
import requests
from bs4 import BeautifulSoup
headers = {'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36'}
data = requests.get('https://movie.naver.com/movie/sdb/rank/rmovie.naver?sel=pnt&date=20210829',headers=headers)
soup = BeautifulSoup(data.text, 'html.parser')
movies = soup.select('#old_content > table > tbody > tr')
for movie in movies:
a = movie.select_one('td.title > div > a')
b = movie.select_one('td:nth-child(1) > img')
c = movie.select_one('td.point')
if a is not None:
title = a.text
rank = b['alt']
star = c.text
print(title,rank,star)
#old_content > table > tbody > tr:nth-child(2) > td.title > div > a
#old_content > table > tbody > tr:nth-child(2) > td:nth-child(1) > img
#old_content > table > tbody > tr:nth-child(2) > td.point
*************
b = movie.select_one('td:nth-child(1) > img') 를
b = movie.select_one('td:nth-child(1)') >img를 빼고 이렇게해서
print(b) 하면
<td class="ac"><img alt="50" height="13" src="https://ssl.pstatic.net/imgmovie/2007/img/common/bullet_r_g50.gif" width="14"/></td>
이렇게 나오는데여, 여기서 ['alt']값을 못 빼는 이유가 있을까용???
