initial
This commit is contained in:
saidsurucu
@@ -0,0 +1,175 @@
|
||||
# yargitay_mcp_module/client.py
|
||||
|
||||
import httpx
|
||||
from bs4 import BeautifulSoup # Still needed for pre-processing HTML before markitdown
|
||||
from typing import Dict, Any, List, Optional
|
||||
import logging
|
||||
import html
|
||||
import re
|
||||
import tempfile
|
||||
import os
|
||||
from markitdown import MarkItDown
|
||||
|
||||
from .models import (
|
||||
YargitayDetailedSearchRequest,
|
||||
YargitayApiSearchResponse,
|
||||
YargitayApiDecisionEntry,
|
||||
YargitayDocumentMarkdown,
|
||||
CompactYargitaySearchResult
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
# Basic logging configuration if no handlers are configured
|
||||
if not logger.hasHandlers():
|
||||
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
||||
|
||||
class YargitayOfficialApiClient:
|
||||
"""
|
||||
API Client for Yargitay's official decision search system.
|
||||
Targets the detailed search endpoint (e.g., /aramadetaylist) based on user-provided payload.
|
||||
"""
|
||||
BASE_URL = "https://karararama.yargitay.gov.tr"
|
||||
# The form action was "/detayliArama". This often maps to an API endpoint like "/aramadetaylist".
|
||||
# This should be confirmed with the actual API.
|
||||
DETAILED_SEARCH_ENDPOINT = "/aramadetaylist"
|
||||
DOCUMENT_ENDPOINT = "/getDokuman"
|
||||
|
||||
def __init__(self, request_timeout: float = 60.0):
|
||||
self.http_client = httpx.AsyncClient(
|
||||
base_url=self.BASE_URL,
|
||||
headers={
|
||||
"Content-Type": "application/json; charset=UTF-8",
|
||||
"Accept": "application/json, text/plain, */*",
|
||||
"X-Requested-With": "XMLHttpRequest",
|
||||
"X-KL-KIS-Ajax-Request": "Ajax_Request", # Seen in a Yargitay client example
|
||||
"Referer": f"{self.BASE_URL}/" # Some APIs might check referer
|
||||
},
|
||||
timeout=request_timeout,
|
||||
verify=False # SSL verification disabled as per original user code - use with caution
|
||||
)
|
||||
|
||||
async def search_detailed_decisions(
|
||||
self,
|
||||
search_params: YargitayDetailedSearchRequest
|
||||
) -> YargitayApiSearchResponse:
|
||||
"""
|
||||
Performs a detailed search for decisions in Yargitay
|
||||
using the structured search_params.
|
||||
"""
|
||||
# Create the main payload structure with the 'data' key
|
||||
request_payload = {"data": search_params.model_dump(exclude_none=True, by_alias=True)}
|
||||
|
||||
logger.info(f"YargitayOfficialApiClient: Performing detailed search with payload: {request_payload}")
|
||||
|
||||
try:
|
||||
response = await self.http_client.post(self.DETAILED_SEARCH_ENDPOINT, json=request_payload)
|
||||
response.raise_for_status() # Raise an exception for HTTP 4xx or 5xx status codes
|
||||
response_json_data = response.json()
|
||||
|
||||
# Validate and parse the response using Pydantic models
|
||||
api_response = YargitayApiSearchResponse(**response_json_data)
|
||||
|
||||
# Populate the document_url for each decision entry
|
||||
if api_response.data and api_response.data.data:
|
||||
for decision_item in api_response.data.data:
|
||||
decision_item.document_url = f"{self.BASE_URL}{self.DOCUMENT_ENDPOINT}?id={decision_item.id}"
|
||||
|
||||
return api_response
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"YargitayOfficialApiClient: HTTP request error during detailed search: {e}")
|
||||
raise # Re-raise to be handled by the calling MCP tool
|
||||
except Exception as e: # Catches Pydantic ValidationErrors as well
|
||||
logger.error(f"YargitayOfficialApiClient: Error processing or validating detailed search response: {e}")
|
||||
raise
|
||||
|
||||
def _convert_html_to_markdown(self, html_from_api_data_field: str) -> Optional[str]:
|
||||
"""
|
||||
Takes raw HTML string (from Yargitay API 'data' field for a document),
|
||||
pre-processes it, and converts it to Markdown using MarkItDown.
|
||||
Returns only the Markdown string or None if conversion fails.
