extract_content

Instructions

Extract content from specific pages of a PDF file.

Args:
    pdf_path: Path to the PDF file (relative to the downloads directory or absolute path)
    pages: Comma-separated page numbers to extract (e.g., "1,3,5-7"). 
           If not specified, extracts all pages. Supports negative indexing (-1 for last page).

Returns:
    Extracted text content from the specified pages

Implementation Reference

• server.py:224-265 (handler)

  MCP tool handler for 'extract_content'. This is the main async function registered via @mcp.tool() that handles the tool execution, resolves the PDF path, delegates to PDFReader, and returns the extracted content.

  @mcp.tool()
  async def extract_content(pdf_path: str, pages: Optional[str] = None) -> str:
      """
      Extract content from specific pages of a PDF file.
      
      Args:
          pdf_path: Path to the PDF file (relative to the downloads directory or absolute path)
          pages: Comma-separated page numbers to extract (e.g., "1,3,5-7"). 
                 If not specified, extracts all pages. Supports negative indexing (-1 for last page).
      
      Returns:
          Extracted text content from the specified pages
      """
      try:
          # Resolve PDF path
          if not os.path.isabs(pdf_path):
              # Try relative to downloads directory first
              download_path = current_dir / DOWNLOAD_DIR / pdf_path
              if download_path.exists():
                  pdf_path = str(download_path)
              else:
                  # Try relative to current directory
                  current_path = current_dir / pdf_path
                  if current_path.exists():
                      pdf_path = str(current_path)
                  else:
                      logger.error(f"PDF file not found: {pdf_path}")
                      return f"PDF file not found: {pdf_path}"
          
          # Extract content using PDFReader
          content = pdf_reader.extract_content(pdf_path, pages)
          
          if not content.strip():
              logger.warning(f"No content extracted from {pdf_path} (pages: {pages or 'all'})")
              return f"No content extracted from {pdf_path} (pages: {pages or 'all'})"
          
          logger.info(f"Successfully extracted content from {pdf_path} (pages: {pages or 'all'})")
          return content
      
      except Exception as e:
          logger.error(f"Error extracting content from PDF: {str(e)}")
          return f"Error extracting content from PDF: {str(e)}"

• read_pdf.py:252-290 (helper)

  Core helper function in PDFReader class that performs the actual PDF parsing, extracts text with layout preservation, internal links, and formats the content from specified pages.

  def extract_content(self, pdf_path: str, pages: Optional[str] = None) -> str:
      """Main method for extracting PDF content with internal links"""
      if not pdf_path:
          raise ValueError("PDF path cannot be empty")
  
      try:
          logger.info(f"Starting PDF content extraction from: {pdf_path}")
          
          # Open PDF with pypdf
          self.reader = PdfReader(pdf_path)
          total_pages = len(self.reader.pages)
          
          # Build xref to page mapping
          self.build_xref_to_page_mapping(self.reader)
          
          # Build named destinations mapping
          self.build_named_destinations_mapping(self.reader)
          
          selected_pages = self.parse_pages(pages, total_pages)
          
          logger.info(f"PDF has {total_pages} pages, extracting pages: {[p+1 for p in selected_pages]}")
          
          extracted_contents = []
          
          for page_num in selected_pages:
              if page_num < len(self.reader.pages):
                  page = self.reader.pages[page_num]
                  content = self.extract_page_content(page, page_num)
                  formatted_content = self.format_page_content(content)
                  extracted_contents.append(formatted_content)
                  logger.debug(f"Extracted content from page {page_num + 1}")
          
          logger.info(f"Successfully extracted content from {len(extracted_contents)} pages")
          return "\n\n".join(extracted_contents)
              
      except Exception as e:
          logger.error(f"Failed to extract PDF content: {str(e)}")
          raise ValueError(f"Failed to extract PDF content: {str(e)}")

• server.py:59-59 (registration)

  Initialization of the FastMCP server instance where tools are registered via decorators.

  mcp = FastMCP("nccn-guidelines")