[파이썬] 웹크롤링 주식 데이터 가져오기

 

# -*- coding: utf-8 -*-
"""CH 02_02.주식 데이터 가져오기.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/12NAlW9QiyWko31SpWwBoYRMxJue-Drt0
"""

# 해당 페이지의 page source를 직접 가져옵니다. 웹페이지에서도 우클릭 "페이지 소스 보기"로 같은 HTML 소스를 볼 수 있습니다.
import requests
import bs4

page_no = 1
page_url = f'https://finance.naver.com/sise/sise_index_day.naver?code=KPI200&page={page_no}'

source = requests.get(page_url).text

# BeautifulSoup 함수를 사용해서 불러온 html source를 "lxml" parser로 parsing 합니다.
source = bs4.BeautifulSoup(source)

dates = source.find_all('td', class_='date')

dates

date_list = []

for date in dates:
    date_list.append(date.text)

date_list

prices = source.find_all('td', class_ = 'number_1')
price_list = []
for price in prices[::4]:
    price_list.append(price.text)
price_list

last_url = source.find_all('td', class_='pgRR')[0].find_all('a')[0]['href']
last_url

last_page = int(last_url.split('&page=')[-1])
last_page

date_list = []
price_list = []

for page_no in range(1, last_page+1):
    page_url = f'https://finance.naver.com/sise/sise_index_day.naver?code=KPI200&page={page_no}'

    source = requests.get(page_url).text
    source = bs4.BeautifulSoup(source)

    dates = source.find_all('td', class_='date')
    for date in dates:
        date_list.append(date.text)

    prices = source.find_all('td', class_ = 'number_1')
    for price in prices[::4]:
        price_list.append(price.text)

import pandas as pd

df = pd.DataFrame({"date" : date_list, "price" : price_list})
df.to_excel("kpi200.xlsx", index=False)

ch_02_02_주식_데이터_가져오기.py

0.00MB

CH_02_02_주식_데이터_가져오기.ipynb

0.01MB