fix(parser): keep Unit3D username as user id

app/modules/indexer/parser/unit3d.py

@@ -4,17 +4,20 @@ from typing import Optional
 
 from lxml import etree
 
-from app.modules.indexer.parser import SiteParserBase, SiteSchema
 from app.foundation import size as size_tools
 from app.foundation import temporal as time_tools
 from app.foundation import text as text_tools
 from app.foundation.dom import DomUtils
+from app.modules.indexer.parser import SiteParserBase, SiteSchema
 
 
 class Unit3dSiteUserInfo(SiteParserBase):
+    """Unit3D 架构站点的用户信息解析器。"""
+
     schema = SiteSchema.Unit3d
 
     def _parse_user_base_info(self, html_text: str):
+        """解析用户名并将 Unit3D 的用户名作为用户标识供后续请求使用。"""
         html_text = self._prepare_html_text(html_text)
         html = etree.HTML(html_text)
         try:
@@ -23,6 +26,7 @@ class Unit3dSiteUserInfo(SiteParserBase):
                 user_name_match = re.search(r"/users/(.+)/settings", tmps[0])
                 if user_name_match and user_name_match.group().strip():
                     self.username = user_name_match.group(1)
+                    self.userid = self.username
                     self._torrent_seeding_page = f"/users/{self.username}/active?perPage=100&client=&seeding=include"
                     self._user_detail_page = f"/users/{self.username}"
 
@@ -37,6 +41,7 @@ class Unit3dSiteUserInfo(SiteParserBase):
                 del html
 
     def _parse_site_page(self, html_text: str):
+        """Unit3D 不需要从站点首页解析额外的站点级数据。"""
         pass
 
     def _parse_user_detail_info(self, html_text: str):
@@ -120,6 +125,7 @@ class Unit3dSiteUserInfo(SiteParserBase):
         return next_page
 
     def _parse_user_traffic_info(self, html_text: str):
+        """解析用户上传量、下载量和分享率。"""
         html_text = self._prepare_html_text(html_text)
         upload_match = re.search(r"[^总]上[传傳]量?[:：_<>/a-zA-Z-=\"'\s#;]+([\d,.\s]+[KMGTPI]*B)", html_text,
                                  re.IGNORECASE)
@@ -132,7 +138,9 @@ class Unit3dSiteUserInfo(SiteParserBase):
             ratio_match and ratio_match.group(1).strip()) else 0.0
 
     def _parse_message_unread_links(self, html_text: str, msg_links: list) -> Optional[str]:
+        """Unit3D 没有兼容的未读消息列表解析。"""
         return None
 
     def _parse_message_content(self, html_text):
+        """Unit3D 没有兼容的未读消息正文解析。"""
         return None, None, None

tests/test_unit3d_parser.py

@@ -0,0 +1,36 @@
+# -*- coding: utf-8 -*-
+from app.modules.indexer.parser.unit3d import Unit3dSiteUserInfo
+
+USER_BASE_HTML = """
+<html>
+  <body>
+    <a href="/users/monica/settings">设置</a>
+    <a href="/bonus/earnings">积分 1,234.5</a>
+  </body>
+</html>
+"""
+
+
+def _build_parser() -> Unit3dSiteUserInfo:
+    """构造一个用于测试的 Unit3D 解析器。"""
+    return Unit3dSiteUserInfo(
+        site_name="莫妮卡",
+        url="https://udm.example/",
+        site_cookie="test-cookie",
+        apikey=None,
+        token=None,
+    )
+
+
+def test_unit3d_user_name_is_used_as_valid_userid() -> None:
+    """解析用户设置链接后，应允许详情页和做种页继续请求。"""
+    parser = _build_parser()
+
+    parser._parse_user_base_info(USER_BASE_HTML)
+
+    assert parser.username == "monica"
+    assert parser.userid == "monica"
+    assert parser._has_valid_userid()
+    assert parser._user_detail_page == "/users/monica"
+    assert parser._torrent_seeding_page.startswith("/users/monica/active?")
+    assert parser.bonus == 1234.5