tt-help-cli-ycl 1.0.1

package/README.md

@@ -0,0 +1,17 @@
+# tt-help
+
+TikTok user & video data scraper — extract ttSeller, verified, locationCreated from HTML source.
+
+## Install
+
+```bash
+npm i -g tt-help
+```
+
+## Usage
+
+```bash
+tt-help [options] <urls...>
+```
+
+示例、代理配置、和更多用法请查看仓库或 `src/main.mjs` 中的帮助文本。

package/cli.js

@@ -0,0 +1,9 @@
+#!/usr/bin/env node
+import { fileURLToPath } from 'url';
+import { dirname, resolve } from 'path';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+
+const mainPath = resolve(__dirname, 'src', 'main.mjs');
+await import(`file://${mainPath}`);

package/package.json

@@ -0,0 +1,44 @@
+{
+  "name": "tt-help-cli-ycl",
+  "version": "1.0.1",
+  "description": "TikTok user & video data scraper - extract ttSeller, verified, locationCreated from HTML source",
+  "type": "module",
+  "bin": {
+    "tt-help": "cli.js"
+  },
+  "main": "src/main.mjs",
+  "files": [
+    "cli.js",
+    "src/"
+  ],
+  "scripts": {
+    "start": "node src/main.mjs"
+  },
+  "keywords": [
+    "tiktok",
+    "scraper",
+    "cli",
+    "seller",
+    "ttSeller"
+  ],
+  "author": "",
+  "license": "ISC",
+  "engines": {
+    "node": ">=18"
+  },
+  "publishConfig": {
+    "access": "public"
+  },
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/yourname/tt-help.git"
+  },
+  "bugs": {
+    "url": "https://github.com/yourname/tt-help/issues"
+  },
+  "homepage": "https://github.com/yourname/tt-help#readme",
+  "dependencies": {
+    "playwright": "^1.59.1",
+    "undici": "^8.1.0"
+  }
+}

package/src/lib/args.js

@@ -0,0 +1,59 @@
+import { readFileSync } from 'fs';
+import { proxy } from './constants.js';
+
+export function parseArgs() {
+  const args = process.argv.slice(2);
+  const urls = [];
+  let inputFile = null;
+  let outputFile = null;
+  let outputFormat = 'json';
+  let exploreCount = 0;
+  let showConfig = false;
+  let showHelp = false;
+  let customProxy = null;
+  let configAction = null;
+  let configValue = null;
+  let pipeMode = false;
+
+  for (let i = 0; i < args.length; i++) {
+    const arg = args[i];
+
+    if (arg === '--explore') {
+      exploreCount = args[i + 1] && !args[i + 1].startsWith('http')
+        ? parseInt(args[++i], 10)
+        : 100;
+    } else if (arg === '--proxy') {
+      customProxy = args[++i];
+    } else if (arg === 'config') {
+      configAction = args[i + 1];
+      if (configAction === 'set' || configAction === 'set-proxy') {
+        configValue = args[i + 2];
+        i += 2;
+      } else {
+        i++;
+      }
+    } else if (arg === '--pipe') {
+      pipeMode = true;
+    } else if (arg === '-i' || arg === '--input') {
+      inputFile = args[++i];
+    } else if (arg === '-o' || arg === '--output') {
+      outputFile = args[++i];
+    } else if (arg === '-f' || arg === '--format') {
+      outputFormat = args[++i];
+    } else if (arg === '-c' || arg === '--config') {
+      showConfig = true;
+    } else if (arg === '-h' || arg === '--help') {
+      showHelp = true;
+    } else if (arg.startsWith('http')) {
+      urls.push(arg);
+    }
+  }
+
+  if (inputFile) {
+    const content = readFileSync(inputFile, 'utf-8');
+    const lines = content.split(/\r?\n/).map(l => l.trim()).filter(l => l.startsWith('http'));
+    urls.push(...lines);
+  }
+
+  return { urls, outputFile, outputFormat, exploreCount, showConfig, showHelp, customProxy, configAction, configValue, pipeMode };
+}

