chore: ruff 代码检查与修复

130 issues auto-fixed (import ordering, UP045/UP006 type annotations),
33 issues manually fixed (E712/E501/E402/E722 + N818 rename + per-file
wechat ignore for N8xx naming conventions). All 33 tests pass.

app/crawler/base.py

@@ -2,7 +2,6 @@ import hashlib
 from abc import ABC, abstractmethod
 from dataclasses import dataclass, field
 from datetime import datetime
-from typing import List, Optional
 
 
 @dataclass
@@ -12,7 +11,7 @@ class CrawlResult:
     total_count: int = 0
     new_count: int = 0
     announcements: list = field(default_factory=list)
-    error_message: Optional[str] = None
+    error_message: str | None = None
     crawled_at: datetime = field(default_factory=datetime.now)
     duration: float = 0.0
 
@@ -24,7 +23,7 @@ class CrawlResult:
 @dataclass
 class PipelineConfig:
     filter_enabled: bool = True
-    keywords: List[str] = field(default_factory=list)
+    keywords: list[str] = field(default_factory=list)
     dedup_enabled: bool = True
     notify_mode: str = "filtered"
     mark_sent: bool = False

app/crawler/dahuagov_spider.py

@@ -1,7 +1,9 @@
 import asyncio
 import random
 from datetime import datetime
+
 import httpx
+
 from app.config import settings
 from app.crawler.base import BaseSpider, CrawlResult, PipelineConfig
 from app.crawler.parsers import parse_dahuagov_html

app/crawler/gxgp_spider.py

@@ -2,11 +2,12 @@ import json
 import random
 import time
 from datetime import datetime
-from typing import List, Optional
+
 import httpx
+
 from app.config import settings
 from app.crawler.base import BaseSpider, CrawlResult, PipelineConfig
-from app.crawler.parsers import parse_gxgp_api_response, extract_pagination
+from app.crawler.parsers import extract_pagination, parse_gxgp_api_response
 
 
 class GXGPSpider(BaseSpider):
@@ -27,8 +28,8 @@ class GXGPSpider(BaseSpider):
             mark_sent=False,
         )
 
-    async def crawl(self, sources: Optional[List[str]] = None,
-                    max_pages: Optional[int] = None) -> CrawlResult:
+    async def crawl(self, sources: list[str] | None = None,
+                    max_pages: int | None = None) -> CrawlResult:
         if max_pages is None:
             max_pages = settings.crawler_max_pages
         if sources is None:
@@ -88,7 +89,7 @@ class GXGPSpider(BaseSpider):
         )
 
     async def _fetch_page(self, client: httpx.AsyncClient, source_code: str,
-                          category_id: int, page_no: int) -> Optional[dict]:
+                          category_id: int, page_no: int) -> dict | None:
         payload = {
             "keyword": "",
             "publishDateBegin": "",
@@ -102,7 +103,7 @@ class GXGPSpider(BaseSpider):
             "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
             "Content-Type": "application/json;charset=UTF-8",
             "Origin": self.base_url,
-            "Referer": f"{self.base_url}/site/category?parentId={category_id}&childrenCode={source_code}",
+            "Referer": f"{self.base_url}/site/category?parentId={category_id}&childrenCode={source_code}",  # noqa: E501
         }
         response = await client.post(
             self.announcement_api, json=payload, headers=headers

app/crawler/parsers.py

@@ -1,18 +1,18 @@
 import hashlib
 from datetime import datetime
-from typing import Any, Dict, List
+from typing import Any
 from urllib.parse import urljoin
 
 from bs4 import BeautifulSoup
 
 
 def parse_gxgp_api_response(
-    response_data: Dict[str, Any],
+    response_data: dict[str, Any],
     source_code: str,
     source_name: str,
     crawled_at: datetime,
     category_id: int,
-) -> List[Dict[str, Any]]:
+) -> list[dict[str, Any]]:
     if not response_data.get("success"):
         return []
     data = response_data.get("result", {}).get("data", {})
@@ -62,7 +62,7 @@ def parse_gxgp_api_response(
     return results
 
 
-def extract_pagination(response_data: Dict[str, Any]) -> Dict[str, Any]:
+def extract_pagination(response_data: dict[str, Any]) -> dict[str, Any]:
     data = response_data.get("result", {}).get("data", {})
     return {
         "total": data.get("total", 0),
@@ -75,7 +75,7 @@ def extract_pagination(response_data: Dict[str, Any]) -> Dict[str, Any]:
     }
 
 
-def parse_dahuagov_html(html: str, crawled_at: datetime) -> List[Dict[str, Any]]:
+def parse_dahuagov_html(html: str, crawled_at: datetime) -> list[dict[str, Any]]:
     soup = BeautifulSoup(html, "html.parser")
     lists = soup.find_all("ul", class_="more-list")
     if not lists:
@@ -131,7 +131,7 @@ def parse_dahuagov_html(html: str, crawled_at: datetime) -> List[Dict[str, Any]]
     return results
 
 
-def _generate_hash(ann: Dict[str, Any]) -> str:
+def _generate_hash(ann: dict[str, Any]) -> str:
     content = (
         f"{ann['title']}|{ann['publish_date'].strftime('%Y-%m-%d')}"
         f"|{ann['purchase_name']}|{ann['content_url']}|{ann['source_code']}"