google-news-trends-mcp 0.1.10__py3-none-any.whl → 0.2.1__py3-none-any.whl

google_news_trends_mcp/__init__.py

@@ -1,2 +1,3 @@
 import logging
+
 logging.getLogger(__name__).addHandler(logging.NullHandler())

google_news_trends_mcp/cli.py

@@ -7,6 +7,7 @@ from google_news_trends_mcp.news import (
     get_trending_terms,
     get_top_news,
     save_article_to_json,
+    BrowserManager,
 )
 
 
@@ -27,9 +28,13 @@ def cli():
 )
 @click.option("--no-nlp", is_flag=True, default=False, help="Disable NLP processing for articles.")
 def keyword(keyword, period, max_results, no_nlp):
-    articles = asyncio.run(get_news_by_keyword(keyword, period=period, max_results=max_results, nlp=not no_nlp))
-    # asyncio.run(articles)  # Ensure the articles are fetched asynchronously
-    print_articles(articles)
+    @BrowserManager()
+    async def _keyword():
+        articles = await get_news_by_keyword(keyword, period=period, max_results=max_results, nlp=not no_nlp)
+        print_articles(articles)
+        print(f"Found {len(articles)} articles for keyword '{keyword}'.")
+
+    asyncio.run(_keyword())
 
 
 @cli.command(help=get_news_by_location.__doc__)
@@ -44,8 +49,13 @@ def keyword(keyword, period, max_results, no_nlp):
 )
 @click.option("--no-nlp", is_flag=True, default=False, help="Disable NLP processing for articles.")
 def location(location, period, max_results, no_nlp):
-    articles = asyncio.run(get_news_by_location(location, period=period, max_results=max_results, nlp=not no_nlp))
-    print_articles(articles)
+    @BrowserManager()
+    async def _location():
+        articles = await get_news_by_location(location, period=period, max_results=max_results, nlp=not no_nlp)
+        print_articles(articles)
+        print(f"Found {len(articles)} articles for location '{location}'.")
+
+    asyncio.run(_location())
 
 
 @cli.command(help=get_news_by_topic.__doc__)
@@ -60,8 +70,13 @@ def location(location, period, max_results, no_nlp):
 )
 @click.option("--no-nlp", is_flag=True, default=False, help="Disable NLP processing for articles.")
 def topic(topic, period, max_results, no_nlp):
-    articles = asyncio.run(get_news_by_topic(topic, period=period, max_results=max_results, nlp=not no_nlp))
-    print_articles(articles)
+    @BrowserManager()
+    async def _topic():
+        articles = await get_news_by_topic(topic, period=period, max_results=max_results, nlp=not no_nlp)
+        print_articles(articles)
+        print(f"Found {len(articles)} articles for topic '{topic}'.")
+
+    asyncio.run(_topic())
 
 
 @cli.command(help=get_trending_terms.__doc__)
@@ -75,16 +90,20 @@ def topic(topic, period, max_results, no_nlp):
     help="Maximum number of results to return.",
 )
 def trending(geo, full_data, max_results):
-    trending_terms = asyncio.run(get_trending_terms(geo=geo, full_data=full_data, max_results=max_results))
-    if trending_terms:
-        print("Trending terms:")
-        for term in trending_terms:
-            if isinstance(term, dict):
-                print(f"{term['keyword']:<40} - {term['volume']}")
-            else:
-                print(term)
-    else:
-        print("No trending terms found.")
+    # Browser not used for Google Trends
+    async def _trending():
+        trending_terms = await get_trending_terms(geo=geo, full_data=full_data, max_results=max_results)
+        if trending_terms:
+            print("Trending terms:")
+            for term in trending_terms:
+                if isinstance(term, dict):
+                    print(f"{term['keyword']:<40} - {term['volume']}")
+                else:
+                    print(term)
+        else:
+            print("No trending terms found.")
+
+    asyncio.run(_trending())
 