|
||||
"""
|
||||
if not html_from_api_data_field:
|
||||
return None
|
||||
|
||||
# Pre-process HTML: unescape entities and fix common escaped sequences
|
||||
# Based on user's original fix_html_content
|
||||
processed_html = html.unescape(html_from_api_data_field)
|
||||
processed_html = processed_html.replace('\\"', '"')
|
||||
processed_html = processed_html.replace('\\r\\n', '\n')
|
||||
processed_html = processed_html.replace('\\n', '\n')
|
||||
processed_html = processed_html.replace('\\t', '\t')
|
||||
|
||||
# MarkItDown often works best with a full HTML document structure.
|
||||
# The Yargitay /getDokuman response already provides a full <html>...</html> string.
|
||||
# If it were just a fragment, we might wrap it like:
|
||||
# html_to_convert = f"<html><head><meta charset=\"UTF-8\"></head><body>{processed_html}</body></html>"
|
||||
# But since it's already a full HTML string in "data":
|
||||
html_to_convert = processed_html
|
||||
|
||||
markdown_output = None
|
||||
temp_file_path = None
|
||||
try:
|
||||
md_converter = MarkItDown(enable_plugins=False) # Plugins disabled as per basic usage
|
||||
|
||||
# Write the HTML to a temporary file for MarkItDown to process
|
||||
with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".html", encoding="utf-8") as tmp_html_file:
|
||||
tmp_html_file.write(html_to_convert)
|
||||
temp_file_path = tmp_html_file.name
|
||||
|
||||
conversion_result = md_converter.convert(temp_file_path)
|
||||
markdown_output = conversion_result.text_content
|
||||
|
||||
logger.info("Successfully converted HTML to Markdown.")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error during MarkItDown HTML to Markdown conversion: {e}")
|
||||
finally:
|
||||
if temp_file_path and os.path.exists(temp_file_path):
|
||||
os.remove(temp_file_path) # Clean up the temporary file
|
||||
|
||||
return markdown_output
|
||||
|
||||
async def get_decision_document_as_markdown(self, document_id: str) -> YargitayDocumentMarkdown:
|
||||
"""
|
||||
Retrieves a specific Yargitay decision by its ID and returns its content
|
||||
as Markdown.
|
||||
Based on user-provided /getDokuman response structure.
|
||||
"""
|
||||
document_api_url = f"{self.DOCUMENT_ENDPOINT}?id={document_id}"
|
||||
source_url = f"{self.BASE_URL}{document_api_url}" # The original URL of the document
|
||||
logger.info(f"YargitayOfficialApiClient: Fetching document for Markdown conversion (ID: {document_id})")
|
||||
|
||||
try:
|
||||
response = await self.http_client.get(document_api_url)
|
||||
response.raise_for_status()
|
||||
|
||||
# Expecting JSON response with HTML content in the 'data' field
|
||||
response_json = response.json()
|
||||
html_content_from_api = response_json.get("data")
|
||||
|
||||
if not isinstance(html_content_from_api, str):
|
||||
logger.error(f"YargitayOfficialApiClient: 'data' field in API response is not a string or not found (ID: {document_id}).")
|
||||
raise ValueError("Expected HTML content not found in API response's 'data' field.")
|
||||
|
||||
markdown_content = self._convert_html_to_markdown(html_content_from_api)
|
||||
|
||||
return YargitayDocumentMarkdown(
|
||||
document_id=document_id,
|
||||
markdown_content=markdown_content,
|
||||
source_url=source_url
|
||||
)
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"YargitayOfficialApiClient: HTTP error fetching document for Markdown (ID: {document_id}): {e}")
|
||||
raise
|
||||
except ValueError as e: # For JSON parsing errors or missing 'data' field
|
||||
logger.error(f"YargitayOfficialApiClient: Error processing document response for Markdown (ID: {document_id}): {e}")
|
||||
raise
|
||||
except Exception as e: # For other unexpected errors
|
||||
logger.error(f"YargitayOfficialApiClient: General error fetching/processing document for Markdown (ID: {document_id}): {e}")
|
||||
raise
|
||||
|
||||
async def close_client_session(self):
|
||||
"""Closes the HTTPX client session."""
|
||||
await self.http_client.aclose()
|
||||
logger.info("YargitayOfficialApiClient: HTTP client session closed.")
|
||||
@@ -0,0 +1,76 @@
|
||||
# yargitay_mcp_module/models.py
|
||||
|
||||
from pydantic import BaseModel, Field, HttpUrl
|
||||
from typing import List, Optional, Dict, Any
|
||||
|
||||
class YargitayDetailedSearchRequest(BaseModel):
|
||||
"""
|
||||
Model for the 'data' object sent in the request payload
|
||||
to Yargitay's detailed search endpoint (e.g., /aramadetaylist).
|
||||
Based on the payload provided by the user.
|
||||
"""
|
||||
arananKelime: Optional[str] = Field("", description="Keyword to search for.")
