fix(sites): HHClub parsing, resource list layout and request restraint

HHClub (憨憨) was checked read-only against a real account (one detail
request; list, user data and health came from the product's own fetch).

Parsing fixes:
- list titles carried the site's new-torrent marker "[新]" (58 of 100
  rows; the detail page title has none); stripped with a replace filter
- refreshing a detail overwrote seeders / leechers / snatched / category
  name / H&R with null because the HHClub div detail page lacks them;
  detail values now fall back to the list snapshot (mergeDetailOverList),
  and an unknown detail promotion keeps the list promotion
- level "贵宾" is VIP (umt.vipLevels)
- sanitized minimal fixture HHANCLUB_LIST_PAGE_2026 + tests; README marks
  HHClub as verified 2026-09-29
Size, counts, category ids/names, +08:00 time and subtitle were correct.

Request restraint:
- site definitions may carry umt.defaults; merged with settings.sites
  (longer intervals, fewer pages): new settings defaultSnapshotMaxPages 1,
  defaultHealthCheckIntervalSec 6 h, defaultDetailCacheSec 24 h; default
  burst 2. HHClub: snapshot 60 min page 1 only, health 6 h, search
  concurrency 1, detail cache 24 h, 1 token / 3 s burst 2
- periodic / manual snapshots are capped to that page count; scheduled
  health checks skip sites checked within the interval; detail refresh is
  served from cache inside the window; live searches on one site queue
- every rate-limiter token is counted per site per hour
  (site_request_count, migration 0046); GET /sites/{id}/request-stats;
  site overview and resource list show requests in the last 24 hours

Resource list: two-layer rows. Main line: title + spec tags (episodes,
resolution, source, codec, HDR, group, 国语/中字, site tags) + promotion
with time left + H&R. Second line: subtitle (one line, ellipsis) and
fixed-width category / size / seed-leech-snatched / upload time
(relative, absolute on hover) columns, stale badge, inventory overlay;
folds into a card on phones.

Also aligns identity_candidate.normalized_title order in db types with
the migrations (schema drift test).

Takes effect after the stack is rebuilt (migration 0046).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
rootandClaude Opus 5.5 committed 2026-09-29 15:18:15 +08:00
1 parent 20b63db254
commit 901b01d1a1
43 files changed
+1222 -1315

No files matched your search

+8
View File
@@ -472,6 +472,14 @@ export const Api = {
query: CursorQuery,
response: cursorPage(sources.SiteSnapshot),
}),
requestStats: ep({
method: "get",
path: "/sites/{id}/request-stats",
scope: "read",
summary: "站点请求统计:最近 24 小时对该站发出的请求次数(按小时)与生效的访问默认",
params: IdParam,
response: sources.SiteRequestStats,
}),
credentials: ep({
method: "put",
path: "/sites/{id}/credentials",
+21 -1
View File
@@ -237,6 +237,20 @@ export const SitesSettings = z.object({
proxyUrl: z.url().nullable(),
/** 用户数据做种分页上限 */
userDataMaxSeedingPages: z.number().int().min(1).max(50),
/** 快照(定时 / 手动)最多抓几页列表;站点定义给了更小的值时取更小的 */
defaultSnapshotMaxPages: z.number().int().min(1).max(20),
/** 同一站点两次定时健康检测的最短间隔(秒);站点定义给了更长的取更长的 */
defaultHealthCheckIntervalSec: z
.number()
.int()
.min(900)
.max(7 * 24 * 3600),
/** 详情页结果缓存(秒):期内不重复抓同一条详情;0 = 不缓存 */
defaultDetailCacheSec: z
.number()
.int()
.min(0)
.max(7 * 24 * 3600),
});
export type SitesSettings = z.infer<typeof SitesSettings>;
@@ -459,11 +473,14 @@ export const DEFAULT_SETTINGS: GlobalSettings = {
},
metadata: { tmdbApiKeySecretRef: null, tmdbBaseUrl: null },
sites: {
defaultRateLimit: { requestsPerMinute: 20, concurrency: 1 },
defaultRateLimit: { requestsPerMinute: 20, concurrency: 2 },
defaultSnapshotIntervalSec: 3600,
userAgent: DEFAULT_SITE_USER_AGENT,
proxyUrl: null,
userDataMaxSeedingPages: 10,
defaultSnapshotMaxPages: 1,
defaultHealthCheckIntervalSec: 21600,
defaultDetailCacheSec: 86400,
},
naming: { ...DEFAULT_NAMING_TEMPLATES, lockFileNameForBound: false },
identity: { eagerTmdbLookup: false, poolArchiveDays: 30 },
@@ -655,6 +672,9 @@ export const SETTINGS_SECTIONS: readonly SettingsSectionDef[] = [
"sites.userAgent",
"sites.proxyUrl",
"sites.userDataMaxSeedingPages",
"sites.defaultSnapshotMaxPages",
"sites.defaultHealthCheckIntervalSec",
"sites.defaultDetailCacheSec",
"search.defaultSiteMode",
"search.siteIds",
],
+22
View File
@@ -523,6 +523,28 @@ export const SiteSnapshot = EntityBase.extend({
});
export type SiteSnapshot = z.infer<typeof SiteSnapshot>;
/** 站点访问默认(站点定义 umt.defaults 与 settings.sites 合并后,取更保守的一方) */
export const SiteAccessDefaults = z.object({
snapshotIntervalSec: z.number().int(),
snapshotMaxPages: z.number().int(),
healthCheckIntervalSec: z.number().int(),
detailCacheSec: z.number().int(),
searchConcurrency: z.number().int(),
});
export type SiteAccessDefaults = z.infer<typeof SiteAccessDefaults>;
/** 站点请求统计:每从站点限流器拿到一个令牌记一次(列表 / 搜索 / 详情 / 下载 / 登录 / 用户数据 / 原站视图) */
export const SiteRequestStats = z.object({
siteId: z.string(),
last24h: z.number().int(),
/** 最近 24 个整点小时(旧 → 新),没有请求的小时计 0 */
hourly: z.array(z.object({ hour: z.string(), count: z.number().int() })),
/** 快照实际周期(站点行设置优先) */
snapshotIntervalSec: z.number().int(),
access: SiteAccessDefaults,
});
export type SiteRequestStats = z.infer<typeof SiteRequestStats>;
/** 站点注册表条目(随产品发布的适配器定义)+ 是否已在本系统登记 */
export const SiteDefinitionView = z.object({
key: z.string(),
+2
View File
@@ -138,6 +138,8 @@ const INTERNAL_TABLES = [
// C2-A 跨进程限流桶(0041)与 PG 缓存(0042):服务端内部,缓存经 /cache/* 的专用 DTO 暴露
"RateLimitBucket",
"KvCache",
// 站点请求计数(0046):服务端内部,经 GET /sites/{id}/request-stats 的专用 DTO 暴露
"SiteRequestCount",
// W9-I 进程心跳(0034):服务端内部,经 /system/health 的专用 DTO 暴露
"ProcessHeartbeat",
"ProcessHeartbeatSample",