feat: 完善视频任务与 KOC 资源库

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(/<c\b([^>]*)>([\s\S]*?)<\/c>/g)) {
+    for (const cellMatch of rowMatch[2].matchAll(
+      /<c\b([^>]*?)(?:\/>|>([\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(/<v>([\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,
     });