Spaces:
Running
Running
| import requests | |
| from bs4 import BeautifulSoup | |
| import streamlit as st | |
| import time | |
| import random | |
| # Target URL | |
| url = "https://m.news.naver.com/rankingList" | |
| # Headers | |
| headers = { | |
| "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:92.0) Gecko/20100101 Firefox/92.0", | |
| "Referer": "https://m.news.naver.com/" | |
| } | |
| def random_delay(): | |
| time.sleep(random.uniform(1, 3)) | |
| def safe_find(element, selector, class_name, attribute=None): | |
| """Safely find elements and their attributes""" | |
| found = element.find(selector, class_=class_name) | |
| if found and attribute: | |
| return found.get(attribute) | |
| return found.text if found else None | |
| def scrape_ranking_news(): | |
| try: | |
| random_delay() | |
| response = requests.get(url, headers=headers) | |
| response.raise_for_status() # Check for HTTP errors | |
| soup = BeautifulSoup(response.text, "html.parser") | |
| ranking_news_sections = soup.find_all("div", class_="rankingnews_box") | |
| news_list = [] | |
| for section in ranking_news_sections: | |
| office_name = safe_find(section, "strong", "rankingnews_name") | |
| if not office_name: | |
| continue | |
| articles = section.find_all("li") | |
| for article in articles: | |
| # Safely extract all attributes | |
| rank = safe_find(article, "em", "list_ranking_num") | |
| title = safe_find(article, "strong", "list_title") | |
| time_posted = safe_find(article, "span", "list_time") | |
| link = safe_find(article, "a", None, "href") | |
| # Handle image separately as it needs specific null checking | |
| img_tag = article.find("img") | |
| image = img_tag.get('src') if img_tag else None | |
| if all([rank, title, time_posted, link]): # Ensure all required fields exist | |
| news_list.append({ | |
| "rank": rank, | |
| "title": title, | |
| "time": time_posted, | |
| "link": link, | |
| "image": image, | |
| "office": office_name | |
| }) | |
| return news_list | |
| except Exception as e: | |
| st.error(f"Error scraping news: {str(e)}") | |
| return [] | |
| def display_news(news_data, num_columns=5): | |
| if not news_data: | |
| st.warning("No news articles found.") | |
| return | |
| col_count = 0 | |
| cols = st.columns(num_columns) | |
| for news in news_data: | |
| with cols[col_count]: | |
| if news['image']: | |
| try: | |
| st.image(news['image']) | |
| except Exception: | |
| st.warning("Image unavailable") | |
| st.write(f"**{news['rank']}μ - {news['office']}**") | |
| st.write(f"[{news['title']}]({news['link']})") | |
| st.write(f"π {news['time']}") | |
| col_count = (col_count + 1) % num_columns | |
| if col_count == 0: | |
| cols = st.columns(num_columns) | |
| # Main app | |
| st.title("Daily News Scrap in Korea") | |
| if st.button("Start"): | |
| news_data = scrape_ranking_news() | |
| display_news(news_data) |