In [23]:
import requests
from bs4 import BeautifulSoup
import pandas as pd
In [2]:
url = 'https://movie.naver.com/movie/running/current.naver'
resp = requests.get(url)
resp.text
soup = BeautifulSoup(resp.text)
In [13]:
lst_dsc = soup.find_all('dl', class_='lst_dsc')[0]
In [4]:
dt_tit = lst_dsc.find('dt', class_='tit')
In [5]:
dt_tit.find('a').get_text()
Out[5]:
'베르네 부인의 장미정원'
In [6]:
dl_info_star = lst_dsc.find('dl', class_='info_star')
In [7]:
dl_info_star.find_all('span', class_='num')
Out[7]:
[<span class="num">9.39</span>, <span class="num">7.00</span>]
In [8]:
net = dl_info_star.find_all('span', class_='num')[0].get_text()
gija = dl_info_star.find_all('span', class_='num')[1].get_text()
In [9]:
print(net)
print(gija)

9.39
7.00
In [24]:
lst_dsc = soup.find_all('dl', class_='lst_dsc')
movie_list = list()
df = pd.DataFrame()
for dsc in lst_dsc:
    dt_tit = dsc.find('dt', class_='tit')
    title = dt_tit.find('a').get_text()
    dl_info_star = dsc.find('dl', class_='info_star')
    net = dl_info_star.find_all('span', class_='num')[0].get_text()
    if(len(dl_info_star.find_all('span', class_='num')) == 2):
        gija = dl_info_star.find_all('span', class_='num')[1].get_text()
    movie = dict()
    movie['title'] = title
    movie['net'] = net
    movie['gija'] = gija
    movie_list.append(movie)
In [12]:
movie_list[0]
Out[12]:
{'title': '베르네 부인의 장미정원', 'net': '9.39', 'gija': '7.00'}