get_news_by_topic

Instructions

Implementation Reference

• src/google_news_trends_mcp/server.py:233-263 (handler)

  The MCP tool handler for 'get_news_by_topic'. Registered with @mcp.tool decorator, accepts a topic string, period, max_results, full_data, and summarize flags. Delegates to news.get_news_by_topic for fetching articles, then optionally summarizes them.

  @mcp.tool(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)] = 7,
      max_results: Annotated[int, Field(description="Maximum number of results to return.", ge=1)] = 10,
      full_data: Annotated[
          bool,
          Field(
              description="Return full data for each article. If False a summary should be created by setting the summarize flag"
          ),
      ] = False,
      summarize: Annotated[
          bool,
          Field(
              description="Generate a summary of the article, will first try LLM Sampling but if unavailable will use nlp"
          ),
      ] = True,
  ) -> list[ArticleOut]:
      set_newspaper_article_fields(full_data)
      articles = await news.get_news_by_topic(
          topic=topic,
          period=period,
          max_results=max_results,
          nlp=False,
          report_progress=ctx.report_progress,
      )
      if summarize:
          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]

• src/google_news_trends_mcp/news.py:253-277 (helper)

  Core business logic for 'get_news_by_topic'. Calls gnews library's get_news_by_topic(topic), then downloads and processes articles (with optional NLP). Documents the valid topic values.

  async def get_news_by_topic(
      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
      WORLD, NATION, BUSINESS, TECHNOLOGY, ENTERTAINMENT, SPORTS, SCIENCE, HEALTH,
      POLITICS, CELEBRITIES, TV, MUSIC, MOVIES, THEATER, SOCCER, CYCLING, MOTOR SPORTS,
      TENNIS, COMBAT SPORTS, BASKETBALL, BASEBALL, FOOTBALL, SPORTS BETTING, WATER SPORTS,
      HOCKEY, GOLF, CRICKET, RUGBY, ECONOMY, PERSONAL FINANCE, FINANCE, DIGITAL CURRENCIES,
      MOBILE, ENERGY, GAMING, INTERNET SECURITY, GADGETS, VIRTUAL REALITY, ROBOTICS, NUTRITION,
      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.
      """
      google_news.period = f"{period}d"
      google_news.max_results = max_results
      gnews_articles = google_news.get_news_by_topic(topic)
      if not gnews_articles:
          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)

• src/google_news_trends_mcp/server.py:30-53 (schema)

  Output schema (ArticleOut) used by the tool to return structured article data to the client.

  class ArticleOut(BaseModelClean):
      title: Annotated[str, Field(description="Title of the article.")]
      url: Annotated[str, Field(description="Original article URL.")]
      read_more_link: Annotated[Optional[str], Field(description="Link to read more about the article.")] = None
      language: Annotated[Optional[str], Field(description="Language code of the article.")] = None
      meta_img: Annotated[Optional[str], Field(description="Meta image URL.")] = None
      movies: Annotated[Optional[list[str]], Field(description="List of movie URLs or IDs.")] = None
      meta_favicon: Annotated[Optional[str], Field(description="Favicon URL from meta data.")] = None
      meta_site_name: Annotated[Optional[str], Field(description="Site name from meta data.")] = None
      authors: Annotated[Optional[list[str]], Field(description="list of authors.")] = None
      publish_date: Annotated[Optional[str], Field(description="Publish date in ISO format.")] = None
      top_image: Annotated[Optional[str], Field(description="URL of the top image.")] = None
      images: Annotated[Optional[list[str]], Field(description="list of image URLs.")] = None
      text: Annotated[Optional[str], Field(description="Full text of the article.")] = None
      summary: Annotated[Optional[str], Field(description="Summary of the article.")] = None
      keywords: Annotated[Optional[list[str]], Field(description="Extracted keywords.")] = None
      tags: Annotated[Optional[list[str]], Field(description="Tags for the article.")] = None
      meta_keywords: Annotated[Optional[list[str]], Field(description="Meta keywords from the article.")] = None
      meta_description: Annotated[Optional[str], Field(description="Meta description from the article.")] = None
      canonical_link: Annotated[Optional[str], Field(description="Canonical link for the article.")] = None
      meta_data: Annotated[Optional[dict[str, str | int]], Field(description="Meta data dictionary.")] = None
      meta_lang: Annotated[Optional[str], Field(description="Language of the article.")] = None
      source_url: Annotated[Optional[str], Field(description="Source URL if different from original.")] = None

• src/google_news_trends_mcp/server.py:233-233 (registration)

  Registration of the 'get_news_by_topic' tool via the @mcp.tool decorator with description and tags.

  @mcp.tool(description=news.get_news_by_topic.__doc__, tags={"news", "articles", "topic"})

• src/google_news_trends_mcp/cli.py:64-82 (helper)

  CLI command wrapper for 'get_news_by_topic' using Click, providing a command-line interface to the same functionality.

  @cli.command(help=get_news_by_topic.__doc__)
  @click.argument("topic")
  @click.option("--period", type=int, default=7, help="Period in days to search for articles.")
  @click.option(
      "--max-results",
      "max_results",
      type=int,
      default=10,
      help="Maximum number of results to return.",
  )
  @click.option("--no-nlp", is_flag=True, default=False, help="Disable NLP processing for articles.")
  def topic(topic, period, max_results, no_nlp):
      @BrowserManager()
      async def _topic():
          articles = await get_news_by_topic(topic, period=period, max_results=max_results, nlp=not no_nlp)
          print_articles(articles)
          logger.info(f"Found {len(articles)} articles for topic '{topic}'.")
  
      asyncio.run(_topic())