package/src/lib/constants.js

@@ -0,0 +1,76 @@
+import { join, dirname } from 'path';
+import { readFileSync, writeFileSync, existsSync } from 'fs';
+import { fileURLToPath } from 'url';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+const homeDir = process.env.HOME || process.env.USERPROFILE || '';
+const configPath = join(homeDir, '.tt-help.json');
+
+const DEFAULT_PROXY = 'http://127.0.0.1:7897';
+const DEFAULT_OUTPUT = 'tiktok_data.json';
+const USER_SECTION_SIZE = 12000;
+
+let proxy = DEFAULT_PROXY;
+let configFile = null;
+
+try {
+  if (existsSync(configPath)) {
+    const cfg = JSON.parse(readFileSync(configPath, 'utf-8'));
+    if (cfg.proxy) {
+      proxy = cfg.proxy;
+      configFile = configPath;
+    }
+  }
+} catch {
+  // no config file
+}
+
+const HELP_TEXT = [
+  '用法: tt-help [选项]',
+  '',
+  '参数:',
+  '  --explore [count]      从 Explore 页面获取视频列表（默认: 100）',
+  '  --pipe                 将 Explore 结果自动传给 URL 爬取',
+  '  --proxy <地址>          临时指定代理地址',
+  '  -i, --input <file>     从文件读取 URL 列表（每行一个）',
+  '  -o, --output <file>    指定输出文件（默认: tiktok_data.json）',
+  '  -f, --format <fmt>     输出格式: json（默认）, table, raw',
+  '  -c, --config           显示当前配置',
+  '  -h, --help             显示帮助',
+  '',
+  '配置代理:',
+  '  tt-help config set http://127.0.0.1:7890  设置代理',
+  '  tt-help config show                        查看配置',
+  '  tt-help config reset                       恢复默认',
+  '',
+  '示例:',
+  '  tt-help --explore 200                    # 先预览 Explore 结果',
+  '  tt-help --explore 50 --pipe -o result.json  # 自动抓取用户数据',
+  '  tt-help --explore -f raw                 # 仅输出 URL 列表',
+  '  tt-help --explore -f raw -o urls.txt     # 保存 URL 到文件',
+  '  tt-help -i urls.txt -o result.json       # 再爬取这些 URL',
+  '  tt-help config set http://127.0.0.1:7890',
+  '  tt-help https://www.tiktok.com/@username',
+];
+
+const CONFIG_TEXT = [
+  'tt-help v1.0.1',
+  '',
+  '配置:',
+  `  代理: ${proxy}`,
+  `  输出格式: json`,
+  `  默认输出: ${DEFAULT_OUTPUT}`,
+  `  配置文件: ${configFile || '无（使用默认值）'}`,
+];
+
+export {
+  proxy,
+  configFile,
+  configPath,
+  DEFAULT_PROXY,
+  DEFAULT_OUTPUT,
+  USER_SECTION_SIZE,
+  HELP_TEXT,
+  CONFIG_TEXT,
+};

