펀드슈퍼마켓 (전체펀드) 크롤링

from selenium import webdriver

import chromedriver_autoinstaller

from selenium.webdriver.common.keys import Keys

from selenium.webdriver.common.by import By

import time

import csv

import re

# 브라우저 접속

driver = webdriver.Chrome('')

driver.get('https://www.fosskorea.com/fmm/FMM1010301/main.do')

time.sleep(1)

list_result = []

page_number = 2

   

for b in range(3): # 1~n 페이지까지 추출 (창은 n+1페이지에서 종료)

   

    time.sleep(1)

   

    for i in range(1,21): #페이지 당 관측치 20개 수집

   

        # 행 변수 추출

       

        # 편드명

        fund_name = driver.find_elements(By.CSS_SELECTOR, f'#fundList > div.new-fund-list > ul > li:nth-child({i}) > dl > dt > a')

        var1 = fund_name[0].text

        # 기준가

        fund_element_1 = driver.find_elements(By.CSS_SELECTOR, f'#fundList > div.new-fund-list > ul > li:nth-child({i}) > dl > dd.info-txt > table > tbody > tr:nth-child(3) > td:nth-child(2) > ul > li:nth-child(1)')

        var2 = fund_element_1[0].text

        var2_cleaned = var2.split('\n') # var2_cleaned 는 list

        var2_cleaned_text = var2_cleaned[0] # 이제 text

        # 운용규모

        fund_element_2 = driver.find_elements(By.CSS_SELECTOR, f'#fundList > div.new-fund-list > ul > li:nth-child({i}) > dl > dd.info-txt > table > tbody > tr:nth-child(2) > td:nth-child(2)')

        var3 = fund_element_2[0].text

        var3_cleaned_text = re.findall(r'\d+', var3)[0] # var3_cleaned 는 text

        # 총보수

        fund_date = driver.find_elements(By.CSS_SELECTOR, f'#fundList > div.new-fund-list > ul > li:nth-child({i}) > dl > dd.info-txt > table > tbody > tr:nth-child(1) > td:nth-child(4)')

        var4 = fund_date[0].text

       

        if len(var4.split("연 ")) > 1:

            var4_cleaned = var4.split("연 ")[1]

        else:

            var4_cleaned = "투설직접확인"

       

        # 하나의 행으로 저장해 result에 행을 쌓기

        list_1 = [var1, var2_cleaned_text, var3_cleaned_text, var4_cleaned]

        list_result.append(list_1)

       

    # 다음 페이지

    next_page = driver.find_element(By.CSS_SELECTOR, (f'a[href="javascript:pageClick({page_number})"]'))

    driver.execute_script('arguments[0].click();', next_page)

    page_number = page_number + 1

# CSV 파일에 데이터 쓰기

csv_file_path = 'fund_data.csv'

with open(csv_file_path, 'w', newline='', encoding='utf-8-sig') as csvfile: # utf-8-sig : 엑셀에서 한글 깨짐 방지

    csv_writer = csv.writer(csvfile)

   

    # 헤더 작성

    header = ['Fund Name', 'Price', 'AUM', 'Fee']

    csv_writer.writerow(header)

    # 데이터 작성

    for row in list_result:

        csv_writer.writerow(row)

print(f'Data saved to {csv_file_path}')

# 사용자 입력을 기다림

input("Press Enter to close the browser...")