wufengping/koc-loop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: 完善视频任务与 KOC 资源库

Browse Source
This commit is contained in:
巫凤萍
2026-08-15 03:53:09 +08:00
parent ad3dbdcc86
commit f37d05dd88
66 changed files with 6633 additions and 558 deletions
Download Patch File Download Diff File Expand all files Collapse all files

200
lib/account-enrichment-service.ts
View File

@@ -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<DistributionAccountRow>();
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<string>();
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) {