-
正在招募 · {payload.task.brand}
+
+
正在招募 · {payload.task.brand}
+
+
{payload.task.name}
{payload.task.type === "screenshot_collect"
diff --git a/koc-portal/tests/rendered-html.test.mjs b/koc-portal/tests/rendered-html.test.mjs
index d4a3aef..0ea1a0c 100644
--- a/koc-portal/tests/rendered-html.test.mjs
+++ b/koc-portal/tests/rendered-html.test.mjs
@@ -37,14 +37,31 @@ test("keeps claiming minimal and backfill one-to-one", async () => {
assert.match(page, /发布链接/);
assert.match(page, /识别发布账号/);
assert.match(page, /inputMode="url"/);
- assert.match(page, /长链、短链或整段分享文案/);
+ assert.match(page, /作品链接或整段分享文案/);
assert.doesNotMatch(page, /type="url"/);
assert.match(page, /发布截图/);
assert.match(page, /发布配图/);
assert.match(page, /复制标题/);
assert.match(page, /复制文案/);
assert.match(page, /下载原图/);
+ assert.match(page, /下载视频/);
+ assert.match(page, /download\s*=\s*false/);
+ assert.match(page, /params\.set\("download", "1"\)/);
+ assert.match(page, /视频-\$\{index \+ 1\}\.mp4/);
+ assert.match(page, /function PlatformBadge/);
+ assert.match(page, /platform-logo/);
+ assert.match(page, /logoOnly/);
+ assert.match(page, /platform-video-thumb/);
+ assert.match(styles, /\.platform-logo\.xiaohongshu/);
+ assert.match(styles, /\.platform-logo\.douyin/);
+ assert.match(styles, /\.platform-badge\.logo-only/);
assert.match(page, /批量保存图片/);
+ assert.match(page, /导出Excel/);
+ assert.match(page, /上传回填表/);
+ assert.match(page, /\/api\/partner-batch-workbook/);
+ assert.match(page, /compactPartnerBatchWorkbookForUpload/);
+ assert.match(page, /Content-Type/);
+ assert.match(page, /response\.status === 413/);
assert.match(page, /navigator\.share/);
assert.match(page, /zipSync/);
assert.match(page, /navigator\.clipboard\.writeText/);
@@ -61,7 +78,7 @@ test("keeps claiming minimal and backfill one-to-one", async () => {
assert.match(page, /scrollIntoView/);
assert.match(page, /matchMedia\("\(max-width: 620px\)"\)/);
assert.match(styles, /\.note-document\.mobile-collapsed/);
- assert.doesNotMatch(page, /批量回填/);
+ assert.match(page, /批量回填/);
assert.doesNotMatch(page, /复制标题和正文/);
assert.match(page, /CONFIGURED_ADMIN_ORIGIN/);
assert.match(page, /window\.location\.origin/);
diff --git a/lib/account-enrichment-service.ts b/lib/account-enrichment-service.ts
index a4cd75b..738747b 100644
--- a/lib/account-enrichment-service.ts
+++ b/lib/account-enrichment-service.ts
@@ -1,7 +1,7 @@
import {
resolveXhsPublicAccountDetails,
- resolveXhsAccountProfileFromMcp,
- resolveXhsProfileDetailsFromMcp,
+ resolveAccountProfileFromMcp,
+ resolveProfileDetailsFromMcp,
type CollectionMcpConfig,
} from "./mcp-collection-client";
import { hashText } from "./mvp-db";
@@ -11,15 +11,20 @@ type DistributionAccountRow = {
id: string;
account_id: string | null;
publish_url: string | null;
+ platform: string;
+ claimant_contact: string | null;
};
type BackfillRow = DistributionAccountRow & {
+ resolved_account_id: string | null;
nickname: string | null;
- platform: string | null;
platform_uid: string | null;
public_account_id: string | null;
profile_url: string | null;
followers: number | null;
+ gender: string | null;
+ bio: string | null;
+ tags: string | null;
};
function isVerifiedXhsProfileUrl(value: string | null) {
@@ -37,6 +42,23 @@ function isVerifiedXhsProfileUrl(value: string | null) {
}
}
+function isVerifiedDouyinProfileUrl(value: string | null) {
+ if (!value) return false;
+ try {
+ const url = new URL(value);
+ const secUid = decodeURIComponent(url.pathname.match(/^\/user\/([^/?#]+)/)?.[1] ?? "");
+ return (
+ url.protocol === "https:" &&
+ (url.hostname === "douyin.com" ||
+ url.hostname.endsWith(".douyin.com")) &&
+ /^[A-Za-z0-9_-]{20,220}$/.test(secUid) &&
+ !/^\d+$/.test(secUid)
+ );
+ } catch {
+ return false;
+ }
+}
+
export async function enrichDistributionAccount(
db: DatabaseClient,
distributionId: string,
@@ -44,27 +66,42 @@ export async function enrichDistributionAccount(
fallbackNickname: string,
mcpConfig: CollectionMcpConfig,
) {
- const profile = await resolveXhsAccountProfileFromMcp(
- publishUrl,
- fallbackNickname,
- mcpConfig,
- );
const current = await db
.prepare(
- `SELECT id, account_id, publish_url
- FROM distributions
- WHERE id = ?`,
+ `SELECT d.id, d.account_id, d.publish_url, t.platform,
+ cl.claimant_name AS claimant_contact
+ FROM distributions d
+ JOIN tasks t ON t.id = d.task_id
+ LEFT JOIN claims cl ON cl.id = d.claim_id
+ WHERE d.id = ?`,
)
.bind(distributionId)
.first();
if (!current || current.publish_url !== publishUrl) {
return { updated: false, reason: "stale" as const };
}
+ const platform = current.platform === "抖音" ? "抖音" : "小红书";
+ const profile = await resolveAccountProfileFromMcp(
+ publishUrl,
+ fallbackNickname,
+ platform,
+ mcpConfig,
+ );
const canonicalAccountId = `account-${hashText(
- `小红书:${profile.platformUid}`,
+ `${platform}:${profile.platformUid}`,
)}`;
- if (current.account_id === canonicalAccountId) {
+ const existingAccount = await db
+ .prepare(
+ `SELECT id FROM accounts
+ WHERE platform = ? AND platform_uid = ?
+ LIMIT 1`,
+ )
+ .bind(platform, profile.platformUid)
+ .first<{ id: string }>();
+ const targetAccountId = existingAccount?.id || canonicalAccountId;
+ const currentContact = (current.claimant_contact || "").trim();
+ if (current.account_id === targetAccountId) {
await db
.prepare(
`UPDATE accounts SET
@@ -82,6 +119,12 @@ export async function enrichDistributionAccount(
WHEN ? IS NOT NULL AND (? > 0 OR followers = 0) THEN ?
ELSE followers
END,
+ gender = CASE WHEN ? != '' THEN ? ELSE gender END,
+ bio = CASE WHEN ? != '' THEN ? ELSE bio END,
+ current_contact = CASE WHEN ? != '' THEN ? ELSE current_contact END,
+ post_count = (
+ SELECT COUNT(*) FROM distributions WHERE account_id = ?
+ ),
last_seen_at = CURRENT_TIMESTAMP
WHERE id = ?`,
)
@@ -96,12 +139,19 @@ export async function enrichDistributionAccount(
profile.followers,
profile.followers,
profile.followers,
- canonicalAccountId,
+ profile.gender,
+ profile.gender,
+ profile.bio,
+ profile.bio,
+ currentContact,
+ currentContact,
+ targetAccountId,
+ targetAccountId,
)
.run();
return {
updated: true,
- accountId: canonicalAccountId,
+ accountId: targetAccountId,
profileUrl: profile.profileUrl,
};
}
@@ -111,8 +161,9 @@ export async function enrichDistributionAccount(
db
.prepare(
`INSERT INTO accounts
- (id, platform, platform_uid, public_account_id, nickname, profile_url, ip_location, followers, post_count)
- VALUES (?, '小红书', ?, ?, ?, ?, ?, ?, 1)
+ (id, platform, platform_uid, public_account_id, nickname, profile_url,
+ ip_location, followers, gender, bio, current_contact, post_count)
+ VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, 1)
ON CONFLICT(platform, platform_uid) DO UPDATE SET
public_account_id = CASE
WHEN excluded.public_account_id != ''
@@ -131,17 +182,29 @@ export async function enrichDistributionAccount(
THEN excluded.followers
ELSE accounts.followers
END,
- post_count = accounts.post_count + 1,
+ gender = CASE
+ WHEN excluded.gender != '' THEN excluded.gender ELSE accounts.gender END,
+ bio = CASE
+ WHEN excluded.bio != '' THEN excluded.bio ELSE accounts.bio END,
+ current_contact = CASE
+ WHEN excluded.current_contact != ''
+ THEN excluded.current_contact
+ ELSE accounts.current_contact
+ END,
last_seen_at = CURRENT_TIMESTAMP`,
)
.bind(
- canonicalAccountId,
+ targetAccountId,
+ platform,
profile.platformUid,
profile.redId,
profile.nickname || fallbackNickname,
profile.profileUrl,
profile.ipLocation,
profile.followers ?? 0,
+ profile.gender,
+ profile.bio,
+ currentContact,
),
db
.prepare(
@@ -150,10 +213,25 @@ export async function enrichDistributionAccount(
updated_at = CURRENT_TIMESTAMP
WHERE id = ? AND publish_url = ?`,
)
- .bind(canonicalAccountId, distributionId, publishUrl),
+ .bind(targetAccountId, distributionId, publishUrl),
+ db
+ .prepare(
+ `UPDATE accounts SET post_count = (
+ SELECT COUNT(*) FROM distributions WHERE account_id = ?
+ ) WHERE id = ?`,
+ )
+ .bind(targetAccountId, targetAccountId),
]);
- if (provisionalAccountId) {
+ if (provisionalAccountId && provisionalAccountId !== targetAccountId) {
+ await db
+ .prepare(
+ `UPDATE accounts SET post_count = (
+ SELECT COUNT(*) FROM distributions WHERE account_id = ?
+ ) WHERE id = ?`,
+ )
+ .bind(provisionalAccountId, provisionalAccountId)
+ .run();
await db
.prepare(
`DELETE FROM accounts
@@ -165,14 +243,14 @@ export async function enrichDistributionAccount(
)
.bind(
provisionalAccountId,
- canonicalAccountId,
+ targetAccountId,
provisionalAccountId,
)
.run();
}
return {
updated: true,
- accountId: canonicalAccountId,
+ accountId: targetAccountId,
profileUrl: profile.profileUrl,
};
}
@@ -188,15 +266,22 @@ export async function backfillAccountProfiles(
d.id,
d.account_id,
d.publish_url,
+ a.id AS resolved_account_id,
a.nickname,
- a.platform,
+ COALESCE(a.platform, t.platform) AS platform,
a.platform_uid,
a.public_account_id,
a.profile_url,
- a.followers
+ a.followers,
+ a.gender,
+ a.bio,
+ a.tags,
+ cl.claimant_name AS claimant_contact
FROM distributions d
+ JOIN tasks t ON t.id = d.task_id
LEFT JOIN accounts a ON a.id = d.account_id
- WHERE d.publish_url IS NOT NULL
+ LEFT JOIN claims cl ON cl.id = d.claim_id
+ WHERE d.publish_url IS NOT NULL
AND d.publish_url != ''
ORDER BY d.updated_at DESC
LIMIT 100`,
@@ -205,8 +290,34 @@ export async function backfillAccountProfiles(
let attempted = 0;
let updated = 0;
let failed = 0;
+ const backfilledAccounts = new Set();
for (const row of rows.results) {
+ if (
+ row.resolved_account_id &&
+ !backfilledAccounts.has(row.resolved_account_id)
+ ) {
+ backfilledAccounts.add(row.resolved_account_id);
+ const claimantContact = row.claimant_contact?.trim() || "";
+ await db
+ .prepare(
+ `UPDATE accounts
+ SET current_contact = CASE
+ WHEN ? != '' THEN ? ELSE current_contact
+ END,
+ post_count = (
+ SELECT COUNT(*) FROM distributions WHERE account_id = ?
+ )
+ WHERE id = ?`,
+ )
+ .bind(
+ claimantContact,
+ claimantContact,
+ row.resolved_account_id,
+ row.resolved_account_id,
+ )
+ .run();
+ }
if (attempted >= Math.max(1, Math.min(25, limit))) break;
const noteId = (() => {
try {
@@ -227,19 +338,31 @@ export async function backfillAccountProfiles(
row.platform === "小红书" &&
!isDemoAccount &&
isVerifiedXhsProfileUrl(row.profile_url) &&
- (!row.public_account_id || Number(row.followers ?? 0) === 0)
+ (!row.public_account_id ||
+ Number(row.followers ?? 0) === 0 ||
+ !row.gender ||
+ !row.bio)
) {
attempted += 1;
attemptedThisRow = true;
- const details = await resolveXhsProfileDetailsFromMcp(
+ const details = await resolveProfileDetailsFromMcp(
row.profile_url ?? "",
+ "小红书",
mcpConfig,
- ).catch(() =>
- resolveXhsPublicAccountDetails(row.profile_url ?? ""),
- );
+ ).catch(async () => ({
+ ...(await resolveXhsPublicAccountDetails(row.profile_url ?? "")),
+ gender: "" as const,
+ bio: "",
+ recentNoteTitles: [] as string[],
+ providerTags: [] as string[],
+ }));
if (
row.account_id &&
- (details.redId || details.followers !== null)
+ (details.redId ||
+ details.followers !== null ||
+ details.gender ||
+ details.bio ||
+ details.recentNoteTitles.length > 0)
) {
await db
.prepare(
@@ -256,6 +379,8 @@ export async function backfillAccountProfiles(
WHEN ? != '' AND ? != '待识别' THEN ?
ELSE ip_location
END,
+ gender = CASE WHEN ? != '' THEN ? ELSE gender END,
+ bio = CASE WHEN ? != '' THEN ? ELSE bio END,
last_seen_at = CURRENT_TIMESTAMP
WHERE id = ?`,
)
@@ -268,6 +393,10 @@ export async function backfillAccountProfiles(
details.ipLocation ?? "",
details.ipLocation ?? "",
details.ipLocation ?? "",
+ details.gender,
+ details.gender,
+ details.bio,
+ details.bio,
row.account_id,
)
.run();
@@ -287,12 +416,17 @@ export async function backfillAccountProfiles(
}
const needsEnrichment =
!isDemoAccount &&
- (!row.account_id ||
+ (!row.resolved_account_id ||
(row.platform === "小红书" &&
!isVerifiedXhsProfileUrl(row.profile_url)) ||
+ (row.platform === "抖音" &&
+ !isVerifiedDouyinProfileUrl(row.profile_url)) ||
(row.platform === "小红书" && !row.public_account_id) ||
+ (row.platform === "抖音" && !row.public_account_id) ||
(row.platform === "小红书" &&
Number(row.followers ?? 0) === 0) ||
+ (row.platform === "抖音" &&
+ Number(row.followers ?? 0) === 0) ||
row.platform_uid?.startsWith("pending-") ||
Boolean(noteId && row.platform_uid === noteId));
if (!needsEnrichment || !row.publish_url) {
diff --git a/lib/collection-service.ts b/lib/collection-service.ts
index f0022e1..2af7559 100644
--- a/lib/collection-service.ts
+++ b/lib/collection-service.ts
@@ -1,5 +1,5 @@
import {
- collectXhsMetricsFromMcp,
+ collectMetricsFromMcp,
type CollectionMcpConfig,
} from "./mcp-collection-client";
import { uid } from "./mvp-db";
@@ -10,6 +10,7 @@ type DistributionForCollection = {
task_id: string;
publish_url: string | null;
ocr_status: string;
+ platform: string;
};
type ScheduledTask = {
@@ -165,11 +166,16 @@ export async function collectDistributionMetrics(
mcpConfig: CollectionMcpConfig,
) {
const current = await db
- .prepare("SELECT * FROM distributions WHERE id = ?")
+ .prepare(
+ `SELECT d.*, t.platform
+ FROM distributions d
+ JOIN tasks t ON t.id = d.task_id
+ WHERE d.id = ?`,
+ )
.bind(distributionId)
.first();
if (!current) throw new Error("分发记录不存在");
- if (!current.publish_url) throw new Error("笔记尚未回填发布链接");
+ if (!current.publish_url) throw new Error("作品尚未回填发布链接");
const scheduledAt = `${scheduledDate}T09:00:00+08:00`;
const runId = uid("run");
@@ -203,7 +209,12 @@ export async function collectDistributionMetrics(
.bind(distributionId, scheduledDate)
.first<{ id: string; status: string }>();
if (!run) throw new Error("采集任务创建失败");
- if (run.status === "success") return { skipped: true };
+ // Scheduled jobs should remain idempotent, but an operator clicking
+ // “立即采集” is explicitly asking for a fresh snapshot. Reusing the same
+ // daily run lets us correct stale or previously mis-mapped platform data.
