google-news-trends-mcp 0.1.5__py3-none-any.whl → 0.1.7__py3-none-any.whl

google_news_trends_mcp/news.py

@@ -17,10 +17,11 @@ import cloudscraper
 from playwright.async_api import async_playwright, Browser, Playwright
 from trendspy import Trends, TrendKeyword
 import click
-from typing import Optional, cast
+from typing import Optional, cast, overload, Literal, Awaitable
 import atexit
 from contextlib import asynccontextmanager
 import logging
+from collections.abc import Callable
 
 logger = logging.getLogger(__name__)
 
@@ -53,6 +54,8 @@ google_news = GNews(
 playwright: Optional[Playwright] = None
 browser: Optional[Browser] = None
 
+ProgressCallback = Callable[[float, Optional[float]], Awaitable[None]]
+
 
 async def startup_browser():
     global playwright, browser
@@ -97,7 +100,9 @@ async def download_article_with_playwright(url) -> newspaper.Article | None:
             article = newspaper.article(url, input_html=content, language="en")
             return article
     except Exception as e:
-        logging.warning(f"Error downloading article with Playwright from {url}\n {e.args}")
+        logging.warning(
+            f"Error downloading article with Playwright from {url}\n {e.args}"
+        )
         return None
 
 
@@ -130,7 +135,9 @@ async def download_article(url: str, nlp: bool = True) -> newspaper.Article | No
                     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}")
+            logging.debug(
+                f"Error downloading article with cloudscraper from {url}\n {e.args}"
+            )
 
     try:
         if article is None or not article.text:
@@ -148,23 +155,35 @@ async def download_article(url: str, nlp: bool = True) -> newspaper.Article | No
 
 
 async def process_gnews_articles(
-    gnews_articles: list[dict], nlp: bool = True
-) -> list["newspaper.Article"]:
+    gnews_articles: list[dict],
+    nlp: bool = True,
+    report_progress: Optional[ProgressCallback] = None,
+) -> list[newspaper.Article]:
     """
     Process a list of Google News articles and download them (async).
+    Optionally report progress via report_progress callback.
     """
     articles = []
-    for gnews_article in gnews_articles:
+    total = len(gnews_articles)
+    for idx, gnews_article in enumerate(gnews_articles):
         article = await download_article(gnews_article["url"], nlp=nlp)
         if article is None or not article.text:
-            logging.debug(f"Failed to download article from {gnews_article['url']}:\n{article}")
+            logging.debug(
+                f"Failed to download article from {gnews_article['url']}:\n{article}"
+            )
             continue
         articles.append(article)
+        if report_progress:
+            await report_progress(idx, total)
     return articles
 
 
 async def get_news_by_keyword(
-    keyword: str, period=7, max_results: int = 10, nlp: bool = True
+    keyword: str,
+    period=7,
+    max_results: int = 10,
+    nlp: bool = True,
+    report_progress: Optional[ProgressCallback] = None,
 ) -> list[newspaper.Article]:
     """
     Find articles by keyword using Google News.
@@ -177,14 +196,21 @@ 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.")
+        logging.debug(
+            f"No articles found for keyword '{keyword}' in the last {period} days."
+        )
         return []
-    return await process_gnews_articles(gnews_articles, nlp=nlp)
+    return await process_gnews_articles(
+        gnews_articles, nlp=nlp, report_progress=report_progress
+    )
 
 
 async def get_top_news(
-    period: int = 3, max_results: int = 10, nlp: bool = True
-) -> list["newspaper.Article"]:
+    period: int = 3,
+    max_results: int = 10,
+    nlp: bool = True,
+    report_progress: Optional[ProgressCallback] = None,
+) -> list[newspaper.Article]:
     """
     Get top news stories from Google News.
     period: is the number of days to look back for top articles.
@@ -197,11 +223,17 @@ async def get_top_news(
     if not gnews_articles:
         logging.debug("No top news articles found.")
         return []
-    return await process_gnews_articles(gnews_articles, nlp=nlp)
+    return await process_gnews_articles(
+        gnews_articles, nlp=nlp, report_progress=report_progress
+    )
 
