def getWatPDF(self, url, title=None):
print(url)
time.sleep(15)
status = WatLibSeleniumParser.downloadFromWatLib(url, 'paper.pdf')
if status is None:
return None
else:
newPdf = PdfObj('local', 'paper.pdf')
return newPdf
def getWatPDF(self, url, title=None):
print(url)
time.sleep(15)
status = WatLibSeleniumParser.downloadFromWatLib(url, 'paper.pdf')
if status is None:
return None
else:
newPdf = PdfObj('local', 'paper.pdf')
return newPdf
def count_overcites_paper(paper, author, cite_num_to_load=40):
overcites_info = []
try:
all_pdfObjs = paper.getCitingPdfs(cite_num_to_load)
analyzer = PaperReferenceExtractor()
for idx, pdf in enumerate(all_pdfObjs):
content = analyzer.getReferencesContent(pdf)
title = pdf.getTitle()
if content is None and title is not None:
print("Citing paper number " + str(idx+1) + ": " + title + " had no PDF content found.")
info_dict = {}
info_dict['Citing Paper Number'] = idx+1
info_dict['Title'] = title
info_dict['Over-cite Count'] = "No PDF Found"
overcites_info.append(info_dict)
continue
elif content is None:
continue
# print(content)
lname = author.getLastName().title()
numCites = analyzer.getCitesToAuthor(lname, content)
if title is None:
title = 'Unknown Title'
print("Citing paper number " + str(idx+1) + ": " + title + " cites " + lname + " " + str(numCites) + " times.")
info_dict = {}
info_dict['Citing Paper Number'] = idx+1
info_dict['Title'] = title
info_dict['Over-cite Count'] = numCites
overcites_info.append(info_dict)
except KeyboardInterrupt:
print('User ended program. Returning existing Data')
WatLibSeleniumParser.reset()
return overcites_info
return overcites_info
def getWatPDF(self, url, title=None, pdfName='paper.pdf'):
print('Getting pdf from WatLib')
print(url)
status = WatLibSeleniumParser.downloadFromWatLib(url, 'paper.pdf')
if status is None:
print('None status')
return None
else:
# try:
newPdf = PdfObj('local', pdfName)
# except KeyboardInterrupt:
# return None
return newPdf
'''
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')