+ if (run.status === "success" && source !== "manual") {
+ return { skipped: true };
+ }
const collectingDescription =
source === "automatic"
@@ -235,8 +246,12 @@ export async function collectDistributionMetrics(
]);
try {
- const { likes, comments, collects } =
- await collectXhsMetricsFromMcp(current.publish_url, mcpConfig);
+ const { likes, comments, collects, shares } =
+ await collectMetricsFromMcp(
+ current.publish_url,
+ current.platform === "抖音" ? "抖音" : "小红书",
+ mcpConfig,
+ );
const dayWeight = scheduleDay ?? 1;
const successDescription =
source === "automatic"
@@ -253,6 +268,7 @@ export async function collectDistributionMetrics(
likes = ?,
comments = ?,
collects = ?,
+ shares = ?,
status_description = ?,
completed_at = CURRENT_TIMESTAMP
WHERE id = ?`,
@@ -261,6 +277,7 @@ export async function collectDistributionMetrics(
likes,
comments,
collects,
+ shares,
successDescription,
run.id,
),
@@ -270,6 +287,7 @@ export async function collectDistributionMetrics(
SET latest_likes = ?,
latest_comments = ?,
latest_collects = ?,
+ latest_shares = ?,
collection_status = 'success',
collection_status_description = ?,
collection_updated_at = CURRENT_TIMESTAMP,
@@ -285,12 +303,13 @@ export async function collectDistributionMetrics(
likes,
comments,
collects,
+ shares,
successDescription,
scheduleDay,
distributionId,
),
]);
- return { skipped: false, likes, comments, collects };
+ return { skipped: false, likes, comments, collects, shares };
} catch (error) {
const message =
error instanceof Error ? error.message : "公开数据采集失败";
diff --git a/lib/feishu-client.ts b/lib/feishu-client.ts
index cc5ef49..32138ad 100644
--- a/lib/feishu-client.ts
+++ b/lib/feishu-client.ts
@@ -2,7 +2,7 @@ const FEISHU_API_ORIGIN = "https://open.feishu.cn";
const MAX_SHEET_ROWS = 5_000;
const MAX_SHEET_COLUMNS = 100;
const MAX_CONTENT_ROWS = 1_000;
-const MAX_MEDIA_BYTES = 20_000_000;
+const DEFAULT_MAX_MEDIA_BYTES = 200_000_000;
export type FeishuBindings = {
FEISHU_APP_ID?: string;
@@ -16,11 +16,20 @@ export type FeishuSourceImage = {
height: number | null;
};
+export type FeishuSourceVideo = {
+ index: number;
+ fileToken: string;
+ name: string;
+ mimeType: string;
+ size: number | null;
+};
+
export type FeishuSourceRow = {
sourceRow: number;
title: string;
body: string;
images: FeishuSourceImage[];
+ videos: FeishuSourceVideo[];
};
export type FeishuSource = {
@@ -106,12 +115,47 @@ function cellText(value: unknown): string {
.filter(Boolean)
.join("");
}
- if (!isRecord(value) || value.type === "embed-image") return "";
+ if (
+ !isRecord(value) ||
+ value.type === "embed-image" ||
+ value.type === "attachment"
+ ) return "";
if (typeof value.text === "string") return value.text.trim();
if (typeof value.value === "string") return value.value.trim();
return "";
}
+function extractVideos(value: unknown, output: FeishuSourceVideo[]) {
+ if (Array.isArray(value)) {
+ for (const item of value) extractVideos(item, output);
+ return;
+ }
+ if (!isRecord(value)) return;
+ const fileToken = bindingValue(value.fileToken ?? value.file_token);
+ const mimeType = bindingValue(value.mimeType ?? value.mime_type);
+ const name = bindingValue(value.text ?? value.name ?? value.file_name);
+ const isVideo =
+ value.type === "attachment" &&
+ (mimeType.startsWith("video/") || /\.(?:mp4|mov|m4v|webm)$/i.test(name));
+ if (isVideo && fileToken) {
+ output.push({
+ index: 0,
+ fileToken,
+ name: name || "视频",
+ mimeType: mimeType || "video/mp4",
+ size:
+ typeof value.size === "number" && Number.isFinite(value.size)
+ ? value.size
+ : null,
+ });
+ }
+ for (const child of Object.values(value)) {
+ if (child !== value.fileToken && child !== value.file_token) {
+ extractVideos(child, output);
+ }
+ }
+}
+
function extractImages(value: unknown, output: FeishuSourceImage[]) {
if (Array.isArray(value)) {
for (const item of value) extractImages(item, output);
@@ -167,6 +211,7 @@ function findHeader(values: unknown[][]) {
titleIndex: number;
bodyIndex: number;
tagsIndex: number;
+ videoIndex: number;
score: number;
}
| undefined;
@@ -185,9 +230,13 @@ function findHeader(values: unknown[][]) {
const tagsIndex = headers.findIndex((header) =>
headerMatches(header, [/标签/, /话题/, /^tags?$/]),
);
+ const videoIndex = headers.findIndex((header) =>
+ headerMatches(header, [/^视频\d*$/, /视频文件/, /视频素材/]),
+ );
const score =
(titleIndex >= 0 ? 5 : 0) +
(bodyIndex >= 0 ? 5 : 0) +
+ (videoIndex >= 0 ? 2 : 0) +
(idIndex >= 0 ? 1 : 0) +
(tagsIndex >= 0 ? 1 : 0);
if (!best || score > best.score) {
@@ -197,6 +246,7 @@ function findHeader(values: unknown[][]) {
titleIndex,
bodyIndex,
tagsIndex,
+ videoIndex,
score,
};
}
@@ -217,6 +267,7 @@ function parseRows(values: unknown[][]) {
const usedSourceRows = new Set();
const rows: FeishuSourceRow[] = [];
let maxImageCount = 0;
+ let maxVideoCount = 0;
for (
let rowIndex = header.rowIndex + 1;
@@ -253,7 +304,20 @@ function parseRows(values: unknown[][]) {
})
.map((image, imageIndex) => ({ ...image, index: imageIndex + 1 }));
maxImageCount = Math.max(maxImageCount, images.length);
- rows.push({ sourceRow, title, body, images });
+ const collectedVideos: FeishuSourceVideo[] = [];
+ if (header.videoIndex >= 0) {
+ extractVideos(row[header.videoIndex], collectedVideos);
+ }
+ const seenVideoTokens = new Set();
+ const videos = collectedVideos
+ .filter((video) => {
+ if (seenVideoTokens.has(video.fileToken)) return false;
+ seenVideoTokens.add(video.fileToken);
+ return true;
+ })
+ .map((video, videoIndex) => ({ ...video, index: videoIndex + 1 }));
+ maxVideoCount = Math.max(maxVideoCount, videos.length);
+ rows.push({ sourceRow, title, body, images, videos });
}
if (rows.length === 0) {
@@ -266,6 +330,7 @@ function parseRows(values: unknown[][]) {
header.tagsIndex >= 0 ? cellText(headerRow[header.tagsIndex]) : "",
cellText(headerRow[header.bodyIndex]) || "正文",
...Array.from({ length: maxImageCount }, (_, index) => `图片${index + 1}`),
+ ...Array.from({ length: maxVideoCount }, (_, index) => `视频${index + 1}`),
].filter(Boolean);
return {
@@ -515,34 +580,37 @@ export async function downloadFeishuMedia(
fileToken: string,
bindings: FeishuBindings,
fetchImpl: FetchLike = fetch,
+ options: { maxBytes?: number; label?: string; timeoutMs?: number } = {},
) {
+ const maxBytes = Math.max(1, options.maxBytes ?? DEFAULT_MAX_MEDIA_BYTES);
+ const label = bindingValue(options.label) || "素材";
const normalizedToken = bindingValue(fileToken);
if (!/^[A-Za-z0-9_-]{8,240}$/.test(normalizedToken)) {
- throw new FeishuSourceError("飞书图片标识无效", 400);
+ throw new FeishuSourceError(`飞书${label}标识无效`, 400);
}
const token = await accessToken(bindings, fetchImpl);
const response = await fetchImpl(
`${FEISHU_API_ORIGIN}/open-apis/drive/v1/medias/${encodeURIComponent(normalizedToken)}/download`,
{
headers: { Authorization: `Bearer ${token}` },
- signal: AbortSignal.timeout(20_000),
+ signal: AbortSignal.timeout(options.timeoutMs ?? 120_000),
},
);
const declaredSize = Number(response.headers.get("content-length"));
- if (Number.isFinite(declaredSize) && declaredSize > MAX_MEDIA_BYTES) {
- throw new FeishuSourceError("飞书图片超过20MB，无法同步", 413);
+ if (Number.isFinite(declaredSize) && declaredSize > maxBytes) {
+ throw new FeishuSourceError(`飞书${label}文件过大，无法同步`, 413);
}
if (!response.ok) {
throw new FeishuSourceError(
response.status === 403
- ? "飞书应用没有这张图片的下载权限"
- : `下载飞书图片失败（HTTP ${response.status}）`,
+ ? `飞书应用没有这个${label}的下载权限`
+ : `下载飞书${label}失败（HTTP ${response.status}）`,
response.status === 403 ? 403 : 502,
);
}
const bytes = await response.arrayBuffer();
- if (bytes.byteLength > MAX_MEDIA_BYTES) {
- throw new FeishuSourceError("飞书图片超过20MB，无法同步", 413);
+ if (bytes.byteLength > maxBytes) {
+ throw new FeishuSourceError(`飞书${label}文件过大，无法同步`, 413);
}
return {
bytes,
diff --git a/lib/mcp-collection-client.ts b/lib/mcp-collection-client.ts
index df73d23..7b2a709 100644
--- a/lib/mcp-collection-client.ts
+++ b/lib/mcp-collection-client.ts
@@ -17,6 +17,7 @@ export type XhsPublicMetrics = {
likes: number;
comments: number;
collects: number;
+ shares: number;
};
export type XhsAccountProfile = {
@@ -26,6 +27,10 @@ export type XhsAccountProfile = {
redId: string;
ipLocation: string;
followers: number | null;
+ gender: "" | "男" | "女";
+ bio: string;
+ recentNoteTitles: string[];
+ providerTags: string[];
};
type JsonRpcEnvelope = {
@@ -341,16 +346,118 @@ function metricsFromToolResult(result: ToolResult): XhsPublicMetrics {
}
if (!data) throw new Error("采集结果缺少互动数据");
+ const count = (value: unknown, label: string) =>
+ value === null || value === undefined || value === ""
+ ? 0
+ : metricValue(value, label);
return {
- likes: metricValue(data.likes, "点赞数"),
- comments: metricValue(data.comments, "评论数"),
- collects: metricValue(
- data.collects ?? data.favorites ?? data.favourites,
+ likes: count(
+ data.likes ??
+ data.liked_count ??
+ data.likedCount ??
+ data.like_count ??
+ data.likeCount ??
+ data.digg_count ??
+ data.diggCount,
+ "点赞数",
+ ),
+ comments: count(
+ data.comments ?? data.comment_count ?? data.commentCount,
+ "评论数",
+ ),
+ collects: count(
+ data.collects ??
+ data.collected_count ??
+ data.collectedCount ??
+ data.favorites ??
+ data.favourites ??
+ data.collect_count ??
+ data.collectCount,
"收藏数",
),
+ shares: count(
+ data.shares ??
+ data.share_count ??
+ data.shareCount ??
+ data.forwards ??
+ data.forward_count ??
+ data.forwardCount,
+ "转发数",
+ ),
};
}
+function usableDouyinSecUid(value: unknown) {
+ const candidate = stringValue(value);
+ return candidate && !/^\d+$/.test(candidate) && /^[A-Za-z0-9_-]{20,220}$/.test(candidate)
+ ? candidate
+ : "";
+}
+
+function verifiedDouyinProfileUrl(value: unknown) {
+ const candidate = stringValue(value);
+ if (!candidate) return "";
+ try {
+ const parsed = new URL(candidate);
+ const secUid = decodeURIComponent(parsed.pathname.match(/^\/user\/([^/?#]+)/)?.[1] ?? "");
+ if (
+ parsed.protocol === "https:" &&
+ (parsed.hostname === "douyin.com" || parsed.hostname.endsWith(".douyin.com")) &&
+ usableDouyinSecUid(secUid)
+ ) {
+ return parsed.toString();
+ }
+ } catch {
+ // The public redirect fallback below can still recover the profile URL.
+ }
+ return "";
+}
+
+async function douyinProfileFromPublicRedirect(
+ publishUrl: string,
+ fetchImpl: typeof fetch,
+ timeoutMs: number,
+) {
+ let parsed: URL;
+ try {
+ parsed = new URL(publishUrl);
+ } catch {
+ return null;
+ }
+ if (
+ parsed.protocol !== "https:" ||
+ !(parsed.hostname === "douyin.com" || parsed.hostname.endsWith(".douyin.com"))
+ ) {
+ return null;
+ }
+ try {
+ const response = await fetchImpl(parsed.toString(), {
+ method: "GET",
+ redirect: "manual",
+ signal: AbortSignal.timeout(Math.min(timeoutMs, 15_000)),
+ headers: {
+ "user-agent":
+ "Mozilla/5.0 (iPhone; CPU iPhone OS 18_0 like Mac OS X) AppleWebKit/605.1.15 Mobile/15E148",
+ },
+ });
+ const location = response.headers.get("location");
+ if (!location) return null;
+ const redirectUrl = new URL(location, parsed);
+ const secUid = usableDouyinSecUid(
+ redirectUrl.searchParams.get("sec_uid") ??
+ redirectUrl.searchParams.get("sec_user_id"),
+ );
+ return secUid
+ ? {
+ platformUid: secUid,
+ profileUrl: `https://www.douyin.com/user/${encodeURIComponent(secUid)}`,
+ }
+ : null;
+ } catch {
+ return null;
+ }
+}
+
function successfulToolData(result: ToolResult, fallbackMessage: string) {
const root = asRecord(result.payload);
const response = asRecord(root?.response) ?? root;
@@ -446,6 +553,64 @@ function findValueByKeys(
return undefined;
}
+function profileGender(value: unknown): "" | "男" | "女" {
+ if (value === 1) return "男";
+ if (value === 2) return "女";
+ const normalized = String(value ?? "").trim().toLocaleLowerCase("zh-CN");
+ if (["男", "男性", "male", "m", "1"].includes(normalized)) return "男";
+ if (["女", "女性", "female", "f", "2"].includes(normalized)) return "女";
+ return "";
+}
+
+function recentNoteTitlesFromPayload(value: unknown) {
+ const titles: string[] = [];
+ const visit = (current: unknown, depth = 0) => {
+ if (depth > 12 || titles.length >= 20) return;
+ if (Array.isArray(current)) {
+ current.forEach((item) => visit(item, depth + 1));
+ return;
+ }
+ const record = asRecord(current);
+ if (!record) return;
+ const title = stringValue(record.title ?? record.note_title ?? record.noteTitle);
+ if (
+ title &&
+ (record.note_id || record.noteId || record.url || record.cover) &&
+ !titles.includes(title)
+ ) {
+ titles.push(title);
+ }
+ Object.values(record).forEach((child) => visit(child, depth + 1));
+ };
+ visit(value);
+ return titles;
+}
+
+function providerTagsFromUser(value: unknown) {
+ const user = findRecord(value, (record) =>
+ Boolean(
+ record.gender !== undefined ||
+ record.desc !== undefined ||
+ record.signature !== undefined ||
+ record.fansCount !== undefined ||
+ record.fans_count !== undefined,
+ ),
+ );
+ const raw = user?.tags;
+ if (!Array.isArray(raw)) return [];
+ return [
+ ...new Set(
+ raw
+ .map((item) =>
+ typeof item === "string"
+ ? item.trim()
+ : stringValue(asRecord(item)?.name ?? asRecord(item)?.title),
+ )
+ .filter(Boolean),
+ ),
+ ].slice(0, 5);
+}
+
const FOLLOWER_KEYS = new Set([
"fans",
"fans_count",
@@ -529,10 +694,13 @@ async function xhsNoteIdFromShortLink(
) {
return { noteId: "", profile: null };
}
- if (
- url.hostname !== "xhslink.cn" &&
- !url.hostname.endsWith(".xhslink.cn")
- ) {
+ const isShortLink =
+ url.hostname === "xhslink.cn" ||
+ url.hostname.endsWith(".xhslink.cn");
+ const isXhsPage =
+ url.hostname === "xiaohongshu.com" ||
+ url.hostname.endsWith(".xiaohongshu.com");
+ if (!isShortLink && !isXhsPage) {
return { noteId: "", profile: null };
}
@@ -608,6 +776,10 @@ function accountProfileFromPublicPage(
redId,
ipLocation: "待识别",
followers: null,
+ gender: "",
+ bio: "",
+ recentNoteTitles: [],
+ providerTags: [],
};
}
@@ -698,15 +870,45 @@ function profileDetailsFromToolResult(result: ToolResult) {
const redId =
findStringByKey(payload, "red_id") ||
findStringByKey(payload, "redId") ||
+ findStringByKey(payload, "unique_id") ||
+ findStringByKey(payload, "uniqueId") ||
+ findStringByKey(payload, "short_id") ||
+ findStringByKey(payload, "shortId") ||
+ findStringByKey(payload, "douyin_id") ||
findStringByKey(payload, "userId") ||
findStringByKey(payload, "user_id");
const ipLocation =
findStringByKey(payload, "ip_location") ||
findStringByKey(payload, "ipLocation");
- if (followers === null && !nickname && !redId && !ipLocation) {
+ const gender = profileGender(findValueByKeys(payload, new Set(["gender", "sex"])));
+ const bio =
+ findStringByKey(payload, "desc") ||
+ findStringByKey(payload, "description") ||
+ findStringByKey(payload, "signature") ||
+ findStringByKey(payload, "bio");
+ const recentNoteTitles = recentNoteTitlesFromPayload(payload);
+ const providerTags = providerTagsFromUser(payload);
+ if (
+ followers === null &&
+ !nickname &&
+ !redId &&
+ !ipLocation &&
+ !gender &&
+ !bio &&
+ recentNoteTitles.length === 0
+ ) {
throw new Error("账号主页采集结果缺少可用字段");
}
- return { nickname, followers, redId, ipLocation };
+ return {
+ nickname,
+ followers,
+ redId,
+ ipLocation,
+ gender,
+ bio,
+ recentNoteTitles,
+ providerTags,
+ };
}
function accountProfileFromToolResult(
@@ -718,14 +920,18 @@ function accountProfileFromToolResult(
data,
(record) =>
Boolean(
- stringValue(record.user_id ?? record.userid) &&
+ stringValue(record.user_id ?? record.userid ?? record.userId) &&
(stringValue(record.profile_url) ||
stringValue(record.nickname ?? record.name)),
),
);
if (!user) throw new Error("账号主页识别结果缺少作者信息");
- const platformUid = stringValue(user.user_id ?? user.userid);
- const candidateProfileUrl = stringValue(user.profile_url);
+ const platformUid = stringValue(
+ user.user_id ?? user.userid ?? user.userId,
+ );
+ const candidateProfileUrl = stringValue(
+ user.profile_url ?? user.profileUrl,
+ );
let profileUrl = "";
if (candidateProfileUrl) {
try {
@@ -755,6 +961,10 @@ function accountProfileFromToolResult(
redId: stringValue(user.red_id),
ipLocation: findStringByKey(data, "ip_location") || "待识别",
followers: followerCountFromPayload(data),
+ gender: "",
+ bio: "",
+ recentNoteTitles: [],
+ providerTags: [],
};
}
@@ -771,18 +981,7 @@ async function completeAccountProfile(
"parse_xhs_user_summary",
{ url: profile.profileUrl, use_proxy: true },
],
- [
- "fetch_user_detail",
- { link: profile.profileUrl, plant: "xhs" },
- ],
] as const) {
- if (
- completed.followers !== null &&
- completed.redId &&
- completed.ipLocation !== "待识别"
- ) {
- break;
- }
try {
const result = await callMcpTool(
fetchImpl,
@@ -801,6 +1000,16 @@ async function completeAccountProfile(
details.ipLocation && details.ipLocation !== "待识别"