 
 async def get_news_by_location(
-    location: str, period=7, max_results: int = 10, nlp: bool = True
+    location: str,
+    period=7,
+    max_results: int = 10,
+    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
@@ -213,13 +245,21 @@ async def get_news_by_location(
     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.")
+        logging.debug(
+            f"No articles found for location '{location}' in the last {period} days."
+        )
         return []
-    return await process_gnews_articles(gnews_articles, nlp=nlp)
+    return await process_gnews_articles(
+        gnews_articles, nlp=nlp, report_progress=report_progress
+    )
 
 
 async def get_news_by_topic(
-    topic: str, period=7, max_results: int = 10, nlp: bool = True
+    topic: str,
+    period=7,
+    max_results: int = 10,
+    nlp: bool = True,
+    report_progress: Optional[ProgressCallback] = None,
 ) -> list[newspaper.Article]:
     """Find articles by topic using Google News.
     topic is one of
@@ -239,9 +279,27 @@ 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.")
+        logging.debug(
+            f"No articles found for topic '{topic}' in the last {period} days."
+        )
         return []
-    return await process_gnews_articles(gnews_articles, nlp=nlp)
+    return await process_gnews_articles(
+        gnews_articles, nlp=nlp, report_progress=report_progress
+    )
+
+
+@overload
+async def get_trending_terms(
+    geo: str = "US", full_data: Literal[False] = False, max_results: int = 100
+) -> list[dict[str, int]]:
+    pass
+
+
+@overload
+async def get_trending_terms(
+    geo: str = "US", full_data: Literal[True] = True, max_results: int = 100
+) -> list[TrendKeyword]:
+    pass
 
 
 async def get_trending_terms(
@@ -260,7 +318,9 @@ async def get_trending_terms(
             :max_results
         ]
         if not full_data:
-            return [{"keyword": trend.keyword, "volume": trend.volume} for trend in trends]
+            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}")

google_news_trends_mcp/server.py

@@ -1,10 +1,11 @@
-from fastmcp import FastMCP
+from fastmcp import FastMCP, Context
 from fastmcp.exceptions import ToolError
 from fastmcp.server.dependencies import get_context
 from pydantic import BaseModel, Field
 from typing import Optional
 from google_news_trends_mcp import news
 from typing import Annotated
+from newspaper import settings as newspaper_settings
 from fastmcp.server.middleware.timing import TimingMiddleware
 from fastmcp.server.middleware.logging import LoggingMiddleware
 from fastmcp.server.middleware.rate_limiting import RateLimitingMiddleware
@@ -132,11 +133,49 @@ mcp.add_middleware(TimingMiddleware())  # Time actual execution
 mcp.add_middleware(LoggingMiddleware())  # Log everything
 
 
+# Configure newspaper settings for article extraction
+def set_newspaper_article_fields(full_data: bool = False):
+    if full_data:
+        newspaper_settings.article_json_fields = [
+            "url",
+            "read_more_link",
+            "language",
+            "title",
+            "top_image",
+            "meta_img",
+            "images",
+            "movies",
+            "keywords",
+            "keyword_scores",
+            "meta_keywords",
+            "tags",
+            "authors",
+            "publish_date",
+            "summary",
+            "meta_description",
+            "meta_lang",
+            "meta_favicon",
+            "meta_site_name",
+            "canonical_link",
+            "text",
+        ]
+    else:
+        newspaper_settings.article_json_fields = [
+            "url",
+            "title",
+            "text",
+            "publish_date",
+            "summary",
+            "keywords",
+        ]
+
+
 @mcp.tool(
     description=news.get_news_by_keyword.__doc__,
     tags={"news", "articles", "keyword"},
 )
 async def get_news_by_keyword(
+    ctx: Context,
     keyword: Annotated[str, Field(description="Search term to find articles.")],
     period: Annotated[
         int, Field(description="Number of days to look back for articles.", ge=1)
@@ -146,14 +185,20 @@ async def get_news_by_keyword(
     ] = 10,
     nlp: Annotated[
         bool, Field(description="Whether to perform NLP on the articles.")
-    ] = True,
+    ] = False,
+    full_data: Annotated[
+        bool, Field(description="Return full data for each article.")
+    ] = False,
 ) -> list[ArticleOut]:
+    set_newspaper_article_fields(full_data)
     articles = await news.get_news_by_keyword(
         keyword=keyword,
         period=period,
         max_results=max_results,
         nlp=nlp,
+        report_progress=ctx.report_progress,
     )
+    await ctx.report_progress(progress=len(articles), total=len(articles))
     return [ArticleOut(**a.to_json(False)) for a in articles]
 
