google-news-trends-mcp 0.1.8__py3-none-any.whl → 0.1.10__py3-none-any.whl

google_news_trends_mcp/__init__.py

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

google_news_trends_mcp/news.py

@@ -8,7 +8,6 @@ It will fallback to using Playwright for websites that are difficult to scrape w
 
 import re
 import json
-import time
 import asyncio
 from gnews import GNews
 import newspaper  # newspaper4k
@@ -16,7 +15,6 @@ from googlenewsdecoder import gnewsdecoder
 import cloudscraper
 from playwright.async_api import async_playwright, Browser, Playwright
 from trendspy import Trends, TrendKeyword
-import click
 from typing import Optional, cast, overload, Literal, Awaitable
 import atexit
 from contextlib import asynccontextmanager
@@ -97,28 +95,15 @@ async def download_article_with_playwright(url) -> newspaper.Article | None:
             await page.goto(url, wait_until="domcontentloaded")
             await asyncio.sleep(2)  # Wait for the page to load completely
             content = await page.content()
-            article = newspaper.article(url, input_html=content, language="en")
+            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}")
         return None
 
 
-async def download_article(url: str, nlp: bool = True) -> newspaper.Article | None:
-    """
-    Download an article from a given URL using newspaper4k and cloudscraper (async).
-    """
+def download_article_with_scraper(url) -> newspaper.Article | None:
     article = None
-    if url.startswith("https://news.google.com/rss/"):
-        try:
-            decoded_url = gnewsdecoder(url)
-            if decoded_url.get("status"):
-                url = decoded_url["decoded_url"]
-            else:
-                logging.debug("Failed to decode Google News RSS link:")
-                return None
-        except Exception as err:
-            logging.warning(f"Error while decoding url {url}\n {err.args}")
     try:
         article = newspaper.article(url)
     except Exception as e:
@@ -134,19 +119,32 @@ async def download_article(url: str, nlp: bool = True) -> newspaper.Article | No
                 )
         except Exception as e:
             logging.debug(f"Error downloading article with cloudscraper from {url}\n {e.args}")
+    return article
 
-    try:
-        if article is None or not article.text:
-            # If newspaper failed, try downloading with Playwright
-            logging.debug(f"Retrying with Playwright for {url}")
-            article = await download_article_with_playwright(url)
-        article = cast(newspaper.Article, article)
-        article.parse()
-        if nlp:
-            article.nlp()
-    except Exception as e:
-        logging.warning(f"Error parsing article from {url}\n {e.args}")
+
+def decode_url(url: str) -> str:
+    if url.startswith("https://news.google.com/rss/"):
+        try:
+            decoded_url = gnewsdecoder(url)
+            if decoded_url.get("status"):
+                url = decoded_url["decoded_url"]
+            else:
+                logging.debug("Failed to decode Google News RSS link:")
+                return ""
+        except Exception as err:
+            logging.warning(f"Error while decoding url {url}\n {err.args}")
+    return url
+
+
+async def download_article(url: str) -> newspaper.Article | None:
+    """
+    Download an article from a given URL using newspaper4k and cloudscraper (async).
+    """
+    if not (url := decode_url(url)):
         return None
+    article = download_article_with_scraper(url)
+    if article is None or not article.text:
+        article = await download_article_with_playwright(url)
     return article
 
 
@@ -162,10 +160,13 @@ async def process_gnews_articles(
     articles = []
     total = len(gnews_articles)
     for idx, gnews_article in enumerate(gnews_articles):
-        article = await download_article(gnews_article["url"], nlp=nlp)
+        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}")
             continue
+        article.parse()
+        if nlp:
+            article.nlp()
         articles.append(article)
         if report_progress:
             await report_progress(idx, total)
@@ -181,10 +182,6 @@ 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
@@ -203,9 +200,6 @@ 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
@@ -224,10 +218,6 @@ async def get_news_by_location(
     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.
     """
     google_news.period = f"{period}d"
     google_news.max_results = max_results
@@ -255,9 +245,6 @@ 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
@@ -287,10 +274,6 @@ 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

