Spaces:
Sleeping
Sleeping
import requests | |
from bs4 import BeautifulSoup | |
import pandas as pd | |
import streamlit as st | |
import random | |
import time # time ๋ชจ๋์ ์ํฌํธ | |
# ๋ค์ด๋ฒ ๋ชจ๋ฐ์ผ ๋ด์ค ๋ญํน URL | |
url = "https://m.news.naver.com/rankingList" | |
# ํค๋ ์ค์ (User-Agent ๋ฐ Referer ์ถ๊ฐ) | |
headers = { | |
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36", | |
"Referer": "https://m.news.naver.com/" | |
} | |
# ๋๋ค ๋๋ ์ด ํจ์ | |
def random_delay(min_delay=1, max_delay=3): | |
delay = random.uniform(min_delay, max_delay) | |
time.sleep(delay) # time ๋ชจ๋์ sleep ํจ์ ์ฌ์ฉ | |
# ์น ํ์ด์ง ์์ฒญ ๋ฐ ํ์ฑ | |
response = requests.get(url, headers=headers) | |
soup = BeautifulSoup(response.content, 'html.parser') | |
# ๋ด์ค ๋ฆฌ์คํธ ์ถ์ถ | |
news_list = [] | |
# ์๋ก์ด HTML ๊ตฌ์กฐ์ ๋ง๊ฒ ๋ฐ์ดํฐ ์ถ์ถ | |
for news_box in soup.select('div.rankingnews_box'): | |
# ์ธ๋ก ์ฌ ์ด๋ฆ ์ถ์ถ | |
press_name = news_box.find('strong', class_='rankingnews_name').text.strip() | |
# ๊ฐ ๋ด์ค ํญ๋ชฉ์ ๋ฆฌ์คํธ๋ก ์ถ์ถ | |
for news_item in news_box.select('ul.rankingnews_list li'): | |
random_delay() # ๋๋ ์ด ์ถ๊ฐ | |
# ์์ ๋ฒํธ ์ถ์ถ | |
rank_tag = news_item.find('em', class_='list_ranking_num') | |
rank = rank_tag.text if rank_tag else 'No Rank' | |
# ์ ๋ชฉ ์ถ์ถ | |
title_tag = news_item.find('strong', class_='list_title') | |
title = title_tag.text.strip() if title_tag else 'No Title' | |
# ๋งํฌ ์ถ์ถ | |
link = news_item.find('a')['href'] if news_item.find('a') else '#' | |
# ์๊ฐ ์ถ์ถ | |
time_tag = news_item.find('span', class_='list_time') | |
time_info = time_tag.text.strip() if time_tag else 'No Time' | |
# ์ด๋ฏธ์ง URL ์ถ์ถ | |
img_tag = news_item.find('img') | |
image_url = img_tag['src'] if img_tag and 'src' in img_tag.attrs else 'No Image Available' | |
# ๋ฐ์ดํฐ ๋ฆฌ์คํธ์ ์ถ๊ฐ | |
news_list.append({ | |
'Press': press_name, | |
'Rank': rank, | |
'Title': title, | |
'Link': link, | |
'Time': time_info, | |
'Image URL': image_url | |
}) | |
# ๋ฐ์ดํฐํ๋ ์์ผ๋ก ๋ณํ | |
df = pd.DataFrame(news_list) | |
# Streamlit์์ ๊ฒฐ๊ณผ ํ์ | |
st.title("Naver Mobile Ranking News Scraper") | |
# ๊ฐ๋ณ ๋ด์ค ํญ๋ชฉ ์ถ๋ ฅ | |
for index, row in df.iterrows(): | |
if row['Image URL'] != 'No Image Available': | |
st.image(row['Image URL'], width=100) | |
st.markdown(f"**[{row['Title']}]({row['Link']})**") | |
st.write(f"Press: {row['Press']} | Rank: {row['Rank']} | Time: {row['Time']}") | |
st.write("---") | |