package/src/lib/explore.js

@@ -0,0 +1,124 @@
+import { chromium } from 'playwright';
+
+const EXPLORE_URL = 'https://www.tiktok.com/explore';
+
+function sleep(ms) {
+  return new Promise(r => setTimeout(r, ms));
+}
+
+export async function fetchExplore(count = 100) {
+  const browser = await chromium.launch({
+    headless: true,
+    args: [
+      '--no-sandbox',
+      '--disable-setuid-sandbox',
+      '--disable-blink-features=AutomationControlled',
+      '--disable-dev-shm-usage',
+    ],
+  });
+  try {
+    const context = await browser.newContext({
+      viewport: { width: 1280, height: 900 },
+      userAgent: 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
+      locale: 'en-US',
+    });
+
+    // 注入反检测脚本
+    await context.addInitScript(() => {
+      // 重写 navigator.webdriver
+      Object.defineProperty(navigator, 'webdriver', { get: () => false });
+
+      // 伪造 window.chrome
+      if (!window.chrome) {
+        window.chrome = { runtime: {} };
+      }
+
+      // 覆写 permissions query
+      const originalQuery = window.navigator.permissions.query;
+      window.navigator.permissions.query = (params) =>
+        params.name === 'notifications'
+          ? Promise.resolve({ state: Notification.permission })
+          : originalQuery(params);
+
+      // 覆写 languages
+      Object.defineProperty(navigator, 'languages', {
+        get: () => ['en-US', 'en'],
+      });
+
+      // 覆写 plugins
+      Object.defineProperty(navigator, 'plugins', {
+        get: () => [1, 2, 3, 4, 5],
+      });
+    });
+
+    const page = await context.newPage();
+    await page.goto(EXPLORE_URL, { waitUntil: 'domcontentloaded', timeout: 30000 });
+    console.log(`  [1/6] 页面已加载`);
+
+    await sleep(5000);
+
+    let lastCount = 0;
+    let noNewCount = 0;
+
+    for (let i = 0; i < 50; i++) {
+      await page.evaluate(() => {
+        window.scrollBy({ top: window.innerHeight * 0.8, behavior: 'smooth' });
+      });
+
+      await sleep(1500 + Math.random() * 1000);
+
+      const urls = await page.$$eval('a', els =>
+        els.map(a => a.href).filter(u => /\/video\/\d{16,20}/.test(u))
+      );
+      const uniqueCount = [...new Set(urls)].length;
+
+      if (uniqueCount > lastCount) {
+        noNewCount = 0;
+      } else {
+        noNewCount++;
+      }
+      lastCount = uniqueCount;
+
+      if ((i + 1) % 10 === 0) {
+        console.log(`  [2/6] 滚动 ${i + 1}/50，当前 ${uniqueCount} 个视频`);
+      }
+
+      if (noNewCount >= 5) {
+        console.log(`  [3/6] 内容加载完成（${uniqueCount} 个视频）`);
+        break;
+      }
+
+      if (uniqueCount >= count * 2) {
+        console.log(`  [3/6] 视频数量已充足（${uniqueCount} 个）`);
+        break;
+      }
+    }
+
+    await sleep(3000);
+
+    const urls = await page.$$eval('a', els =>
+      els.map(a => a.href).filter(u => /\/video\/\d{16,20}/.test(u))
+    );
+    const unique = [...new Set(urls)];
+    console.log(`  [4/6] 共检测到 ${unique.length} 个不重复视频`);
+
+    const results = [];
+    const seen = new Set();
+    for (const url of unique) {
+      if (results.length >= count) break;
+      const videoId = url.match(/video\/(\d{16,20})$/)?.[1];
+      if (videoId && !seen.has(videoId)) {
+        seen.add(videoId);
+        const user = url.match(/\/@([^\/]+)/)?.[1];
+        if (user) {
+          results.push({ user, id: videoId, url });
+        }
+      }
+    }
+
+    console.log(`  [5/6] 去重后 ${results.length} 个`);
+    return results;
+  } finally {
+    await browser.close();
+  }
+}

package/src/lib/fetcher.js

@@ -0,0 +1,36 @@
+import { fetch, ProxyAgent } from 'undici';
+import { DEFAULT_PROXY } from './constants.js';
+
+const HEADERS = {
+  'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
+  'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+};
+
+export async function fetchHtml(url, proxyUrl) {
+  const p = proxyUrl || DEFAULT_PROXY;
+  const agent = new ProxyAgent(p);
+  try {
+    const res = await fetch(url, { headers: HEADERS, dispatcher: agent });
+    return res.text();
+  } catch (err) {
+    throw new Error(`请求 ${url} 失败，代理 ${p} 不可用`);
+  }
+}
+
+export function makeProfileUrl(handle) {
+  if (handle.startsWith('http')) return handle;
+  return `https://www.tiktok.com/${handle}`;
+}
+
+export function isProfileUrl(url) {
+  return /\/@[\w-]+(?:$|[?#])/.test(url);
+}
+
+export function isVideoUrl(url) {
+  return /\/video\/\d+/.test(url);
+}
+
+export function extractProfileHandle(url) {
+  const m = url.match(/https:\/\/www\.tiktok\.com\/(@[\w-]+)/);
+  return m ? m[1] : null;
+}

