fix(indexer): fetch TNode current user before requiring an id (#6895)

app/modules/indexer/parser/__init__.py

@@ -47,6 +47,8 @@ class SiteParserBase(metaclass=ABCMeta):
     schema = None
     # 请求模式 cookie/apikey
     request_mode = "cookie"
+    # 详情页默认依赖用户 ID；当前会话接口可在配置页面时关闭此前置校验。
+    _user_detail_requires_userid = True
 
     def __init__(self, site_name: str,
                  url: str,
@@ -227,7 +229,7 @@ class SiteParserBase(metaclass=ABCMeta):
                 self._parse_user_base_info(self._index_html)
             # 解析用户详细信息
             if self._user_detail_page:
-                if not self._has_valid_userid():
+                if self._user_detail_requires_userid and not self._has_valid_userid():
                     logger.warn(f"{self._site_name} 未解析到有效用户 ID，跳过用户详情页请求")
                 else:
                     self._parse_user_detail_info(

app/modules/indexer/parser/tnode.py

@@ -9,16 +9,21 @@ from app.foundation import temporal as time_tools
 
 
 class TNodeSiteUserInfo(SiteParserBase):
+    """通过当前会话 API 获取 TNode 站点用户资料与做种信息。"""
+
     schema = SiteSchema.TNode
 
     def _parse_site_page(self, html_text: str):
+        """提取 CSRF 令牌，并配置用于取得用户 ID 的当前会话接口。"""
         html_text = self._prepare_html_text(html_text)
 
         # <meta name="x-csrf-token" content="fd169876a7b4846f3a7a16fcd5cccf8d">
         csrf_token = re.search(r'<meta name="x-csrf-token" content="(.+?)">', html_text)
         if csrf_token:
             self._addition_headers = {'X-CSRF-TOKEN': csrf_token.group(1)}
+            # 当前用户接口依赖 Cookie 会话，不需要预先知道用户 ID。
             self._user_detail_page = "api/user/getMainInfo"
+            self._user_detail_requires_userid = False
             self._torrent_seeding_page = "api/user/listTorrentActivity?id=&type=seeding&page=1&size=20000"
 
     def _parse_logged_in(self, html_text):
@@ -31,12 +36,15 @@ class TNodeSiteUserInfo(SiteParserBase):
         return True
 
     def _parse_user_base_info(self, html_text: str):
+        """首页不提供用户 ID，身份信息需在详情接口返回后补齐。"""
         self.username = self.userid
 
     def _parse_user_traffic_info(self, html_text: str):
+        """流量信息已由当前用户接口返回，无需单独解析。"""
         pass
 
     def _parse_user_detail_info(self, html_text: str):
+        """从当前用户接口一次解析身份、资料、流量及未读消息数量。"""
         try:
             detail = json.loads(html_text)
         except json.JSONDecodeError:
@@ -98,6 +106,7 @@ class TNodeSiteUserInfo(SiteParserBase):
         return next_page
 
     def _parse_message_unread_links(self, html_text: str, msg_links: list) -> Optional[str]:
+        """当前仅支持 API 返回的未读数量，不解析消息链接。"""
         return None
 
     def _parse_message_content(self, html_text):

