def get_share_code_from_naver():
from scraping.web_scraping import create_soup
from openpyxl import Workbook
import time
wb = Workbook()
ws = wb.active
ws.title = "네이버 업종 종목코드"
ws.append(['종목코드', '종목명', '업종코드', '업종명'])
# 업종코드 딕셔너리
mk_code_dict = get_market_code_from_naver()
# key = 업종명, value = 업종코드
for key, value in mk_code_dict.items():
print(f"Start {value} Category")
# time.sleep(2)
url = f'https://finance.naver.com/sise/sise_group_detail.nhn?type=upjong&no={value}'
soup = create_soup(url)
table = soup.select('#contentarea > div.box_type_l')[1].select(
'tbody > tr > td.name')
for line in table:
share_name = line.text
share_code = line.a['href'].replace("/item/main.nhn?code=", "")
# 마켓과 종목 코드를 엑셀파일로 저장
ws.append([share_code, share_name, value, key])
wb.save("stock_data\\종목코드.xlsx")
print("Total Code file Completed")
def get_theme_share_info():
import csv
import time
import datetime
from scraping.web_scraping import create_soup
print("Start get share code")
print(time.strftime("%Y-%m-%d %H:%M:%S"))
csv_file = open(
f"stock_data\\theme_share_info_{datetime.date.today()}.csv",
"w",
encoding='utf-8-sig',
newline="")
csv_writer = csv.writer(csv_file)
# 헤더
header = (['테마명', '테마코드', '종목명', '종목코드', '종목정보', '종목링크'])
csv_writer.writerow(header)
# 테마 코드 리스트
th_code_list = get_theme_code_from_naver()
# th_sh_info = [] # 테마명, 테마코드, 테마설명, 종목명, 종목코드, 종목 설명 리스트화
for th_code in th_code_list:
print(f"theme code: {th_code}")
# time.sleep(3)
url = f'https://finance.naver.com/sise/sise_group_detail.nhn?type=theme&no={th_code}'
soup = create_soup(url)
# 테마명, 테마 설명 가져오기
th_name = soup.select_one(
'#contentarea_left > table > tr > td > div > div > strong'
).get_text()
th_info = soup.select(
'#contentarea_left > table > tr > td')[1].p.get_text()
# th_sh_info.append([th_name, th_code, '', '', th_info]) # 리스트에 추가
# ws.append([th_name, th_code, '', '', th_info]) # 엑셀에 저장
csv_writer.writerow([th_name, str(th_code), '', '', th_info])
# 테마별 종목명, 종목코드
sh_data = soup.find('tbody').select('tr')[:-2]
for tag in sh_data:
# sh_link = "https://finance.naver.com/" + tag.select('td')[0].a['href']
sh_name = tag.select('td')[0].text
sh_code = tag.select('td')[0].a['href'].replace(
"/item/main.nhn?code=", "")
sh_info = tag.select('td')[1].p.text
sh_link = "https://finance.naver.com/item/main.nhn?code=" + sh_code
# th_sh_info.append([th_name, th_code, sh_name, sh_code, sh_info, sh_link]) # 리스트에 추가
# ws.append([th_name, th_code, sh_name, sh_code, sh_info, sh_link]) # 엑셀에 저장
csv_writer.writerow([
th_name,
str(th_code), sh_name,
str(sh_code), sh_info, sh_link
])
csv_file.close()
print("Share code done")
print(time.strftime("%Y-%m-%d %H:%M:%S"))
def get_etn_code_from_wise():
from scraping.web_scraping import create_soup
soup = create_soup("http://comp.wisereport.co.kr/ETF/lookup.aspx")
table = soup.select_one('table.table').tbody.select('tr')
etn_code = []
for tag in table:
td = tag.select('td')
if td[0].text == "ETN":
etn_code.append(td[1].text.strip())
# else:
# etf_list.append([data.text.strip() for data in td])
print("ETN code done")
return etn_code
def get_market_code_from_naver():
from scraping.web_scraping import create_soup
soup = create_soup(
'https://finance.naver.com/sise/sise_group.nhn?type=upjong')
table = soup.select('table.type_1 > tr > td > a')
# 기타 항목 제거 위해 딕셔너리로 반환
mk_code_dict = {}
for line in table:
market_name = line.text
market_code = line['href'].replace(
"/sise/sise_group_detail.nhn?type=upjong&no=", "")
mk_code_dict[market_name] = market_code
del mk_code_dict['기타']
print(mk_code_dict)
print('mk_code_dict completed')
# mk_code_dict를 리턴 {업종명: 업종코드}
return mk_code_dict
def get_theme_code_from_naver():
import time
from scraping.web_scraping import create_soup
theme_code_list = [] # 테마 코드 리스트로 저장
print("Start get share code")
for page in range(1, 7):
print(f"On page : {page}")
url = f"https://finance.naver.com/sise/theme.nhn?&page={page}"
soup = create_soup(url)
theme_data = soup.select_one("table.type_1").select("td.col_type1")
for line in theme_data:
theme_code = line.select_one("a")["href"].replace(
"/sise/sise_group_detail.nhn?type=theme&no=", "")
theme_code_list.append(theme_code)
print("Theme code done")
# 테마 코드 리스트를 리턴
return theme_code_list
def get_theme_fluctuation():
import csv
import time
import datetime
from scraping.web_scraping import create_soup
csv_file = open(
f"stock_data\\테마데일리등락률\\theme_fluctuation_{datetime.date.today()}.csv",
"w",
