def overcite_an(path):
titles = []
with open(path, "r", encoding='latin1') as file:
reader = csv.reader(file)
for idx,line in enumerate(reader):
if idx>0:
t=[line[1].strip(),line[2]]
if t[0] != 'Paper Title' and t[0] != 'Total' and t[1].isdigit():
titles.append([t[0], int(t[1])])
titles = [t for t in titles if t[1] >=25]
print(len(titles))
titles = dedupe(titles)
print(len(titles))
s = 0
for t in titles:
s += t[1]
print(s)
session = SessionInitializer.getSesh()
headers = SessionInitializer.getHeaders()
final_dict = {'authors': {}, 'journals': {}, 'publishers': {}}
for t in titles:
paper_name = t[0]
paper_cites = t[1]
query = "+".join(paper_name.split())
url = SessionInitializer.ROOT_URL + '/scholar?q=' + query + '&btnG=&hl=en&as_sdt=0%2C5'
print(url)
response = session.get(url, headers=headers)
soup = BeautifulSoup(response.content, 'lxml')
info_list = ""
try:
info_list = soup.find('div', attrs={'class' : 'gs_a'}).text
except:
print('cant find for ' + paper_name)
continue
info_list = [i.strip() for i in info_list.split(' - ')]
authors = info_list[0].split(',')
journal = info_list[1].split(',')[0]
publisher = info_list[2]
for a in authors:
add_freq_dict(final_dict['authors'], a)
add_freq_dict(final_dict['journals'], journal)
add_freq_dict(final_dict['publishers'], publisher)
print(publisher)
print(final_dict)
def __init__ (self, link, loadPdf=True):
self.__url = link
self.__pdfObj = None
self.__pap_info = {}
self.__pap_info['Publisher'] = ''
self.__citedByUrl = None
self.__citedByNum = 0
self.__allAuthors = None
#Internet Session Setup
self.session = SessionInitializer.getSesh()
self.headers = SessionInitializer.getHeaders()
self.loadFromGoogleScholar(loadPdf=loadPdf)
def __init__(self, mainUrl, numPapers, loadPaperPDFs=True, pubFilter=False):
self.first_name = None
self.last_name = None
self.url = None
self.__paper_list = []
#Internet Session Setup
self.session = SessionInitializer.getSesh()
self.headers = SessionInitializer.getHeaders()
if (mainUrl is not None):
self.url = mainUrl
self.loadPapers(numPapers, loadPaperPDFs=loadPaperPDFs, pubFilter=pubFilter)
def __init__(self, link, loadPdf=True):
self.__url = link
self.__pdfObj = None
self.__pap_info = {}
self.__pap_info['Publisher'] = ''
self.__citedByUrl = None
self.__citedByNum = 0
self.__allAuthors = None
#Internet Session Setup
self.session = SessionInitializer.getSesh()
self.headers = SessionInitializer.getHeaders()
self.loadFromGoogleScholar(loadPdf=loadPdf)
def downloadSpringerOpen(path):
try:
pdfTag = ch.find_element_by_xpath("//p[@class='SideBox_action']/a[text()='Download PDF']")
pdfLink = pdfTag.get_attribute('href')
p1idx = pdfLink.find(';jwcn')
pdfLink = pdfLink[p1idx+1:] + pdfLink[:p1idx + 1]
extidx = pdfLink.find('?site=')
if (extidx!=-1):
pdfLink = pdfLink[:extidx]
except selenium.common.exceptions.NoSuchElementException:
print('Springer open link has no PDF, return trying v2...')
try:
pdfTag = ch.find_element_by_xpath("//p[@class='u-marginBtmM']/a[text()='Download PDF']")
pdfLink = pdfTag.get_attribute('href')
except selenium.common.exceptions.NoSuchElementException:
print('Springer open link has no PDF, trying V2...')
return None
print(pdfLink)
session = SessionInitializer.getSesh()
r = session.get(pdfLink, stream=True)
if r.status_code == 200:
with open(path, 'wb') as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw, f)
return 1
print('ERROR: watlib pdf springeropen was not downloaded correctly')
return None
def downloadIEEE(self, href, path):
href.click()
session = SessionInitializer.getSesh()
resp = session.get(self.ch.current_url)
src = BeautifulSoup(resp.content, 'lxml').text
idx = src.find('"pdfUrl"')
src = src[idx:]
idx = src.find(':')
idx2 = src.find(',')
src = src[idx+1:idx2].strip().strip('"')
url = 'http://ieeexplore.ieee.org.proxy.lib.uwaterloo.ca' + src
print(url)
resp2 = session.get(url)
wrapperPage = BeautifulSoup(resp2.content, 'lxml')
frames = wrapperPage.findAll('frame')
srcFrame = None
for frame in frames:
if frame['src'] and 'http' in frame['src']:
srcFrame = frame['src']
if srcFrame:
return self.downloadPdfLink(srcFrame, path, 'IEEE')
else:
return None
def count_journal_frequency(author, num_papers):
author.loadPapers(num_papers, loadPaperPDFs=False)
print("Author fully loaded. Processing loaded papers...")
