src/streamlit_app.py

import streamlit as st
import pandas as pd
import requests
from bs4 import BeautifulSoup

st.set_page_config(page_title="SMRJ 最新ニュース", layout="wide")

@st.cache_data(ttl=3600)
def fetch_news():
    """爬取 SMRJ 官方新聞列表"""
    url = "https://www.smrj.go.jp/news/index.html"
    headers = {"User-Agent": "Mozilla/5.0"}
    res = requests.get(url, headers=headers)
    res.encoding = "utf-8"
    soup = BeautifulSoup(res.text, "html.parser")

    news_items = soup.select("li.news-list__item")[:15]

    data = []
    for item in news_items:
        date = item.select_one(".news-item__date")
        labels = item.select(".news-item__label")
        title = item.select_one(".news-item__text")

        data.append({
            "日期": date.get_text(strip=True) if date else "",
            "分類": ", ".join([lbl.get_text(strip=True) for lbl in labels]) if labels else "",
            "標題": title.get_text(strip=True) if title else ""
        })

    df = pd.DataFrame(data)
    return df

# ---------------- Streamlit UI ----------------
st.title("📢 SMRJ 最新ニュース (前15件)")

df = fetch_news()

if df.empty:
    st.warning("⚠️ 無法取得資料，請稍後再試")
else:
    st.dataframe(df, use_container_width=True)

    # CSV 下載
    csv = df.to_csv(index=False, encoding="utf-8")
    st.download_button(
        label="📥 下載 CSV",
        data=csv,
        file_name="smrj_announcement.csv",
        mime="text/csv",
    )

st.caption("データ出典: 中小企業基盤整備機構 (SMRJ)")