package/src/lib/io.js

@@ -0,0 +1,13 @@
+import { writeFileSync, readFileSync } from 'fs';
+
+export function writeOutput(data, outputFile) {
+  const output = JSON.stringify(data, null, 2);
+  const target = outputFile || 'tiktok_data.json';
+  writeFileSync(target, output, 'utf-8');
+  console.log(`结果已写入: ${target}`);
+}
+
+export function readUrlFile(filePath) {
+  const content = readFileSync(filePath, 'utf-8');
+  return content.split(/\r?\n/).map(l => l.trim()).filter(l => l.startsWith('http'));
+}

package/src/lib/output.js

@@ -0,0 +1,80 @@
+export function deduplicate(results) {
+  const seen = new Set();
+  return results.filter(r => {
+    if (r.id) {
+      const key = r.id;
+      if (seen.has(key)) return false;
+      seen.add(key);
+      return true;
+    }
+    const key = r.secUid || r.uniqueId;
+    if (seen.has(key)) return false;
+    seen.add(key);
+    return true;
+  });
+}
+
+export function formatTable(data) {
+  if (data.length === 0) return '';
+
+  if (data.length === 1) {
+    const lines = [];
+    for (const [key, val] of Object.entries(data[0])) {
+      if (typeof val === 'string' && val.length > 80) {
+        lines.push(`  ${key}: ${val.substring(0, 80)}...`);
+      } else {
+        lines.push(`  ${key}: ${val}`);
+      }
+    }
+    return lines.join('\n');
+  }
+
+  const cols = [
+    { key: 'uniqueId', label: '用户名', width: 20 },
+    { key: 'locationCreated', label: '地区', width: 6 },
+    { key: 'nickname', label: '昵称', width: 20 },
+    { key: 'ttSeller', label: 'TT卖家', width: 8 },
+    { key: 'verified', label: '已认证', width: 8 },
+    { key: 'followerCount', label: '粉丝', width: 10 },
+    { key: 'videoCount', label: '视频', width: 8 },
+  ];
+
+  for (const row of data) {
+    for (const col of cols) {
+      const val = String(row[col.key] ?? '-');
+      col.width = Math.max(col.width, val.length, col.label.length);
+    }
+  }
+
+  const sep = (w) => '-'.repeat(w);
+  const pad = (s, w) => s.padEnd(w);
+
+  const header = cols.map(c => pad(c.label, c.width)).join(' │ ');
+  const divider = cols.map(c => sep(c.width)).join('-+-');
+  const rows = data.map(r =>
+    cols.map(c => pad(String(r[c.key] ?? '-'), c.width)).join(' │ ')
+  );
+
+  return [header, divider, ...rows].join('\n');
+}
+
+export function formatOutput(data, format) {
+  if (format === 'table') return formatTable(data);
+
+  if (format === 'raw') {
+    if (Array.isArray(data) && data.length > 0 && 'url' in data[0]) {
+      return data.map(d => d.url).join('\n');
+    }
+    if (Array.isArray(data) && data.length > 0 && 'uniqueId' in data[0]) {
+      return data.map(d => `https://www.tiktok.com/@${d.uniqueId}`).join('\n');
+    }
+    return JSON.stringify(data, null, 2);
+  }
+
+  // Default JSON output, but for explore results (url-only) output pure text
+  if (Array.isArray(data) && data.length > 0 && 'url' in data[0]) {
+    return data.map(d => d.url).join('\n');
+  }
+
+  return JSON.stringify(data, null, 2);
+}