pap_arr = []
count = 0
try:
for idx, paper in enumerate(author.getPapers()[45:]):
time.sleep(10)
info_list = []
one_pap_arr = []
cited_by_url = paper.getCitedByUrl()
session = SessionInitializer.getSesh()
url_part_one = SessionInitializer.ROOT_URL + '/scholar?start='
url_part_two = '&hl=en&as_sdt=0,5&sciodt=0,5&cites='
cited_by_url = cited_by_url[:cited_by_url.rfind('&')]
paper_code = cited_by_url[cited_by_url.rfind('=') + 1:]
for i in range(0, 30, 10):
time.sleep(10)
final_url = url_part_one + str(i) + url_part_two + paper_code
print(final_url)
response = session.get(final_url)
soup = BeautifulSoup(response.content, "lxml")
info_list += soup.findAll('div', attrs={'class': 'gs_a'})
journal_dict = {}
for info_str in info_list:
info_str = info_str.text
info_str = info_str.split(' - ')[1].split(',')[0].replace(
'…', '').strip()
if info_str.isdigit():
continue
#print('final info string: ' + info_str)
info_str = info_str.lower().title()
if (info_str in journal_dict):
journal_dict[info_str] += 1
else:
journal_dict[info_str] = 1
one_pap_arr.append(paper.getInfo()['Title'])
one_pap_arr.append(journal_dict)
print(one_pap_arr)
pap_arr.append(one_pap_arr)
print('Paper ' + str(idx) + ' complete.')
count += 1
except KeyboardInterrupt:
print('User ended program, returning journal array')
print(pap_arr)
return pap_arr
def count_journal_frequency (author, num_papers):
author.loadPapers(num_papers, loadPaperPDFs=False)
print("Author fully loaded. Processing loaded papers...")
pap_arr = []
count = 0
try:
for idx, paper in enumerate(author.getPapers()[45:]):
time.sleep(10)
info_list = []
one_pap_arr = []
cited_by_url = paper.getCitedByUrl()
session = SessionInitializer.getSesh()
url_part_one = SessionInitializer.ROOT_URL + '/scholar?start='
url_part_two = '&hl=en&as_sdt=0,5&sciodt=0,5&cites='
cited_by_url = cited_by_url[:cited_by_url.rfind('&')]
paper_code = cited_by_url[cited_by_url.rfind('=')+1:]
for i in range(0, 30, 10):
time.sleep(10)
final_url = url_part_one+str(i)+url_part_two+paper_code
print(final_url)
response = session.get(final_url)
soup = BeautifulSoup(response.content, "lxml")
info_list += soup.findAll('div', attrs={'class':'gs_a'})
journal_dict = {}
for info_str in info_list:
info_str = info_str.text
info_str = info_str.split(' - ')[1].split(',')[0].replace('…', '').strip()
if info_str.isdigit():
continue
#print('final info string: ' + info_str)
info_str = info_str.lower().title()
if (info_str in journal_dict):
journal_dict[info_str]+=1
else:
journal_dict[info_str] = 1
one_pap_arr.append(paper.getInfo()['Title'])
one_pap_arr.append(journal_dict)
print(one_pap_arr)
pap_arr.append(one_pap_arr)
print('Paper ' + str(idx) + ' complete.')
count+=1
except KeyboardInterrupt:
print('User ended program, returning journal array')
print(pap_arr)
return pap_arr
def __init__(self,
mainUrl,
numPapers,
loadPaperPDFs=True,
pubFilter=False):
self.first_name = None
self.last_name = None
self.url = None
self.__paper_list = []
#Internet Session Setup
self.session = SessionInitializer.getSesh()
self.headers = SessionInitializer.getHeaders()
if (mainUrl is not None):
self.url = mainUrl
self.loadPapers(numPapers,
loadPaperPDFs=loadPaperPDFs,
pubFilter=pubFilter)
def downloadPdfLink(self, link, path, source):
print(link)
session = SessionInitializer.getSesh()
r = session.get(link, stream=True)
if r.status_code == 200:
with open(path, 'wb') as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw, f)
return 1
print('Error: ' + source + ' pdf was not downloaded correctly.')
