feat: 用户数据解析器自动探测 + Gazelle/NexusProject 变种兼容 (#6403)

app/modules/indexer/__init__.py

@@ -634,12 +634,14 @@ class IndexerModule(_ModuleBase):
         :return: 用户数据
         """
 
-        def __get_site_obj() -> Optional[SiteParserBase]:
+        def __get_site_obj(schema_value: Optional[str] = None) -> Optional[SiteParserBase]:
             """
             获取站点解析器
+            :param schema_value: 指定 schema, 默认取站点声明的 schema
             """
+            schema_value = schema_value or site.get("schema")
             for site_schema in self._site_schemas:
-                if site_schema.schema and site_schema.schema.value == site.get("schema"):
+                if site_schema.schema and site_schema.schema.value == schema_value:
                     return site_schema(
                         site_name=site.get("name"),
                         url=site.get("url"),
@@ -651,6 +653,7 @@ class IndexerModule(_ModuleBase):
                         api_url=site.get("api_url"))
             return None
 
+        # 按站点声明的 schema 获取解析器
         site_obj = __get_site_obj()
         if not site_obj:
             if not site.get("public"):
@@ -662,6 +665,28 @@ class IndexerModule(_ModuleBase):
             logger.info(f"站点 {site.get('name')} 开始以 {site.get('schema')} 模型解析数据...")
             site_obj.parse()
             logger.debug(f"站点 {site.get('name')} 数据解析完成")
+            # 站点声明的 schema 解析失败(userid 为空)时, 自动尝试其他解析器,
+            # 兼容资源文件 schema 标注错误/变种站点的场景
+            if not site_obj.userid and not site.get("public"):
+                tried = {site.get("schema")}
+                for site_schema in self._site_schemas:
+                    if not site_schema.schema or site_schema.schema.value in tried:
+                        continue
+                    tried.add(site_schema.schema.value)
+                    logger.info(f"站点 {site.get('name')} schema {site.get('schema')} 解析失败, "
+                                f"尝试 {site_schema.schema.value} 模型...")
+                    alt_obj = __get_site_obj(site_schema.schema.value)
+                    if not alt_obj:
+                        continue
+                    try:
+                        alt_obj.parse()
+                    except Exception as e:
+                        logger.error(f"站点 {site.get('name')} 以 {site_schema.schema.value} 解析失败: {str(e)}")
+                        continue
+                    if alt_obj.userid:
+                        site_obj = alt_obj
+                        logger.info(f"站点 {site.get('name')} 改用 {site_schema.schema.value} 模型解析成功")
+                        break
             return SiteUserData(
                 domain=site_rules.extract_domain(site.get("url")),
                 userid=site_obj.userid,

app/modules/indexer/parser/gazelle.py

@@ -93,6 +93,27 @@ class GazelleSiteUserInfo(SiteParserBase):
                     '//div[contains(@class, "box_userinfo_stats")]//li[contains(text(), "加入时间")]/span/text()')
                 if join_at_text:
                     self.join_at = time_tools.normalize_datetime(join_at_text[0].strip())
+
+            # 兼容部分 Gazelle 站点(如 JPopsuki)以文本形式展示上传/下载:
+            # <li>Uploaded: 77.44 GB</li> / <li>Downloaded: 8.51 GB</li>
+            if not self.upload:
+                upload_text = html.xpath(
+                    '//li[starts-with(normalize-space(text()), "Uploaded:")]')
+                if upload_text:
+                    size_match = re.search(
+                        r"([\d.,]+\s*[GMKT]?i?B)", upload_text[0].xpath("string(.)"), re.I)
+                    if size_match:
+                        self.upload = size_tools.parse_size(size_match.group(1))
+            if not self.download:
+                download_text = html.xpath(
+                    '//li[starts-with(normalize-space(text()), "Downloaded:")]')
+                if download_text:
+                    size_match = re.search(
+                        r"([\d.,]+\s*[GMKT]?i?B)", download_text[0].xpath("string(.)"), re.I)
+                    if size_match:
+                        self.download = size_tools.parse_size(size_match.group(1))
+            if not self.ratio and self.upload and self.download:
+                self.ratio = round(self.upload / self.download, 3)
         finally:
             if html is not None:
                 del html

app/modules/indexer/parser/nexus_project.py

@@ -1,6 +1,8 @@
 # -*- coding: utf-8 -*-
 import re
 
+from lxml import etree
+
 from app.modules.indexer.parser import SiteSchema
 from app.modules.indexer.parser.nexus_php import NexusPhpSiteUserInfo
 
@@ -11,9 +13,45 @@ class NexusProjectSiteUserInfo(NexusPhpSiteUserInfo):
     def _parse_site_page(self, html_text: str):
         html_text = self._prepare_html_text(html_text)
 
-        user_detail = re.search(r"userdetails.php\?id=(\d+)", html_text)
+        user_detail = re.search(r"userdetails\.php\?id=(\d+)", html_text)
         if user_detail and user_detail.group().strip():
             self._user_detail_page = user_detail.group().strip().lstrip('/')
             self.userid = user_detail.group(1)
+        else:
+            # 兼容部分 NexusProject 变种站点(如 star-space.net)的
+            # p_user/user_detail.php?uid= 用户定位格式
+            user_detail = re.search(r"user_detail\.php\?uid=(\d+)", html_text)
+            if user_detail and user_detail.group().strip():
+                self._user_detail_page = user_detail.group().strip().lstrip('/')
+                self.userid = user_detail.group(1)
+                uname = re.search(
+                    r"user_detail\.php\?uid=\d+[^>]*?>\s*<[^>]*>([^<]+)<", html_text)
+                if uname:
+                    self.username = uname.group(1).strip()
 
         self._torrent_seeding_page = f"viewusertorrents.php?id={self.userid}&show=seeding"
+
+    def _parse_user_traffic_info(self, html_text):
+        # 兼容部分 NexusProject 变种站点(如 star-space.net)以
+        # span#user_info / span#user_info_no_hover 文本展示流量:
+        # "上传：445.11 G" / "下载：29.61 G"(单位无 B 后缀)
+        try:
+            html = etree.HTML(html_text)
+            if html is not None:
+                body_text = " ".join(html.xpath(
+                    '//span[@id="user_info"]//text() | //span[@id="user_info_no_hover"]//text()'))
+                size_match = re.search(r"上传[：:]\s*([\d.,]+)\s*([GMKT]?i?B?)", body_text, re.I)
+                if size_match:
+                    self.upload = self.num_filesize(
+                        f"{size_match.group(1).replace(',', '')} {size_match.group(2).upper()}B")
+                size_match = re.search(r"下载[：:]\s*([\d.,]+)\s*([GMKT]?i?B?)", body_text, re.I)
+                if size_match:
+                    self.download = self.num_filesize(
+                        f"{size_match.group(1).replace(',', '')} {size_match.group(2).upper()}B")
+                if self.upload and self.download:
+                    self.ratio = round(self.upload / self.download, 3)
+                if self.upload or self.download:
+                    return
+        except Exception:
+            pass
+        super()._parse_user_traffic_info(html_text)