tt-help-cli-ycl 1.3.6 → 1.3.8

package/src/test-follow.cjs

@@ -0,0 +1,41 @@
+const path = require('path');
+const { ensureBrowserReady, ensureTikTokPage, delay } = require('./scraper/modules/page-helpers.cjs');
+const { extractFollowAndFollowers } = require('./scraper/modules/follow-extractor.cjs');
+
+async function main() {
+  const url = process.argv[2] || 'https://www.tiktok.com/@qiqi23280';
+  console.error(`目标: ${url}`);
+
+  const browser = await ensureBrowserReady();
+  try {
+    const page = await ensureTikTokPage(browser, url);
+    await page.goto(url, { waitUntil: 'load', timeout: 30000 });
+    console.error('等待页面加载...');
+    await delay(3000, 5000);
+
+    console.error('开始提取关注和粉丝...\n');
+    const result = await extractFollowAndFollowers(page, {
+      log: console.error,
+    });
+
+    console.error('\n--- 提取完成 ---');
+    console.error(`关注: ${result.following.length} 人`);
+    console.error(`粉丝: ${result.followers.length} 人`);
+
+    const outDir = path.join(__dirname, '..', 'results');
+    const fs = require('fs');
+    fs.mkdirSync(outDir, { recursive: true });
+    const outPath = path.join(outDir, 'follow-result.json');
+    fs.writeFileSync(outPath, JSON.stringify(result, null, 2));
+    console.error(`已保存到 ${outPath}`);
+
+    console.log(JSON.stringify(result, null, 2));
+  } finally {
+    await browser.close().catch(() => {});
+  }
+}
+
+main().catch(err => {
+  console.error('错误:', err.message);
+  process.exit(1);
+});

package/src/videos/core.mjs

@@ -1,126 +1,126 @@
-import { delay, ensureBrowserReady, ensureTikTokPage, retryWithBackoff } from '../scraper/modules/page-helpers.mjs';
-import { scrollAndCollect } from '../scraper/modules/scroll-collector.mjs';
-
-async function getUserInfo(page) {
-  return await page.evaluate(() => {
-    const html = document.documentElement.outerHTML;
-    const result = {};
-
-    const m = window.location.href.match(/\/@([^/]+)/);
-    if (m) result.uniqueId = m[1];
-
-    const patterns = {
-      secUid: /"secUid":"([^"]+)"/,
-      nickname: /"nickname":"((?:[^"\\]|\\.)*)"/,
-      ttSeller: /"ttSeller":\s*(true|false)/,
-      verified: /"verified":\s*(true|false)/,
-      followerCount: /"followerCount":(\d+)/,
-      videoCount: /"videoCount":(\d+)/,
-      followingCount: /"followingCount":(\d+)/,
-      heartCount: /"heartCount":(\d+)/,
-      signature: /"signature":"((?:[^"\\]|\\.)*)"/,
-      locationCreated: /"locationCreated":"([^"]*)/,
-      region: /"region":"([^"]*)/,
-    };
-
-    const boolKeys = ['ttSeller', 'verified'];
-    const numKeys = ['followerCount', 'videoCount', 'followingCount', 'heartCount'];
-
-    for (const [key, pat] of Object.entries(patterns)) {
-      const match = html.match(pat);
-      if (match) {
-        if (boolKeys.includes(key)) result[key] = match[1] === 'true';
-        else if (numKeys.includes(key)) result[key] = parseInt(match[1], 10);
-        else if (key === 'signature') result[key] = match[1].replace(/\\n/g, '\n').replace(/\\\\/g, '\\');
-        else result[key] = match[1];
-      }
-    }
-
-    return result;
-  });
-}
-
-async function collectVideos(page, username, maxVideos, log) {
-  const allLinks = await scrollAndCollect(page, {
-    container: '[class*="ColumnListContainer"]',