 
 @cli.command(help=get_top_news.__doc__)
@@ -98,9 +117,13 @@ def trending(geo, full_data, max_results):
 )
 @click.option("--no-nlp", is_flag=True, default=False, help="Disable NLP processing for articles.")
 def top(period, max_results, no_nlp):
-    articles = asyncio.run(get_top_news(max_results=max_results, period=period, nlp=not no_nlp))
-    print_articles(articles)
-    print(f"Found {len(articles)} top articles.")
+    @BrowserManager()
+    async def _top():
+        articles = await get_top_news(max_results=max_results, period=period, nlp=not no_nlp)
+        print_articles(articles)
+        print(f"Found {len(articles)} top articles.")
+
+    asyncio.run(_top())
 
 
 def print_articles(articles):

google_news_trends_mcp/news.py

@@ -16,8 +16,7 @@ import cloudscraper
 from playwright.async_api import async_playwright, Browser, Playwright
 from trendspy import Trends, TrendKeyword
 from typing import Optional, cast, overload, Literal, Awaitable
-import atexit
-from contextlib import asynccontextmanager
+from contextlib import asynccontextmanager, AsyncContextDecorator
 import logging
 from collections.abc import Callable
 
@@ -49,40 +48,60 @@ google_news = GNews(
     # exclude_websites=[],
 )
 
-playwright: Optional[Playwright] = None
-browser: Optional[Browser] = None
-
 ProgressCallback = Callable[[float, Optional[float]], Awaitable[None]]
 
 
-async def startup_browser():
-    global playwright, browser
-    playwright = await async_playwright().start()
-    browser = await playwright.chromium.launch(headless=True)
-
-
-@atexit.register
-def shutdown_browser():
-    if browser:
-        asyncio.run(browser.close())
-    if playwright:
-        asyncio.run(playwright.stop())
-
-
-async def get_browser() -> Browser:
-    if browser is None:
-        await startup_browser()
-    return cast(Browser, browser)
-
-
-@asynccontextmanager
-async def browser_context():
-    context = await (await get_browser()).new_context()
-    try:
-        yield context
-    finally:
-        logging.debug("Closing browser context...")
-        await context.close()
+class BrowserManager(AsyncContextDecorator):
+    playwright: Optional[Playwright] = None
+    browser: Optional[Browser] = None
+    _lock = asyncio.Lock()
+
+    @classmethod
+    async def _get_browser(cls) -> Browser:
+        if cls.browser is None:
+            async with cls._lock:
+                if cls.browser is None:
+                    logger.info("Starting browser...")
+                    try:
+                        cls.playwright = await async_playwright().start()
+                        cls.browser = await cls.playwright.chromium.launch(headless=True)
+                    except Exception as e:
+                        logger.critical("Browser startup failed", exc_info=e)
+                        raise SystemExit(1)
+        return cast(Browser, cls.browser)
+
+
+    @classmethod
+    async def _shutdown(cls):
+        logger.info("Shutting down browser...")
+        if cls.browser:
+            await cls.browser.close()
+            cls.browser = None
+        if cls.playwright:
+            await cls.playwright.stop()
+            cls.playwright = None
+
+    @classmethod
+    def browser_context(cls):
+        @asynccontextmanager
+        async def _browser_context_cm():
+            browser_inst = await cls._get_browser()
+            context = await browser_inst.new_context()
+            logger.debug("Created browser context...")
+            try:
+                yield context
+            finally:
+                logger.debug("Closing browser context...")
+                await context.close()
+
+        return _browser_context_cm()
+
+    async def __aenter__(self):
+        return self
+
+    async def __aexit__(self, *exc):
+        await self._shutdown()
+        return False
 
