import django
django.setup()
from django_crawl.models import BlogData
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
def parse_blog():
html_url = 'http://cms.pknu.ac.kr/pknujob/view.do?no=2342'
req = requests.get(html_url)
html = req.text
soup = BeautifulSoup(html, 'html.parser')
my_titles = soup.find('ul', {'id': 'board_list'})
my_titles = my_titles.select('li > a')
data = {}
for title in my_titles:
data[title.find("h4").text] = [
title.get('href'),
title.find('span', {
'class': 'date'
}).text
]
return data
if __name__ == '__main__':
blog_data_dict = parse_blog()
for t, l in blog_data_dict.items():
try:
BlogData(title=t, link=l[0], tag='job_general', date=l[1]).save()
except:
pass
# my_googles = soup.find_all('div', {'class':'BNeawe vvjwJb AP7Wnd'})
#case incruit
req = requests.get('http://www.pknu.ac.kr/usrBoardActn.do?p_bm_idx=5&p_boardcode=PK10000005&p_sbsidx=2')
html = req.text
soup = BeautifulSoup(html, 'html.parser')
my_incruit = soup.find_all('td', {'class':'title'})
data = {}
for title in my_incruit:
data[title.text] = title.get('href')
return data
if __name__=='__main__':
blog_data_dict = parse_blog()
for t, l in blog_data_dict.items():
BlogData(title=t).save()
# req = requests.get('https://www.google.com/search?q=%ED%81%AC%EB%A1%A4%EB%9F%AC&rlz=1C1OKWM_enKR881KR881&oq=%ED%81%AC%EB%A1%A4%EB%9F%AC&aqs=chrome..69i57j0l4j69i61l3.2578j0j7&sourceid=chrome&ie=UTF-8')
# html = req.text
# soup = BeautifulSoup(html, 'html.parser')
# my_googles = soup.find_all('div', {'class':'BNeawe vvjwJb AP7Wnd'})
def my_cron_job():
req = requests.get('http://www.pknu.ac.kr/usrBoardActn.do?p_bm_idx=5&p_boardcode=PK10000005&p_sbsidx=2')
html = req.text
soup = BeautifulSoup(html, 'html.parser')
my_incruit = soup.find_all('td', {'class':'title'})
data = {}
for title in my_incruit:
import django
django.setup()
from django_crawl.models import BlogData
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
def parse_blog():
html_url = 'http://cms.pknu.ac.kr/lincplus/view.do?no=9100'
req = requests.get(html_url)
html = req.text
soup = BeautifulSoup(html, 'html.parser')
my_titles = soup.find('ul', {'id': 'board_list'})
my_titles = my_titles.select('li > a')
data = {}
for title in my_titles:
data[title.find("h4").text] = [
title.get('href'),
title.find('span', {
'class': 'date'
}).text
]
return data
if __name__ == '__main__':
blog_data_dict = parse_blog()
for t, l in blog_data_dict.items():
try:
BlogData(title=t, link=l[0], tag='link', date=l[1]).save()
except:
pass