? details.ipLocation
: completed.ipLocation,
+ gender: details.gender || completed.gender,
+ bio: details.bio || completed.bio,
+ recentNoteTitles:
+ details.recentNoteTitles.length > 0
+ ? details.recentNoteTitles
+ : completed.recentNoteTitles,
+ providerTags:
+ details.providerTags.length > 0
+ ? details.providerTags
+ : completed.providerTags,
};
} catch (error) {
if (error instanceof McpSessionLostError) throw error;
@@ -852,17 +1061,14 @@ async function resolveAccountInSession(
const endpoint = buildMcpUrl(config);
const timeoutMs = Math.max(5_000, config.timeoutMs ?? 30_000);
let noteId = xhsNoteIdFromUrl(publishUrl);
- let publicPageProfile: XhsAccountProfile | null = null;
- if (!noteId) {
- const shortLink = await xhsNoteIdFromShortLink(
- publishUrl,
- fallbackNickname,
- fetchImpl,
- timeoutMs,
- );
- noteId = shortLink.noteId;
- publicPageProfile = shortLink.profile;
- }
+ const linkPage = await xhsNoteIdFromShortLink(
+ publishUrl,
+ fallbackNickname,
+ fetchImpl,
+ timeoutMs,
+ );
+ noteId = noteId || linkPage.noteId;
+ const publicPageProfile = linkPage.profile;
try {
const sessionId = await createMcpSession(
@@ -870,47 +1076,39 @@ async function resolveAccountInSession(
endpoint,
timeoutMs,
);
- if (!noteId) {
- const noteResult = await callMcpTool(
- fetchImpl,
- endpoint,
- sessionId,
- timeoutMs,
- "fetch_content_detail",
- {
- link: publishUrl,
- plant: "xhs",
- include_comments: false,
- auto_cookie: true,
- },
- );
- const noteData = successfulToolData(
- noteResult,
- "无法识别小红书笔记",
- );
- noteId =
- stringValue(noteData.noteId ?? noteData.note_id) ||
- findStringByKey(noteData, "noteId") ||
- findStringByKey(noteData, "note_id");
- }
- if (!noteId) throw new Error("无法从发布链接识别小红书笔记ID");
-
- const authorResult = await callMcpTool(
+ const noteResult = await callMcpTool(
fetchImpl,
endpoint,
sessionId,
timeoutMs,
- "collect_xhs_wen_note_detail",
+ "fetch_content_detail",
{
- note_id: noteId,
- need_desc: false,
- include_raw: false,
+ link: publishUrl,
+ plant: "xhs",
+ include_comments: false,
+ auto_cookie: true,
},
);
- const profile = accountProfileFromToolResult(
- authorResult,
- fallbackNickname,
+ const noteData = successfulToolData(
+ noteResult,
+ "无法识别小红书笔记",
);
+ noteId =
+ noteId ||
+ stringValue(noteData.noteId ?? noteData.note_id) ||
+ findStringByKey(noteData, "noteId") ||
+ findStringByKey(noteData, "note_id");
+ if (!noteId) throw new Error("无法从发布链接识别小红书笔记ID");
+ let profile: XhsAccountProfile;
+ try {
+ profile = accountProfileFromToolResult(
+ noteResult,
+ fallbackNickname,
+ );
+ } catch {
+ if (!publicPageProfile) throw new Error("笔记数据缺少公开作者主页");
+ profile = publicPageProfile;
+ }
return completeAccountProfile(
profile,
fetchImpl,
@@ -937,6 +1135,7 @@ async function resolveAccountInSession(
async function collectInSession(
publishUrl: string,
+ platform: "小红书" | "抖音",
config: CollectionMcpConfig,
fetchImpl: typeof fetch,
) {
@@ -952,28 +1151,12 @@ async function collectInSession(
"fetch_content_detail",
{
link: publishUrl,
- plant: "xhs",
+ plant: platform === "抖音" ? "dy" : "xhs",
include_comments: false,
auto_cookie: true,
},
);
- try {
- return metricsFromToolResult(primary);
- } catch {
- const fallback = await callMcpTool(
- fetchImpl,
- endpoint,
- sessionId,
- timeoutMs,
- "parse_xhs_note",
- {
- url: publishUrl,
- include_comments: false,
- auto_cookie: true,
- },
- );
- return metricsFromToolResult(fallback);
- }
+ return metricsFromToolResult(primary);
}
export function resolveCollectionMcpConfig(
@@ -1005,7 +1188,7 @@ export async function collectXhsMetricsFromMcp(
let lastError: unknown;
for (let attempt = 0; attempt < MAX_MCP_ATTEMPTS; attempt += 1) {
try {
- return await collectInSession(parsed.toString(), config, fetchImpl);
+ return await collectInSession(parsed.toString(), "小红书", config, fetchImpl);
} catch (error) {
lastError = error;
if (!isRetryableTransportError(error)) throw error;
@@ -1022,6 +1205,211 @@ export async function collectXhsMetricsFromMcp(
: new Error("MCP采集服务暂时不可用");
}
+export async function collectMetricsFromMcp(
+ publishUrl: string,
+ platform: "小红书" | "抖音",
+ config: CollectionMcpConfig,
+ fetchImpl: typeof fetch = fetch,
+) {
+ if (platform === "小红书") {
+ return collectXhsMetricsFromMcp(publishUrl, config, fetchImpl);
+ }
+ let parsed: URL;
+ try {
+ parsed = new URL(publishUrl);
+ } catch {
+ throw new Error("发布链接无效");
+ }
+ if (!["http:", "https:"].includes(parsed.protocol)) {
+ throw new Error("发布链接无效");
+ }
+ let lastError: unknown;
+ for (let attempt = 0; attempt < MAX_MCP_ATTEMPTS; attempt += 1) {
+ try {
+ return await collectInSession(parsed.toString(), platform, config, fetchImpl);
+ } catch (error) {
+ lastError = error;
+ if (!isRetryableTransportError(error)) throw error;
+ }
+ }
+ throw lastError instanceof Error
+ ? lastError
+ : new Error("MCP采集服务暂时不可用");
+}
+
+function douyinProfileFromToolResult(
+ result: ToolResult,
+ fallbackNickname: string,
+): XhsAccountProfile {
+ const data = successfulToolData(result, "无法识别抖音作品");
+ const author = findRecord(data, (record) =>
+ Boolean(
+ stringValue(
+ record.sec_uid ?? record.secUid ?? record.uid ?? record.user_id ?? record.userId,
+ ) && stringValue(record.nickname ?? record.name ?? record.unique_id ?? record.uniqueId),
+ ),
+ );
+ if (!author) throw new Error("抖音作品数据缺少作者信息");
+ const verifiedSecUid = usableDouyinSecUid(author.sec_uid ?? author.secUid);
+ const fallbackUid = stringValue(author.uid ?? author.user_id ?? author.userId);
+ const platformUid = verifiedSecUid || fallbackUid;
+ const publicId = stringValue(
+ author.unique_id ?? author.uniqueId ?? author.short_id ?? author.shortId ?? author.douyin_id,
+ );
+ const candidateProfileUrl = verifiedDouyinProfileUrl(
+ author.profile_url ?? author.profileUrl,
+ );
+ const profileUrl = candidateProfileUrl ||
+ (verifiedSecUid
+ ? `https://www.douyin.com/user/${encodeURIComponent(verifiedSecUid)}`
+ : "");
+ return {
+ platformUid,
+ nickname: stringValue(author.nickname ?? author.name) || fallbackNickname.trim(),
+ profileUrl,
+ redId: publicId,
+ ipLocation:
+ stringValue(author.ip_location ?? author.ipLocation) ||
+ findStringByKey(data, "ip_location") ||
+ findStringByKey(data, "ipLocation") ||
+ "待识别",
+ followers: followerCountFromPayload(author) ?? followerCountFromPayload(data),
+ gender: profileGender(author.gender ?? author.sex),
+ bio: stringValue(author.desc ?? author.description ?? author.signature ?? author.bio),
+ recentNoteTitles: recentNoteTitlesFromPayload(data),
+ providerTags: providerTagsFromUser(data),
+ };
+}
+
+async function resolveDouyinAccountInSession(
+ publishUrl: string,
+ fallbackNickname: string,
+ config: CollectionMcpConfig,
+ fetchImpl: typeof fetch,
+) {
+ const endpoint = buildMcpUrl(config);
+ const timeoutMs = Math.max(5_000, config.timeoutMs ?? 30_000);
+ const sessionId = await createMcpSession(fetchImpl, endpoint, timeoutMs);
+ const result = await callMcpTool(
+ fetchImpl,
+ endpoint,
+ sessionId,
+ timeoutMs,
+ "fetch_content_detail",
+ {
+ link: publishUrl,
+ plant: "dy",
+ include_comments: false,
+ auto_cookie: true,
+ },
+ );
+ let profile = douyinProfileFromToolResult(result, fallbackNickname);
+ if (!verifiedDouyinProfileUrl(profile.profileUrl)) {
+ const resolved = await douyinProfileFromPublicRedirect(
+ publishUrl,
+ fetchImpl,
+ timeoutMs,
+ );
+ if (resolved) {
+ profile = {
+ ...profile,
+ platformUid: resolved.platformUid,
+ profileUrl: resolved.profileUrl,
+ };
+ }
+ }
+ if (!verifiedDouyinProfileUrl(profile.profileUrl)) return profile;
+ try {
+ const detailsResult = await callMcpTool(
+ fetchImpl,
+ endpoint,
+ sessionId,
+ timeoutMs,
+ "parse_dy_user_summary",
+ { url: profile.profileUrl },
+ );
+ const details = profileDetailsFromToolResult(detailsResult);
+ profile = {
+ ...profile,
+ nickname: details.nickname || profile.nickname,
+ redId: details.redId || profile.redId,
+ followers: details.followers ?? profile.followers,
+ ipLocation:
+ details.ipLocation && details.ipLocation !== "待识别"
+ ? details.ipLocation
+ : profile.ipLocation,
+ gender: details.gender || profile.gender,
+ bio: details.bio || profile.bio,
+ recentNoteTitles:
+ details.recentNoteTitles.length > 0
+ ? details.recentNoteTitles
+ : profile.recentNoteTitles,
+ providerTags:
+ details.providerTags.length > 0
+ ? details.providerTags
+ : profile.providerTags,
+ };
+ } catch (error) {
+ if (error instanceof McpSessionLostError) throw error;
+ }
+ return profile;
+}
+
+export async function resolveAccountProfileFromMcp(
+ publishUrl: string,
+ fallbackNickname: string,
+ platform: "小红书" | "抖音",
+ config: CollectionMcpConfig,
+ fetchImpl: typeof fetch = fetch,
+) {
+ if (platform === "小红书") {
+ return resolveXhsAccountProfileFromMcp(
+ publishUrl,
+ fallbackNickname,
+ config,
+ fetchImpl,
+ );
+ }
+ let lastError: unknown;
+ for (let attempt = 0; attempt < MAX_MCP_ATTEMPTS; attempt += 1) {
+ try {
+ return await resolveDouyinAccountInSession(
+ publishUrl,
+ fallbackNickname,
+ config,
+ fetchImpl,
+ );
+ } catch (error) {
+ lastError = error;
+ if (!isRetryableTransportError(error)) throw error;
+ }
+ }
+ throw lastError instanceof Error ? lastError : new Error("抖音账号识别失败");
+}
+
+export async function resolveProfileDetailsFromMcp(
+ profileUrl: string,
+ platform: "小红书" | "抖音",
+ config: CollectionMcpConfig,
+ fetchImpl: typeof fetch = fetch,
+) {
+ if (platform === "小红书") {
+ return resolveXhsProfileDetailsFromMcp(profileUrl, config, fetchImpl);
+ }
+ const endpoint = buildMcpUrl(config);
+ const timeoutMs = Math.max(5_000, config.timeoutMs ?? 30_000);
+ const sessionId = await createMcpSession(fetchImpl, endpoint, timeoutMs);
+ const result = await callMcpTool(
+ fetchImpl,
+ endpoint,
+ sessionId,
+ timeoutMs,
+ "parse_dy_user_summary",
+ { url: profileUrl },
+ );
+ return profileDetailsFromToolResult(result);
+}
+
export async function resolveXhsAccountProfileFromMcp(
publishUrl: string,
fallbackNickname: string,
diff --git a/lib/mcp-operations.ts b/lib/mcp-operations.ts
index 609b9c8..7deca3f 100644
--- a/lib/mcp-operations.ts
+++ b/lib/mcp-operations.ts
@@ -12,7 +12,7 @@ import {
type CollectionMcpBindings,
} from "./mcp-collection-client";
import { ensureSchema, getRawDb } from "./mvp-db";
-import { extractXhsPublishUrl } from "./publish-url";
+import { extractAnyPublishUrl } from "./publish-url";
import { buildClaimUrl } from "./task-service";
export type McpOperationBindings = CollectionMcpBindings & {
@@ -123,9 +123,9 @@ export async function taskGet(taskId: string, portalUrl: string) {
const [notes, claims, runs] = await Promise.all([
db
.prepare(
- `SELECT c.id AS content_id, c.source_row, c.title, c.body, c.image_assets, c.status AS content_status,
+ `SELECT c.id AS content_id, c.source_row, c.title, c.body, c.image_assets, c.video_assets, c.status AS content_status,
d.id AS distribution_id, d.status AS distribution_status, d.publish_url, d.publish_time,
- d.exposure, d.views, d.latest_likes, d.latest_comments, d.latest_collects,
+ d.exposure, d.views, d.latest_likes, d.latest_comments, d.latest_collects, d.latest_shares,
d.collection_status, d.collection_status_description, d.collection_updated_at,
a.id AS account_id, a.nickname AS account_nickname, a.profile_url, a.followers,
p.name AS cooperation_source, cl.claimant_name
@@ -172,12 +172,14 @@ export async function taskGet(taskId: string, portalUrl: string) {
notes: notes.results.map((row) => ({
...row,
image_assets: parseJsonArray(row.image_assets),
+ video_assets: parseJsonArray(row.video_assets),
total_interactions:
row.latest_likes == null
? null
: Number(row.latest_likes) +
Number(row.latest_comments ?? 0) +
- Number(row.latest_collects ?? 0),
+ Number(row.latest_collects ?? 0) +
+ Number(row.latest_shares ?? 0),
})),
claims: claims.results,
collection_runs: runs.results,
@@ -220,7 +222,8 @@ export async function recoveryList(
const [rows, count] = await Promise.all([
db
.prepare(
- `SELECT d.*, t.name AS task_name, c.source_row, c.title,
+ `SELECT d.*, t.name AS task_name, t.platform AS task_platform,
+ t.content_format, c.source_row, c.title,
a.nickname AS account_nickname, a.profile_url, p.name AS cooperation_source,
cl.claimant_name ${base}
ORDER BY COALESCE(d.publish_time, d.claimed_at) DESC LIMIT ${limit} OFFSET ${offset}`,
@@ -241,7 +244,7 @@ export async function recoveryList(
total_interactions:
row.latest_likes == null
? null
- : Number(row.latest_likes) + Number(row.latest_comments ?? 0) + Number(row.latest_collects ?? 0),
+ : Number(row.latest_likes) + Number(row.latest_comments ?? 0) + Number(row.latest_collects ?? 0) + Number(row.latest_shares ?? 0),
})),
};
}
@@ -358,9 +361,11 @@ function resourceWhere(input: ResourceFilters) {
const conditions: string[] = [];
const bindings: unknown[] = [];
if (input.query?.trim()) {
- conditions.push("(a.nickname LIKE ? ESCAPE '\\' OR a.public_account_id LIKE ? ESCAPE '\\')");
+ conditions.push(
+ "(a.nickname LIKE ? ESCAPE '\\' OR a.public_account_id LIKE ? ESCAPE '\\' OR a.current_contact LIKE ? ESCAPE '\\' OR a.tags LIKE ? ESCAPE '\\' OR a.bio LIKE ? ESCAPE '\\')",
+ );
const pattern = like(input.query.trim());
- bindings.push(pattern, pattern);
+ bindings.push(pattern, pattern, pattern, pattern, pattern);
}
if (input.ipLocation?.trim()) {
conditions.push("a.ip_location LIKE ? ESCAPE '\\'");
@@ -369,8 +374,12 @@ function resourceWhere(input: ResourceFilters) {
if (input.cooperationSource?.trim()) {
conditions.push(
`(a.cooperation_source LIKE ? ESCAPE '\\' OR
- EXISTS (SELECT 1 FROM distributions dx JOIN partners px ON px.id = dx.partner_id
- WHERE dx.account_id = a.id AND px.name LIKE ? ESCAPE '\\'))`,
+ EXISTS (SELECT 1 FROM distributions dx
+ JOIN partners px ON px.id = dx.partner_id
+ LEFT JOIN claims cx ON cx.id = dx.claim_id
+ WHERE dx.account_id = a.id
+ AND (cx.claimant_name IS NULL OR px.name != cx.claimant_name)
+ AND px.name LIKE ? ESCAPE '\\'))`,
);
const pattern = like(input.cooperationSource.trim());
bindings.push(pattern, pattern);
@@ -389,7 +398,12 @@ export async function resourceSearch(input: ResourceFilters) {
const db = getRawDb();
const select = `SELECT a.*,
(SELECT COUNT(*) FROM distributions d WHERE d.account_id = a.id) AS cooperation_count,
- (SELECT GROUP_CONCAT(DISTINCT p.name) FROM distributions d JOIN partners p ON p.id = d.partner_id WHERE d.account_id = a.id) AS cooperation_sources`;
+ (SELECT GROUP_CONCAT(DISTINCT p.name)
+ FROM distributions d
+ JOIN partners p ON p.id = d.partner_id
+ LEFT JOIN claims c ON c.id = d.claim_id
+ WHERE d.account_id = a.id
+ AND (c.claimant_name IS NULL OR p.name != c.claimant_name)) AS cooperation_sources`;
const [rows, count] = await Promise.all([
db.prepare(`${select} FROM accounts a ${where} ORDER BY a.last_seen_at DESC LIMIT ${limit} OFFSET ${offset}`)
.bind(...bindings).all>(),
@@ -422,7 +436,7 @@ export async function resourceGet(accountId: string) {
if (!account) throw new Error("账号不存在");
const history = await db.prepare(
`SELECT d.id AS distribution_id, d.task_id, t.name AS task_name, c.title,
- d.publish_url, d.publish_time, d.latest_likes, d.latest_comments, d.latest_collects,
+ d.publish_url, d.publish_time, d.latest_likes, d.latest_comments, d.latest_collects, d.latest_shares,
d.exposure, d.views, p.name AS cooperation_source, cl.claimant_name
FROM distributions d JOIN tasks t ON t.id = d.task_id
JOIN contents c ON c.id = d.content_id JOIN partners p ON p.id = d.partner_id
@@ -438,7 +452,7 @@ export async function backfillResourceProfile(
) {
await ensureSchema();
const db = getRawDb();
- const publishUrl = input.publishUrl ? extractXhsPublishUrl(input.publishUrl) : "";
+ const publishUrl = input.publishUrl ? extractAnyPublishUrl(input.publishUrl) : "";
const row = input.distributionId
? await db.prepare(
`SELECT d.id, d.publish_url, COALESCE(a.nickname, '') AS nickname
diff --git a/lib/mcp-tools.ts b/lib/mcp-tools.ts
index 297749b..cdff5d7 100644
--- a/lib/mcp-tools.ts
+++ b/lib/mcp-tools.ts
@@ -52,7 +52,7 @@ const pagination = {
};
const resourceFilters = {
- query: z.string().max(100).optional().describe("账号名称或小红书号/抖音号，支持模糊搜索"),
+ query: z.string().max(100).optional().describe("账号名称、账号号、简介或标签，支持模糊搜索"),
ip_location: z.string().max(100).optional().describe("IP地区关键词，支持模糊搜索"),
cooperation_source: z.string().max(100).optional().describe("历史合作来源关键词，支持模糊搜索"),
platform: z.string().max(30).optional().describe("平台，例如小红书；不传表示全部"),
@@ -159,7 +159,7 @@ export function registerMcpOperationTools(server: McpServer, options: Options) {
"collection_collect_now",
{
title: "立即采集指定笔记",
- description: "对指定分发记录立即采集点赞、收藏和评论数据。",
+ description: "对指定分发记录立即采集互动数据；小红书为点赞/收藏/评论，抖音另含转发。",
inputSchema: z.object({
