스파르타코딩클럽 파이썬 혼자놀기 패키지 2

신문기사 검색결과 엑셀에 저장하기

from bs4 import BeautifulSoup
from selenium import webdriver

from openpyxl import Workbook


driver = webdriver.Chrome('chromedriver')

url = "https://search.naver.com/search.naver?where=news&sm=tab_jum&query=추석"

driver.get(url)
req = driver.page_source
soup = BeautifulSoup(req, 'html.parser')

wb = Workbook()
ws1 = wb.active
ws1.title = "articles"
ws1.append(["제목", "링크", "신문사", "썸네일"])

articles = soup.select('#main_pack > div.news.mynews.section._prs_nws > ul > li')

for article in articles:
    a_tag = article.select_one('dl > dt > a')

    title = a_tag.text
    url = a_tag['href']
    comp = article.select_one('dd.txt_inline > span._sp_each_source').text.split(' ')[0].replace('언론사','')
    thumbnail = article.select_one('div > a > img')['src']

    ws1.append([title, url, comp, thumbnail])

driver.quit()
wb.save(filename='articles.xlsx')