ai-trade/modules/services/news.py

import time
import requests
import xml.etree.ElementTree as ET


class NewsCollector:
    """동기 뉴스 수집 (Google News RSS)"""
    @staticmethod
    def get_market_news(query="주식 시장"):
        url = f"https://news.google.com/rss/search?q={query}&hl=ko&gl=KR&ceid=KR:ko"
        try:
            resp = requests.get(url, timeout=5)
            root = ET.fromstring(resp.content)
            items = []
            for item in root.findall(".//item")[:5]:
                title = item.find("title").text
                items.append({"title": title, "source": "Google News"})
            return items
        except Exception as e:
            print(f"[News] Collection failed: {e}")
            return []


class AsyncNewsCollector:
    """비동기 뉴스 수집 + 5분 캐싱"""

    def __init__(self):
        self._cache = None
        self._cache_time = 0
        self._cache_ttl = 300  # 5분
        self._stock_cache = {}  # {stock_name: (items, timestamp)}

    def get_market_news(self, query="주식 시장"):
        """동기 인터페이스 (하위 호환)"""
        now = time.time()
        if self._cache and (now - self._cache_time) < self._cache_ttl:
            return self._cache

        result = NewsCollector.get_market_news(query)
        self._cache = result
        self._cache_time = now
        return result

    async def get_market_news_async(self, query="주식 시장"):
        """비동기 뉴스 수집 (aiohttp + 캐싱)"""
        now = time.time()
        if self._cache and (now - self._cache_time) < self._cache_ttl:
            return self._cache

        try:
            import aiohttp
            url = f"https://news.google.com/rss/search?q={query}&hl=ko&gl=KR&ceid=KR:ko"
            async with aiohttp.ClientSession() as session:
                async with session.get(url, timeout=aiohttp.ClientTimeout(total=5)) as resp:
                    content = await resp.read()
                    root = ET.fromstring(content)
                    items = []
                    for item in root.findall(".//item")[:5]:
                        title = item.find("title").text
                        items.append({"title": title, "source": "Google News"})

                    self._cache = items
                    self._cache_time = now
                    return items
        except ImportError:
            return self.get_market_news(query)
        except Exception as e:
            print(f"[News Async] Collection failed: {e}")
            if self._cache:
                return self._cache
            return self.get_market_news(query)

    async def get_stock_news_async(self, stock_name, max_items=3):
        """종목별 뉴스 수집 (5분 캐싱)
        stock_name: 종목 이름 (e.g. '삼성전자', 'SK하이닉스')
        """
        now = time.time()
        cached = self._stock_cache.get(stock_name)
        if cached and (now - cached[1]) < self._cache_ttl:
            return cached[0]

        try:
            import aiohttp
            import urllib.parse
            query = urllib.parse.quote(f"{stock_name} 주가")
            url = f"https://news.google.com/rss/search?q={query}&hl=ko&gl=KR&ceid=KR:ko"
            async with aiohttp.ClientSession() as session:
                async with session.get(url, timeout=aiohttp.ClientTimeout(total=5)) as resp:
                    content = await resp.read()
                    root = ET.fromstring(content)
                    items = []
                    for item in root.findall(".//item")[:max_items]:
                        title_el = item.find("title")
                        if title_el is not None and title_el.text:
                            items.append({"title": title_el.text, "source": "Google News"})

                    self._stock_cache[stock_name] = (items, now)
                    return items
        except Exception as e:
            print(f"[News] 종목 뉴스 수집 실패 ({stock_name}): {e}")
            return []

    def clear_stock_cache(self):
        """종목 뉴스 캐시 전체 초기화"""
        self._stock_cache.clear()