distribution_id: z.string().min(1).describe("分发记录ID，可从 task_get 或 recovery_list 获取"),
schedule_day: z.number().int().min(1).max(7).optional().describe("标记为第几天采集，可不传"),
@@ -190,7 +190,7 @@ export function registerMcpOperationTools(server: McpServer, options: Options) {
"resource_search",
{
title: "搜索 KOC 账号资源",
- description: "按账号名称/账号号、IP地区、合作来源或平台搜索 KOC 资源。",
+ description: "按账号名称/账号号/标签、IP地区、合作来源或平台搜索 KOC 资源。",
inputSchema: z.object({ ...resourceFilters, ...pagination }),
annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true },
},
@@ -204,7 +204,7 @@ export function registerMcpOperationTools(server: McpServer, options: Options) {
"resource_get",
{
title: "查看 KOC 账号详情",
- description: "查看账号主页、账号号、粉丝数、IP地区以及全部合作记录。",
+ description: "查看账号主页、账号号、粉丝数、性别、简介、标签、IP地区以及全部合作记录。",
inputSchema: z.object({ account_id: z.string().min(1).describe("KOC LOOP 账号ID") }),
annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true },
},
@@ -218,10 +218,10 @@ export function registerMcpOperationTools(server: McpServer, options: Options) {
"resource_backfill_profile",
{
title: "补全公开账号信息",
- description: "根据已回填的发布链接补全账号主页、昵称、小红书号、IP地区和粉丝数。",
+ description: "根据已回填的小红书或抖音作品链接补全账号主页、昵称、账号号、IP地区和粉丝数。",
inputSchema: z.object({
distribution_id: z.string().optional().describe("分发记录ID，和发布链接二选一"),
- publish_url: z.string().optional().describe("小红书发布链接或包含链接的分享文案"),
+ publish_url: z.string().optional().describe("小红书或抖音作品链接，也可传包含链接的分享文案"),
}).refine((value) => Boolean(value.distribution_id || value.publish_url), "请提供分发记录ID或发布链接"),
annotations: { readOnlyHint: false, destructiveHint: false, idempotentHint: true, openWorldHint: true },
},
diff --git a/lib/mvp-db.ts b/lib/mvp-db.ts
index 66687a9..f4feb92 100644
--- a/lib/mvp-db.ts
+++ b/lib/mvp-db.ts
@@ -94,6 +94,8 @@ export async function ensureSchema(database?: DatabaseClient) {
due_at TEXT NOT NULL,
status TEXT NOT NULL DEFAULT 'active',
task_type TEXT NOT NULL DEFAULT 'content_publish',
+ platform TEXT NOT NULL DEFAULT '小红书',
+ content_format TEXT NOT NULL DEFAULT 'image_text',
source_url TEXT NOT NULL DEFAULT '',
source_sheet_id TEXT NOT NULL DEFAULT '',
source_sheet_name TEXT NOT NULL DEFAULT '',
@@ -110,6 +112,7 @@ export async function ensureSchema(database?: DatabaseClient) {
title TEXT NOT NULL,
body TEXT NOT NULL DEFAULT '',
image_assets TEXT NOT NULL DEFAULT '[]',
+ video_assets TEXT NOT NULL DEFAULT '[]',
status TEXT NOT NULL DEFAULT 'available',
source TEXT NOT NULL DEFAULT '飞书内容表',
source_row INTEGER,
@@ -124,9 +127,13 @@ export async function ensureSchema(database?: DatabaseClient) {
profile_url TEXT NOT NULL DEFAULT '',
ip_location TEXT NOT NULL DEFAULT '待识别',
followers INTEGER NOT NULL DEFAULT 0,
+ gender TEXT NOT NULL DEFAULT '',
+ bio TEXT NOT NULL DEFAULT '',
+ tags TEXT NOT NULL DEFAULT '',
post_count INTEGER NOT NULL DEFAULT 0,
avg_views INTEGER NOT NULL DEFAULT 0,
cooperation_source TEXT NOT NULL DEFAULT '',
+ current_contact TEXT NOT NULL DEFAULT '',
first_seen_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
last_seen_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP
)`,
@@ -185,6 +192,7 @@ export async function ensureSchema(database?: DatabaseClient) {
latest_likes INTEGER,
latest_comments INTEGER,
latest_collects INTEGER,
+ latest_shares INTEGER,
collection_status TEXT NOT NULL DEFAULT 'pending',
collection_status_description TEXT,
collection_updated_at TEXT,
@@ -202,6 +210,7 @@ export async function ensureSchema(database?: DatabaseClient) {
likes INTEGER,
comments INTEGER,
collects INTEGER,
+ shares INTEGER,
status_description TEXT,
started_at TEXT,
completed_at TEXT,
@@ -293,6 +302,14 @@ export async function ensureSchema(database?: DatabaseClient) {
"public_account_id",
"public_account_id TEXT NOT NULL DEFAULT ''",
);
+ await ensureColumn("accounts", "gender", "gender TEXT NOT NULL DEFAULT ''");
+ await ensureColumn("accounts", "bio", "bio TEXT NOT NULL DEFAULT ''");
+ await ensureColumn("accounts", "tags", "tags TEXT NOT NULL DEFAULT ''");
+ await ensureColumn(
+ "accounts",
+ "current_contact",
+ "current_contact TEXT NOT NULL DEFAULT ''",
+ );
await ensureColumn("distributions", "claim_id", "claim_id TEXT");
await ensureColumn(
"distributions",
@@ -796,22 +813,44 @@ export async function getDashboardData() {
await Promise.all([
db.prepare("SELECT * FROM partners ORDER BY created_at DESC").all(),
db.prepare("SELECT * FROM tasks ORDER BY created_at DESC").all(),
- db.prepare("SELECT * FROM accounts ORDER BY last_seen_at DESC").all(),
+ db
+ .prepare(
+ `SELECT
+ a.*,
+ COALESCE(
+ (
+ SELECT d.publish_url
+ FROM distributions d
+ WHERE d.account_id = a.id
+ AND TRIM(COALESCE(d.publish_url, '')) != ''
+ ORDER BY d.updated_at DESC, d.claimed_at DESC
+ LIMIT 1
+ ),
+ ''
+ ) AS latest_publish_url
+ FROM accounts a
+ ORDER BY a.last_seen_at DESC`,
+ )
+ .all(),
db
.prepare(
`SELECT
d.*,
c.title AS content_title,
p.name AS partner_name,
+ cl.claimant_name AS claimant_name,
a.nickname AS account_nickname,
a.platform AS account_platform,
t.name AS task_name,
t.brand AS task_brand,
t.task_type AS task_type,
+ t.platform AS task_platform,
+ t.content_format AS content_format,
t.due_at AS due_at
FROM distributions d
JOIN contents c ON c.id = d.content_id
JOIN partners p ON p.id = d.partner_id
+ LEFT JOIN claims cl ON cl.id = d.claim_id
JOIN tasks t ON t.id = d.task_id
LEFT JOIN accounts a ON a.id = d.account_id
ORDER BY d.updated_at DESC, d.claimed_at DESC`,
diff --git a/lib/partner-batch-workbook.ts b/lib/partner-batch-workbook.ts
new file mode 100644
index 0000000..b931b07
--- /dev/null
+++ b/lib/partner-batch-workbook.ts
@@ -0,0 +1,547 @@
+import path from "node:path";
+import { strFromU8, unzipSync } from "fflate";
+
+export const PARTNER_BATCH_HEADERS = [
+ "序号（不能改）",
+ "标题",
+ "笔记内容（正文+话题）",
+ "图片",
+ "发布链接",
+ "笔记截图",
+ "数据分析截图（单篇笔记数据分析截图）",
+ "_系统笔记ID",
+ "_原笔记截图",
+ "_原数据分析截图",
+] as const;
+
+export const PARTNER_BATCH_VISIBLE_COLUMN_COUNT = 7;
+export const PARTNER_BATCH_MAX_BYTES = 80_000_000;
+
+export type PartnerBatchWorkbookColumns = {
+ headers: string[];
+ columnWidths: number[];
+ sourceImageStartColumn: number;
+ sourceImageCount: number;
+ sourceVideoStartColumn: number;
+ sourceVideoCount: number;
+ publishUrlColumn: number;
+ publishScreenshotColumn: number;
+ creatorScreenshotColumn: number;
+ systemColumn: number;
+};
+
+function nonNegativeInteger(value: number) {
+ return Number.isFinite(value) ? Math.max(0, Math.floor(value)) : 0;
+}
+
+export function buildPartnerBatchWorkbookColumns(input: {
+ contentFormat: "image_text" | "video";
+ maxSourceImages: number;
+ maxSourceVideos: number;
+}): PartnerBatchWorkbookColumns {
+ const sourceImageCount =
+ input.contentFormat === "video"
+ ? 0
+ : Math.max(1, nonNegativeInteger(input.maxSourceImages));
+ const sourceVideoCount =
+ input.contentFormat === "video"
+ ? Math.max(1, nonNegativeInteger(input.maxSourceVideos))
+ : 0;
+ const sourceImageStartColumn = 3;
+ const sourceVideoStartColumn = sourceImageStartColumn + sourceImageCount;
+ const publishUrlColumn = sourceVideoStartColumn + sourceVideoCount;
+ const publishScreenshotColumn = publishUrlColumn + 1;
+ const creatorScreenshotColumn = publishScreenshotColumn + 1;
+ const systemColumn = creatorScreenshotColumn + 1;
+ return {
+ headers: [
+ "序号（不能改）",
+ "标题",
+ "笔记内容（正文+话题）",
+ ...Array.from(
+ { length: sourceImageCount },
+ (_, index) => `图片${index + 1}`,
+ ),
+ ...Array.from(
+ { length: sourceVideoCount },
+ (_, index) => `视频${index + 1}`,
+ ),
+ "发布链接",
+ "笔记截图",
+ "数据分析截图（单篇笔记数据分析截图）",
+ "_系统笔记ID",
+ "_原笔记截图",
+ "_原数据分析截图",
+ ],
+ columnWidths: [
+ 14,
+ 30,
+ 62,
+ ...Array.from({ length: sourceImageCount }, () => 24),
+ ...Array.from({ length: sourceVideoCount }, () => 20),
+ 45,
+ 28,
+ 32,
+ 22,
+ 22,
+ 22,
+ ],
+ sourceImageStartColumn,
+ sourceImageCount,
+ sourceVideoStartColumn,
+ sourceVideoCount,
+ publishUrlColumn,
+ publishScreenshotColumn,
+ creatorScreenshotColumn,
+ systemColumn,
+ };
+}
+
+function firstForwardedValue(value: string | null) {
+ return value?.split(",")[0]?.trim() ?? "";
+}
+
+function httpOrigin(value: string) {
+ try {
+ const url = new URL(value);
+ return url.protocol === "http:" || url.protocol === "https:"
+ ? url.origin
+ : "";
+ } catch {
+ return "";
+ }
+}
+
+export function resolvePartnerWorkbookOrigin(
+ request: Request,
+ configuredOrigin = "",
+) {
+ const requestUrl = new URL(request.url);
+ const host =
+ firstForwardedValue(request.headers.get("x-forwarded-host")) ||
+ firstForwardedValue(request.headers.get("host"));
+ const forwardedProtocol = firstForwardedValue(
+ request.headers.get("x-forwarded-proto"),
+ ).toLowerCase();
+ const protocol = ["http", "https"].includes(forwardedProtocol)
+ ? forwardedProtocol
+ : requestUrl.protocol.replace(":", "");
+ const proxyOrigin = host ? httpOrigin(`${protocol}://${host}`) : "";
+ return (
+ httpOrigin(configuredOrigin) ||
+ proxyOrigin ||
+ httpOrigin(requestUrl.origin) ||
+ requestUrl.origin
+ );
+}
+
+export type PartnerBatchImage = {
+ bytes: Uint8Array;
+ contentType: string;
+ fileName: string;
+};
+
+export type PartnerBatchImportRow = {
+ spreadsheetRow: number;
+ sequence: string;
+ title: string;
+ publishUrl: string;
+ distributionId: string;
+ originalPublishScreenshotKey: string;
+ originalCreatorScreenshotKey: string;
+ publishScreenshot: PartnerBatchImage | null;
+ creatorScreenshot: PartnerBatchImage | null;
+};
+
+function decodeXml(value: string) {
+ return value
+ .replace(/<[^>]+>/g, "")
+ .replace(/</g, "<")
+ .replace(/>/g, ">")
+ .replace(/"/g, '"')
+ .replace(/'/g, "'")
+ .replace(/&/g, "&")
+ .replace(/&#(\d+);/g, (_, code) => String.fromCodePoint(Number(code)))
+ .replace(/&#x([0-9a-f]+);/gi, (_, code) =>
+ String.fromCodePoint(Number.parseInt(code, 16)),
+ );
+}
+
+function xmlAttribute(value: string) {
+ return decodeXml(value);
+}
+
+function textNodes(xml: string) {
+ return [...xml.matchAll(/]*>([\s\S]*?)<\/t>/g)]
+ .map((match) => decodeXml(match[1]))
+ .join("");
+}
+
+function columnIndex(reference: string) {
+ const letters = reference.match(/^[A-Z]+/i)?.[0]?.toUpperCase() ?? "";
+ let result = 0;
+ for (const letter of letters) result = result * 26 + letter.charCodeAt(0) - 64;
+ return Math.max(0, result - 1);
+}
+
+function parseWorksheet(xml: string, sharedStrings: string[]) {
+ const rows: string[][] = [];
+ for (const rowMatch of xml.matchAll(/]*)>([\s\S]*?)<\/row>/g)) {
+ const rowNumber = Number(
+ rowMatch[1].match(/\br="(\d+)"/)?.[1] ?? rows.length + 1,
+ );
+ const values: string[] = [];
+ for (const cellMatch of rowMatch[2].matchAll(
+ /]*)>([\s\S]*?)<\/c>/g,
+ )) {
+ const attributes = cellMatch[1];
+ const body = cellMatch[2];
+ const reference = attributes.match(/\br="([A-Z]+\d+)"/i)?.[1] ?? "A1";
+ const type = attributes.match(/\bt="([^"]+)"/)?.[1] ?? "";
+ const rawValue = body.match(/([\s\S]*?)<\/v>/)?.[1] ?? "";
+ let value = "";
+ if (type === "s") value = sharedStrings[Number(rawValue)] ?? "";
+ else if (type === "inlineStr") value = textNodes(body);
+ else if (type === "b") value = rawValue === "1" ? "TRUE" : "FALSE";
+ else value = decodeXml(rawValue);
+ values[columnIndex(reference)] = value.trim();
+ }
+ while (rows.length < rowNumber - 1) rows.push([]);
+ rows[rowNumber - 1] = values;
+ }
+ return rows;
+}
+
+function normalizeHeader(value: string) {
+ return value.replace(/[\s_\-（）()]/g, "").toLocaleLowerCase("zh-CN");
+}
+
+function isSourceImageHeader(value: string) {
+ return /^(?:图片|发布配图)\d*$/.test(normalizeHeader(value));
+}
+
+function headerAliases(header: (typeof PARTNER_BATCH_HEADERS)[number]) {
+ const aliases: Record = {
+ "序号（不能改）": ["序号（不能改）", "序号"],
+ 标题: ["标题"],
+ "笔记内容（正文+话题）": ["笔记内容（正文+话题）", "笔记内容"],
+ 图片: ["图片", "发布配图"],
+ 发布链接: ["发布链接"],
+ 笔记截图: ["笔记截图", "发布截图"],
+ "数据分析截图（单篇笔记数据分析截图）": [
+ "数据分析截图（单篇笔记数据分析截图）",
+ "数据分析截图",
+ "创作者中心截图",
+ ],
+ _系统笔记ID: ["_系统笔记ID", "系统笔记ID"],
+ _原笔记截图: ["_原笔记截图"],
+ _原数据分析截图: ["_原数据分析截图"],
+ };
+ return aliases[header] ?? [header];
+}
+
+function findHeader(rows: string[][]) {
+ for (let rowIndex = 0; rowIndex < Math.min(rows.length, 8); rowIndex += 1) {
+ const mapping = new Map<(typeof PARTNER_BATCH_HEADERS)[number], number>();
+ rows[rowIndex].forEach((value, column) => {
+ for (const header of PARTNER_BATCH_HEADERS) {
+ if (header === "图片" && isSourceImageHeader(value)) {
+ if (!mapping.has(header)) mapping.set(header, column);
+ break;
+ }
+ if (
+ headerAliases(header).some(
+ (alias) => normalizeHeader(alias) === normalizeHeader(value),
+ )
+ ) {
+ mapping.set(header, column);
+ break;
+ }
+ }
+ });
+ if (
+ mapping.has("序号（不能改）") &&
+ mapping.has("标题") &&
+ mapping.has("发布链接") &&
+ mapping.has("笔记截图") &&
+ mapping.has("数据分析截图（单篇笔记数据分析截图）") &&
+ mapping.has("_系统笔记ID")
+ ) {
+ return { rowIndex, mapping };
+ }
+ }
+ return null;
+}
+
+function relationshipMap(xml: string) {
+ const relationships = new Map();
+ for (const match of xml.matchAll(/]*)\/?\s*>/g)) {
+ const attributes = match[1];
+ const id = attributes.match(/\bId="([^"]+)"/)?.[1] ?? "";
+ const target = attributes.match(/\bTarget="([^"]+)"/)?.[1] ?? "";
+ if (id && target) relationships.set(id, xmlAttribute(target));
+ }
+ return relationships;
+}
+
+function contentType(bytes: Uint8Array, fileName: string) {
+ if (bytes[0] === 0x89 && bytes[1] === 0x50) return "image/png";
+ if (bytes[0] === 0xff && bytes[1] === 0xd8) return "image/jpeg";
+ if (bytes[0] === 0x47 && bytes[1] === 0x49 && bytes[2] === 0x46) {
+ return "image/gif";
+ }
+ if (String.fromCharCode(...bytes.slice(8, 12)) === "WEBP") return "image/webp";
+ const extension = path.extname(fileName).toLowerCase();
+ return extension === ".png"
+ ? "image/png"
+ : extension === ".gif"
+ ? "image/gif"
+ : extension === ".webp"
+ ? "image/webp"
+ : "image/jpeg";
+}
+
+function resolveZipPath(base: string, target: string) {
+ return path.posix.normalize(path.posix.join(path.posix.dirname(base), target));
+}
+
+function parseDrawingImages(entries: Record) {
+ const images = new Map();
+ const sheetRelationshipsXml = entries["xl/worksheets/_rels/sheet1.xml.rels"]
+ ? strFromU8(entries["xl/worksheets/_rels/sheet1.xml.rels"])
+ : "";
+ const sheetRelationships = relationshipMap(sheetRelationshipsXml);
+ const sheetXml = entries["xl/worksheets/sheet1.xml"]
+ ? strFromU8(entries["xl/worksheets/sheet1.xml"])
+ : "";
+ const drawingId = sheetXml.match(/]*r:id="([^"]+)"/)?.[1] ?? "";
+ const drawingTarget = sheetRelationships.get(drawingId);
+ if (!drawingTarget) return images;
+ const drawingPath = resolveZipPath("xl/worksheets/sheet1.xml", drawingTarget);
+ const drawingXml = entries[drawingPath] ? strFromU8(entries[drawingPath]) : "";
+ const drawingRelationshipsPath = path.posix.join(
+ path.posix.dirname(drawingPath),
+ "_rels",
+ `${path.posix.basename(drawingPath)}.rels`,
+ );
+ const drawingRelationships = relationshipMap(
+ entries[drawingRelationshipsPath]
+ ? strFromU8(entries[drawingRelationshipsPath])
+ : "",
+ );
+ for (const anchor of drawingXml.matchAll(
+ /]*>[\s\S]*?([\s\S]*?)<\/xdr:from>[\s\S]*?]*r:embed="([^"]+)"[\s\S]*?<\/xdr:(?:oneCellAnchor|twoCellAnchor)>/g,
+ )) {
+ const column = Number(anchor[1].match(/(\d+)<\/xdr:col>/)?.[1]);
+ const row = Number(anchor[1].match(/(\d+)<\/xdr:row>/)?.[1]);
+ const mediaTarget = drawingRelationships.get(anchor[2]);
+ if (!Number.isInteger(column) || !Number.isInteger(row) || !mediaTarget) continue;
+ const mediaPath = resolveZipPath(drawingPath, mediaTarget);
+ const bytes = entries[mediaPath];
+ if (!bytes) continue;
+ images.set(`${row + 1}:${column}`, {
+ bytes,
+ contentType: contentType(bytes, mediaPath),
+ fileName: path.posix.basename(mediaPath),
+ });
+ }
+ return images;
+}
+
+function parseRichValueImages(entries: Record) {
+ const images = new Map();
+ const worksheetXml = entries["xl/worksheets/sheet1.xml"]
+ ? strFromU8(entries["xl/worksheets/sheet1.xml"])
+ : "";
+ const metadataXml = entries["xl/metadata.xml"]
+ ? strFromU8(entries["xl/metadata.xml"])
+ : "";
+ const richValueXml = entries["xl/richData/rdrichvalue.xml"]
+ ? strFromU8(entries["xl/richData/rdrichvalue.xml"])
+ : "";
+ const richValueRelXml = entries["xl/richData/richValueRel.xml"]
+ ? strFromU8(entries["xl/richData/richValueRel.xml"])
+ : "";
+ const richValueRelRelationships = relationshipMap(
+ entries["xl/richData/_rels/richValueRel.xml.rels"]
+ ? strFromU8(entries["xl/richData/_rels/richValueRel.xml.rels"])
+ : "",
+ );
+ if (
+ !worksheetXml ||
+ !metadataXml ||
+ !richValueXml ||
+ !richValueRelXml ||
+ !richValueRelRelationships.size
+ ) {
+ return images;
+ }
+
+ const valueMetadataXml =
+ metadataXml.match(/]*>([\s\S]*?)<\/valueMetadata>/)?.[1] ??
