google-news-trends-mcp 0.1.9__py3-none-any.whl → 0.2.0__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
 
@@ -55,34 +54,56 @@ 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:
+                    await cls._startup()
+        return cast(Browser, cls.browser)
+
+    @classmethod
+    async def _startup(cls):
+        logger.info("Starting browser...")
+        cls.playwright = await async_playwright().start()
+        cls.browser = await cls.playwright.chromium.launch(headless=True)
+
+    @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()
+            logging.debug("Created browser context...")
+            try:
+                yield context
+            finally:
+                logging.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 +111,7 @@ 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
@@ -144,6 +165,7 @@ 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
 
@@ -182,10 +204,6 @@ async def get_news_by_keyword(
 ) -> list[newspaper.Article]:
     """
     Find articles by keyword using Google News.
-    keyword: is the search term to find articles.
-    period: is the number of days to look back for articles.
-    max_results: is the maximum number of results to return.
-    nlp: If True, will perform NLP on the articles to extract keywords and summary.
     """
     google_news.period = f"{period}d"
     google_news.max_results = max_results
@@ -204,9 +222,6 @@ async def get_top_news(
 ) -> list[newspaper.Article]:
     """
     Get top news stories from Google News.
-    period: is the number of days to look back for top articles.
-    max_results: is the maximum number of results to return.
-    nlp: If True, will perform NLP on the articles to extract keywords and summary.
     """
     google_news.period = f"{period}d"
     google_news.max_results = max_results
@@ -224,12 +239,7 @@ async def get_news_by_location(
     nlp: bool = True,
     report_progress: Optional[ProgressCallback] = None,
 ) -> list[newspaper.Article]:
-    """Find articles by location using Google News.
-    location: is the name of city/state/country
-    period: is the number of days to look back for articles.
-    max_results: is the maximum number of results to return.
-    nlp: If True, will perform NLP on the articles to extract keywords and summary.
-    """
+    """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)
@@ -256,9 +266,6 @@ async def get_news_by_topic(
     PUBLIC HEALTH, MENTAL HEALTH, MEDICINE, SPACE, WILDLIFE, ENVIRONMENT, NEUROSCIENCE, PHYSICS,
     GEOLOGY, PALEONTOLOGY, SOCIAL SCIENCES, EDUCATION, JOBS, ONLINE EDUCATION, HIGHER EDUCATION,
     VEHICLES, ARTS-DESIGN, BEAUTY, FOOD, TRAVEL, SHOPPING, HOME, OUTDOORS, FASHION.
-    period: is the number of days to look back for articles.
-    max_results: is the maximum number of results to return.
-    nlp: If True, will perform NLP on the articles to extract keywords and summary.
     """
     google_news.period = f"{period}d"
     google_news.max_results = max_results
@@ -288,10 +295,6 @@ async def get_trending_terms(
 ) -> list[dict[str, int]] | list[TrendKeyword]:
     """
     Returns google trends for a specific geo location.
-    Default is US.
-    geo: is the country code, e.g. 'US', 'GB', 'IN', etc.
-    full_data: if True, returns full data for each trend, otherwise returns only the trend and volume.
-    max_results: is the maximum number of results to return, default is 100.
     """
     try:
         trends = list(tr.trending_now(geo=geo))

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",
 )
 
@@ -328,7 +337,6 @@ 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]

{google_news_trends_mcp-0.1.9.dist-info → google_news_trends_mcp-0.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: google-news-trends-mcp
-Version: 0.1.9
+Version: 0.2.0
 Summary: An MCP server to access Google News and Google Trends.
 Author-email: Jesse Manek <jesse.manek@gmail.com>
 License-Expression: MIT
@@ -22,8 +22,6 @@ 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-0.2.0.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=MPNZlzI7KXkhQ2uj7233N2i9kFHGUgGMdRBCAbj-B44,12471
+google_news_trends_mcp/server.py,sha256=S-tlFY1wiFm9VPeb4NDnV0NGtczaQDmx20kIrZZQHto,15031
+google_news_trends_mcp-0.2.0.dist-info/licenses/LICENSE,sha256=5dsv2ZI5EZIer0a9MktVmILVrlp5vqH_0tPIe3bRLgE,1067
+google_news_trends_mcp-0.2.0.dist-info/METADATA,sha256=rok_3L-eDVXQJSuG6ze1Vuicnh-kpcWyJxaF2DbqZ1s,4454
+google_news_trends_mcp-0.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+google_news_trends_mcp-0.2.0.dist-info/entry_points.txt,sha256=eVT3xd6YJQgsWAUBwhnffuwhXNF7yyt_uco6fjBy-1o,130
+google_news_trends_mcp-0.2.0.dist-info/top_level.txt,sha256=RFheDbzhNnEV_Y3iFNm7jhRhY1P1wQgfiYqVpXCTD_U,23
+google_news_trends_mcp-0.2.0.dist-info/RECORD,,

google_news_trends_mcp-0.1.9.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=CpNIOJ4NA-BFmiE0d4Jadn20apMTf8vNDMsqZjFVl6A,12707
-google_news_trends_mcp/server.py,sha256=h8GP_XUPqiPw4vFu1jy9MFv0i384rBARePvm15YOZJo,14807
-google_news_trends_mcp-0.1.9.dist-info/licenses/LICENSE,sha256=5dsv2ZI5EZIer0a9MktVmILVrlp5vqH_0tPIe3bRLgE,1067
-google_news_trends_mcp-0.1.9.dist-info/METADATA,sha256=t76FntOxc0t_CFvzcaWB0lVdXmcv5J9SnLCcIYMwcfY,4520
-google_news_trends_mcp-0.1.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-google_news_trends_mcp-0.1.9.dist-info/entry_points.txt,sha256=eVT3xd6YJQgsWAUBwhnffuwhXNF7yyt_uco6fjBy-1o,130
-google_news_trends_mcp-0.1.9.dist-info/top_level.txt,sha256=RFheDbzhNnEV_Y3iFNm7jhRhY1P1wQgfiYqVpXCTD_U,23
-google_news_trends_mcp-0.1.9.dist-info/RECORD,,