 
 async def download_article_with_playwright(url) -> newspaper.Article | None:
@@ -90,7 +109,7 @@ async def download_article_with_playwright(url) -> newspaper.Article | None:
     Download an article using Playwright to handle complex websites (async).
     """
     try:
-        async with browser_context() as context:
+        async with BrowserManager.browser_context() as context:
             page = await context.new_page()
             await page.goto(url, wait_until="domcontentloaded")
             await asyncio.sleep(2)  # Wait for the page to load completely
@@ -98,7 +117,7 @@ async def download_article_with_playwright(url) -> newspaper.Article | None:
             article = newspaper.article(url, input_html=content)
             return article
     except Exception as e:
-        logging.warning(f"Error downloading article with Playwright from {url}\n {e.args}")
+        logger.warning(f"Error downloading article with Playwright from {url}\n {e.args}")
         return None
 
 
@@ -107,18 +126,18 @@ def download_article_with_scraper(url) -> newspaper.Article | None:
     try:
         article = newspaper.article(url)
     except Exception as e:
-        logging.debug(f"Error downloading article with newspaper from {url}\n {e.args}")
+        logger.debug(f"Error downloading article with newspaper from {url}\n {e.args}")
         try:
             # Retry with cloudscraper
             response = scraper.get(url)
             if response.status_code < 400:
                 article = newspaper.article(url, input_html=response.text)
             else:
-                logging.debug(
+                logger.debug(
                     f"Failed to download article with cloudscraper from {url}, status code: {response.status_code}"
                 )
         except Exception as e:
-            logging.debug(f"Error downloading article with cloudscraper from {url}\n {e.args}")
+            logger.debug(f"Error downloading article with cloudscraper from {url}\n {e.args}")
     return article
 
 
@@ -129,10 +148,10 @@ def decode_url(url: str) -> str:
             if decoded_url.get("status"):
                 url = decoded_url["decoded_url"]
             else:
-                logging.debug("Failed to decode Google News RSS link:")
+                logger.debug("Failed to decode Google News RSS link:")
                 return ""
         except Exception as err:
-            logging.warning(f"Error while decoding url {url}\n {err.args}")
+            logger.warning(f"Error while decoding url {url}\n {err.args}")
     return url
 
 
@@ -144,6 +163,7 @@ async def download_article(url: str) -> newspaper.Article | None:
         return None
     article = download_article_with_scraper(url)
     if article is None or not article.text:
+        logger.debug("Attempting to download article with playwright")
         article = await download_article_with_playwright(url)
     return article
 
@@ -162,7 +182,7 @@ async def process_gnews_articles(
     for idx, gnews_article in enumerate(gnews_articles):
         article = await download_article(gnews_article["url"])
         if article is None or not article.text:
-            logging.debug(f"Failed to download article from {gnews_article['url']}:\n{article}")
+            logger.debug(f"Failed to download article from {gnews_article['url']}:\n{article}")
             continue
         article.parse()
         if nlp:
@@ -187,7 +207,7 @@ async def get_news_by_keyword(
     google_news.max_results = max_results
     gnews_articles = google_news.get_news(keyword)
     if not gnews_articles:
-        logging.debug(f"No articles found for keyword '{keyword}' in the last {period} days.")
+        logger.debug(f"No articles found for keyword '{keyword}' in the last {period} days.")
         return []
     return await process_gnews_articles(gnews_articles, nlp=nlp, report_progress=report_progress)
 
@@ -205,7 +225,7 @@ async def get_top_news(
     google_news.max_results = max_results
     gnews_articles = google_news.get_top_news()
     if not gnews_articles:
-        logging.debug("No top news articles found.")
+        logger.debug("No top news articles found.")
         return []
     return await process_gnews_articles(gnews_articles, nlp=nlp, report_progress=report_progress)
 