+ "";
+ const metadataToRichValue = [
+ ...valueMetadataXml.matchAll(/]*>[\s\S]*?]*\bv="(\d+)"[^>]*\/>[\s\S]*?<\/bk>/g),
+ ].map((match) => Number(match[1]));
+ const richValueToRelationship = [
+ ...richValueXml.matchAll(/]*>([\s\S]*?)<\/rv>/g),
+ ].map((match) => Number(match[1].match(/(\d+)<\/v>/)?.[1] ?? -1));
+ const relationshipIds = [
+ ...richValueRelXml.matchAll(/]*\br:id="([^"]+)"[^>]*\/>/g),
+ ].map((match) => match[1]);
+
+ for (const cell of worksheetXml.matchAll(
+ /]*)>[\s\S]*?<\/c>/g,
+ )) {
+ const reference = cell[1].match(/\br="([A-Z]+\d+)"/i)?.[1] ?? "";
+ const metadataIndex = Number(cell[1].match(/\bvm="(\d+)"/)?.[1] ?? 0);
+ const row = Number(reference.match(/\d+$/)?.[0] ?? 0);
+ const column = columnIndex(reference);
+ if (!reference || !metadataIndex || !row) continue;
+ const richValueIndex = metadataToRichValue[metadataIndex - 1];
+ const relationshipIndex = richValueToRelationship[richValueIndex];
+ const relationshipId = relationshipIds[relationshipIndex];
+ const mediaTarget = richValueRelRelationships.get(relationshipId);
+ if (!mediaTarget) continue;
+ const mediaPath = resolveZipPath(
+ "xl/richData/richValueRel.xml",
+ mediaTarget,
+ );
+ const bytes = entries[mediaPath];
+ if (!bytes) continue;
+ images.set(`${row}:${column}`, {
+ bytes,
+ contentType: contentType(bytes, mediaPath),
+ fileName: path.posix.basename(mediaPath),
+ });
+ }
+ return images;
+}
+
+function parseWpsCellImages(entries: Record) {
+ const images = new Map();
+ const worksheetXml = entries["xl/worksheets/sheet1.xml"]
+ ? strFromU8(entries["xl/worksheets/sheet1.xml"])
+ : "";
+ const cellImagesXml = entries["xl/cellimages.xml"]
+ ? strFromU8(entries["xl/cellimages.xml"])
+ : "";
+ const relationships = relationshipMap(
+ entries["xl/_rels/cellimages.xml.rels"]
+ ? strFromU8(entries["xl/_rels/cellimages.xml.rels"])
+ : "",
+ );
+ if (!worksheetXml || !cellImagesXml || !relationships.size) return images;
+
+ const imageIdToRelationship = new Map();
+ for (const match of cellImagesXml.matchAll(
+ /<(?:etc:)?cellImage\b[^>]*>([\s\S]*?)<\/(?:etc:)?cellImage>/g,
+ )) {
+ const imageId = match[1].match(
+ /<(?:xdr:)?cNvPr\b[^>]*\bname="([^"]+)"/,
+ )?.[1];
+ const relationshipId = match[1].match(
+ /<(?:a:)?blip\b[^>]*\br:embed="([^"]+)"/,
+ )?.[1];
+ if (imageId && relationshipId) {
+ imageIdToRelationship.set(imageId, relationshipId);
+ }
+ }
+
+ for (const cell of worksheetXml.matchAll(/]*)>([\s\S]*?)<\/c>/g)) {
+ const reference = cell[1].match(/\br="([A-Z]+\d+)"/i)?.[1] ?? "";
+ const imageId = decodeXml(cell[2]).match(/DISPIMG\("([^"]+)"/i)?.[1];
+ if (!reference || !imageId) continue;
+ const relationshipId = imageIdToRelationship.get(imageId);
+ const mediaTarget = relationshipId
+ ? relationships.get(relationshipId)
+ : undefined;
+ if (!mediaTarget) continue;
+ const mediaPath = resolveZipPath("xl/cellimages.xml", mediaTarget);
+ const bytes = entries[mediaPath];
+ if (!bytes) continue;
+ const row = Number(reference.match(/\d+$/)?.[0] ?? 0);
+ if (!row) continue;
+ images.set(`${row}:${columnIndex(reference)}`, {
+ bytes,
+ contentType: contentType(bytes, mediaPath),
+ fileName: path.posix.basename(mediaPath),
+ });
+ }
+ return images;
+}
+
+function parseImages(entries: Record) {
+ const images = parseDrawingImages(entries);
+ for (const [cell, image] of parseRichValueImages(entries)) {
+ images.set(cell, image);
+ }
+ for (const [cell, image] of parseWpsCellImages(entries)) {
+ images.set(cell, image);
+ }
+ return images;
+}
+
+function valueAt(
+ row: string[],
+ mapping: Map<(typeof PARTNER_BATCH_HEADERS)[number], number>,
+ header: (typeof PARTNER_BATCH_HEADERS)[number],
+) {
+ const column = mapping.get(header);
+ return column === undefined ? "" : String(row[column] ?? "").trim();
+}
+
+export function parsePartnerBatchWorkbook(input: ArrayBuffer | Uint8Array) {
+ const bytes = input instanceof Uint8Array ? input : new Uint8Array(input);
+ if (bytes.byteLength > PARTNER_BATCH_MAX_BYTES) {
+ throw new Error("批量回填表不能超过80MB");
+ }
+ const entries = unzipSync(bytes);
+ const worksheetBytes = entries["xl/worksheets/sheet1.xml"];
+ if (!worksheetBytes) throw new Error("Excel 中没有可读取的批量回填工作表");
+ const sharedXml = entries["xl/sharedStrings.xml"]
+ ? strFromU8(entries["xl/sharedStrings.xml"])
+ : "";
+ const sharedStrings = [
+ ...sharedXml.matchAll(/]*>([\s\S]*?)<\/si>/g),
+ ].map((match) => textNodes(match[1]));
+ const rows = parseWorksheet(strFromU8(worksheetBytes), sharedStrings);
+ const header = findHeader(rows);
+ if (!header) {
+ throw new Error("表格结构不正确，请使用本领取页面导出的批量回填表");
+ }
+ const images = parseImages(entries);
+ const publishScreenshotColumn = header.mapping.get("笔记截图")!;
+ const creatorScreenshotColumn = header.mapping.get(
+ "数据分析截图（单篇笔记数据分析截图）",
+ )!;
+ const result: PartnerBatchImportRow[] = [];
+ for (let index = header.rowIndex + 1; index < rows.length; index += 1) {
+ const row = rows[index];
+ const distributionId = valueAt(row, header.mapping, "_系统笔记ID");
+ if (!distributionId && !row.some((value) => String(value ?? "").trim())) continue;
+ result.push({
+ spreadsheetRow: index + 1,
+ sequence: valueAt(row, header.mapping, "序号（不能改）"),
+ title: valueAt(row, header.mapping, "标题"),
+ publishUrl: valueAt(row, header.mapping, "发布链接"),
+ distributionId,
+ originalPublishScreenshotKey: valueAt(
+ row,
+ header.mapping,
+ "_原笔记截图",
+ ),
+ originalCreatorScreenshotKey: valueAt(
+ row,
+ header.mapping,
+ "_原数据分析截图",
+ ),
+ publishScreenshot:
+ images.get(`${index + 1}:${publishScreenshotColumn}`) ?? null,
+ creatorScreenshot:
+ images.get(`${index + 1}:${creatorScreenshotColumn}`) ?? null,
+ });
+ }
+ if (result.length === 0) throw new Error("表格中没有可回填的笔记");
+ return result;
+}
diff --git a/lib/partner-utils.ts b/lib/partner-utils.ts
index d93d026..39ad1c1 100644
--- a/lib/partner-utils.ts
+++ b/lib/partner-utils.ts
@@ -1,22 +1,31 @@
import { hashText } from "./mvp-db";
import {
+ extractPublishUrl,
extractXhsPublishUrl,
+ platformFromPublishUrl,
safeHttpUrl,
+ type SupportedPlatform,
} from "./publish-url";
export { extractXhsPublishUrl } from "./publish-url";
-export function accountFromPublishLink(input: string) {
- const url = safeHttpUrl(extractXhsPublishUrl(input));
+export function accountFromPublishLink(
+ input: string,
+ expectedPlatform?: SupportedPlatform,
+) {
+ const extracted = expectedPlatform
+ ? extractPublishUrl(input, expectedPlatform)
+ : extractXhsPublishUrl(input) || extractPublishUrl(input, "抖音");
+ const url = safeHttpUrl(extracted);
if (!url) return null;
- const platform =
- url.hostname.includes("xiaohongshu") || url.hostname.includes("xhslink")
- ? "小红书"
- : "其他平台";
+ const platform = platformFromPublishUrl(url.toString());
+ if (!platform || (expectedPlatform && platform !== expectedPlatform)) return null;
const noteId =
- url.pathname.match(
- /\/(?:discovery\/item|explore)\/([A-Za-z0-9_-]{8,80})/,
- )?.[1] ?? "";
+ platform === "抖音"
+ ? url.pathname.match(/\/(?:video|note)\/([A-Za-z0-9_-]{8,80})/)?.[1] ?? ""
+ : url.pathname.match(
+ /\/(?:discovery\/item|explore)\/([A-Za-z0-9_-]{8,80})/,
+ )?.[1] ?? "";
const platformUid = `pending-${hashText(
noteId || `${url.origin}${url.pathname}`,
)}`;
diff --git a/lib/publish-url.ts b/lib/publish-url.ts
index 829da4f..dc31bc9 100644
--- a/lib/publish-url.ts
+++ b/lib/publish-url.ts
@@ -25,3 +25,44 @@ export function extractXhsPublishUrl(input: string) {
}
return "";
}
+
+export type SupportedPlatform = "小红书" | "抖音";
+
+function platformMatches(url: URL, platform: SupportedPlatform) {
+ const hostname = url.hostname.toLowerCase();
+ if (platform === "抖音") {
+ return hostname === "douyin.com" || hostname.endsWith(".douyin.com");
+ }
+ return (
+ hostname === "xiaohongshu.com" ||
+ hostname.endsWith(".xiaohongshu.com") ||
+ hostname === "xhslink.cn" ||
+ hostname.endsWith(".xhslink.cn")
+ );
+}
+
+export function extractPublishUrl(
+ input: string,
+ platform: SupportedPlatform = "小红书",
+) {
+ const candidates =
+ input.match(/https?:\/\/[^\s<>"'，。！？；：、【】（）]+/gi) ?? [];
+ for (const candidate of candidates) {
+ const cleaned = candidate.replace(/[.,!?;:~)\]}]+$/g, "");
+ const url = safeHttpUrl(cleaned);
+ if (url && platformMatches(url, platform)) return url.toString();
+ }
+ return "";
+}
+
+export function extractAnyPublishUrl(input: string) {
+ return extractPublishUrl(input, "小红书") || extractPublishUrl(input, "抖音");
+}
+
+export function platformFromPublishUrl(input: string): SupportedPlatform | "" {
+ const url = safeHttpUrl(input);
+ if (!url) return "";
+ if (platformMatches(url, "小红书")) return "小红书";
+ if (platformMatches(url, "抖音")) return "抖音";
+ return "";
+}
diff --git a/lib/recovery-workbook.ts b/lib/recovery-workbook.ts
index b3f062f..d3689ef 100644
--- a/lib/recovery-workbook.ts
+++ b/lib/recovery-workbook.ts
@@ -13,6 +13,9 @@ export type RecoveryWorkbookRow = {
images: Array<{
column: number;
image: RecoveryWorkbookImage;
+ offsetX?: number;
+ maxWidth?: number;
+ maxHeight?: number;
}>;
hyperlinks?: Array<{
column: number;
@@ -25,6 +28,7 @@ type WorkbookOptions = {
headers: string[];
columnWidths: number[];
rows: RecoveryWorkbookRow[];
+ hiddenColumns?: number[];
};
const XML_HEADER = '';
@@ -130,9 +134,17 @@ function imageDimensions(image: RecoveryWorkbookImage) {
return { width: 4, height: 3 };
}
-function imageDisplaySize(image: RecoveryWorkbookImage) {
+function imageDisplaySize(
+ image: RecoveryWorkbookImage,
+ maxWidth = 160,
+ maxHeight = 150,
+) {
const dimensions = imageDimensions(image);
- const scale = Math.min(160 / dimensions.width, 150 / dimensions.height, 1);
+ const scale = Math.min(
+ maxWidth / dimensions.width,
+ maxHeight / dimensions.height,
+ 1,
+ );
return {
width: Math.max(28, Math.round(dimensions.width * scale)),
height: Math.max(28, Math.round(dimensions.height * scale)),
@@ -152,6 +164,14 @@ export function buildRecoveryWorkbook(options: WorkbookOptions) {
const imageEntries = options.rows.flatMap((row, rowIndex) =>
row.images.map((item) => ({ ...item, row: rowIndex + 1 })),
);
+ const imageCells = new Set();
+ imageEntries.forEach((entry) => {
+ const key = `${entry.row}:${entry.column}`;
+ if (imageCells.has(key)) {
+ throw new Error("Excel 单元格内只能嵌入一张图片，请为每张图片分配独立列");
+ }
+ imageCells.add(key);
+ });
const hyperlinkEntries = options.rows.flatMap((row, rowIndex) =>
(row.hyperlinks ?? [])
.map((item) => ({
@@ -178,7 +198,7 @@ export function buildRecoveryWorkbook(options: WorkbookOptions) {
const reference = `${columnName(columnIndex)}${number}`;
const value = row.cells[columnIndex] ?? "";
if (imageColumns.has(columnIndex)) {
- return inlineCell(reference, value || "见图", 4);
+ return inlineCell(reference, value, 4);
}
return typeof value === "number"
? numberCell(reference, value, 3)
@@ -196,17 +216,22 @@ export function buildRecoveryWorkbook(options: WorkbookOptions) {
const columns = options.headers
.map((_, index) => {
const width = Math.min(70, Math.max(8, options.columnWidths[index] ?? 14));
- return ``;
+ const hidden = options.hiddenColumns?.includes(index) ? ' hidden="1"' : "";
+ return ``;
})
.join("");
const drawingXml = imageEntries.length
? `${XML_HEADER}${imageEntries
.map((entry, index) => {
- const size = imageDisplaySize(entry.image);
- const width = size.width * 9525;
- const height = size.height * 9525;
- return `${entry.column}57150${entry.row}57150`;
+ const size = imageDisplaySize(
+ entry.image,
+ entry.maxWidth ?? 160,
+ entry.maxHeight ?? 150,
+ );
+ const offsetX = entry.offsetX ?? 6;
+ const offsetY = 6;
+ return `${entry.column}${offsetX * 9525}${entry.row}${offsetY * 9525}${entry.column}${(offsetX + size.width) * 9525}${entry.row}${(offsetY + size.height) * 9525}`;
})
.join("")}`
: "";
@@ -227,7 +252,10 @@ export function buildRecoveryWorkbook(options: WorkbookOptions) {
const imageContentTypes = [...imageFormats.entries()]
.map(([extension, contentType]) => ``)
.join("");
- const contentTypes = `${XML_HEADER}${imageContentTypes}${imageEntries.length ? '' : ""}`;
+ const drawingContentType = imageEntries.length
+ ? ''
+ : "";
+ const contentTypes = `${XML_HEADER}${imageContentTypes}${drawingContentType}`;
const hyperlinkRelationshipOffset = imageEntries.length ? 2 : 1;
const hyperlinksXml = hyperlinkEntries.length
? `${hyperlinkEntries
@@ -266,7 +294,9 @@ export function buildRecoveryWorkbook(options: WorkbookOptions) {
}
if (imageEntries.length) {
files["xl/drawings/drawing1.xml"] = strToU8(drawingXml);
- files["xl/drawings/_rels/drawing1.xml.rels"] = strToU8(drawingRelationships);
+ files["xl/drawings/_rels/drawing1.xml.rels"] = strToU8(
+ drawingRelationships,
+ );
imageEntries.forEach((entry, index) => {
const format = imageFormat(entry.image.contentType, entry.image.bytes);
files[`xl/media/image${index + 1}.${format.extension}`] = entry.image.bytes;
diff --git a/lib/resource-import.ts b/lib/resource-import.ts
index cb14ef7..df203aa 100644
--- a/lib/resource-import.ts
+++ b/lib/resource-import.ts
@@ -1,7 +1,7 @@
import { strFromU8, unzipSync } from "fflate";
-export const RESOURCE_IMPORT_MAX_ROWS = 100;
-export const RESOURCE_IMPORT_MAX_BYTES = 5 * 1024 * 1024;
+export const RESOURCE_IMPORT_MAX_ROWS = 10_000;
+export const RESOURCE_IMPORT_MAX_BYTES = 20 * 1024 * 1024;
export type ResourceImportRow = {
rowNumber: number;
@@ -12,6 +12,9 @@ export type ResourceImportRow = {
ipLocation: string;
followers: number;
followersResolved: boolean;
+ gender: "" | "男" | "女";
+ bio: string;
+ tags: string[];
cooperationSource: string;
errors: string[];
};
@@ -22,6 +25,9 @@ const HEADER_ALIASES = {
publicAccountId: ["账号ID", "账号号", "小红书号", "抖音号"],
ipLocation: ["IP属地", "IP地址", "IP地区", "IP所在地"],
followers: ["粉丝数", "粉丝", "粉丝量"],
+ gender: ["性别"],
+ bio: ["简介", "账号简介", "个人简介"],
+ tags: ["标签", "账号标签"],
cooperationSource: ["合作来源", "资源来源", "历史合作来源"],
} as const;
@@ -60,9 +66,11 @@ function parseWorksheet(xml: string, sharedStrings: string[]) {
const rowAttributes = rowMatch[1];
const rowNumber = Number(rowAttributes.match(/\br="(\d+)"/)?.[1] ?? rows.length + 1);
const values: string[] = [];
- for (const cellMatch of rowMatch[2].matchAll(/]*)>([\s\S]*?)<\/c>/g)) {
+ for (const cellMatch of rowMatch[2].matchAll(
+ /]*?)(?:\/>|>([\s\S]*?)<\/c>)/g,
+ )) {
const attributes = cellMatch[1];
- const body = cellMatch[2];
+ const body = cellMatch[2] ?? "";
const reference = attributes.match(/\br="([A-Z]+\d+)"/i)?.[1] ?? "A1";
const type = attributes.match(/\bt="([^"]+)"/)?.[1] ?? "";
const rawValue = body.match(/([\s\S]*?)<\/v>/)?.[1] ?? "";
@@ -183,6 +191,15 @@ export function platformFromProfileUrl(profileUrl: string) {
) {
return "小红书";
}
+ if (
+ ((url.hostname === "douyin.com" || url.hostname.endsWith(".douyin.com")) &&
+ /^\/user\/[^/]+/i.test(url.pathname)) ||
+ ((url.hostname === "iesdouyin.com" ||
+ url.hostname.endsWith(".iesdouyin.com")) &&
+ /^\/share\/user\/[^/]+/i.test(url.pathname))
+ ) {
+ return "抖音";
+ }
} catch {
// URL validation is reported by normalizeRows.