package/src/lib/parser.js

@@ -0,0 +1,47 @@
+import { USER_SECTION_SIZE } from './constants.js';
+
+export function extractUserSection(html) {
+  const idx = html.indexOf('"uniqueId"');
+  if (idx < 0) return null;
+  return html.substring(idx, idx + USER_SECTION_SIZE);
+}
+
+export function parseUserSection(section) {
+  const data = {};
+
+  for (const key of ['uniqueId', 'uid', 'secUid']) {
+    const m = section.match(new RegExp(`"${key}":"([^"]*)`));
+    if (m) data[key] = m[1];
+  }
+
+  for (const key of ['nickname', 'signature']) {
+    const m = section.match(new RegExp(`"${key}":"((?:[^"\\\\]|\\\\.)*)"`, 'g'));
+    if (m) {
+      const raw = m[0].replace(`"${key}":"`, '').replace(/"$/, '');
+      data[key] = raw.replace(/\\n/g, '\n').replace(/\\\\/g, '\\');
+    }
+  }
+
+  for (const key of ['ttSeller', 'verified']) {
+    const m = section.match(new RegExp(`"${key}":\\s*(true|false)`));
+    data[key] = m ? m[1] === 'true' : undefined;
+  }
+
+  for (const key of ['followerCount', 'followingCount', 'heartCount', 'videoCount', 'diggCount']) {
+    const m = section.match(new RegExp(`"${key}":(\\d+)`));
+    if (m) data[key] = parseInt(m[1], 10);
+  }
+
+  const mt = section.match(/"createTime":(\d+)/);
+  if (mt) data.createTime = parseInt(mt[1], 10);
+
+  const ma = section.match(/"avatarLarger":"([^"]*)/);
+  if (ma) data.avatarLarger = ma[1].replace(/\\u002F/g, '/');
+
+  return data;
+}
+
+export function extractLocationCreated(html) {
+  const m = html.match(/"locationCreated":"([^"]*)/);
+  return m ? m[1] : null;
+}

package/src/lib/scrape.js

@@ -0,0 +1,39 @@
+import { extractUserSection, parseUserSection, extractLocationCreated } from './parser.js';
+import { fetchHtml, makeProfileUrl, isProfileUrl, isVideoUrl, extractProfileHandle } from './fetcher.js';
+
+export async function extractUserData(profileUrl, proxyUrl) {
+  const profileHtml = await fetchHtml(profileUrl, proxyUrl);
+  const section = extractUserSection(profileHtml);
+  if (!section) throw new Error('无法解析用户信息');
+  const data = parseUserSection(section);
+  data.locationCreated = extractLocationCreated(profileHtml);
+  return data;
+}
+
+export async function extractVideoLocation(videoUrl, proxyUrl) {
+  const videoHtml = await fetchHtml(videoUrl, proxyUrl);
+  return extractLocationCreated(videoHtml);
+}
+
+export async function processUrl(url, proxyUrl) {
+  if (isProfileUrl(url)) {
+    const profileUrl = makeProfileUrl(url);
+    const profileData = await extractUserData(profileUrl, proxyUrl);
+    return [profileData];
+  }
+
+  if (isVideoUrl(url)) {
+    const profileHandle = extractProfileHandle(url);
+    if (!profileHandle) throw new Error(`无法从视频URL提取用户主页: ${url}`);
+
+    const profileUrl = makeProfileUrl(profileHandle);
+    const [profileData, locationCreated] = await Promise.all([
+      extractUserData(profileUrl, proxyUrl),
+      extractVideoLocation(url, proxyUrl),
+    ]);
+
+    return [{ ...profileData, locationCreated }];
+  }
+
+  return [];
+}

