options.add_argument('headless')
browser = webdriver.Chrome(options=options)
# browser = webdriver.Chrome() # 브라우저 켠채로 실행하는 코드
browser.get(new_url)
# .tit > a로 검색시 신규페이지, 갯수는 유동적인듯 16~20개
link_list = []
elmt_list = browser.find_elements_by_css_selector('.tit > a')
for elmt in elmt_list:
link_list.append(elmt.get_attribute('href'))
for idx, link in enumerate(link_list):
print(f'{idx+1}번째 크롤링 시작: {link.split("/")[-1]}')
browser.get(link)
dto = DTO()
dto.title = browser.find_element_by_css_selector('.tit').text
dto.view_count = browser.find_element_by_css_selector('.read').text.split(
':')[-1].strip().replace(',', '')
raw_list = browser.find_element_by_css_selector(
'.cd-info-list').text.split('\n')
dto.contest_field = list(
map(lambda x: x.strip(),
raw_list[raw_list.index('분야') + 1].replace('/', '-').split(',')))
dto.target = raw_list[raw_list.index('응모대상') + 1]
dto.host = raw_list[raw_list.index('주최/주관') + 1]
dto.sponsor = None if raw_list[raw_list.index('후원/협찬') +
1] == '접수기간' else raw_list[
raw_list.index('후원/협찬') + 1]
# 데이터 빼보기
# 3. 브라우저 창 띄울 필요없음
# 4. 제목
# 5. DTO만들기
from selenium import webdriver
from dto import DTO
# 43959
def url(no):
return f'https://www.wevity.com/?c=find&s=1&gbn=viewok&gp=1&ix={no}'
dto = DTO()
options = webdriver.ChromeOptions()
options.add_argument('headless')
browser = webdriver.Chrome(options=options)
browser.get(url(43959))
dto.title = browser.find_element_by_css_selector('.tit').text
print(dto.__dict__)
# 데이터 빼보기
# 3. 브라우저 창 띄울 필요없음
# 4. 제목
# 5. DTO만들기
# 6. 조회수
from selenium import webdriver
from dto import DTO
# 43959
def url(no):
return f'https://www.wevity.com/?c=find&s=1&gbn=viewok&gp=1&ix={no}'
dto = DTO()
options = webdriver.ChromeOptions()
options.add_argument('headless')
browser = webdriver.Chrome(options=options)
browser.get(url(43959))
dto.title = browser.find_element_by_css_selector('.tit').text
dto.view_count = browser.find_element_by_css_selector('.read').text.split(
':')[-1].strip().replace(',', '')
print(dto.__dict__)