}
@@ -212,10 +229,42 @@ export function parseResourceFollowers(value: string) {
};
}
+export function normalizeResourceGender(value: string) {
+ const normalized = value.trim().toLocaleLowerCase("zh-CN");
+ if (!normalized || ["未知", "未填写", "待识别", "unknown"].includes(normalized)) {
+ return { value: "" as const, valid: true };
+ }
+ if (["男", "男性", "male", "m"].includes(normalized)) {
+ return { value: "男" as const, valid: true };
+ }
+ if (["女", "女性", "female", "f"].includes(normalized)) {
+ return { value: "女" as const, valid: true };
+ }
+ return { value: "" as const, valid: false };
+}
+
+export function normalizeResourceTags(value: string | string[]) {
+ const source = Array.isArray(value) ? value.join(",") : value;
+ return [
+ ...new Set(
+ source
+ .split(/[,，、;；|]/)
+ .map((item) => item.trim().replace(/^#+/, ""))
+ .filter(Boolean),
+ ),
+ ];
+}
+
export function resourceImportMissingFields(
row: Pick<
ResourceImportRow,
- "nickname" | "publicAccountId" | "ipLocation" | "followersResolved"
+ | "nickname"
+ | "publicAccountId"
+ | "ipLocation"
+ | "followersResolved"
+ | "gender"
+ | "bio"
+ | "tags"
>,
) {
const missing: string[] = [];
@@ -225,6 +274,8 @@ export function resourceImportMissingFields(
missing.push("ipLocation");
}
if (!row.followersResolved) missing.push("followers");
+ if (!row.gender) missing.push("gender");
+ if (!row.bio.trim()) missing.push("bio");
return missing;
}
@@ -242,22 +293,39 @@ function normalizeRows(rows: string[][]) {
const platform = platformFromProfileUrl(profileUrl);
const rawFollowers = valueAt(source, header.mapping, "followers");
const parsedFollowers = parseResourceFollowers(rawFollowers);
+ const parsedGender = normalizeResourceGender(
+ valueAt(source, header.mapping, "gender"),
+ );
+ const tags = normalizeResourceTags(valueAt(source, header.mapping, "tags"));
+ const ipLocation = valueAt(source, header.mapping, "ipLocation");
const errors: string[] = [];
if (!rawProfileUrl) errors.push("账号主页不能为空");
else if (!profileUrl) errors.push("账号主页链接格式不正确");
- else if (!platform) errors.push("当前自动解析仅支持小红书账号主页");
+ else if (!platform) errors.push("当前自动解析仅支持小红书或抖音账号主页");
if (!parsedFollowers.valid) {
errors.push("粉丝数格式不正确，请填写数字或如 1.3万、10+");
}
+ if (!parsedGender.valid) {
+ errors.push("性别格式不正确，请填写男、女或留空");
+ }
+ if (tags.length > 5) {
+ errors.push("单个账号最多填写 5 个标签，请用逗号分隔");
+ }
+ if (/^\d+$/.test(ipLocation)) {
+ errors.push("IP属地格式不正确，请填写省份、地区或国家名称");
+ }
result.push({
rowNumber: index + 1,
platform,
nickname: valueAt(source, header.mapping, "nickname"),
publicAccountId: valueAt(source, header.mapping, "publicAccountId"),
profileUrl,
- ipLocation: valueAt(source, header.mapping, "ipLocation"),
+ ipLocation,
followers: parsedFollowers.value,
followersResolved: parsedFollowers.resolved,
+ gender: parsedGender.value,
+ bio: valueAt(source, header.mapping, "bio"),
+ tags: tags.slice(0, 5),
cooperationSource: valueAt(source, header.mapping, "cooperationSource"),
errors,
});
diff --git a/lib/task-service.ts b/lib/task-service.ts
index 8b582eb..944a73a 100644
--- a/lib/task-service.ts
+++ b/lib/task-service.ts
@@ -10,6 +10,8 @@ export type CreateDistributionTaskInput = {
name: string;
brand: string;
dueAt: string;
+ platform?: "小红书" | "抖音";
+ contentFormat?: "image_text" | "video";
};
export type CreateScreenshotTaskInput = {
@@ -33,6 +35,8 @@ export type DistributionTaskCreation = {
sheetId: string;
sheetName: string;
sourceUrl: string;
+ platform: "小红书" | "抖音";
+ contentFormat: "image_text" | "video";
};
export type ScreenshotTaskCreation = {
@@ -55,6 +59,8 @@ type TaskRow = {
source_url: string;
source_sheet_id: string;
source_sheet_name: string;
+ platform: "小红书" | "抖音";
+ content_format: "image_text" | "video";
};
function normalizedValue(value: string) {
@@ -99,17 +105,27 @@ async function findExistingTask(
return db
.prepare(
`SELECT id, share_token, name, brand, due_at, quantity,
- source_url, source_sheet_id, source_sheet_name
+ source_url, source_sheet_id, source_sheet_name,
+ platform, content_format
FROM tasks
WHERE name = ?
AND brand = ?
AND due_at = ?
AND source_url = ?
+ AND platform = ?
+ AND content_format = ?
AND status IN ('active', 'importing')
ORDER BY created_at DESC
LIMIT 1`,
)
- .bind(input.name, input.brand, input.dueAt, sourceUrl)
+ .bind(
+ input.name,
+ input.brand,
+ input.dueAt,
+ sourceUrl,
+ input.platform ?? "小红书",
+ input.contentFormat ?? "image_text",
+ )
.first();
}
@@ -124,9 +140,10 @@ async function insertTaskFromSource(
.prepare(
`INSERT INTO tasks
(id, name, brand, quantity, claimed_quantity, due_at, status,
+ platform, content_format,
source_url, source_sheet_id, source_sheet_name, source_synced_at,
share_token)
- VALUES (?, ?, ?, ?, 0, ?, 'importing', ?, ?, ?, ?, ?)`,
+ VALUES (?, ?, ?, ?, 0, ?, 'importing', ?, ?, ?, ?, ?, ?, ?)`,
)
.bind(
taskId,
@@ -134,6 +151,8 @@ async function insertTaskFromSource(
input.brand,
source.rows.length,
input.dueAt,
+ input.platform ?? "小红书",
+ input.contentFormat ?? "image_text",
source.url,
source.sheetId,
source.sheetName,
@@ -149,11 +168,15 @@ async function insertTaskFromSource(
...image,
key: `content-assets/${taskId}/${contentId}/${image.index}`,
}));
+ const videoAssets = row.videos.map((video) => ({
+ ...video,
+ key: `content-videos/${taskId}/${contentId}/${video.index}`,
+ }));
return db
.prepare(
`INSERT INTO contents
- (id, task_id, title, body, image_assets, status, source, source_row)
- VALUES (?, ?, ?, ?, ?, 'available', ?, ?)`,
+ (id, task_id, title, body, image_assets, video_assets, status, source, source_row)
+ VALUES (?, ?, ?, ?, ?, ?, 'available', ?, ?)`,
)
.bind(
contentId,
@@ -161,6 +184,7 @@ async function insertTaskFromSource(
row.title,
row.body,
JSON.stringify(imageAssets),
+ JSON.stringify(videoAssets),
`飞书 · ${source.sheetName}`,
row.sourceRow,
);
@@ -189,11 +213,13 @@ export async function createDistributionTask(
options: { deduplicate?: boolean } = {},
): Promise {
await ensureSchema();
- const input = {
+ const input: Required = {
feishuUrl: normalizedFeishuUrl(rawInput.feishuUrl),
name: normalizedValue(rawInput.name),
brand: normalizedValue(rawInput.brand),
dueAt: normalizedDueDate(rawInput.dueAt),
+ platform: rawInput.platform === "抖音" ? "抖音" : "小红书",
+ contentFormat: rawInput.contentFormat === "video" ? "video" : "image_text",
};
if (!input.feishuUrl || !input.name || !input.brand) {
throw new Error("请补全飞书链接、任务名称和品牌/项目");
@@ -213,11 +239,19 @@ export async function createDistributionTask(
sheetId: existing.source_sheet_id,
sheetName: existing.source_sheet_name,
sourceUrl: existing.source_url,
+ platform: existing.platform,
+ contentFormat: existing.content_format,
};
}
}
const source = await readFeishuSource(input.feishuUrl, bindings);
+ if (
+ input.contentFormat === "video" &&
+ source.rows.some((row) => row.videos.length === 0)
+ ) {
+ throw new Error("视频任务中存在未识别到视频的内容行，请检查飞书“视频”列");
+ }
const inserted = await insertTaskFromSource(source, input);
return {
created: true,
@@ -230,6 +264,8 @@ export async function createDistributionTask(
sheetId: source.sheetId,
sheetName: source.sheetName,
sourceUrl: source.url,
+ platform: input.platform,
+ contentFormat: input.contentFormat,
};
}
@@ -287,8 +323,8 @@ export async function createScreenshotTask(
db
.prepare(
`INSERT INTO contents
- (id, task_id, title, body, image_assets, status, source, source_row)
- VALUES (?, ?, ?, ?, ?, 'available', '截图回收任务', ?)`,
+ (id, task_id, title, body, image_assets, video_assets, status, source, source_row)
+ VALUES (?, ?, ?, ?, ?, '[]', 'available', '截图回收任务', ?)`,
)
.bind(
uid("content"),
diff --git a/lib/video-file.ts b/lib/video-file.ts
new file mode 100644
index 0000000..08f9937
--- /dev/null
+++ b/lib/video-file.ts
@@ -0,0 +1,45 @@
+const MP4_BRANDS = new Set([
+ "avc1",
+ "dash",
+ "isom",
+ "M4A ",
+ "M4B ",
+ "M4P ",
+ "M4V ",
+ "mp41",
+ "mp42",
+ "MSNV",
+]);
+
+function fourCharacters(bytes: Uint8Array, offset: number) {
+ return String.fromCharCode(...bytes.slice(offset, offset + 4));
+}
+
+function isMp4Brand(brand: string) {
+ return (
+ MP4_BRANDS.has(brand) ||
+ /^iso[2-9]$/.test(brand) ||
+ /^3g[2p]$/.test(brand.slice(0, 3))
+ );
+}
+
+/** Rejects HTML/JSON/error payloads and non-MP4 containers before download. */
+export function hasMp4FileSignature(input: ArrayBuffer | Uint8Array) {
+ const bytes = input instanceof Uint8Array ? input : new Uint8Array(input);
+ if (bytes.byteLength < 12 || fourCharacters(bytes, 4) !== "ftyp") {
+ return false;
+ }
+ const declaredSize = new DataView(
+ bytes.buffer,
+ bytes.byteOffset,
+ bytes.byteLength,
+ ).getUint32(0);
+ const boxEnd = Math.min(
+ bytes.byteLength,
+ declaredSize >= 12 ? declaredSize : bytes.byteLength,
+ );
+ for (let offset = 8; offset + 4 <= boxEnd; offset += 4) {
+ if (isMp4Brand(fourCharacters(bytes, offset))) return true;
+ }
+ return false;
+}
diff --git a/lib/workbook-image.ts b/lib/workbook-image.ts
new file mode 100644
index 0000000..bea011f
--- /dev/null
+++ b/lib/workbook-image.ts
@@ -0,0 +1,83 @@
+import sharp from "sharp";
+
+export type WorkbookSourceImage = {
+ bytes: Uint8Array;
+ contentType: string;
+ width?: number | null;
+ height?: number | null;
+ description: string;
+};
+
+export type WorkbookImageNormalizationOptions = {
+ maxDimension?: number;
+ outputFormat?: "png" | "jpeg";
+ jpegQuality?: number;
+};
+
+const NORMALIZABLE_IMAGE = /^image\/(?:jpe?g|png|webp|gif|tiff?|avif|heic|heif)$/i;
+
+function hasImageSignature(bytes: Uint8Array) {
+ if (bytes.length < 4) return false;
+ if (bytes[0] === 0xff && bytes[1] === 0xd8) return true;
+ if (bytes[0] === 0x89 && bytes[1] === 0x50 && bytes[2] === 0x4e && bytes[3] === 0x47) {
+ return true;
+ }
+ if (bytes[0] === 0x47 && bytes[1] === 0x49 && bytes[2] === 0x46) return true;
+ if (
+ bytes.length >= 12 &&
+ String.fromCharCode(...bytes.slice(0, 4)) === "RIFF" &&
+ String.fromCharCode(...bytes.slice(8, 12)) === "WEBP"
+ ) {
+ return true;
+ }
+ return (
+ (bytes[0] === 0x49 && bytes[1] === 0x49 && bytes[2] === 0x2a && bytes[3] === 0x00) ||
+ (bytes[0] === 0x4d && bytes[1] === 0x4d && bytes[2] === 0x00 && bytes[3] === 0x2a)
+ );
+}
+
+/**
+ * Excel viewers disagree on whether JPEG EXIF orientation should be applied.
+ * Bake that orientation into the pixels before the image enters the workbook.
+ * Callers may also resize and encode large source images as JPEG to keep the
+ * generated workbook within the upload limit.
