국내주식 크롤링 코드 정리

import sys, os

import requests
import bs4
import pandas as pd

import xlrd
import openpyxl 

import time
from datetime import datetime, date, timedelta

import random

 

---

if os.path.isfile("C:/Users/g0917/Desktop/Test5.xlsx"):
    df = pd.read_excel("C:/Users/g0917/Desktop/Test5.xlsx", index_col=0)
        
else:
    stats = { "날짜" : ["2000.01.02","2000.01.01"]}
    df = pd.DataFrame(stats)
    with pd.ExcelWriter("C:/Users/g0917/Desktop/Test5.xlsx", engine = 'openpyxl') as writer:
        df.to_excel(writer, sheet_name = "sheet1")
        
last_date_time = datetime.strptime(df.iloc[0, 0], "%Y.%m.%d")


code_list = ['005930']

if datetime.now() > last_date_time:

    for code_number in code_list:
        total_data_list = []

        my_headers = {
            "referer": "https://finance.naver.com/item/sise_day.nhn?code={}&page=1".format(code_number),
            }

        
        for page_number in range(1, 21):
            url = "https://finance.naver.com/item/sise_day.nhn?code={0}&page={1}".format(code_number, page_number)
            res = requests.get(url = url, headers = my_headers)

            soup = bs4.BeautifulSoup(res.text)
            tr_elements = soup.select("table.type2 >  tr[onmouseover='mouseOver(this)']")

            current_date_time_set = set()  #현재페이지(1p)의 date_time_set. 추후 현재날짜와 비교용도로 사용
            for tr in tr_elements:
                td_elements = tr.select("td")
                data_list = [] 

                for i, td_e in enumerate(td_elements):
                    if i == 0 : #날짜값 index == 0, 즉 i=0인 data(날짜 data)만 따로 관리
                        current_date_time_set.add(td_e.text.strip()) #날짜 Data current_data_time_set에 추가
                        
                    #여기서 else를 쓰면 i==0 외의 data만 추가된다. 지금 원하는건 i==0 data도 data_list에 append를 하는것이기에 else를 쓰지 않고, if i==0 일때에만 따로 current data time set을 넣고 그 외에는 그냥 for 문을 받게 냅둔다.
                    
                    data_list.append(td_e.text.strip().replace(",","")) #data int로 바꿔줘야 함. 먼저 , 없애고..       
                data_list_int = [data_list[0], int(data_list[1]), int(data_list[2]), int(data_list[3]), int(data_list[4]), int(data_list[5]), int(data_list[6])]
                total_data_list.append(data_list_int)
                                
                time.sleep(random.random()/1000)

            globals()['df_{}'.format(code_number)] = pd.DataFrame(total_data_list, columns=["날짜", "종가", "전일비", "시가", "고가", "저가", "거래량"])
            #df = df.iloc[::-1].reset_index(drop=True)  #날짜 내림차순인데 쓸모 없을듯 ?   


with pd.ExcelWriter("C:/Users/g0917/Desktop/Test5.xlsx") as writer:
    for code_number_save in code_list:
        globals()['df_{}'.format(code_number_save)].to_excel(writer, sheet_name = f'{code_number_save}')