base_url = 'http://m.38.co.kr/ipo/'
page_url = 'http://m.38.co.kr/ipo/fund.php?&page={}'
each_url = 'http://m.38.co.kr/ipo/fund_view.php?no=1591&page=2'
last_page = 10
result = {}
for page_num in range(1, last_page + 1):
bs = get_soup(page_url.format(page_num), 'cp949')
tds = bs.find_all('td')
tds = [tds[i] for i in range(len(tds)) if i % 6 == 0]
for td in tds:
url = base_url + td.find('a')['href'].replace('./', '')
result[td.text] = url
스팩 = re.compile(r'\d+호$')
삭제들 = []
for key in result.keys():
if 스팩.search(key) != None:
삭제들.append(key)
for 삭제 in 삭제들:
del result[삭제]
for value in result.values():
bs = get_soup(value, 'cp949')
tds = bs.find_all('td')
tds = [td.text.strip() for td in tds if td.text]
정리 = {}
for i, td in enumerate(tds):
if i % 2 == 0:
title = td
else:
content = td
정리[title] = content
for key, val in 정리.items():
print(f'{key}: {val}')