+ */
+export async function normalizeWorkbookImage(
+ image: WorkbookSourceImage,
+ options: WorkbookImageNormalizationOptions = {},
+): Promise {
+ if (!NORMALIZABLE_IMAGE.test(image.contentType) && !hasImageSignature(image.bytes)) {
+ return image;
+ }
+ try {
+ let normalized = sharp(image.bytes, { animated: false }).rotate();
+ if (options.maxDimension && options.maxDimension > 0) {
+ normalized = normalized.resize({
+ width: Math.floor(options.maxDimension),
+ height: Math.floor(options.maxDimension),
+ fit: "inside",
+ withoutEnlargement: true,
+ });
+ }
+ normalized =
+ options.outputFormat === "jpeg"
+ ? normalized
+ .flatten({ background: "#ffffff" })
+ .jpeg({
+ quality: Math.min(95, Math.max(50, options.jpegQuality ?? 82)),
+ mozjpeg: true,
+ })
+ : normalized.png({ compressionLevel: 6 });
+ const { data, info } = await normalized.toBuffer({ resolveWithObject: true });
+ return {
+ ...image,
+ bytes: new Uint8Array(data),
+ contentType:
+ options.outputFormat === "jpeg" ? "image/jpeg" : "image/png",
+ width: info.width,
+ height: info.height,
+ };
+ } catch {
+ return image;
+ }
+}
diff --git a/mysql/0001_init.sql b/mysql/0001_init.sql
index 843ed21..94708d8 100644
--- a/mysql/0001_init.sql
+++ b/mysql/0001_init.sql
@@ -50,6 +50,9 @@ CREATE TABLE IF NOT EXISTS accounts (
profile_url TEXT NOT NULL DEFAULT (''),
ip_location VARCHAR(255) NOT NULL DEFAULT '待识别',
followers INT NOT NULL DEFAULT 0,
+ gender VARCHAR(16) NOT NULL DEFAULT '',
+ bio TEXT NOT NULL DEFAULT (''),
+ tags VARCHAR(500) NOT NULL DEFAULT '',
post_count INT NOT NULL DEFAULT 0,
avg_views INT NOT NULL DEFAULT 0,
first_seen_at DATETIME(3) NOT NULL DEFAULT CURRENT_TIMESTAMP(3),
diff --git a/mysql/0005_platform_video_douyin.sql b/mysql/0005_platform_video_douyin.sql
new file mode 100644
index 0000000..5893da7
--- /dev/null
+++ b/mysql/0005_platform_video_douyin.sql
@@ -0,0 +1,14 @@
+ALTER TABLE tasks
+ ADD COLUMN platform VARCHAR(32) NOT NULL DEFAULT '小红书' AFTER task_type;
+-- statement-breakpoint
+ALTER TABLE tasks
+ ADD COLUMN content_format VARCHAR(32) NOT NULL DEFAULT 'image_text' AFTER platform;
+-- statement-breakpoint
+ALTER TABLE contents
+ ADD COLUMN video_assets LONGTEXT NOT NULL DEFAULT ('[]') AFTER image_assets;
+-- statement-breakpoint
+ALTER TABLE distributions
+ ADD COLUMN latest_shares INT NULL AFTER latest_collects;
+-- statement-breakpoint
+ALTER TABLE collection_runs
+ ADD COLUMN shares INT NULL AFTER collects;
diff --git a/mysql/0006_account_profile_tags.sql b/mysql/0006_account_profile_tags.sql
new file mode 100644
index 0000000..f09877f
--- /dev/null
+++ b/mysql/0006_account_profile_tags.sql
@@ -0,0 +1,8 @@
+ALTER TABLE accounts
+ ADD COLUMN gender VARCHAR(16) NOT NULL DEFAULT '' AFTER followers;
+-- statement-breakpoint
+ALTER TABLE accounts
+ ADD COLUMN bio TEXT NOT NULL DEFAULT ('') AFTER gender;
+-- statement-breakpoint
+ALTER TABLE accounts
+ ADD COLUMN tags VARCHAR(500) NOT NULL DEFAULT '' AFTER bio;
diff --git a/mysql/0007_account_current_contact.sql b/mysql/0007_account_current_contact.sql
new file mode 100644
index 0000000..308ed42
--- /dev/null
+++ b/mysql/0007_account_current_contact.sql
@@ -0,0 +1,2 @@
+ALTER TABLE accounts
+ ADD COLUMN current_contact VARCHAR(255) NOT NULL DEFAULT '' AFTER cooperation_source;
diff --git a/next.config.ts b/next.config.ts
index 73427b4..1a79ed8 100644
--- a/next.config.ts
+++ b/next.config.ts
@@ -2,7 +2,7 @@ import type { NextConfig } from "next";
const nextConfig: NextConfig = {
output: "standalone",
- serverExternalPackages: ["mysql2"],
+ serverExternalPackages: ["mysql2", "sharp"],
};
export default nextConfig;
diff --git a/package-lock.json b/package-lock.json
index f6b1f1d..6c8656f 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -16,6 +16,7 @@
"node-cron": "^4.2.1",
"react": "19.2.6",
"react-dom": "19.2.6",
+ "sharp": "^0.35.3",
"zod": "^4.4.3"
},
"devDependencies": {
@@ -1420,7 +1421,6 @@
"resolved": "https://registry.npmjs.org/@img/colour/-/colour-1.1.0.tgz",
"integrity": "sha512-Td76q7j57o/tLVdgS746cYARfSyxk8iEfRxewL9h4OMzYhbW4TAcppl0mT4eyqXddh6L/jwoM75mo7ixa/pCeQ==",
"license": "MIT",
- "optional": true,
"engines": {
"node": ">=18"
}
@@ -3836,7 +3836,6 @@
"version": "2.1.2",
"resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-2.1.2.tgz",
"integrity": "sha512-Btj2BOOO83o3WyH59e8MgXsxEQVcarkUOpEYrubB0urwnN10yQ364rsiByU11nZlqWYZm05i/of7io4mzihBtQ==",
- "devOptional": true,
"license": "Apache-2.0",
"engines": {
"node": ">=8"
@@ -7492,7 +7491,6 @@
"resolved": "https://registry.npmjs.org/sharp/-/sharp-0.35.3.tgz",
"integrity": "sha512-ej0zVHuZGHCiABXcNxeYhpRnPNPAcvbG8RMdBAhDAxLKkCRVSpK3Iyu7qbqw3JMzoj0REeM6f3tJLtVwl0023Q==",
"license": "Apache-2.0",
- "optional": true,
"dependencies": {
"@img/colour": "^1.1.0",
"detect-libc": "^2.1.2",
@@ -7542,7 +7540,6 @@
"resolved": "https://registry.npmjs.org/semver/-/semver-7.8.5.tgz",
"integrity": "sha512-Y7/KDsb8LjooZpwaqGyulO6DQlksgCncchHGk+sZIY4SBvUocMBEFH5Ur1fI4dV+Jvl0w6cjvucaIi40puRioA==",
"license": "ISC",
- "optional": true,
"bin": {
"semver": "bin/semver.js"
},
diff --git a/package.json b/package.json
index db9eda7..546ad44 100644
--- a/package.json
+++ b/package.json
@@ -7,7 +7,7 @@
},
"scripts": {
"dev": "next dev",
- "build": "next build",
+ "build": "next build --webpack",
"start": "next start",
"test": "npm run build && node --import tsx --test tests/*.test.mjs",
"lint": "eslint . --ignore-pattern dist --ignore-pattern .next --ignore-pattern koc-portal/out",
@@ -26,6 +26,7 @@
"node-cron": "^4.2.1",
"react": "19.2.6",
"react-dom": "19.2.6",
+ "sharp": "^0.35.3",
"zod": "^4.4.3"
},
"devDependencies": {
diff --git a/public/KOC资源导入模板.xlsx b/public/KOC资源导入模板.xlsx
index 15346f9..6d726b5 100644
Binary files a/public/KOC资源导入模板.xlsx and b/public/KOC资源导入模板.xlsx differ
diff --git a/scripts/setup.sh b/scripts/setup.sh
new file mode 100755
index 0000000..ded3310
--- /dev/null
+++ b/scripts/setup.sh
@@ -0,0 +1,7 @@
+#!/bin/sh
+set -eu
+
+APP_DIR=$(CDPATH= cd -- "$(dirname -- "$0")/.." && pwd)
+cd "$APP_DIR"
+npm ci
+npm run build
diff --git a/scripts/start.sh b/scripts/start.sh
new file mode 100755
index 0000000..eab1ddd
--- /dev/null
+++ b/scripts/start.sh
@@ -0,0 +1,8 @@
+#!/bin/sh
+set -eu
+
+APP_DIR=$(CDPATH= cd -- "$(dirname -- "$0")/.." && pwd)
+cd "$APP_DIR"
+export HOSTNAME=0.0.0.0
+export PORT="${PORT:-9000}"
+exec node .next/standalone/server.js
diff --git a/tests/feishu-client.test.mjs b/tests/feishu-client.test.mjs
index 193d6a3..af601b5 100644
--- a/tests/feishu-client.test.mjs
+++ b/tests/feishu-client.test.mjs
@@ -120,6 +120,55 @@ test("resolves a wiki sheet and imports title, body, tags, and all images", asyn
assert.equal(valuesCall.url.searchParams.get("ranges"), "sheet-one!A1:J20");
});
+test("imports video attachments from a Feishu video task sheet", async () => {
+ clearFeishuAccessTokenCacheForTests();
+ const { fetchImpl } = fakeFeishu();
+ const videoFetch = async (input, init = {}) => {
+ const url = new URL(String(input));
+ if (url.pathname.endsWith("/values_batch_get")) {
+ return apiResponse({
+ valueRanges: [
+ {
+ values: [
+ ["标题", "内容（标题+正文+tag）", "视频"],
+ [
+ "一条测试视频",
+ "一条测试视频\n视频正文 #测试",
+ {
+ type: "attachment",
+ fileToken: "video-token-one",
+ text: "demo.mp4",
+ mimeType: "video/mp4",
+ size: 1024,
+ },
+ ],
+ ],
+ },
+ ],
+ });
+ }
+ return fetchImpl(input, init);
+ };
+ const source = await readFeishuSource(
+ "https://tenant.feishu.cn/wiki/wiki-test",
+ bindings,
+ videoFetch,
+ );
+
+ assert.equal(source.rows.length, 1);
+ assert.equal(source.rows[0].title, "一条测试视频");
+ assert.equal(source.rows[0].body, "一条测试视频\n视频正文 #测试");
+ assert.deepEqual(source.rows[0].videos, [
+ {
+ index: 1,
+ fileToken: "video-token-one",
+ name: "demo.mp4",
+ mimeType: "video/mp4",
+ size: 1024,
+ },
+ ]);
+});
+
test("requires an exact sheet link when a workbook has multiple visible sheets", async () => {
clearFeishuAccessTokenCacheForTests();
const { fetchImpl } = fakeFeishu({
diff --git a/tests/mcp-collection-client.test.mjs b/tests/mcp-collection-client.test.mjs
index 29eafc3..a5b2ed4 100644
--- a/tests/mcp-collection-client.test.mjs
+++ b/tests/mcp-collection-client.test.mjs
@@ -1,7 +1,9 @@
import assert from "node:assert/strict";
import test from "node:test";
import {
+ collectMetricsFromMcp,
collectXhsMetricsFromMcp,
+ resolveAccountProfileFromMcp,
resolveCollectionMcpConfig,
resolveXhsPublicAccountDetails,
resolveXhsPublicAccountId,
@@ -40,10 +42,17 @@ function toolEnvelope(payload, isError = false) {
};
}
-function createFakeMcp(toolResults) {
+function createFakeMcp(toolResults, redirects = {}) {
let toolIndex = 0;
const calls = [];
const fetchImpl = async (url, init) => {
+ if (!init?.body) {
+ const requestUrl = String(url);
+ calls.push({ url: requestUrl, body: null, headers: new Headers(init?.headers) });
+ const location = redirects[requestUrl];
+ if (!location) throw new Error(`Unexpected public request: ${requestUrl}`);
+ return new Response("", { status: 302, headers: { location } });
+ }
const body = JSON.parse(init.body);
calls.push({ url: String(url), body, headers: new Headers(init.headers) });
if (body.method === "initialize") {
@@ -103,6 +112,7 @@ test("collects likes, comments and favorites from the verified MCP shape", async
likes: 483,
comments: 41,
collects: 519,
+ shares: 0,
});
assert.equal(calls.length, 3);
assert.equal(calls[2].body.params.name, "fetch_content_detail");
@@ -147,7 +157,7 @@ test("collects through a stateless MCP server without a session header", async (
fetchImpl,
);
- assert.deepEqual(result, { likes: 12, comments: 3, collects: 6 });
+ assert.deepEqual(result, { likes: 12, comments: 3, collects: 6, shares: 0 });
assert.deepEqual(
calls.map((call) => call.body.method),
["initialize", "tools/call"],
@@ -217,19 +227,24 @@ test("resolves the real XHS account profile from a submitted note link", async (
redId: "94329495984",
ipLocation: "重庆",
followers: 734,
+ gender: "",
+ bio: "",
+ recentNoteTitles: [],
+ providerTags: [],
});
- assert.equal(calls.length, 4);
+ const mcpCalls = calls.filter((call) => call.body?.method);
+ assert.equal(mcpCalls.length, 4);
assert.equal(
- calls[2].body.params.name,
- "collect_xhs_wen_note_detail",
+ mcpCalls[2].body.params.name,
+ "fetch_content_detail",
);
assert.equal(
- calls[2].body.params.arguments.request.note_id,
- "6a671108000000000f004bef",
+ mcpCalls[2].body.params.arguments.request.link,
+ "https://www.xiaohongshu.com/discovery/item/6a671108000000000f004bef",
);
- assert.equal(calls[3].body.params.name, "parse_xhs_user_summary");
+ assert.equal(mcpCalls[3].body.params.name, "parse_xhs_user_summary");
assert.equal(
- calls[3].body.params.arguments.request.url,
+ mcpCalls[3].body.params.arguments.request.url,
"https://www.xiaohongshu.com/user/profile/6905cbca0000000037009f49",
);
assert.equal(
@@ -253,7 +268,17 @@ test("resolves followers directly from the supported XHS user summary tool", asy
ipLocation: "福建",
nickname: "555 五",
userId: "1020668113",
+ gender: "女",
+ desc: "分享城市周末与美食",
+ tags: ["本地生活"],
},
+ notes: [
+ {
+ note_id: "note-1",
+ title: "长沙湘菜探店",
+ url: "https://www.xiaohongshu.com/explore/note-1",
+ },
+ ],
},
},
}),
@@ -273,6 +298,10 @@ test("resolves followers directly from the supported XHS user summary tool", asy
followers: 6,
redId: "1020668113",
ipLocation: "福建",
+ gender: "女",
+ bio: "分享城市周末与美食",
+ recentNoteTitles: ["长沙湘菜探店"],
+ providerTags: ["本地生活"],
});
assert.equal(calls[2].body.params.name, "parse_xhs_user_summary");
});
@@ -338,8 +367,8 @@ test("resolves an xhslink short URL before requesting the author profile", async
"https://www.xiaohongshu.com/user/profile/6905cbca0000000037009f49",
);
assert.equal(
- fakeMcp.calls[2].body.params.arguments.request.note_id,
- "6a572da40000000021018bd2",
+ fakeMcp.calls[2].body.params.arguments.request.link,
+ "http://xhslink.cn/o/AJFyP5dnj7O",
);
});
@@ -400,10 +429,14 @@ test("uses the public note author when MCP profile lookup fails", async () => {
redId: "1020668113",
ipLocation: "待识别",
followers: 6,
+ gender: "",
+ bio: "",
+ recentNoteTitles: [],
+ providerTags: [],
});
assert.equal(
fakeMcp.calls[2].body.params.name,
- "collect_xhs_wen_note_detail",
+ "fetch_content_detail",
);
});
@@ -431,27 +464,16 @@ test("reads the user-visible Xiaohongshu number from a public profile", async ()
});
});
-test("falls back to parse_xhs_note when the primary tool fails", async () => {
+test("treats empty interaction counters from the current detail tool as zero", async () => {
const { calls, fetchImpl } = createFakeMcp([
- toolEnvelope(
- {
- response: {
- code: 400,
- success: false,
- msg: "获取内容详情失败",
- data: null,
- },
- },
- true,
- ),
toolEnvelope({
response: {
code: 200,
success: true,
data: {
- likes: "1.2万",
- comments: 32,
- collects: "2,345",
+ likes: "2",
+ comments: "",
+ collects: "",
},
},
}),
@@ -466,11 +488,42 @@ test("falls back to parse_xhs_note when the primary tool fails", async () => {
);
assert.deepEqual(result, {
- likes: 12_000,
- comments: 32,
- collects: 2_345,
+ likes: 2,
+ comments: 0,
+ collects: 0,
+ shares: 0,
});
- assert.equal(calls[3].body.params.name, "parse_xhs_note");
+ assert.equal(calls.length, 3);
+ assert.equal(calls[2].body.params.name, "fetch_content_detail");
+});
+
+test("surfaces current detail tool failures without calling removed tools", async () => {
+ const { calls, fetchImpl } = createFakeMcp([
+ toolEnvelope(
+ {
+ response: {
+ code: 400,
+ success: false,
+ msg: "获取内容详情失败",
+ data: null,
+ },
+ },
+ true,
+ ),
+ ]);
+
+ await assert.rejects(
+ collectXhsMetricsFromMcp(
+ "https://www.xiaohongshu.com/explore/test",
+ {
+ endpoint: "https://collector.example/mcp?key=test-key",
+ },
+ fetchImpl,
+ ),
+ /获取内容详情失败/,
+ );
+ assert.equal(calls.length, 3);
+ assert.equal(calls[2].body.params.name, "fetch_content_detail");
});
test("requires the MCP key without sending a network request", async () => {
@@ -551,6 +604,237 @@ test("rebuilds the MCP session after a gateway session miss", async () => {
fetchImpl,
);
- assert.deepEqual(result, { likes: 8, comments: 2, collects: 5 });
+ assert.deepEqual(result, { likes: 8, comments: 2, collects: 5, shares: 0 });
assert.equal(initializeCount, 2);
});
+
+test("collects Douyin likes, favorites, shares and comments", async () => {
+ const { calls, fetchImpl } = createFakeMcp([
+ toolEnvelope({
+ response: {
+ code: 200,
+ success: true,
+ data: {
+ digg_count: "120",
+ collect_count: "30",
+ share_count: "8",
+ comment_count: "12",
+ },
+ },
+ }),
+ ]);
+
+ const result = await collectMetricsFromMcp(
+ "https://www.douyin.com/video/7520000000000000000",
+ "抖音",
+ { endpoint: "https://collector.example/mcp", key: "test-key" },
+ fetchImpl,
+ );
+
+ assert.deepEqual(result, {
+ likes: 120,
+ collects: 30,
+ shares: 8,
+ comments: 12,
+ });
+ assert.equal(calls[2].body.params.name, "fetch_content_detail");
+ assert.equal(calls[2].body.params.arguments.request.plant, "dy");
+});
+
+test("maps the current Douyin MCP metric field names", async () => {
+ const { fetchImpl } = createFakeMcp([
+ toolEnvelope({
+ response: {
+ code: 200,
+ success: true,
+ data: {
+ liked_count: "5682",
+ collected_count: "565",
+ share_count: "6878",
+ comment_count: "332",
+ },
+ },
+ }),
+ ]);
+
+ const result = await collectMetricsFromMcp(
+ "https://v.douyin.com/5O5VpgomO2U/",
+ "抖音",
+ { endpoint: "https://collector.example/mcp", key: "test-key" },
+ fetchImpl,
+ );
+
+ assert.deepEqual(result, {
+ likes: 5682,
+ collects: 565,
+ shares: 6878,
+ comments: 332,
+ });
+});
+
+test("resolves a Douyin account from a submitted work link", async () => {
+ const secUid = "MS4wLjABAAAA-test-profile-123456";
+ const { calls, fetchImpl } = createFakeMcp([
+ toolEnvelope({
+ response: {
+ code: 200,
+ success: true,
+ data: {
+ author: {
+ nickname: "抖音作者",
+ sec_uid: secUid,
+ unique_id: "douyin-123",
+ },
+ },
+ },
+ }),
+ toolEnvelope({
+ response: {
+ code: 200,
+ success: true,
+ data: {
+ user: {
+ nickname: "抖音作者",
+ unique_id: "douyin-123",
+ sec_uid: secUid,
+ follower_count: "1.5万",
+ ip_location: "上海",
+ },
+ },
+ },
+ }),
+ ]);
+
+ const profile = await resolveAccountProfileFromMcp(
+ "https://www.douyin.com/video/7520000000000000000",
+ "抖音",
+ "回填昵称",
+ { endpoint: "https://collector.example/mcp", key: "test-key" },