|
||||
# Department/Board selection. Based on user provided payload.
|
||||
# birimYrg* fields seem to be the ones used for filtering.
|
||||
birimYrgKurulDaire: Optional[str] = Field("", description="Yargitay Board Unit (e.g., 'Hukuk Genel Kurulu').")
|
||||
birimYrgHukukDaire: Optional[str] = Field("", description="Yargitay Civil Chamber (e.g., '1. Hukuk Dairesi').")
|
||||
birimYrgCezaDaire: Optional[str] = Field("", description="Yargitay Criminal Chamber.")
|
||||
|
||||
esasYil: Optional[str] = Field("", description="Case year for 'Esas No'.")
|
||||
esasIlkSiraNo: Optional[str] = Field("", description="Starting sequence number for 'Esas No'.")
|
||||
esasSonSiraNo: Optional[str] = Field("", description="Ending sequence number for 'Esas No'.")
|
||||
|
||||
kararYil: Optional[str] = Field("", description="Decision year for 'Karar No'.")
|
||||
kararIlkSiraNo: Optional[str] = Field("", description="Starting sequence number for 'Karar No'.")
|
||||
kararSonSiraNo: Optional[str] = Field("", description="Ending sequence number for 'Karar No'.")
|
||||
|
||||
baslangicTarihi: Optional[str] = Field("", description="Start date for decision search (DD.MM.YYYY).")
|
||||
bitisTarihi: Optional[str] = Field("", description="End date for decision search (DD.MM.YYYY).")
|
||||
|
||||
siralama: Optional[str] = Field("3", description="Sorting criteria (1: Esas No, 2: Karar No, 3: Karar Tarihi).") # Default to 'Karar Tarihine Göre'
|
||||
siralamaDirection: Optional[str] = Field("desc", description="Sorting direction ('asc' or 'desc').") # Default to 'Büyükten Küçüğe'
|
||||
|
||||
pageSize: int = Field(10, ge=1, le=100, description="Number of results per page.")
|
||||
pageNumber: int = Field(1, ge=1, description="Page number to retrieve.")
|
||||
|
||||
class YargitayApiDecisionEntry(BaseModel):
|
||||
"""Model for an individual decision entry from the Yargitay API search response."""
|
||||
id: str # Unique system ID of the decision
|
||||
daire: Optional[str] = Field(None, description="The chamber that made the decision.")
|
||||
esasNo: Optional[str] = Field(None, alias="esasNo", description="Case registry number ('Esas No').")
|
||||
kararNo: Optional[str] = Field(None, alias="kararNo", description="Decision number ('Karar No').")
|
||||
kararTarihi: Optional[str] = Field(None, alias="kararTarihi", description="Date of the decision.")
|
||||
arananKelime: Optional[str] = Field(None, alias="arananKelime", description="Matched keyword in the search result item.")
|
||||
# 'index' and 'siraNo' from API response are not critical for MCP tool, so omitted for brevity
|
||||
|
||||
# This field will be populated by the client after fetching the search list
|
||||
document_url: Optional[HttpUrl] = Field(None, description="Direct URL to the decision document.")
|
||||
|
||||
class Config:
|
||||
populate_by_name = True # To allow populating by alias from API response
|
||||
|
||||
|
||||
class YargitayApiResponseInnerData(BaseModel):
|
||||
"""Model for the inner 'data' object in the Yargitay API search response."""
|
||||
data: List[YargitayApiDecisionEntry]
|
||||
# draw: Optional[int] = None # Typically used by DataTables, not essential for MCP
|
||||
recordsTotal: int # Total number of records matching the query
|
||||
recordsFiltered: int # Total number of records after filtering (usually same as recordsTotal)
|
||||
|
||||
class YargitayApiSearchResponse(BaseModel):
|
||||
"""Model for the complete search response from the Yargitay API."""
|
||||
data: YargitayApiResponseInnerData
|
||||
# metadata: Optional[Dict[str, Any]] = None # Optional metadata from API
|
||||
|
||||
class YargitayDocumentMarkdown(BaseModel):
|
||||
"""Model for a Yargitay decision document, containing only Markdown content."""
|
||||
document_id: str = Field(..., description="The unique ID of the document.")
|
||||
markdown_content: Optional[str] = Field(None, description="The decision content converted to Markdown.")
|
||||
source_url: HttpUrl = Field(..., description="The source URL of the original document.")
|
||||
|
||||
class CompactYargitaySearchResult(BaseModel):
|
||||
"""A more compact search result model for the MCP tool to return."""
|
||||
decisions: List[YargitayApiDecisionEntry]
|
||||
total_records: int
|
||||
requested_page: int
|
||||
page_size: int
|
||||
Reference in New Issue
Block a user