encoding='utf-8-sig',
newline="")
csv_writer = csv.writer(csv_file)
# period = datetime.date.today()
# 헤더
header = (['테마명', '테마코드', '전일대비 등락률'])
csv_writer.writerow(header)
# 테마명 테마코드 전일대비등락률
print("데일리 테마별 등락률 스크랩 시작")
for page in range(1, 7):
print(f"On page : {page}")
# 네이버 금융 테마별 시세
url = f"https://finance.naver.com/sise/theme.nhn?&page={page}"
time.sleep(1.5)
soup = create_soup(url)
theme_data = soup.select("td.col_type1")
flucs = soup.select("td.col_type2")
for i in range(len(theme_data)):
theme_name = theme_data[i].text.strip()
theme_code = theme_data[i].a["href"].replace(
"/sise/sise_group_detail.nhn?type=theme&no=", "")
fluc = flucs[i].text.strip().replace("+", "").replace("%", "")
print(theme_name, theme_code, fluc)
print(i)
csv_writer.writerow([theme_name, theme_code, fluc])
print("테마별 등락률 완료")
print()
def get_market_fluctuation():
import csv
import datetime
from scraping.web_scraping import create_soup
csv_file = open(
f"stock_data\\업종데일리등락률\\market_fluctuation_{datetime.date.today()}.csv",
"w",
encoding='utf-8-sig',
newline="")
csv_writer = csv.writer(csv_file)
# period = datetime.date.today()
# 헤더
header = (['업종명', '업종코드', '전일대비 등락률'])
csv_writer.writerow(header)
# 종목코드 종목명 전일대비등락률
print("데일리 업종별 등락률 스크랩 시작")
# 네이버 금융 업종
url = "https://finance.naver.com/sise/sise_group.nhn?type=upjong"
soup = create_soup(url)
theme_data = soup.select_one("table.type_1").select("tr")[3:]
for line in theme_data:
td = line.select('td')
if len(td) <= 1: # 의미없는 자료 제거
continue
market_name = td[0].text.strip()
market_code = td[0].a["href"].replace(
"/sise/sise_group_detail.nhn?type=upjong&no=", "")
fluc = td[1].text.strip().replace('%', '').replace('+', '')
# link = "https://finance.naver.com/sise/sise_group_detail.nhn?type=theme&no=" + market_code
csv_writer.writerow([market_name, market_code, fluc])
print("업종별 등락률 완료")
print()
def get_etf_info_from_naver():
import time
import datetime
import csv
from scraping.web_scraping import create_soup
from selenium import webdriver
from bs4 import BeautifulSoup
# # CSV
csv_file = open(f'stock_data\\etf_{datetime.date.today()}.csv',
'w',
encoding='utf-8-sig',
newline='')
csv_writer = csv.writer(csv_file)
csv_writer.writerow([
'ETF이름', '링크', 'ETF코드', '운용사', '수수료', '시가총액(억 원)', '수익률', '', '', '',
'구성종목 TOP 10'
])
csv_writer.writerow([
'', '', '', '', '', '', '1개월', '3개월', '6개월', '1년', '1위', '', '2위', '',
'3위', '', '4위', '', '5위', '', '6위', '', '7위', '', '8위', '', '9위', '',
'10위', ''
])
# ETF 코드
etf_code = get_etf_code_from_wise()
# 헤드리스 셀레니움
options = webdriver.ChromeOptions()
options.headless = True
options.add_argument("window-size=1920x1080")
options.add_argument(
"user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36"
)
driver = webdriver.Chrome(options=options)
print(f"Get ETF info :")
print(time.strftime("%Y-%m-%d %H:%M:%S"))
for code in etf_code:
print(f"Start : {code}")
url = f'https://finance.naver.com/item/coinfo.nhn?code={code}'
driver.get(url)
driver.implicitly_wait(3)
soup = create_soup(url)
# 이름, 링크, 운용사, 수수료
etf_name = soup.select_one(
'#middle > div.h_company > div.wrap_company > h2 > a').text
etf_link = f'https://finance.naver.com/item/coinfo.nhn?code={code}'
company = soup.select_one('#tab_con1').select_one(
'div:nth-child(4)').select('td')[1].text
commission = soup.select_one('#tab_con1').select_one(
'div:nth-child(4)').select('td')[0].em.text.replace('%', '')
each_etf_info = [etf_name, etf_link,
str(code), company, commission] # 1차 리스트 저장
# iframe으로 이동
driver.switch_to.frame('coinfo_cp')
time.sleep(1)
soup_iframe = BeautifulSoup(driver.page_source, "lxml")
# 시가총액
capital = soup_iframe.select_one('#status_grid_body').select(
'tr')[5].td.text.replace(',', '')[:-2]
each_etf_info.append(capital)
# 수익률
earnings = soup_iframe.select_one('#status_grid_body').select(
'tr')[-1].td.select('span')
for line in earnings:
earning = line.text.replace('%', '').replace('+', '')
each_etf_info.append(earning)
# 구성종목
top_10 = soup_iframe.select_one('#CU_grid_body').select('tr')[:10]
for line in top_10:
sh_name = line.select('td')[0].text
percent = line.select('td')[2].text
if percent == '-':
percent = ''
else:
percent = percent
each_etf_info.extend([sh_name, percent])
# 리스트 진짜 이방법밖에 없는거 실화..? 더 찾아보기
# each_etf_info.append(sh_name) # 3차 리스트 저장
# each_etf_info.append(percent)
# csv에 입력
csv_writer.writerow(each_etf_info)
driver.quit()
print(f"ETF info completed")
print(time.strftime("%Y-%m-%d %H:%M:%S"))