@@ -217,13 +237,12 @@ async def get_news_by_location(
     nlp: bool = True,
     report_progress: Optional[ProgressCallback] = None,
 ) -> list[newspaper.Article]:
-    """Find articles by location using Google News.
-    """
+    """Find articles by location using Google News."""
     google_news.period = f"{period}d"
     google_news.max_results = max_results
     gnews_articles = google_news.get_news_by_location(location)
     if not gnews_articles:
-        logging.debug(f"No articles found for location '{location}' in the last {period} days.")
+        logger.debug(f"No articles found for location '{location}' in the last {period} days.")
         return []
     return await process_gnews_articles(gnews_articles, nlp=nlp, report_progress=report_progress)
 
@@ -250,7 +269,7 @@ async def get_news_by_topic(
     google_news.max_results = max_results
     gnews_articles = google_news.get_news_by_topic(topic)
     if not gnews_articles:
-        logging.debug(f"No articles found for topic '{topic}' in the last {period} days.")
+        logger.debug(f"No articles found for topic '{topic}' in the last {period} days.")
         return []
     return await process_gnews_articles(gnews_articles, nlp=nlp, report_progress=report_progress)
 
@@ -282,7 +301,7 @@ async def get_trending_terms(
             return [{"keyword": trend.keyword, "volume": trend.volume} for trend in trends]
         return trends
     except Exception as e:
-        logging.warning(f"Error fetching trending terms: {e}")
+        logger.warning(f"Error fetching trending terms: {e}")
         return []
 
 
@@ -330,4 +349,4 @@ def save_article_to_json(article: newspaper.Article, filename: str = "") -> None
             filename += ".json"
     with open(filename, "w") as f:
         json.dump(article_data, f, indent=4)
-    logging.debug(f"Article saved to {filename}")
+    logger.debug(f"Article saved to {filename}")

google_news_trends_mcp/server.py

@@ -7,8 +7,10 @@ from fastmcp.server.middleware.error_handling import ErrorHandlingMiddleware
 from mcp.types import TextContent
 from pydantic import BaseModel, Field, model_serializer
 from google_news_trends_mcp import news
+from google_news_trends_mcp.news import BrowserManager
 from newspaper import settings as newspaper_settings
 from newspaper.article import Article
+from contextlib import asynccontextmanager
 
 
 class BaseModelClean(BaseModel):
@@ -82,9 +84,16 @@ class TrendingTermOut(BaseModelClean):
     normalized_keyword: Annotated[Optional[str], Field(description="Normalized form of the keyword.")] = None
 
 
+@asynccontextmanager
+async def lifespan(app: FastMCP):
+    async with BrowserManager():
+        yield
+
+
 mcp = FastMCP(
     name="google-news-trends",
     instructions="This server provides tools to search, analyze, and summarize Google News articles and Google Trends",
+    lifespan=lifespan,
     on_duplicate_tools="replace",
 )
 
@@ -145,6 +154,19 @@ async def summarize_article(article: Article, ctx: Context) -> None:
         article.summary = "No summary available."
 
 
+async def summarize_articles(articles: list[Article], ctx: Context) -> None:
+    total_articles = len(articles)
+    try:
+        for idx, article in enumerate(articles):
+            await summarize_article(article, ctx)
+            await ctx.report_progress(idx, total_articles)
+    except Exception as err:
+        await ctx.debug(f"Failed to use LLM sampling for article summary:\n{err.args}")
+        for idx, article in enumerate(articles):
+            article.nlp()
+            await ctx.report_progress(idx, total_articles)
+
+
 @mcp.tool(
     description=news.get_news_by_keyword.__doc__,
     tags={"news", "articles", "keyword"},
@@ -176,16 +198,7 @@ async def get_news_by_keyword(
         report_progress=ctx.report_progress,
     )
     if summarize:
-        total_articles = len(articles)
-        try:
-            for idx, article in enumerate(articles):
-                await summarize_article(article, ctx)
-                await ctx.report_progress(idx, total_articles)
-        except Exception as err:
-            await ctx.debug(f"Failed to use LLM sampling for article summary:\n{err.args}")
-            for idx, article in enumerate(articles):
-                article.nlp()
-                await ctx.report_progress(idx, total_articles)
+        await summarize_articles(articles, ctx)
     await ctx.report_progress(progress=len(articles), total=len(articles))
     return [ArticleOut(**a.to_json(False)) for a in articles]
 
