def test_getPaperInfo():
import json
myWebdriver = MyWebdriver()
urls = [
# 'https://doi.org/10.1109/DATE.2001.915037',
# 'https://doi.org/10.1109/DATE.2001.915090',
# 'https://doi.org/10.1109/DATE.2001.915001',
# 'https://doi.org/10.1109/DATE.2001.915008',
# 'https://doi.org/10.1109/DATE.2001.915171',
# 'https://doi.org/10.1109/DATE.2001.915016',
# 'https://doi.org/10.1109/DATE.2001.915024',
# 'https://doi.org/10.1109/DATE.2001.915028',
# 'https://doi.org/10.1109/DATE.2009.5090865',
# 'https://doi.org/10.1109/DATE.2001.915083',
# 'https://doi.org/10.1109/DATE.2001.915050',
# 'https://ieeexplore.ieee.org/document/998473',
# 'https://ieeexplore.ieee.org/document/998470',
# 'https://dl.acm.org/citation.cfm?id=367109'
'https://doi.org/10.1109/DATE.2009.5090799',
]
for url in urls:
print(url)
myWebdriver.get(url)
infos = getPaperInfo(myWebdriver, logPath='TestLog.txt', warningPath='TestWarning.txt')
with open('./json.txt', 'a', encoding='utf-8') as f:
f.write(json.dumps(infos, indent=4, separators=(',', ': ')))
f.write('\n')
f.close()
# print(json.dumps(infos, indent=4, separators=(',', ': ')))
time.sleep(random.randint(60, 70))
def test_getPaperInfo():
import json
myWebdriver = MyWebdriver()
url = 'https://link.springer.com/chapter/10.1007%2F978-3-642-24322-6_22'
myWebdriver.get(url)
infos = getPaperInfo(myWebdriver, logPath='TestLog.txt', warningPath='TestWarning.txt')
print(json.dumps(infos, indent=4, separators=(',', ': ')))
def test_getPaperInfo():
import json
myWebdriver = MyWebdriver()
# url = 'http://drops.dagstuhl.de/opus/volltexte/2011/3082/'
url = 'https://doi.org/10.4230/OASIcs.ASD.2019.7'
myWebdriver.get(url)
infos = getPaperInfo(myWebdriver,
logPath='TestLog.txt',
warningPath='TestWarning.txt')
print(json.dumps(infos, indent=4, separators=(',', ': ')))
def test_getPaperInfo():
import json
# url = 'https://dl.acm.org/citation.cfm?id=367109'
url = 'https://dl.acm.org/citation.cfm?doid=3092627.3092632'
# url = 'https://dl.acm.org/citation.cfm?doid=378239.379025'
# url = 'https://dl.acm.org/citation.cfm?doid=2463209.2488896'
myWebdriver = MyWebdriver()
myWebdriver.get(url)
infos = getPaperInfo(myWebdriver,
logPath='TestLog.txt',
warningPath='TestWarning.txt')
print(json.dumps(infos, indent=4, separators=(',', ': ')))
def test_webdriverGet():
from MyWebdriver import MyWebdriver
urls = [
'//dblp.org/db/conf/dat',
'http://dblp.org/db/conf/date',
]
myWebdriver = MyWebdriver()
for url in urls:
time.sleep(3)
result = webdriverGet(url,
myWebdriver,
logPath='TestLog.txt',
warningPath='TestWarning.txt')
print(myWebdriver.browser)
if result == False:
print('Failed')
else:
print(myWebdriver.current_url())
def test_getPaperInfo():
import json
from MyWebdriver import MyWebdriver
urls = 'https://doi.org/10.1109/DATE.2001.915001'
title = ''
myWebdriver = MyWebdriver()
infos = getPaperInfo(urls,
title,
myWebdriver,
logPath='TestLog.txt',
warningPath='TestWarning.txt')
print(json.dumps(infos, indent=4, separators=(',', ':')))
def main():
myWebdriver = MyWebdriver()
for conference in projectInfo.conferences:
print(conference)
createBaseInfoXML(conference, papersfolderPath=projectInfo.folderPath, logPath='log.txt', warningPath='warning.txt')
folderPaths = tools.getFolders(projectInfo.folderPath, conference)
for folderPath in folderPaths:
getPapers(folderPath, myWebdriver, True, projectInfo.waitingTime[0], projectInfo.waitingTime[1])
def test_IEEE():
# test IEEE
getPapers('../papers/date\date2009', myWebdriver, True)
def test_ACM():
# test ACM
getPapers('../papers/isca/hasp2017', myWebdriver, True)
# getPapers('../papers/dac/dac2013', myWebdriver, True)
def test_Springer():
# test Springer
getPapers('../papers/vlsi/vlsisoc2009', myWebdriver, True)
def test_Schloss():
# test Schloss
getPapers('../papers/date/ppes2011', myWebdriver, True)
def test_CEUR():
# test CEUR
getPapers('../papers/date/ermavss2016', myWebdriver, True)
def test_Kluwer_Technische():
# test Kluwer and Technische
getPapers('../papers/vlsi/vlsisoc2003', myWebdriver, True)
# getPapers('../papers/vlsi\ifip10-5-2001', myWebdriver, True)
def test_ieee_computer():
#test ieee computer
# getPapers('../papers/date/date2003', myWebdriver, True)
getPapers('../papers/date/date2004-1', myWebdriver, True)