+ fetchImpl,
+ );
+
+ assert.deepEqual(profile, {
+ platformUid: secUid,
+ nickname: "抖音作者",
+ profileUrl: `https://www.douyin.com/user/${secUid}`,
+ redId: "douyin-123",
+ ipLocation: "上海",
+ followers: 15_000,
+ gender: "",
+ bio: "",
+ recentNoteTitles: [],
+ providerTags: [],
+ });
+ assert.equal(calls[2].body.params.arguments.request.plant, "dy");
+ assert.equal(calls[3].body.params.name, "parse_dy_user_summary");
+});
+
+test("does not treat a Douyin short-link device id as the author sec_uid", async () => {
+ const shortLink = "https://v.douyin.com/5O5VpgomO2U/";
+ const { calls, fetchImpl } = createFakeMcp(
+ [
+ toolEnvelope({
+ response: {
+ code: 200,
+ success: true,
+ data: {
+ nickname: "搞怪噜噜😜",
+ user_id: "4065311277723529",
+ },
+ },
+ }),
+ ],
+ {
+ [shortLink]: "https://www.iesdouyin.com/share/video/7671270545631842038/?did=MS4wLjABAAAA-device-token&with_sec_did=1",
+ },
+ );
+
+ const profile = await resolveAccountProfileFromMcp(
+ shortLink,
+ "抖音",
+ "回填昵称",
+ { endpoint: "https://collector.example/mcp", key: "test-key" },
+ fetchImpl,
+ );
+
+ assert.deepEqual(profile, {
+ platformUid: "4065311277723529",
+ nickname: "搞怪噜噜😜",
+ profileUrl: "",
+ redId: "",
+ ipLocation: "待识别",
+ followers: null,
+ gender: "",
+ bio: "",
+ recentNoteTitles: [],
+ providerTags: [],
+ });
+ assert.equal(calls.find((call) => call.body === null)?.url, shortLink);
+ assert.equal(
+ calls.find((call) => call.body?.params?.name === "parse_dy_user_summary"),
+ undefined,
+ );
+});
+
+test("resolves a Douyin profile only when the public redirect exposes sec_uid", async () => {
+ const shortLink = "https://v.douyin.com/author-sec-uid/";
+ const secUid = "MS4wLjABAAAAOqL4Jdu8htr7EWCDAyIr5z_7uvCAxhj-GOzCWg5zn8bDiKOp3WPw7lWkTyHvZpMY";
+ const { calls, fetchImpl } = createFakeMcp(
+ [
+ toolEnvelope({
+ response: {
+ code: 200,
+ success: true,
+ data: {
+ nickname: "抖音作者",
+ user_id: "4065311277723529",
+ },
+ },
+ }),
+ toolEnvelope({
+ response: {
+ code: 200,
+ success: true,
+ data: {
+ user: {
+ nickname: "抖音作者",
+ unique_id: "douyin-987",
+ sec_uid: secUid,
+ follower_count: "2.3万",
+ ip_location: "广东",
+ },
+ },
+ },
+ }),
+ ],
+ {
+ [shortLink]: `https://www.iesdouyin.com/share/video/7671270545631842038/?sec_uid=${secUid}`,
+ },
+ );
+
+ const profile = await resolveAccountProfileFromMcp(
+ shortLink,
+ "抖音",
+ "回填昵称",
+ { endpoint: "https://collector.example/mcp", key: "test-key" },
+ fetchImpl,
+ );
+
+ assert.deepEqual(profile, {
+ platformUid: secUid,
+ nickname: "抖音作者",
+ profileUrl: `https://www.douyin.com/user/${secUid}`,
+ redId: "douyin-987",
+ ipLocation: "广东",
+ followers: 23_000,
+ gender: "",
+ bio: "",
+ recentNoteTitles: [],
+ providerTags: [],
+ });
+ assert.equal(
+ calls.find((call) => call.body?.params?.name === "parse_dy_user_summary")
+ ?.body.params.arguments.request.url,
+ `https://www.douyin.com/user/${secUid}`,
+ );
+});
diff --git a/tests/partner-batch-upload.test.mjs b/tests/partner-batch-upload.test.mjs
new file mode 100644
index 0000000..c5a4337
--- /dev/null
+++ b/tests/partner-batch-upload.test.mjs
@@ -0,0 +1,57 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+import { strToU8, unzipSync, zipSync } from "fflate";
+import { compactPartnerBatchWorkbookForUpload } from "../koc-portal/app/batch-workbook-upload.ts";
+
+const imageBytes = (marker, size) => {
+ const bytes = new Uint8Array(size);
+ bytes.set([0x89, 0x50, 0x4e, 0x47, marker]);
+ for (let index = 5; index < bytes.length; index += 1) bytes[index] = marker;
+ return bytes;
+};
+
+test("slims oversized WPS workbooks without removing backfill screenshots", () => {
+ const worksheet = `
+
+
+
+ 序号（不能改）
+ 图片1
+ 笔记截图
+ 数据分析截图（单篇笔记数据分析截图）
+
+
+ _xlfn.DISPIMG("SOURCE",1)=DISPIMG("SOURCE",1)
+ _xlfn.DISPIMG("PUBLISH",1)=DISPIMG("PUBLISH",1)
+
+
+ `;
+ const cellImages = `
+
+
+
+ `;
+ const relationships = `
+
+
+
+ `;
+ const workbook = zipSync(
+ {
+ "xl/worksheets/sheet1.xml": strToU8(worksheet),
+ "xl/cellimages.xml": strToU8(cellImages),
+ "xl/_rels/cellimages.xml.rels": strToU8(relationships),
+ "xl/media/source.png": [imageBytes(1, 2_000_000), { level: 0 }],
+ "xl/media/publish.png": [imageBytes(2, 2_000), { level: 0 }],
+ },
+ { level: 0 },
+ );
+
+ const compacted = compactPartnerBatchWorkbookForUpload(workbook);
+ const entries = unzipSync(compacted.bytes);
+ assert.equal(entries["xl/media/source.png"], undefined);
+ assert.deepEqual(entries["xl/media/publish.png"], imageBytes(2, 2_000));
+ assert.equal(compacted.removedMediaCount, 1);
+ assert.equal(compacted.preservedScreenshotCount, 1);
+ assert.ok(compacted.bytes.byteLength < workbook.byteLength / 10);
+});
diff --git a/tests/partner-batch-workbook.test.mjs b/tests/partner-batch-workbook.test.mjs
new file mode 100644
index 0000000..e194a57
--- /dev/null
+++ b/tests/partner-batch-workbook.test.mjs
@@ -0,0 +1,327 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+import { strFromU8, strToU8, unzipSync, zipSync } from "fflate";
+import { buildRecoveryWorkbook } from "../lib/recovery-workbook.ts";
+import {
+ PARTNER_BATCH_HEADERS,
+ buildPartnerBatchWorkbookColumns,
+ parsePartnerBatchWorkbook,
+ resolvePartnerWorkbookOrigin,
+} from "../lib/partner-batch-workbook.ts";
+import { hasMp4FileSignature } from "../lib/video-file.ts";
+
+const png = Uint8Array.from([
+ 0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a,
+ 0x00, 0x00, 0x00, 0x0d, 0x49, 0x48, 0x44, 0x52,
+ 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x01,
+]);
+
+test("round-trips hidden assignment IDs and embedded backfill screenshots", () => {
+ const workbook = buildRecoveryWorkbook({
+ sheetName: "批量回填",
+ headers: [...PARTNER_BATCH_HEADERS],
+ columnWidths: [10, 20, 40, 30, 40, 24, 28, 20, 20, 20],
+ hiddenColumns: [7, 8, 9],
+ rows: [
+ {
+ cells: [
+ 1,
+ "测试笔记",
+ "正文 #话题",
+ "",
+ "https://www.xiaohongshu.com/explore/1234567890abcdef",
+ "",
+ "",
+ "distribution-1",
+ "",
+ "",
+ ],
+ images: [
+ {
+ column: 3,
+ image: { bytes: png, contentType: "image/png", description: "原图" },
+ },
+ {
+ column: 5,
+ image: { bytes: png, contentType: "image/png", description: "笔记截图" },
+ },
+ {
+ column: 6,
+ image: { bytes: png, contentType: "image/png", description: "数据截图" },
+ },
+ ],
+ },
+ ],
+ });
+ const rows = parsePartnerBatchWorkbook(workbook);
+ assert.equal(rows.length, 1);
+ assert.equal(rows[0].distributionId, "distribution-1");
+ assert.equal(rows[0].title, "测试笔记");
+ assert.match(rows[0].publishUrl, /xiaohongshu\.com/);
+ assert.equal(rows[0].publishScreenshot?.contentType, "image/png");
+ assert.equal(rows[0].creatorScreenshot?.contentType, "image/png");
+
+ const entries = unzipSync(workbook);
+ const worksheet = strFromU8(entries["xl/worksheets/sheet1.xml"]);
+ assert.match(worksheet, /序号（不能改）/);
+ assert.doesNotMatch(worksheet, /张原图（见图）|已回填（见图）|请插入笔记截图/);
+ assert.match(worksheet, //);
+ assert.doesNotMatch(worksheet, /#VALUE!/);
+ const drawing = strFromU8(entries["xl/drawings/drawing1.xml"]);
+ assert.equal((drawing.match(//g) ?? []).length, 3);
+ assert.match(drawing, /3<\/xdr:col>/);
+ assert.match(drawing, /5<\/xdr:col>/);
+ assert.match(drawing, /6<\/xdr:col>/);
+ assert.match(worksheet, /min="8" max="8"[^>]*hidden="1"/);
+});
+
+test("accepts the legacy sequence header for previously exported workbooks", () => {
+ const legacyHeaders = [...PARTNER_BATCH_HEADERS];
+ legacyHeaders[0] = "序号";
+ const workbook = buildRecoveryWorkbook({
+ sheetName: "批量回填",
+ headers: legacyHeaders,
+ columnWidths: [10, 20, 40, 30, 40, 24, 28, 20, 20, 20],
+ hiddenColumns: [7, 8, 9],
+ rows: [
+ {
+ cells: [
+ 1,
+ "旧模板笔记",
+ "正文",
+ "",
+ "",
+ "",
+ "",
+ "distribution-legacy",
+ "",
+ "",
+ ],
+ images: [],
+ },
+ ],
+ });
+ const rows = parsePartnerBatchWorkbook(workbook);
+ assert.equal(rows[0].sequence, "1");
+ assert.equal(rows[0].distributionId, "distribution-legacy");
+});
+
+test("imports dynamic source image columns without confusing screenshot columns", () => {
+ const headers = [
+ "序号（不能改）",
+ "标题",
+ "笔记内容（正文+话题）",
+ "图片1",
+ "图片2",
+ "发布链接",
+ "笔记截图",
+ "数据分析截图（单篇笔记数据分析截图）",
+ "_系统笔记ID",
+ "_原笔记截图",
+ "_原数据分析截图",
+ ];
+ const workbook = buildRecoveryWorkbook({
+ sheetName: "批量回填",
+ headers,
+ columnWidths: headers.map(() => 20),
+ hiddenColumns: [8, 9, 10],
+ rows: [
+ {
+ cells: [
+ 1,
+ "多图笔记",
+ "正文",
+ "",
+ "",
+ "https://www.xiaohongshu.com/explore/dynamic",
+ "",
+ "",
+ "distribution-dynamic",
+ "",
+ "",
+ ],
+ images: [
+ {
+ column: 3,
+ image: { bytes: png, contentType: "image/png", description: "原图1" },
+ },
+ {
+ column: 4,
+ image: { bytes: png, contentType: "image/png", description: "原图2" },
+ },
+ {
+ column: 6,
+ image: { bytes: png, contentType: "image/png", description: "笔记截图" },
+ },
+ {
+ column: 7,
+ image: { bytes: png, contentType: "image/png", description: "数据截图" },
+ },
+ ],
+ },
+ ],
+ });
+ const rows = parsePartnerBatchWorkbook(workbook);
+ assert.equal(rows[0].distributionId, "distribution-dynamic");
+ assert.equal(rows[0].publishScreenshot?.contentType, "image/png");
+ assert.equal(rows[0].creatorScreenshot?.contentType, "image/png");
+});
+
+test("imports screenshots saved by WPS as DISPIMG cell images", () => {
+ const sourceImage = Uint8Array.from([...png, 1]);
+ const publishScreenshot = Uint8Array.from([...png, 2]);
+ const creatorScreenshot = Uint8Array.from([...png, 3]);
+ const worksheet = `
+
+
+
+ 序号（不能改）
+ 标题
+ 笔记内容（正文+话题）
+ 图片1
+ 发布链接
+ 笔记截图
+ 数据分析截图（单篇笔记数据分析截图）
+ _系统笔记ID
+ _原笔记截图
+ _原数据分析截图
+
+
+ 1
+ WPS 笔记
+ _xlfn.DISPIMG("SOURCE",1)=DISPIMG("SOURCE",1)
+ https://www.xiaohongshu.com/explore/wps
+ _xlfn.DISPIMG("PUBLISH",1)=DISPIMG("PUBLISH",1)
+ _xlfn.DISPIMG("CREATOR",1)=DISPIMG("CREATOR",1)
+ distribution-wps
+
+
+ `;
+ const cellImages = `
+
+
+
+
+ `;
+ const relationships = `
+
+
+
+
+ `;
+ const workbook = zipSync({
+ "xl/worksheets/sheet1.xml": strToU8(worksheet),
+ "xl/cellimages.xml": strToU8(cellImages),
+ "xl/_rels/cellimages.xml.rels": strToU8(relationships),
+ "xl/media/source.png": sourceImage,
+ "xl/media/publish.png": publishScreenshot,
+ "xl/media/creator.png": creatorScreenshot,
+ });
+
+ const rows = parsePartnerBatchWorkbook(workbook);
+ assert.equal(rows.length, 1);
+ assert.equal(rows[0].distributionId, "distribution-wps");
+ assert.deepEqual(rows[0].publishScreenshot?.bytes, publishScreenshot);
+ assert.deepEqual(rows[0].creatorScreenshot?.bytes, creatorScreenshot);
+});
+
+test("builds video-task workbooks with video columns and no source image columns", () => {
+ const columns = buildPartnerBatchWorkbookColumns({
+ contentFormat: "video",
+ maxSourceImages: 3,
+ maxSourceVideos: 2,
+ });
+ assert.deepEqual(columns.headers.slice(0, 8), [
+ "序号（不能改）",
+ "标题",
+ "笔记内容（正文+话题）",
+ "视频1",
+ "视频2",
+ "发布链接",
+ "笔记截图",
+ "数据分析截图（单篇笔记数据分析截图）",
+ ]);
+ assert.equal(columns.headers.some((header) => /^图片\d+$/.test(header)), false);
+
+ const workbook = buildRecoveryWorkbook({
+ sheetName: "视频批量回填",
+ headers: columns.headers,
+ columnWidths: columns.columnWidths,
+ hiddenColumns: [
+ columns.systemColumn,
+ columns.systemColumn + 1,
+ columns.systemColumn + 2,
+ ],
+ rows: [
+ {
+ cells: [
+ 1,
+ "视频笔记",
+ "视频正文 #测试",
+ "下载视频1",
+ "下载视频2",
+ "",
+ "",
+ "",
+ "distribution-video",
+ "",
+ "",
+ ],
+ images: [],
+ hyperlinks: [
+ {
+ column: columns.sourceVideoStartColumn,
+ url: "https://koc.example.com/api/partner-image?kind=video&download=1",
+ },
+ ],
+ },
+ ],
+ });
+ const entries = unzipSync(workbook);
+ const worksheet = strFromU8(entries["xl/worksheets/sheet1.xml"]);
+ const relationships = strFromU8(
+ entries["xl/worksheets/_rels/sheet1.xml.rels"],
+ );
+ assert.match(worksheet, /视频1/);
+ assert.doesNotMatch(worksheet, /图片1/);
+ assert.match(relationships, /https:\/\/koc\.example\.com\/api\/partner-image/);
+ assert.match(relationships, /download=1/);
+});
+
+test("uses the configured public origin before proxy or container addresses", () => {
+ const request = new Request("http://app:3000/api/partner-batch-workbook", {
+ headers: {
+ host: "app:3000",
+ "x-forwarded-host": "internal-proxy:8080",
+ "x-forwarded-proto": "https",
+ },
+ });
+ assert.equal(
+ resolvePartnerWorkbookOrigin(request, "https://koc.example.com/koc/"),
+ "https://koc.example.com",
+ );
+});
+
+test("preserves a forwarded non-standard port when no origin is configured", () => {
+ const request = new Request("http://app:3000/api/partner-batch-workbook", {
+ headers: {
+ host: "app:3000",
+ "x-forwarded-host": "localhost:8080",
+ "x-forwarded-proto": "http",
+ },
+ });
+ assert.equal(resolvePartnerWorkbookOrigin(request), "http://localhost:8080");
+});
+
+test("recognizes MP4 bytes instead of trusting a response content type", () => {
+ const mp4Header = Uint8Array.from([
+ 0x00, 0x00, 0x00, 0x18,
+ 0x66, 0x74, 0x79, 0x70,
+ 0x69, 0x73, 0x6f, 0x6d,
+ 0x00, 0x00, 0x02, 0x00,
+ 0x69, 0x73, 0x6f, 0x6d,
+ 0x6d, 0x70, 0x34, 0x32,
+ ]);
+ assert.equal(hasMp4FileSignature(mp4Header), true);
+ assert.equal(hasMp4FileSignature(new TextEncoder().encode("not a video")), false);
+});
diff --git a/tests/recovery-workbook.test.mjs b/tests/recovery-workbook.test.mjs
index d630774..b3d7c94 100644
--- a/tests/recovery-workbook.test.mjs
+++ b/tests/recovery-workbook.test.mjs
@@ -16,7 +16,7 @@ test("creates an xlsx archive whose pictures are embedded in worksheet cells", (
columnWidths: [8, 24, 24, 24],
rows: [
{
- cells: [1, "测试笔记", "见图", "见图"],
+ cells: [1, "测试笔记", "", ""],
images: [
{
column: 2,
@@ -43,12 +43,24 @@ test("creates an xlsx archive whose pictures are embedded in worksheet cells", (
],
});
const archive = unzipSync(workbook);
+ const worksheet = strFromU8(archive["xl/worksheets/sheet1.xml"]);
assert.ok(archive["xl/media/image1.png"]);
assert.ok(archive["xl/media/image2.png"]);
- assert.match(strFromU8(archive["xl/worksheets/sheet1.xml"]), //);
- assert.match(strFromU8(archive["xl/drawings/drawing1.xml"]), /oneCellAnchor/);
- assert.match(strFromU8(archive["xl/drawings/_rels/drawing1.xml.rels"]), /image2\.png/);
+ assert.match(worksheet, //);
+ assert.doesNotMatch(worksheet, /#VALUE!/);
+ const drawing = strFromU8(archive["xl/drawings/drawing1.xml"]);
+ assert.equal((drawing.match(//g) ?? []).length, 2);
+ assert.match(drawing, /2<\/xdr:col>/);
+ assert.match(drawing, /3<\/xdr:col>/);
+ assert.match(
+ strFromU8(archive["xl/drawings/_rels/drawing1.xml.rels"]),
+ /image2\.png/,
+ );
+ assert.doesNotMatch(
+ worksheet,
+ /见图/,
+ );
});
test("creates clickable external hyperlinks for resource exports", () => {
diff --git a/tests/rendered-html.test.mjs b/tests/rendered-html.test.mjs
index 434accd..eb23f93 100644
--- a/tests/rendered-html.test.mjs
+++ b/tests/rendered-html.test.mjs
@@ -23,6 +23,30 @@ test("builds the KOC LOOP product shell", async () => {
await access(new URL("../.next/static", import.meta.url));
});
+test("keeps distribution filters as always-visible fuzzy search fields", async () => {
+ const [adminApp, globalCss] = await Promise.all([
+ readFile(new URL("../app/admin-app.tsx", import.meta.url), "utf8"),
+ readFile(new URL("../app/globals.css", import.meta.url), "utf8"),
+ ]);
+
+ assert.match(globalCss, /\.distribution-task-search\s*\{[^}]*flex-direction:\s*row/s);
+ assert.match(globalCss, /\.distribution-task-search\s*\{[^}]*margin:\s*0/s);
+ assert.match(globalCss, /\.distribution-task-search\s*>\s*span\s*\{[^}]*flex:\s*0\s+0\s+18px/s);
+ assert.match(globalCss, /\.distribution-task-filter-combobox\.brand\s*\{[^}]*flex-basis:\s*176px/s);
+ assert.match(globalCss, /\.distribution-task-filter-menu\s*\{[^}]*position:\s*absolute[^}]*z-index:\s*60/s);
+ assert.match(globalCss, /\.distribution-task-filter-input\s*\{[^}]*display:\s*flex[^}]*margin:\s*0/s);
+ assert.match(adminApp, /aria-expanded=\{openTaskFilter === filter\.key\}/);
+ assert.match(adminApp, /role="combobox"/);
+ assert.match(adminApp, /role="listbox"/);
+ assert.match(adminApp, /placeholder=\{`搜索\$\{filter\.label\}`\}/);
+ assert.match(adminApp, /setTaskFilterValue\(filter\.key, event\.target\.value\)/);
+ assert.doesNotMatch(adminApp, /distribution-task-filter-trigger/);
+ assert.doesNotMatch(adminApp, /distribution-task-filter-menu-search/);
+ assert.doesNotMatch(adminApp, /taskFilterQuery/);
+ assert.doesNotMatch(adminApp, /distribution-task-option-panel/);
+ assert.doesNotMatch(adminApp, /