Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import requests
|
2 |
+
from bs4 import BeautifulSoup
|
3 |
+
import pandas as pd
|
4 |
+
|
5 |
+
# URL 설정
|
6 |
+
url = "https://news.naver.com/main/ranking/popularDay.naver"
|
7 |
+
|
8 |
+
# 요청 보내기
|
9 |
+
response = requests.get(url)
|
10 |
+
soup = BeautifulSoup(response.content, 'html.parser')
|
11 |
+
|
12 |
+
# 뉴스 리스트 추출
|
13 |
+
news_list = []
|
14 |
+
|
15 |
+
for news_item in soup.select('div.rankingnews_box ul.rankingnews_list li'):
|
16 |
+
rank = news_item.find('em', class_='list_ranking_num').text
|
17 |
+
title = news_item.find('a', class_='list_title').text.strip()
|
18 |
+
link = news_item.find('a', class_='list_title')['href']
|
19 |
+
time = news_item.find('span', class_='list_time').text.strip()
|
20 |
+
image_url = news_item.find('img')['src']
|
21 |
+
|
22 |
+
news_list.append({
|
23 |
+
'Rank': rank,
|
24 |
+
'Title': title,
|
25 |
+
'Link': link,
|
26 |
+
'Time': time,
|
27 |
+
'Image URL': image_url
|
28 |
+
})
|
29 |
+
|
30 |
+
# 데이터프레임으로 변환
|
31 |
+
df = pd.DataFrame(news_list)
|
32 |
+
|
33 |
+
# 결과 출력
|
34 |
+
print(df)
|