package/src/main.mjs

@@ -0,0 +1,245 @@
+import { parseArgs } from './lib/args.js';
+import { HELP_TEXT, CONFIG_TEXT, proxy, configFile, configPath, DEFAULT_PROXY } from './lib/constants.js';
+import { fetchExplore } from './lib/explore.js';
+import { processUrl } from './lib/scrape.js';
+import { deduplicate, formatOutput } from './lib/output.js';
+import { writeFileSync, readFileSync, existsSync } from 'fs';
+
+function showConfig(urls, outputFile) {
+  const lines = [...CONFIG_TEXT];
+  if (outputFile) lines.push(`  输出文件: ${outputFile}`);
+  if (urls.length > 0) lines.push(`  待处理URL: ${urls.length}`);
+  lines.push('', '参数:', '  -c, --config   显示当前配置', '  -h, --help     显示帮助');
+  console.log(lines.join('\n'));
+}
+
+function showUsage() {
+  console.log(HELP_TEXT.join('\n'));
+  process.exit(0);
+}
+
+function handleConfig(action, value) {
+  if (action === 'show' || action === null) {
+    showConfig([], null);
+    return;
+  }
+  if (action === 'set' || action === 'set-proxy') {
+    if (!value) {
+      console.error('用法: tt-help config set <代理地址>');
+      process.exit(1);
+    }
+    const cfg = { proxy: value };
+    writeFileSync(configPath, JSON.stringify(cfg, null, 2), 'utf-8');
+    console.log(`代理已设置为: ${value}`);
+    console.log(`配置文件: ${configPath}`);
+    return;
+  }
+  if (action === 'reset') {
+    if (existsSync(configPath)) {
+      readFileSync(configPath, 'utf-8');
+      writeFileSync(configPath, JSON.stringify({ proxy: DEFAULT_PROXY }, null, 2), 'utf-8');
+      console.log(`已恢复默认代理: ${DEFAULT_PROXY}`);
+      console.log(`配置文件: ${configPath}`);
+    } else {
+      console.log('当前使用默认代理，无需重置');
+    }
+    return;
+  }
+  console.error(`未知配置命令: ${action}`);
+  console.error('用法: tt-help config [show|set|reset]');
+  process.exit(1);
+}
+
+function cleanError(msg) {
+  return msg
+    .replace(/\x1b\[[0-9;]*m/g, '')
+    .replace(/\s*- navigating to.*/s, '')
+    .replace(/\s*Call log:/s, '')
+    .trim();
+}
+
+async function runExplore(exploreCount, urls, proxyUrl, outputFile, outputFormat, isPipe) {
+  console.log(`\n代理: ${proxyUrl}`);
+  console.log(`Explore 数量: ${exploreCount}`);
+  if (urls.length > 0) {
+    console.log(`额外 URL: ${urls.length}\n`);
+  } else {
+    console.log('');
+  }
+
+  const allResults = [];
+
+  if (exploreCount > 0) {
+    try {
+      const exploreResults = await fetchExplore(exploreCount);
+      console.log(`  获取到 ${exploreResults.length} 个视频\n`);
+      if (isPipe) {
+        const videoUrls = exploreResults.map(r => r.url).filter(Boolean);
+        if (videoUrls.length > 0) {
+          await runScrape(videoUrls, proxyUrl, outputFile, outputFormat);
+          return;
+        }
+      }
+      allResults.push(...exploreResults);
+    } catch (err) {
+      console.error(`  Explore 获取失败: ${cleanError(err.message)}\n`);
+      console.error(`  请确保代理 ${proxyUrl} 正常运行\n`);
+    }
+  }
+
+  if (urls.length > 0) {
+    const errors = [];
+
+    for (let i = 0; i < urls.length; i++) {
+      const bar = '█'.repeat(i + 1).padEnd(urls.length);
+      process.stdout.write(`\r  [${bar}] ${i + 1}/${urls.length}`);
+      try {
+        const results = await processUrl(urls[i], proxyUrl);
+        allResults.push(...results);
+      } catch (err) {
+        errors.push({ url: urls[i], message: err.message });
+      }
+    }
+    console.log();
+
+    if (errors.length > 0) {
+      const msg = errors[0].message;
+      if (msg.includes('不可用') || msg.includes('连接被拒绝') || msg.includes('连接中断') ||
+          msg.includes('超时') || msg.includes('无法解析')) {
+        console.error(`  ${errors.length} 个请求失败，请检查代理是否可用: ${proxyUrl}\n`);
+      } else {
+        console.error(`  ${errors.length} 个失败:`);