-    extraArgs: { handle: username },
-    collectFn: (container, args) => {
-      const pattern = '/@' + args.handle + '/video/';
-      return {
-        items: Array.from(document.querySelectorAll('a'))
-          .filter(el => (el.getAttribute('href') || '').includes(pattern))
-          .map(el => {
-            const href = el.getAttribute('href') || '';
-            const idMatch = href.match(/\/video\/(\d+)/);
-            return { id: idMatch ? idMatch[1] : null, href };
-          })
-          .filter(v => v.id),
-      };
-    },
-    maxItems: maxVideos,
-    delayRange: [2000, 3000],
-    staleThreshold: 5,
-    maxRounds: 500,
-    onRound: (round, items, allItems) => {
-      const uniqueCount = new Set(allItems.map(v => v.id)).size;
-      if (uniqueCount > 0 && (uniqueCount % 10 === 0 || items.length > 0)) {
-        log(`滚动 ${round + 1}: ${uniqueCount} 个视频 (本轮 ${items.length} 条)`);
-      }
-    },
-  });
-
-  const uniqueVideos = new Map();
-  allLinks.forEach(v => {
-    if (!uniqueVideos.has(v.id)) uniqueVideos.set(v.id, v);
-  });
-
-  log(`收集完成: ${uniqueVideos.size} 个视频`);
-  return uniqueVideos;
-}
-
-async function runGetUserVideos(options) {
-  const { username, maxVideos = 5, log = console.error } = options;
-  const url = `https://www.tiktok.com/@${username}`;
-
-  log(`用户: @${username}`);
-  log(`URL: ${url}`);
-  log(`最大视频数: ${maxVideos}\n`);
-
-  log('连接浏览器...');
-  const browser = await ensureBrowserReady();
-
-  let page;
-  try {
-    page = await ensureTikTokPage(browser, url);
-  } catch (e) {
-    await browser.close().catch(() => {});
-    throw e;
-  }
-
-  await retryWithBackoff(() => page.goto(url, { waitUntil: 'load', timeout: 30000 }), { log });
-  await delay(3000, 5000);
-  await page.waitForSelector('[class*="DivVideoList"]', { timeout: 10000 }).catch(() => {});
-
-  log('获取用户信息...');
-  const userInfo = await getUserInfo(page);
-  log('用户信息: ' + JSON.stringify(userInfo, null, 2));
-
-  log('\n开始滚动收集视频...');
-  const videos = await collectVideos(page, username, maxVideos, log);
-  const allVideos = Array.from(videos.values());
-
-  log(`\n总计: ${allVideos.length} 个视频`);
-
-  const output = {
-    user: userInfo,
-    totalVideos: Math.min(allVideos.length, maxVideos),
-    videos: allVideos.slice(0, maxVideos).map(v => ({
-      id: v.id,
-      url: v.href.startsWith('http') ? v.href : `https://www.tiktok.com${v.href}`,
-    })),
-  };
-
-  return { output, browser };
-}
-
-export { getUserInfo, collectVideos, runGetUserVideos };
+import { delay, ensureBrowserReady, ensureTikTokPage, retryWithBackoff } from '../scraper/modules/page-helpers.mjs';
+import { scrollAndCollect } from '../scraper/modules/scroll-collector.mjs';
+
+async function getUserInfo(page) {
+  return await page.evaluate(() => {
+    const html = document.documentElement.outerHTML;
+    const result = {};
+
+    const m = window.location.href.match(/\/@([^/]+)/);
+    if (m) result.uniqueId = m[1];
+
+    const patterns = {
+      secUid: /"secUid":"([^"]+)"/,
+      nickname: /"nickname":"((?:[^"\\]|\\.)*)"/,
+      ttSeller: /"ttSeller":\s*(true|false)/,
+      verified: /"verified":\s*(true|false)/,
+      followerCount: /"followerCount":(\d+)/,
+      videoCount: /"videoCount":(\d+)/,
+      followingCount: /"followingCount":(\d+)/,
