[Scraping] Naver '이 시각 주요 뉴스' 목록 가져 오기

urllib와 beautifulsoup을 이용해 Naver에서 '이 시각 주요 뉴스' 목록을 가져온다.

 

from bs4 import BeautifulSoup as bs
import urllib.request as req

url = 'https://news.naver.com/'
res = req.urlopen(url)

soup = bs(res, 'html.parser')
title1 = soup.find('h4', 'tit_h4').string # 'tit_h4 tit_main1'
# title1 = soup.find(attrs = {'class' : 'tit_h4 tit_main1'}).string
print('\t\tNAVER', title1, '\n') 

print('-'*20, 'find_all()', '-'*20)
headlines1 = soup.find_all('a', 'nclicks(hom.headcont)')
# headlines1 = soup.find_all(attrs = {'class' : 'nclicks(hom.headcont)'})
# The find_all() method looks through a tag’s descendants and
# retrieves all descendants that match your filters.
for i, news in enumerate(headlines1):
    #if news.string == None:
    #    print('%2d: None' %i)
    #    continue
    print('%2d: %s' %(i + 1, news.string))

print('-'*20, 'select()', '-'*20)
headlines2 = soup.select('div.newsnow_tx_inner > a')
# Beautiful Soup supports the most commonly-used CSS selectors. Just pass a
# string into the .select() method of a Tag object or the BeautifulSoup object itself.
for i, news in enumerate(headlines2):
    #if news.string == None:
    #    print('%2d: None' %i)
    #    continue
    print('%2d: %s' %(i + 1, news.string))