return None
def downloadMdpi(path):
try:
pdfTag = ch.find_element_by_xpath("//li/a[text()='Full-Text PDF']")
pdfLink = pdfTag.get_attribute('href')
except selenium.common.exceptions.NoSuchElementException:
print('MDPI link has no PDF, returning None...')
return None
print(pdfLink)
session = SessionInitializer.getSesh()
r = session.get(pdfLink, stream=True)
if r.status_code == 200:
with open(path, 'wb') as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw, f)
return 1
print('ERROR: watlib pdf MDPI was not downloaded correctly')
return None
def downloadMdpi(path):
try:
pdfTag = ch.find_element_by_xpath("//li/a[text()='Full-Text PDF']")
pdfLink = pdfTag.get_attribute('href')
except selenium.common.exceptions.NoSuchElementException:
print('MDPI link has no PDF, returning None...')
return None
print(pdfLink)
session = SessionInitializer.getSesh()
r = session.get(pdfLink, stream=True)
if r.status_code == 200:
with open(path, 'wb') as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw, f)
return 1
print('ERROR: watlib pdf MDPI was not downloaded correctly')
return None
def downloadScholarPortal(href, path):
href.click()
try:
pdfxmlTag = ch.find_element_by_xpath("//div[@class='download-btn']/a[text()='PDF Download']")
pdfxmllink = pdfxmlTag.get_attribute('href')
except selenium.common.exceptions.NoSuchElementException:
print('Racer or invalid link only, no scholarsportal returning none...')
return None
print(pdfxmllink)
session = SessionInitializer.getSesh()
r = session.get(pdfxmllink, stream=True)
if r.status_code == 200:
with open(path, 'wb') as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw, f)
return 1
print('ERROR: watlib pdf scholarsportal was not downloaded correctly')
return None
def downloadScholarPortal(href, path):
href.click()
try:
pdfxmlTag = ch.find_element_by_xpath(
"//div[@class='download-btn']/a[text()='PDF Download']")
pdfxmllink = pdfxmlTag.get_attribute('href')
except selenium.common.exceptions.NoSuchElementException:
print(
'Racer or invalid link only, no scholarsportal returning none...')
return None
print(pdfxmllink)
session = SessionInitializer.getSesh()
r = session.get(pdfxmllink, stream=True)
if r.status_code == 200:
with open(path, 'wb') as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw, f)
return 1
print('ERROR: watlib pdf scholarsportal was not downloaded correctly')
return None
def __init__(self):
#Internet Session Setup
self.session = SessionInitializer.getSesh()
self.headers = SessionInitializer.getHeaders()
def __init__(self):
#Internet Session Setup
self.session = SessionInitializer.getSesh()
self.headers = SessionInitializer.getHeaders()
'''
Created on Jan 05, 2016
@author: Ankai
'''
from bs4 import BeautifulSoup
import time
from ReferenceParser import IeeeReferenceParser, SpringerReferenceParser, PaperReferenceExtractor, PdfObj
import SessionInitializer
import WatLibSeleniumParser
SESSION = SessionInitializer.getSesh()
class Paper:
def __init__ (self, link, loadPaperPDFs=True):
self.url = link
self.pdfObj = None
self.pap_info = {}
#self.__pap_info['Publisher'] = ''
self.citedByUrl = None
self.citedByNum = 0
#Internet Session Setup
self.loadFromScopus(loadPaperPDFs=loadPaperPDFs)
def loadFromScopus(self, loadPaperPDFs=True):
response = SESSION.get(self.url)
soup = BeautifulSoup(response.content, 'lxml')
# PDF Object
if loadPaperPDFs:
'''
Created on Jan 05, 2016
@author: Ankai
'''
from bs4 import BeautifulSoup
import time
from ReferenceParser import IeeeReferenceParser, SpringerReferenceParser, PaperReferenceExtractor, PdfObj
import SessionInitializer
import WatLibSeleniumParser
SESSION = SessionInitializer.getSesh()
WATPARSER = WatLibSeleniumParser.WatLibParser()
class Paper:
def __init__(self, link, loadPaperPDFs=True):
self.url = link
self.pdfObj = None
self.pap_info = {}
#self.__pap_info['Publisher'] = ''
self.citedByUrl = None
self.citedByNum = 0
#Internet Session Setup
self.loadFromScopus(loadPaperPDFs=loadPaperPDFs)
def loadFromScopus(self, loadPaperPDFs=True):
response = SESSION.get(self.url)
soup = BeautifulSoup(response.content, 'lxml')
