Huggingface Daily Papers

Instructions

Implementation Reference

• scraper.py:44-46 (handler)

  Core handler function that calculates yesterday's date and fetches papers using the generic get_papers_by_date method.

  def get_yesterday_papers(self, fetch_details: bool = True) -> List[Dict]:
      yesterday = (datetime.now() - timedelta(days=1)).strftime("%Y-%m-%d")
      return self.get_papers_by_date(yesterday, fetch_details)

• main.py:163-191 (handler)

  MCP server @server.call_tool() handler implementation that calls the scraper, formats the response as text content.

  elif name == "get_yesterday_papers":
      papers = scraper.get_yesterday_papers()
      yesterday = (datetime.now() - timedelta(days=1)).strftime("%Y-%m-%d")
      
      if not papers:
          return [
              types.TextContent(
                  type="text",
                  text=f"No papers found for yesterday ({yesterday}). There might be no papers published that day or a network issue."
              )
          ]
      
      return [
          types.TextContent(
              type="text",
              text=f"Yesterday's Papers ({yesterday}) - Found {len(papers)} papers:\n\n" +
                   "\n".join([
                       f"Title: {paper['title']}\n"
                       f"Authors: {', '.join(paper['authors'])}\n"
                       f"Abstract: {paper['abstract']}\n"
                       f"URL: {paper['url']}\n" 
                       f"PDF: {paper['pdf_url']}\n"
                       f"Votes: {paper['votes']}\n"
                       f"Submitted by: {paper['submitted_by']}\n"
                       + "-" * 50
                       for paper in papers
                   ])
          )
      ]

• main.py:83-90 (registration)

  Tool registration in @server.list_tools() defining the tool name, description, and input schema.

  types.Tool(
      name="get_yesterday_papers",
      description="Get yesterday's HuggingFace daily papers", 
      inputSchema={
          "type": "object",
          "properties": {},
      },
  ),

• main.py:86-89 (schema)

  Input schema for the get_yesterday_papers tool, specifying an empty object (no required parameters).

  inputSchema={
      "type": "object",
      "properties": {},
  },

• scraper.py:19-39 (helper)

  Helper method delegated to by get_yesterday_papers for fetching and parsing papers from HuggingFace for a specific date, optionally fetching details.

  def get_papers_by_date(self, date: str, fetch_details: bool = True) -> List[Dict]:
      url = f"{self.base_url}/{date}"
      try:
          response = self.session.get(url)
          response.raise_for_status()
          papers = self._parse_papers(response.text)
          
          if fetch_details and papers:
              # 获取所有论文的详细信息，包括具体作者姓名
              for i, paper in enumerate(papers):
                  if paper.get('url'):
                      details = self._fetch_paper_details(paper['url'])
                      if details:
                          paper.update(details)
                      time.sleep(1)  # 避免请求过快
                      
          return papers
      except requests.RequestException as e:
          logging.error(f"Failed to fetch papers for {date}: {e}")
          return []