feat(scrape): 任意目录就地刮削,按路径识别作品,每次刮削一条记录(SCR-2)

- POST /files/scrape 改为对目录 / 视频文件刮削:已登记用作品,否则按路径识别(本地 + TMDB),
  认不准返回候选,选定后再提交;未登记直接用 TMDB 字段,addToLibrary 顺手建作品
- 作品详情重新刮削、入库后自动刮削改为对作品目录刮削,同一实现
- 迁移 0058_scrape_record 替代 media_scrape;GET /files/scrape-records
- 与 MP ScrapingChain 的文件布局差分(7 个场景,3 处登记偏离)

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
rootandClaude Opus 5.5 committed 2026-10-01 00:08:17 +08:00
1 parent f60254e265
commit 87bf33b42b
29 files changed
+2272 -653

No files matched your search

+26 -4
View File
@@ -22,6 +22,7 @@ import { EventBus } from "../../src/http/sse.ts";
import { createLogger } from "../../src/logger.ts";
import { fakeEngine } from "../../src/modules/acquisition-organize/__tests__/harness.ts";
import { executeRecord, type FrozenPlan } from "../../src/modules/acquisition-organize/services/organize.ts";
import { runScrapeRecord } from "../../src/modules/acquisition-organize/services/scrape.ts";
import { createCapabilityRegistry } from "../../src/modules/agent/capability-registry.ts";
import { createFileManagerModule, type FmOverrides } from "../../src/modules/file-manager/index.ts";
import type { ServerContext } from "../../src/modules/types.ts";
@@ -57,6 +58,17 @@ export async function pgAvailable() {
// biome-ignore lint/suspicious/noExplicitAny: 测试断言直接读响应 JSON
type Loose = any;
/** catalog.lookup 远端候选(测试用) */
export interface RemoteHit {
provider: string;
entityType: "movie" | "tv";
externalId: string;
title: string;
originalTitle?: string | null;
year: number | null;
posterPath?: string | null;
}
export interface FmHarness {
db: Kysely<DB>;
engine: ReturnType<typeof fakeEngine>;
@@ -80,7 +92,11 @@ export async function createFmHarness(
name: string,
overrides: FmOverrides = {},
/** runTransfers(默认 true):假引擎收到 /files 移动/复制的 verifyAndImport 时就地执行(模拟 worker) */
opts: { catalog?: boolean; runTransfers?: boolean } = {},
opts: {
/** true = 内置假 catalog.lookup("Remote Film");函数 = 自定义远端候选(按查询词返回) */
catalog?: boolean | ((query: string) => RemoteHit[]);
runTransfers?: boolean;
} = {},
): Promise<FmHarness> {
const schema = `fm_test_${name}_${process.pid.toString(36)}${Math.random().toString(36).slice(2, 7)}`;
const admin = new pg.Client({ connectionString: DB_URL });
@@ -124,9 +140,12 @@ export async function createFmHarness(
if (opts.catalog)
capabilities.register(capabilitySpec("catalog.lookup"), async (input) => ({
local: [],
remote: String(input.query).includes("Remote")
? [{ provider: "tmdb", entityType: "movie" as const, externalId: "999", title: "Remote Film", year: 2019 }]
: [],
remote:
typeof opts.catalog === "function"
? opts.catalog(String(input.query))
: String(input.query).includes("Remote")
? [{ provider: "tmdb", entityType: "movie" as const, externalId: "999", title: "Remote Film", year: 2019 }]
: [],
}));
const ctx: ServerContext = {
role: "all",
@@ -173,6 +192,9 @@ export async function createFmHarness(
engine.enqueue = async (task, input, o) => {
const r = await enqueue(task, input, o);
const recordId = (input as { recordId?: string }).recordId;
// SCR-2 刮削:模拟 worker 就地执行 scrapeMedia
if (task === "scrapeMedia" && recordId)
setTimeout(() => void runScrapeRecord(module.deps().ao, recordId).catch(() => {}), 0);
if (task === "verifyAndImport" && recordId)
setTimeout(async () => {
try {