get_uyusmazlik_document_markdown_from_url

Instructions

Implementation Reference

• uyusmazlik_mcp_module/client.py:219-243 (handler)

  Core handler function that takes a document URL, fetches the HTML content using httpx, converts it to Markdown using the internal _convert_html_to_markdown_uyusmazlik method, and returns a UyusmazlikDocumentMarkdown object. This implements the logic for 'get_uyusmazlik_document_markdown_from_url'.

  async def get_decision_document_as_markdown(self, document_url: str) -> UyusmazlikDocumentMarkdown:
      """
      Retrieves a specific Uyuşmazlık decision from its full URL and returns content as Markdown.
      """
      logger.info(f"UyusmazlikApiClient (httpx for docs): Fetching Uyuşmazlık document for Markdown from URL: {document_url}")
      try:
          # Using a new httpx.AsyncClient instance for this GET request for simplicity
          async with httpx.AsyncClient(verify=False, timeout=self.request_timeout) as doc_fetch_client:
               get_response = await doc_fetch_client.get(document_url, headers={"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"})
          get_response.raise_for_status()
          html_content_from_api = get_response.text
  
          if not isinstance(html_content_from_api, str) or not html_content_from_api.strip():
              logger.warning(f"UyusmazlikApiClient: Received empty or non-string HTML from URL {document_url}.")
              return UyusmazlikDocumentMarkdown(source_url=document_url, markdown_content=None)
  
          markdown_content = self._convert_html_to_markdown_uyusmazlik(html_content_from_api)
          return UyusmazlikDocumentMarkdown(source_url=document_url, markdown_content=markdown_content)
      except httpx.RequestError as e:
          logger.error(f"UyusmazlikApiClient (httpx for docs): HTTP error fetching Uyuşmazlık document from {document_url}: {e}")
          raise
      except Exception as e:
          logger.error(f"UyusmazlikApiClient (httpx for docs): General error processing Uyuşmazlık document from {document_url}: {e}")
          raise

• uyusmazlik_mcp_module/models.py:83-86 (schema)

  Pydantic schema/model for the output of the tool, defining source_url (HttpUrl) and markdown_content (Optional[str]). Likely used for input/output validation in the MCP tool.

  class UyusmazlikDocumentMarkdown(BaseModel):
      """Model for an Uyuşmazlık decision document, containing only Markdown content."""
      source_url: HttpUrl # The URL from which the content was fetched
      markdown_content: Optional[str] = Field(None, description="The decision content converted to Markdown.")

• uyusmazlik_mcp_module/client.py:195-218 (helper)

  Helper function within the client class that performs the HTML to Markdown conversion using MarkItDown library, handling encoding and streaming.

  def _convert_html_to_markdown_uyusmazlik(self, full_decision_html_content: str) -> Optional[str]:
      """Converts direct HTML content (from an Uyuşmazlık decision page) to Markdown."""
      if not full_decision_html_content: 
          return None
      
      processed_html = html.unescape(full_decision_html_content)
      # As per user request, pass the full (unescaped) HTML to MarkItDown
      html_input_for_markdown = processed_html
  
      markdown_text = None
      try:
          # Convert HTML string to bytes and create BytesIO stream
          html_bytes = html_input_for_markdown.encode('utf-8')
          html_stream = io.BytesIO(html_bytes)
          
          # Pass BytesIO stream to MarkItDown to avoid temp file creation
          md_converter = MarkItDown()
          conversion_result = md_converter.convert(html_stream)
          markdown_text = conversion_result.text_content
          logger.info("UyusmazlikApiClient: HTML to Markdown conversion successful.")
      except Exception as e:
          logger.error(f"UyusmazlikApiClient: Error during MarkItDown HTML to Markdown conversion: {e}")
      return markdown_text