@@ -221,16 +234,7 @@ async def get_news_by_location(
         report_progress=ctx.report_progress,
     )
     if summarize:
-        total_articles = len(articles)
-        try:
-            for idx, article in enumerate(articles):
-                await summarize_article(article, ctx)
-                await ctx.report_progress(idx, total_articles)
-        except Exception as err:
-            await ctx.debug(f"Failed to use LLM sampling for article summary:\n{err.args}")
-            for idx, article in enumerate(articles):
-                article.nlp()
-                await ctx.report_progress(idx, total_articles)
+        await summarize_articles(articles, ctx)
     await ctx.report_progress(progress=len(articles), total=len(articles))
     return [ArticleOut(**a.to_json(False)) for a in articles]
 
@@ -263,17 +267,7 @@ async def get_news_by_topic(
         report_progress=ctx.report_progress,
     )
     if summarize:
-        total_articles = len(articles)
-        try:
-            for idx, article in enumerate(articles):
-                await summarize_article(article, ctx)
-                await ctx.report_progress(idx, total_articles)
-        except Exception as err:
-            await ctx.debug(f"Failed to use LLM sampling for article summary:\n{err.args}")
-            for idx, article in enumerate(articles):
-                article.nlp()
-                await ctx.report_progress(idx, total_articles)
-
+        await summarize_articles(articles, ctx)
     await ctx.report_progress(progress=len(articles), total=len(articles))
     return [ArticleOut(**a.to_json(False)) for a in articles]
 
@@ -304,17 +298,7 @@ async def get_top_news(
         report_progress=ctx.report_progress,
     )
     if summarize:
-        total_articles = len(articles)
-        try:
-            for idx, article in enumerate(articles):
-                await summarize_article(article, ctx)
-                await ctx.report_progress(idx, total_articles)
-        except Exception as err:
-            await ctx.debug(f"Failed to use LLM sampling for article summary:\n{err.args}")
-            for idx, article in enumerate(articles):
-                article.nlp()
-                await ctx.report_progress(idx, total_articles)
-
+        await summarize_articles(articles, ctx)
     await ctx.report_progress(progress=len(articles), total=len(articles))
     return [ArticleOut(**a.to_json(False)) for a in articles]
 
@@ -328,11 +312,9 @@ async def get_trending_terms(
     ] = False,
     max_results: Annotated[int, Field(description="Maximum number of results to return.", ge=1)] = 100,
 ) -> list[TrendingTermOut]:
-
     if not full_data:
         trends = await news.get_trending_terms(geo=geo, full_data=False, max_results=max_results)
         return [TrendingTermOut(keyword=str(tt["keyword"]), volume=tt["volume"]) for tt in trends]
-
     trends = await news.get_trending_terms(geo=geo, full_data=True, max_results=max_results)
     return [TrendingTermOut(**tt.__dict__) for tt in trends]
 

{google_news_trends_mcp-0.1.10.dist-info → google_news_trends_mcp-0.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: google-news-trends-mcp
-Version: 0.1.10
+Version: 0.2.1
 Summary: An MCP server to access Google News and Google Trends.
 Author-email: Jesse Manek <jesse.manek@gmail.com>
 License-Expression: MIT
@@ -22,14 +22,12 @@ Requires-Dist: newspaper4k>=0.9.3.1
 Requires-Dist: nltk>=3.9.1
 Requires-Dist: playwright>=1.53.0
 Requires-Dist: pydantic>=2.11.7
-Requires-Dist: pytest>=8.4.1
-Requires-Dist: pytest-asyncio>=1.0.0
 Requires-Dist: trendspy>=0.1.6
 Dynamic: license-file
 
 # Google News Trends MCP
 
-An MCP server to access Google News and Google Trends.  Does not rely on any paid APIs.  
+An MCP server to access Google News and Google Trends.
 
