[파이썬]네이버 데이터랩 추출 및 엑셀 파일 저장(xlsx)

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.action_chains import ActionChains
import chromedriver_autoinstaller
import os
import requests
import warnings
import shutil
import subprocess
import time


warnings.filterwarnings('ignore')

try:
    shutil.rmtree(r"c:\chrometemp")  # 쿠키 / 캐쉬파일 삭제
except FileNotFoundError:
    pass
subprocess.Popen(
    r'C:\Program Files\Google\Chrome\Application\chrome.exe --remote-debugging-port=9222 --user-data-dir="C:\chrometemp"')  # 디버거 크롬 구동
option = Options()
option.add_experimental_option("debuggerAddress", "127.0.0.1:9222")
chrome_ver = chromedriver_autoinstaller.get_chrome_version().split('.')[0]
try:
    driver = webdriver.Chrome(f'./{chrome_ver}/chromedriver.exe', options=option)
except:
    chromedriver_autoinstaller.install(True)
    driver = webdriver.Chrome(f'./{chrome_ver}/chromedriver.exe', options=option)
driver.maximize_window()  # 최대창
time.sleep(3)
driver.implicitly_wait(10)

action = ActionChains(driver)  # 액션지정

#################### 네이버 데이터랩 Top 500 키워드 뽑기 ####################
# 기기별 전체:   //*[@id="18_device_0"]
# 성별 전체:   //*[@id="19_gender_0"]
# 연령 전체: //*[@id="20_age_0"]
# 조회하기 클릭:  //*[@id="content"]/div[2]/div/div[1]/div/a

driver.get(url='https://datalab.naver.com/shoppingInsight/sCategory.naver')
time.sleep(1)

#driver.find_element(By.XPATH, '//*[@id="18_device_0"]').click()  # 기기별 클릭
driver.find_element_by_xpath('//*[@id="18_device_0"]').click()
# time.sleep(0.5)
#driver.find_element(By.XPATH, '//*[@id="19_gender_0"]').click()  # 성별 클릭
# time.sleep(0.5)
#driver.find_element(By.XPATH, '//*[@id="20_age_0"]').click()  # 연령별 클릭
# time.sleep(0.5)

driver.find_element_by_xpath('//*[@id="content"]/div[2]/div/div[1]/div/div/div[1]/div/div[1]/span').click()  # 분야 클릭
# time.sleep(0.5)

driver.find_element_by_xpath('//*[@id="content"]/div[2]/div/div[1]/div/div/div[1]/div/div[1]/ul/li[4]/a').click()  # 디지털/가전 클릭
# time.sleep(0.5)

driver.find_element_by_xpath('//*[@id="content"]/div[2]/div/div[1]/div/a').click()  # 조회하기 클릭
# time.sleep(1)


# 상품정보1 : //*[@id="content"]/div[2]/div/div[2]/div[2]/div/div/div[1]/ul/li[1]/a
# 상품정보2 : //*[@id="content"]/div[2]/div/div[2]/div[2]/div/div/div[1]/ul/li[2]/a
# 상품정보3 : //*[@id="content"]/div[2]/div/div[2]/div[2]/div/div/div[1]/ul/li[3]/a

from openpyxl import Workbook

wb = Workbook()
ws = wb.create_sheet('keyword')
wb.remove_sheet(wb['Sheet'])
ws.append((['No', '인기검색어']))

for i in range(0, 25):
    for j in range(1, 21):
        path = f'//*[@id="content"]/div[2]/div/div[2]/div[2]/div/div/div[1]/ul/li[{j}]/a'
        result = driver.find_element_by_xpath(path).text
        print(result.split('\n'))
        time.sleep(0.1)
        ws.append(result.split('\n'))
    driver.find_element_by_xpath('//*[@id="content"]/div[2]/div/div[2]/div[2]/div/div/div[2]/div/a[2]').click()
    time.sleep(0.1)

wb.save('./naverdatalabtop500.xlsx')
wb.close()

driver.close()
driver.quit()

print("네이버 데이터랩 Top 500 키워드 뽑기 완료")

time.sleep(3)

참고URL
[파이썬] 네이버 데이터랩 상품 인기 키워드 Top 500 크롤링 자동화 (tistory.com)