 
@@ -162,6 +207,7 @@ async def get_news_by_keyword(
     tags={"news", "articles", "location"},
 )
 async def get_news_by_location(
+    ctx: Context,
     location: Annotated[str, Field(description="Name of city/state/country.")],
     period: Annotated[
         int, Field(description="Number of days to look back for articles.", ge=1)
@@ -171,14 +217,20 @@ async def get_news_by_location(
     ] = 10,
     nlp: Annotated[
         bool, Field(description="Whether to perform NLP on the articles.")
-    ] = True,
+    ] = False,
+    full_data: Annotated[
+        bool, Field(description="Return full data for each article.")
+    ] = False,
 ) -> list[ArticleOut]:
+    set_newspaper_article_fields(full_data)
     articles = await news.get_news_by_location(
         location=location,
         period=period,
         max_results=max_results,
         nlp=nlp,
+        report_progress=ctx.report_progress,
     )
+    await ctx.report_progress(progress=len(articles), total=len(articles))
     return [ArticleOut(**a.to_json(False)) for a in articles]
 
 
@@ -186,6 +238,7 @@ async def get_news_by_location(
     description=news.get_news_by_topic.__doc__, tags={"news", "articles", "topic"}
 )
 async def get_news_by_topic(
+    ctx: Context,
     topic: Annotated[str, Field(description="Topic to search for articles.")],
     period: Annotated[
         int, Field(description="Number of days to look back for articles.", ge=1)
@@ -195,19 +248,26 @@ async def get_news_by_topic(
     ] = 10,
     nlp: Annotated[
         bool, Field(description="Whether to perform NLP on the articles.")
-    ] = True,
+    ] = False,
+    full_data: Annotated[
+        bool, Field(description="Return full data for each article.")
+    ] = False,
 ) -> list[ArticleOut]:
+    set_newspaper_article_fields(full_data)
     articles = await news.get_news_by_topic(
         topic=topic,
         period=period,
         max_results=max_results,
         nlp=nlp,
+        report_progress=ctx.report_progress,
     )
+    await ctx.report_progress(progress=len(articles), total=len(articles))
     return [ArticleOut(**a.to_json(False)) for a in articles]
 
 
 @mcp.tool(description=news.get_top_news.__doc__, tags={"news", "articles", "top"})
 async def get_top_news(
+    ctx: Context,
     period: Annotated[
         int, Field(description="Number of days to look back for top articles.", ge=1)
     ] = 3,
@@ -216,13 +276,19 @@ async def get_top_news(
     ] = 10,
     nlp: Annotated[
         bool, Field(description="Whether to perform NLP on the articles.")
-    ] = True,
+    ] = False,
+    full_data: Annotated[
+        bool, Field(description="Return full data for each article.")
+    ] = False,
 ) -> list[ArticleOut]:
+    set_newspaper_article_fields(full_data)
     articles = await news.get_top_news(
         period=period,
         max_results=max_results,
         nlp=nlp,
+        report_progress=ctx.report_progress,
     )
+    await ctx.report_progress(progress=len(articles), total=len(articles))
     return [ArticleOut(**a.to_json(False)) for a in articles]
 
 
@@ -243,8 +309,18 @@ async def get_trending_terms(
         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=full_data, max_results=max_results
+        geo=geo, full_data=True, max_results=max_results
     )
     return [TrendingTermOut(**tt.__dict__) for tt in trends]
 

{google_news_trends_mcp-0.1.5.dist-info → google_news_trends_mcp-0.1.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: google-news-trends-mcp
-Version: 0.1.5
+Version: 0.1.7
 Summary: An MCP server to access Google News and Google Trends.
 Author-email: Jesse Manek <jesse.manek@gmail.com>
 License-Expression: MIT
@@ -30,7 +30,6 @@ Dynamic: license-file
 # Google News Trends MCP
 
 An MCP server to access Google News and Google Trends.  Does not rely on any paid APIs.  
-The returned data currently uses a lot of tokens, so it is recommended to always use limits when making requests.  
 