 ## Features
 

google_news_trends_mcp-0.2.1.dist-info/RECORD

@@ -0,0 +1,11 @@
+google_news_trends_mcp/__init__.py,sha256=nDWNd6_TSf4vDQuHVBoAf4QfZCB3ZUFQ0M7XvifNJ-g,78
+google_news_trends_mcp/__main__.py,sha256=ysiAk_xpnnW3lrLlzdIQQa71tuGBRT8WocbecBsY2Fs,87
+google_news_trends_mcp/cli.py,sha256=3Z916898HXTigmQYEfvb7ybfbuUE7bjMC6yjT5-l6u0,4558
+google_news_trends_mcp/news.py,sha256=EhTIqRmFOQKAhyV8rLySaPoILX3uyKbrzO6jxo89FhA,12528
+google_news_trends_mcp/server.py,sha256=ZFZvCxSVLma7QlanFsXyu6gpCHZSS0y5YfnZl7HnXnc,13780
+google_news_trends_mcp-0.2.1.dist-info/licenses/LICENSE,sha256=5dsv2ZI5EZIer0a9MktVmILVrlp5vqH_0tPIe3bRLgE,1067
+google_news_trends_mcp-0.2.1.dist-info/METADATA,sha256=AdnEqmflIhFNUV052z9VHIOum2x0_TzI_e3hK84vdfM,4419
+google_news_trends_mcp-0.2.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+google_news_trends_mcp-0.2.1.dist-info/entry_points.txt,sha256=eVT3xd6YJQgsWAUBwhnffuwhXNF7yyt_uco6fjBy-1o,130
+google_news_trends_mcp-0.2.1.dist-info/top_level.txt,sha256=RFheDbzhNnEV_Y3iFNm7jhRhY1P1wQgfiYqVpXCTD_U,23
+google_news_trends_mcp-0.2.1.dist-info/RECORD,,

google_news_trends_mcp-0.1.10.dist-info/RECORD

@@ -1,11 +0,0 @@
-google_news_trends_mcp/__init__.py,sha256=NkmudPEEuKk8Geah4EtzeEHQ-ChqR66lZEO5VrMwXNo,77
-google_news_trends_mcp/__main__.py,sha256=ysiAk_xpnnW3lrLlzdIQQa71tuGBRT8WocbecBsY2Fs,87
-google_news_trends_mcp/cli.py,sha256=-Cith02x6-9o91rXpgMM0lrhArPDMB9d3h8AAE1rimw,3959
-google_news_trends_mcp/news.py,sha256=wmFzikDEx_HNVO0vm84gnkgV-LZBOAuW7mNr2uhurEE,11524
-google_news_trends_mcp/server.py,sha256=h8GP_XUPqiPw4vFu1jy9MFv0i384rBARePvm15YOZJo,14807
-google_news_trends_mcp-0.1.10.dist-info/licenses/LICENSE,sha256=5dsv2ZI5EZIer0a9MktVmILVrlp5vqH_0tPIe3bRLgE,1067
-google_news_trends_mcp-0.1.10.dist-info/METADATA,sha256=rbYqd15smnZA0sgOU4Fk6iqvsr8h638U69Ki4VRMddI,4521
-google_news_trends_mcp-0.1.10.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-google_news_trends_mcp-0.1.10.dist-info/entry_points.txt,sha256=eVT3xd6YJQgsWAUBwhnffuwhXNF7yyt_uco6fjBy-1o,130
-google_news_trends_mcp-0.1.10.dist-info/top_level.txt,sha256=RFheDbzhNnEV_Y3iFNm7jhRhY1P1wQgfiYqVpXCTD_U,23
-google_news_trends_mcp-0.1.10.dist-info/RECORD,,