, pop.name, weight=2)
g.add_edge(teodor.name, cristina.name, weight=3)
g.add_edge(marc.name, dana.name, weight=16)
g.add_edge(marc.name, marian.name, weight=4)
g.add_edge(marc.name, daniela.name, weight=3)
g.add_edge(victoria.name, dana.name, weight=2)
g.add_edge(gabriel.name, mircea.name, weight=3)
g.add_edge(ciprianj.name, pop.name, weight=1)
g.add_edge(ciprianj.name, viorel.name, weight=1)
g.add_edge(iuhasz.name, dana.name, weight=1)
g.add_edge(iuhasz.name,viorel.name, weight=6)
g.add_edge(iuhasz.name,daniela.name, weight=1)
g.add_edge(iuhasz.name, monica.name, weight=1)
g.add_edge(eva.name, dana.name, weight=1)
g.add_edge(flavia.name, daniela.name, weight=1)
g.add_edge(cristina.name, viorel.name, weight=2)
g.add_edge(cristina.name, calin.name, weight=2)
g.add_edge(cristina.name, dana.name, weight=1)
g.add_edge(stefanm.name, viorel.name, weight=1)
g.add_edge(marian.name, dana.name, weight=11)
g.add_edge(marian.name, calin.name, weight=2)
g.add_edge(marian.name, daniela.name, weight=2)
g.add_edge(marian.name, pop.name, weight=1)
g.add_edge(viorel.name, ciprianp.name, weight=5)
g.add_edge(viorel.name, daniela.name, weight=17)
g.add_edge(viorel.name, calin.name, weight=6)
g.add_edge(viorel.name, pop.name, weight=9)
g.add_edge(viorel.name, monica.name, weight=9)
g.add_edge(viorel.name, dana.name, weight=10)
g.add_edge(viorel.name, horia.name, weight=8)
g.add_edge(dana.name, calin.name, weight=4)
g.add_edge(dana.name, daniela.name, weight=15)
g.add_edge(dana.name, pop.name, weight=1)
g.add_edge(dana.name, horia.name, weight=1)
g.add_edge(pop.name, daniela.name, weight=1)
g.add_edge(pop.name, calin.name, weight=2)
g.add_edge(pop.name, horia.name, weight=2)
g.add_edge(horia.name, daniela.name, weight=1)
pos = nx.circular_layout(g)
edge_labels = { (u,v): d['weight'] for u,v,d in g.edges(data=True) }
nx.draw_networkx_nodes(g,pos,node_size=1600,node_color= 'white',
node_alpha=0.2,
node_text_size=6,
edge_color='blue', edge_alpha=0.2, edge_tickness=1,
edge_text_pos=0.2,
text_font='sans-serif')
nx.draw_networkx_edges(g,pos)
nx.draw_networkx_labels(g,pos)
nx.draw_networkx_edge_labels(g,pos,edge_labels=edge_labels)
plt.title("Professors Graph")
plt.axis('off')
plt.savefig('output.png')
plt.show()
import dblp
autores = dblp.search('D. Aguirre-Guerrero')
#Tamanio
print autores.size
#Tipo de objeto
print autores.__class__
#Contenido de los objetos
print autores
#Nombre de las columnas y tipo de objeto
print autores.dtypes
print autores['Authors']
print autores['Link']
print autores['Title']
print autores['Type']
print autores['Where']
print autores['Year']
coautores = autores['Authors']
nombres = set()
for coautor in coautores:
nombres.update(coautor)
print nombres
import dblp
fout = open("author_graph_sample.txt", "w")
authors = dblp.search('Fugang Wang')
visitedAuth = []
authCount = 0
# for auth in authors:
# print >>fout,auth.name
for auth in authors:
print >> fout, auth.name
print >> fout, 70 * '='
for pub in auth.publications:
for a in pub.authors:
if a not in visitedAuth and a != auth.name:
visitedAuth.append(a)
authCount += 1
print >> fout, visitedAuth
fout.write('Author count:' + str(authCount))
import dblp
fout = open("author_graph_sample.txt", "w")
authors = dblp.search('Fugang Wang')
visitedAuth = []
authCount = 0
# for auth in authors:
# print >>fout,auth.name
for auth in authors:
print >> fout, auth.name
print >> fout, 70 * '='
for pub in auth.publications:
for a in pub.authors:
if a not in visitedAuth and a != auth.name:
visitedAuth.append(a)
authCount += 1
print >> fout, visitedAuth
fout.write('Author count:' + str(authCount))
import dblp
import csv
import lxml
import time
pubs = {}
auth = {}
with open('people.csv', 'rb') as csvfile:
reader = csv.reader(csvfile, delimiter=',', quotechar='|')
for row in reader:
if row[0] not in auth:
authors = dblp.search(row[0])
print row[0] + ": " + str(len(authors)) + " author(s) found; " + str(len(authors[0].publications)) + " publications"
for i in range(0, len(authors[0].publications)):
year = authors[0].publications[i].year
title = authors[0].publications[i].title
if row[1] and year < row[1]:
break
if row[2] and year > row[2]:
break
if year not in pubs:
pubs[year] = {}
if title not in pubs[year]:
pubs[year][title] = {}
pubs[year][title]['year'] = authors[0].publications[i].year
pubs[year][title]['authors'] = authors[0].publications[i].authors
no_matched_author = []
no_pub_list = []
notes_count = 0
for eachLine in fp.readlines():
emailId, firstName, lastName = eachLine.split(',')
name = firstName + " " + lastName.strip()
file_name = firstName + "_" + lastName.strip()
if name == '' or name == ' ':
print emailId
no_name += 1
no_name_list.append(emailId)
else:
try:
authors = dblp.search(name)
except Exception as e:
sleep(2)
authors = dblp.search(name)
if authors:
if len(authors) > 1:
print "More than one authors found! "
more_than_one += 1
author_disambiguation[name] = []
author = None
for ath in authors:
author_disambiguation[name].append(ath.name)
if name.lower() == ath.name.lower():
author = ath
if not author:
no_matched_author.append(name)
import dblp
authors = dblp.search('Laszewski')
for author in authors:
for p in author.publications:
print p.title