 ## Features
 

google_news_trends_mcp-0.1.7.dist-info/RECORD

@@ -0,0 +1,11 @@
+google_news_trends_mcp/__init__.py,sha256=J9O5WNvC9cNDaxecveSUvzLGOXOYO-pCHbiGopfYoIc,76
+google_news_trends_mcp/__main__.py,sha256=ysiAk_xpnnW3lrLlzdIQQa71tuGBRT8WocbecBsY2Fs,87
+google_news_trends_mcp/cli.py,sha256=XJNnRVpDXX2MCb8dPfDcQJWYYA4CxTuxbhvpJGeVQgs,4133
+google_news_trends_mcp/news.py,sha256=2xmlwe4txaqiB8MljbhbBLmpb6tM35autGJVQ144k0s,13107
+google_news_trends_mcp/server.py,sha256=7hau48vQr_a2YbLgz4MqkwsTHMuSIU8jYEkjInID4gY,11553
+google_news_trends_mcp-0.1.7.dist-info/licenses/LICENSE,sha256=5dsv2ZI5EZIer0a9MktVmILVrlp5vqH_0tPIe3bRLgE,1067
+google_news_trends_mcp-0.1.7.dist-info/METADATA,sha256=qkJh_vuB7gIH2Pp0TorRH_9J6ZvkKmU4JOvjsZqwtoY,4464
+google_news_trends_mcp-0.1.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+google_news_trends_mcp-0.1.7.dist-info/entry_points.txt,sha256=eVT3xd6YJQgsWAUBwhnffuwhXNF7yyt_uco6fjBy-1o,130
+google_news_trends_mcp-0.1.7.dist-info/top_level.txt,sha256=RFheDbzhNnEV_Y3iFNm7jhRhY1P1wQgfiYqVpXCTD_U,23
+google_news_trends_mcp-0.1.7.dist-info/RECORD,,

google_news_trends_mcp-0.1.5.dist-info/RECORD

@@ -1,11 +0,0 @@
-google_news_trends_mcp/__init__.py,sha256=J9O5WNvC9cNDaxecveSUvzLGOXOYO-pCHbiGopfYoIc,76
-google_news_trends_mcp/__main__.py,sha256=ysiAk_xpnnW3lrLlzdIQQa71tuGBRT8WocbecBsY2Fs,87
-google_news_trends_mcp/cli.py,sha256=XJNnRVpDXX2MCb8dPfDcQJWYYA4CxTuxbhvpJGeVQgs,4133
-google_news_trends_mcp/news.py,sha256=FYz1guxLZThMmh_9uN3VcdHBjLHZF5brhk7Bw7QxeDo,11780
-google_news_trends_mcp/server.py,sha256=4l1cslLvQ2gdldRK6DTPmlaO37iLublBT9Y5_9nBj2o,9114
-google_news_trends_mcp-0.1.5.dist-info/licenses/LICENSE,sha256=5dsv2ZI5EZIer0a9MktVmILVrlp5vqH_0tPIe3bRLgE,1067
-google_news_trends_mcp-0.1.5.dist-info/METADATA,sha256=yKcgFJVdy-3o_Ox-F8r0xEbCTZ9ToQJXTlD53JkYtyo,4580
-google_news_trends_mcp-0.1.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-google_news_trends_mcp-0.1.5.dist-info/entry_points.txt,sha256=eVT3xd6YJQgsWAUBwhnffuwhXNF7yyt_uco6fjBy-1o,130
-google_news_trends_mcp-0.1.5.dist-info/top_level.txt,sha256=RFheDbzhNnEV_Y3iFNm7jhRhY1P1wQgfiYqVpXCTD_U,23
-google_news_trends_mcp-0.1.5.dist-info/RECORD,,