+        const show = errors.slice(0, 5);
+        for (const e of show) {
+          console.error(`    ✗ ${e.url}: ${e.message}`);
+        }
+        if (errors.length > 5) {
+          console.error(`    ... 还有 ${errors.length - 5} 个`);
+        }
+      }
+    }
+  }
+
+  const uniqueResults = deduplicate(allResults);
+
+  if (uniqueResults.length === 0) {
+    console.log('\n未获取到数据');
+    if (outputFile) {
+      writeFileSync(outputFile, '[]', 'utf-8');
+    }
+    return;
+  }
+
+  const output = formatOutput(uniqueResults, outputFormat);
+
+  if (outputFile) {
+    writeFileSync(outputFile, output, 'utf-8');
+    console.log(`\n结果已写入: ${outputFile}`);
+  } else {
+    console.log(output);
+  }
+  console.log(`\n共 ${uniqueResults.length} 个数据`);
+}
+
+async function runScrape(urls, proxyUrl, outputFile, outputFormat) {
+  const allResults = [];
+  const errors = [];
+
+  for (let i = 0; i < urls.length; i++) {
+    const bar = '█'.repeat(i + 1).padEnd(urls.length);
+    process.stdout.write(`\r  [${bar}] ${i + 1}/${urls.length}`);
+    try {
+      const results = await processUrl(urls[i], proxyUrl);
+      allResults.push(...results);
+    } catch (err) {
+      errors.push({ url: urls[i], message: err.message });
+    }
+  }
+  console.log();
+
+  const uniqueResults = deduplicate(allResults);
+
+  if (errors.length > 0) {
+    if (uniqueResults.length === 0) {
+      const msg = errors[0].message;
+      if (msg.includes('不可用') || msg.includes('连接被拒绝') || msg.includes('连接中断') ||
+          msg.includes('超时') || msg.includes('无法解析')) {
+        console.error(`  所有请求失败，请检查代理是否可用: ${proxyUrl}\n`);
+      } else {
+        const show = errors.slice(0, 5);
+        for (const e of show) {
+          console.error(`  ✗ ${e.url}: ${e.message}\n`);
+        }
+        if (errors.length > 5) {
+          console.error(`  ... 还有 ${errors.length - 5} 个失败\n`);
+        }
+      }
+      console.log('未获取到数据');
+      if (outputFile) {
+        writeFileSync(outputFile, '[]', 'utf-8');
+      }
+      return;
+    } else {
+      const msg = errors[0].message;
+      if (msg.includes('不可用') || msg.includes('连接被拒绝') || msg.includes('连接中断') ||
+          msg.includes('超时') || msg.includes('无法解析')) {
+        console.error(`  ${errors.length} 个请求失败，请检查代理是否可用: ${proxyUrl}\n`);
+      } else {
+        console.error(`  ${errors.length} 个失败:`);
+        const show = errors.slice(0, 5);
+        for (const e of show) {
+          console.error(`    ✗ ${e.url}: ${e.message}`);
+        }
+        if (errors.length > 5) {
+          console.error(`    ... 还有 ${errors.length - 5} 个`);
+        }
+      }
+    }
+  }
+
+  const output = formatOutput(uniqueResults, outputFormat);
+
+  if (outputFile) {
+    writeFileSync(outputFile, output, 'utf-8');
+    console.log(`\n结果已写入: ${outputFile}`);
+  } else {
+    console.log(output);
+  }
+  console.log(`\n共 ${uniqueResults.length} 个用户的数据`);
+}
+
+async function main() {
+  const { urls, outputFile, outputFormat, exploreCount, showConfig: showCfg, showHelp, customProxy, configAction, configValue, pipeMode } = parseArgs();
+  const proxyUrl = customProxy || proxy;
+
+  if (showHelp) {
+    showUsage();
+    return;
+  }
+
+  if (configAction) {
+    handleConfig(configAction, configValue);
+    return;
+  }
+
+  if (showCfg) {
+    showConfig(urls, outputFile);
+    return;
+  }
+
+  if (urls.length === 0 && exploreCount === 0) {
+    showUsage();
+    return;
+  }
+
+  if (exploreCount > 0) {
+    await runExplore(exploreCount, urls, proxyUrl, outputFile, outputFormat, pipeMode);
+  } else {
+    await runScrape(urls, proxyUrl, outputFile, outputFormat);
+  }
+}
+
+main().catch(err => {
+  console.error(`错误: ${err.message}`);
+  process.exit(1);
+});