get_news_by_keyword

Instructions

Implementation Reference

• src/google_news_trends_mcp/news.py:199-215 (handler)

  Core async function that searches Google News by keyword, configures gnews client, fetches articles and processes them via process_gnews_articles.

  async def get_news_by_keyword(
      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.
      """
      google_news.period = f"{period}d"
      google_news.max_results = max_results
      gnews_articles = google_news.get_news(keyword)
      if not gnews_articles:
          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)

• src/google_news_trends_mcp/server.py:161-194 (handler)

  MCP tool handler for get_news_by_keyword, registered with @mcp.tool decorator. Accepts keyword, period, max_results, full_data, summarize params, calls news.get_news_by_keyword, optionally summarizes, and returns ArticleOut list.

  @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)] = 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_keyword(
          keyword=keyword,
          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/server.py:161-163 (registration)

  Registration of the get_news_by_keyword tool via @mcp.tool decorator with description=news.get_news_by_keyword.__doc__ and tags={'news', 'articles', 'keyword'}.

  @mcp.tool(
      description=news.get_news_by_keyword.__doc__,
      tags={"news", "articles", "keyword"},

• src/google_news_trends_mcp/server.py:30-52 (schema)

  ArticleOut Pydantic model defining the output schema for article results returned by get_news_by_keyword.

  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/cli.py:22-40 (helper)

  CLI command registration for get_news_by_keyword using Click, allowing command-line invocation with keyword, period, max_results, and --no-nlp options.

  @cli.command(help=get_news_by_keyword.__doc__)
  @click.argument("keyword")
  @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 keyword(keyword, period, max_results, no_nlp):
      @BrowserManager()
      async def _keyword():
          articles = await get_news_by_keyword(keyword, period=period, max_results=max_results, nlp=not no_nlp)
          print_articles(articles)
          logger.info(f"Found {len(articles)} articles for keyword '{keyword}'.")
  
      asyncio.run(_keyword())