def get_tc_data(self, report_link, paper_data_id, tc_data):
'''
인용보고서에서 인용년도를 조회하는 함수 (start() 함수에서 사용)
:param report_link: 인용보고서 링크
:param paper_data_id:
:param tc_data: 인용년도 연도별 데이터 저장
:return:
'''
self.ui_stream.push(command='log', msg='인용년도 정보를 가져옵니다.')
session = requests.Session()
session = sju_utiles.set_user_agent(session)
session.cookies.update(self.session.cookies)
# [단계 2/3] 인용년도 조회 (병렬 구성)
#########################################################################
report_link = report_link[0]
http_res = session.get(self.base_url + report_link['href'])
target_content = http_res.content
soup = BeautifulSoup(target_content, 'html.parser')
raw_tc_data = soup.select_one('script#raw_tc_data')
tc_tuple_list = re.findall(r'([0-9]+)\=([0-9]+)', raw_tc_data.text)
# tc_list = list(filter(lambda x: int(x[1]) > 0, tc_tuple_list))
tc_dict = {}
for x in tc_tuple_list:
tc_dict.update({x[0]: x[1]})
tc_data['tc_dict'] = tc_dict
def set_session(self, cookies=None):
'''
세션 갱신 함수
:param cookies: 쿠키 값 저장 변수
:return:
'''
MAX_TRIES = 5
self.qid = 0
ui_stream = self.ui_stream
tries = 0
session = requests.Session()
# SID와 JSESSIONID가 주어질 경우
if cookies:
session = sju_utiles.set_user_agent(session)
session.cookies.update(cookies)
self.SID = session.cookies['SID'].replace("\"", "")
self.jsessionid = session.cookies['JSESSIONID']
ui_stream.push(command='log', msg='SID : %s' % self.SID)
ui_stream.push(command='log',
msg='JSESSIONID : %s' % self.jsessionid)
while tries < MAX_TRIES and not cookies:
# 세션 갱신
ui_stream.push(command='log', msg=sju_CONSTANTS.STATE_MSG[1001])
session = sju_utiles.set_user_agent(session)
# 세션 SID, JSESSIONID 요청
ui_stream.push(command='log', msg=sju_CONSTANTS.STATE_MSG[1101])
res = session.get('http://apps.webofknowledge.com',
allow_redirects=False)
for redirect in session.resolve_redirects(res, res.request):
if 'SID' in session.cookies.keys(): break
# SID요청 에러 판별
if res.status_code == requests.codes.FOUND or res.status_code == requests.codes.OK:
if res.url.find('login') > -1:
raise sju_exceptions.LoginRequired()
self.SID = session.cookies['SID'].replace("\"", "")
self.jsessionid = session.cookies['JSESSIONID']
ui_stream.push(command='log', msg='SID : %s' % self.SID)
ui_stream.push(command='log',
msg='JSESSIONID : %s' % self.jsessionid)
# 요청 성공
ui_stream.push(command='log',
msg=sju_CONSTANTS.STATE_MSG[1201])
break
elif res.status_code == 403:
# ui_stream.push(command='log', msg='스레드가 403 상태 메세지를 받았습니다.')
tries += 1
ui_stream.push(command='log',
msg='서버에서 거부하여 2초 뒤 재시도합니다. [%d/%d]' %
(tries, MAX_TRIES))
continue
else:
# 요청 실패
ui_stream.push(command='err',
msg=sju_CONSTANTS.STATE_MSG[1301][0])
raise sju_exceptions.InitSessionError()
if tries >= MAX_TRIES:
raise sju_exceptions.InitSessionError()
if self.session: self.session.close()
self.session = session