feat(sites): sync MoviePilot v3.2.4 spiders and M-Team subtitle APIs

packages/adapters/src/sites/spider/adapter.ts

@@ -1,7 +1,8 @@
 /**
+ * @mp-source app/modules/indexer/__init__.py @ 3b156a5
  * 通用 spider 站点适配器(NexusPHP 等 HTML 站)。
  *
- * 对应 MoviePilot e6820a8:
+ * 对应 MoviePilot v3.2.4:
  * - `app/modules/indexer/__init__.py IndexerModule.search_torrents / refresh_torrents` → `search` / `list`
  *   (`__search_check` 的英文站不搜中文 → search 前检查;`__clear_search_text` → `clearSearchText`;
  *    `SitesHelper.check(domain)` 流控 → 站点令牌桶)
@@ -134,6 +135,7 @@ export function createSpiderSiteAdapter(input: IndexerDefinition, deps: SiteAdap
 
   async function cookie(): Promise<string> {
     const c = await deps.secrets.resolve({ siteId: def.id, kind: "cookie" });
+    if (!c && def.public) return "";
     if (!c) throw new SiteError(def.id, "auth_missing", "未配置站点 Cookie");
     return c;
   }
@@ -153,9 +155,10 @@ export function createSpiderSiteAdapter(input: IndexerDefinition, deps: SiteAdap
   /** 页面认不出来时的错误:像人机验证就报 challenge,否则 parse_error;都附页面样本 */
   function unrecognized(page: FetchedPage, what: string, kind: SiteRequestKind, parseMessage: string): SiteError {
     const rule = challengeRuleOfUnrecognizedPage(page.html);
+    const title = redactText(loadHtml(page.html)("title").first().text().replace(/\s+/g, " ").trim()).slice(0, 120);
     const message = rule
       ? `${what}：${PAGE_LABEL[kind]}需要人机验证（Cloudflare 等），${challengeOutcomeText("unhandled")}`
-      : `${parseMessage}（页面样本见站点页技术信息）`;
+      : `${parseMessage}（HTTP ${page.status}${title ? `，页面标题：${title}` : ""}；页面样本见站点页技术信息）`;
     const sample = buildFailureSample({
       kind: rule ? "challenge" : "parse_error",
       requestKind: kind,
@@ -186,7 +189,11 @@ export function createSpiderSiteAdapter(input: IndexerDefinition, deps: SiteAdap
     try {
       res = await siteFetch(http, url, {
         method: "GET",
-        headers: { cookie: await cookie(), accept: "text/html,application/xhtml+xml", referer: base },
+        headers: {
+          cookie: await cookie(),
+          accept: "text/html,application/xhtml+xml,application/rss+xml,application/xml",
+          referer: base,
+        },
         redirect: "manual",
         ...(opts.signal ? { signal: opts.signal } : {}),
       });
@@ -260,7 +267,8 @@ export function createSpiderSiteAdapter(input: IndexerDefinition, deps: SiteAdap
     if (parsed.torrents.length === 0) {
       const text = $("body").text();
       const hasList =
-        $(normalizeSelector(spider.def.torrents.list.selector)).length > 0 || $("table.torrents").length > 0;
+        $(normalizeSelector(spider.def.torrents.list.selector)).length > 0 ||
+        $("table.torrents, rss > channel, feed").length > 0;
       const empty = (ext.emptyMarkers ?? []).some((m) => text.includes(m));
       // 认不出列表:先看是不是人机验证页(搜索页单独加盾、间歇触发),不是才报改版
       if (!hasList && !empty) throw unrecognized(page$, what, kind, `${what}:页面结构无法识别(可能改版)`);
@@ -289,8 +297,8 @@ export function createSpiderSiteAdapter(input: IndexerDefinition, deps: SiteAdap
     return {
       items,
       page: Math.max(1, page),
-      totalPages: maxRaw === null ? null : Math.max(page, (maxRaw as number) - start + 1),
-      totalPagesEstimated: true,
+      totalPages: parsed.totalPages ?? (maxRaw === null ? null : Math.max(page, (maxRaw as number) - start + 1)),
+      totalPagesEstimated: parsed.totalPages === undefined,
       fetchedAt: observedAt,
     };
   }