@@ -1,7 +1,5 @@
-from typing import Annotated, cast, Optional, Any, Literal, TYPE_CHECKING
+from typing import Annotated, Optional, Any, TYPE_CHECKING
 from fastmcp import FastMCP, Context
-from fastmcp.exceptions import ToolError
-from fastmcp.server.dependencies import get_context
 from fastmcp.server.middleware.timing import TimingMiddleware
 from fastmcp.server.middleware.logging import LoggingMiddleware
 from fastmcp.server.middleware.rate_limiting import RateLimitingMiddleware
@@ -134,15 +132,14 @@ async def summarize_article(article: Article, ctx: Context) -> None:
     if article.text:
         prompt = f"Please provide a concise summary of the following news article:\n\n{article.text}"
         response = await ctx.sample(prompt)
-        # response = cast(TextContent, response)
         if isinstance(response, TextContent):
             if not response.text:
-                await ctx.warning("NLP response is empty. Unable to summarize article.")
+                await ctx.warning("LLM Sampling response is empty. Unable to summarize article.")
                 article.summary = "No summary available."
             else:
                 article.summary = response.text
         else:
-            await ctx.warning("NLP response is not a TextContent object. Unable to summarize article.")
+            await ctx.warning("LLM Sampling response is not a TextContent object. Unable to summarize article.")
             article.summary = "No summary available."
     else:
         article.summary = "No summary available."

{google_news_trends_mcp-0.1.8.dist-info → google_news_trends_mcp-0.1.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: google-news-trends-mcp
-Version: 0.1.8
+Version: 0.1.10
 Summary: An MCP server to access Google News and Google Trends.
 Author-email: Jesse Manek <jesse.manek@gmail.com>
 License-Expression: MIT
@@ -35,7 +35,7 @@ An MCP server to access Google News and Google Trends.  Does not rely on any pai
 
 - Search Google News articles based on keyword, location, topic
 - Get top news stories from Google News
-- Google Trends keywords base on location
+- Google Trends keywords based on location
 - Optional LLM Sampling and NLP to summarize articles and extract keywords
 
 ## Installation
@@ -141,7 +141,7 @@ The following MCP tools are available:
 | **get_top_news**         | Fetch the top news stories from Google News.                       |
 | **get_trending_keywords**| Return trending keywords from Google Trends for a specified location.|
 
-All of the news related tools have an option to summarize the text of the article using NLP (nltk)
+All of the news related tools have an option to summarize the text of the article using LLM Sampling (if supported) or NLP
 
 
 ## CLI

google_news_trends_mcp-0.1.10.dist-info/RECORD

@@ -0,0 +1,11 @@
+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,,

google_news_trends_mcp-0.1.8.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=-Cith02x6-9o91rXpgMM0lrhArPDMB9d3h8AAE1rimw,3959
-google_news_trends_mcp/news.py,sha256=Anxs65Fxq1Qz_tkmVyTDY3Fn-I0dv0xR3ipDrLBc6gw,12851
-google_news_trends_mcp/server.py,sha256=promIVXRcd1ZUSgFClZ73l2scXlsS-joRHv1AZs73SE,14946
-google_news_trends_mcp-0.1.8.dist-info/licenses/LICENSE,sha256=5dsv2ZI5EZIer0a9MktVmILVrlp5vqH_0tPIe3bRLgE,1067
-google_news_trends_mcp-0.1.8.dist-info/METADATA,sha256=j0yuLLp3OaCYS07o-Q5vNVs3xCk5HHAMcGVUn7kT2TI,4495
-google_news_trends_mcp-0.1.8.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-google_news_trends_mcp-0.1.8.dist-info/entry_points.txt,sha256=eVT3xd6YJQgsWAUBwhnffuwhXNF7yyt_uco6fjBy-1o,130
-google_news_trends_mcp-0.1.8.dist-info/top_level.txt,sha256=RFheDbzhNnEV_Y3iFNm7jhRhY1P1wQgfiYqVpXCTD_U,23
-google_news_trends_mcp-0.1.8.dist-info/RECORD,,