tests/test_tnode_parser.py

@@ -0,0 +1,152 @@
+# -*- coding: utf-8 -*-
+"""TNode 用户信息刷新顺序与失败保护回归测试。"""
+
+import json
+from unittest.mock import Mock
+
+import pytest
+from requests import Response
+
+from app.adapters.network.http import RequestUtils
+from app.modules.indexer.parser.tnode import TNodeSiteUserInfo
+from app.runtime.config import settings
+
+SITE_URL = "https://tnode.example/"
+PROFILE_URL = f"{SITE_URL}api/user/getMainInfo"
+SEEDING_URL = f"{SITE_URL}api/user/listTorrentActivity?id=&type=seeding&page=1&size=20000"
+HOME_HTML = '<html><head><meta name="x-csrf-token" content="test-csrf"></head></html>'
+
+
+@pytest.fixture
+def user_info() -> dict:
+    """构造不含真实账号信息的 TNode 用户资料。"""
+    return {
+        "id": 42,
+        "username": "test-user",
+        "class": {"name": "Power User"},
+        "regTime": "2023-01-02 03:04:05",
+        "upload": 4096,
+        "download": 1024,
+        "bonus": 12.5,
+        "unreadAdmin": 1,
+        "unreadInbox": 2,
+        "unreadSystem": 3,
+    }
+
+
+@pytest.fixture
+def pages(user_info: dict) -> dict[str, str]:
+    """提供完整解析流程所需的离线首页、资料和做种响应。"""
+    return {
+        SITE_URL: HOME_HTML,
+        PROFILE_URL: json.dumps({"status": 200, "data": user_info}),
+        f"{SITE_URL}index.php": HOME_HTML,
+        SEEDING_URL: json.dumps({
+            "status": 200,
+            "data": {"torrents": [{"size": 1024, "seeding": 2}, {"size": 2048, "seeding": 3}]},
+        }),
+    }
+
+
+@pytest.fixture
+def parser(monkeypatch: pytest.MonkeyPatch, pages: dict[str, str]) -> TNodeSiteUserInfo:
+    """只替换 HTTP 边界，保留真实解析、请求头合并和会话关闭行为。"""
+    client = Mock(spec=RequestUtils)
+
+    def get_response(url: str, **_kwargs) -> Response:
+        """拒绝未声明的请求，并返回离线 HTTP 响应。"""
+        response = Response()
+        response.status_code = 200
+        response.encoding = "utf-8"
+        response._content = pages[url].encode("utf-8")
+        return response
+
+    client.get_res.side_effect = get_response
+    monkeypatch.setattr(settings, "SITE_MESSAGE", False)
+    return TNodeSiteUserInfo(
+        site_name="TNode",
+        url=SITE_URL,
+        site_cookie="session=test-cookie",
+        apikey=None,
+        token=None,
+        request_utils=client,
+    )
+
+
+def test_tnode_fetches_current_user_before_seeding(parser: TNodeSiteUserInfo) -> None:
+    """空用户 ID 时仍应获取当前会话资料，之后继续刷新做种数据。"""
+    assert parser.userid is None
+
+    parser.parse()
+
+    assert parser.userid == 42
+    assert parser.username == "test-user"
+    assert parser.user_level == "Power User"
+    assert parser.join_at == "2023-01-02 03:04:05"
+    assert parser.upload == 4096
+    assert parser.download == 1024
+    assert parser.ratio == 4
+    assert parser.bonus == 12.5
+    assert parser.message_unread == 6
+    assert parser.seeding == 2
+    assert parser.seeding_size == 3072
+    assert parser.seeding_info == [[2, 1024], [3, 2048]]
+
+    calls = parser._request_utils.get_res.call_args_list
+    urls = [call.kwargs["url"] for call in calls]
+    assert urls.count(PROFILE_URL) == 1
+    assert urls.index(PROFILE_URL) < urls.index(SEEDING_URL)
+    for call in calls:
+        if call.kwargs["url"] in (PROFILE_URL, SEEDING_URL):
+            assert call.kwargs["headers"]["X-CSRF-TOKEN"] == "test-csrf"
+            assert call.kwargs["cookies"] == "session=test-cookie"
+    parser._request_utils.close.assert_called_once_with()
+
+
+@pytest.mark.parametrize("payload", ["", "<html>Login</html>", '{"status": 401}'])
+def test_tnode_failed_profile_skips_seeding(
+    parser: TNodeSiteUserInfo, pages: dict[str, str], payload: str,
+) -> None:
+    """资料为空、非 JSON 或业务失败时，不应继续请求做种接口。"""
+    pages[PROFILE_URL] = payload
+
+    parser.parse()
+
+    urls = [call.kwargs["url"] for call in parser._request_utils.get_res.call_args_list]
+    assert urls.count(PROFILE_URL) == 1
+    assert SEEDING_URL not in urls
+    assert parser.userid is None
+    assert parser.username is None
+    assert parser.seeding == 0
+    parser._request_utils.close.assert_called_once_with()
+
+
+@pytest.mark.parametrize("userid", [None, "", " ", 0, "0"])
+def test_tnode_invalid_userid_skips_seeding(
+    parser: TNodeSiteUserInfo, pages: dict[str, str], user_info: dict, userid,
+) -> None:
+    """即使资料接口成功，缺失或无效的用户 ID 仍应阻止做种请求。"""
+    user_info["id"] = userid
+    pages[PROFILE_URL] = json.dumps({"status": 200, "data": user_info})
+
+    parser.parse()
+
+    urls = [call.kwargs["url"] for call in parser._request_utils.get_res.call_args_list]
+    assert urls.count(PROFILE_URL) == 1
+    assert SEEDING_URL not in urls
+    assert not parser._has_valid_userid()
+    assert parser.seeding == 0
+    parser._request_utils.close.assert_called_once_with()
+
+
+def test_tnode_missing_csrf_skips_user_requests(parser: TNodeSiteUserInfo, pages: dict[str, str]) -> None:
+    """首页缺少 CSRF 时，不应请求未经配置的资料或做种地址。"""
+    pages[SITE_URL] = "<html>Login</html>"
+
+    parser.parse()
+
+    urls = [call.kwargs["url"] for call in parser._request_utils.get_res.call_args_list]
+    assert urls == [SITE_URL, f"{SITE_URL}index.php"]
+    assert parser.userid is None
+    assert parser.seeding == 0
+    parser._request_utils.close.assert_called_once_with()