+      heartCount: /"heartCount":(\d+)/,
+      signature: /"signature":"((?:[^"\\]|\\.)*)"/,
+      locationCreated: /"locationCreated":"([^"]*)/,
+      region: /"region":"([^"]*)/,
+    };
+
+    const boolKeys = ['ttSeller', 'verified'];
+    const numKeys = ['followerCount', 'videoCount', 'followingCount', 'heartCount'];
+
+    for (const [key, pat] of Object.entries(patterns)) {
+      const match = html.match(pat);
+      if (match) {
+        if (boolKeys.includes(key)) result[key] = match[1] === 'true';
+        else if (numKeys.includes(key)) result[key] = parseInt(match[1], 10);
+        else if (key === 'signature') result[key] = match[1].replace(/\\n/g, '\n').replace(/\\\\/g, '\\');
+        else result[key] = match[1];
+      }
+    }
+
+    return result;
+  });
+}
+
+async function collectVideos(page, username, maxVideos, log) {
+  const allLinks = await scrollAndCollect(page, {
+    container: '[class*="ColumnListContainer"]',
+    extraArgs: { handle: username },
+    collectFn: (container, args) => {
+      const pattern = '/@' + args.handle + '/video/';
+      return {
+        items: Array.from(document.querySelectorAll('a'))
+          .filter(el => (el.getAttribute('href') || '').includes(pattern))
+          .map(el => {
+            const href = el.getAttribute('href') || '';
+            const idMatch = href.match(/\/video\/(\d+)/);
+            return { id: idMatch ? idMatch[1] : null, href };
+          })
+          .filter(v => v.id),
+      };
+    },
+    maxItems: maxVideos,
+    delayRange: [2000, 3000],
+    staleThreshold: 5,
+    maxRounds: 500,
+    onRound: (round, items, allItems) => {
+      const uniqueCount = new Set(allItems.map(v => v.id)).size;
+      if (uniqueCount > 0 && (uniqueCount % 10 === 0 || items.length > 0)) {
+        log(`滚动 ${round + 1}: ${uniqueCount} 个视频 (本轮 ${items.length} 条)`);
+      }
+    },
+  });
+
+  const uniqueVideos = new Map();
+  allLinks.forEach(v => {
+    if (!uniqueVideos.has(v.id)) uniqueVideos.set(v.id, v);
+  });
+
+  log(`收集完成: ${uniqueVideos.size} 个视频`);
+  return uniqueVideos;
+}
+
+async function runGetUserVideos(options) {
+  const { username, maxVideos = 5, log = console.error } = options;
+  const url = `https://www.tiktok.com/@${username}`;
+
+  log(`用户: @${username}`);
+  log(`URL: ${url}`);
+  log(`最大视频数: ${maxVideos}\n`);
+
+  log('连接浏览器...');
+  const browser = await ensureBrowserReady();
+
+  let page;
+  try {
+    page = await ensureTikTokPage(browser, url);
+  } catch (e) {
+    await browser.close().catch(() => {});
+    throw e;
+  }
+
+  await retryWithBackoff(() => page.goto(url, { waitUntil: 'load', timeout: 30000 }), { log });
+  await delay(3000, 5000);
+  await page.waitForSelector('[class*="DivVideoList"]', { timeout: 10000 }).catch(() => {});
+
+  log('获取用户信息...');
+  const userInfo = await getUserInfo(page);
+  log('用户信息: ' + JSON.stringify(userInfo, null, 2));
+
+  log('\n开始滚动收集视频...');
+  const videos = await collectVideos(page, username, maxVideos, log);
+  const allVideos = Array.from(videos.values());
+
+  log(`\n总计: ${allVideos.length} 个视频`);
+
+  const output = {
+    user: userInfo,
+    totalVideos: Math.min(allVideos.length, maxVideos),
+    videos: allVideos.slice(0, maxVideos).map(v => ({
+      id: v.id,
+      url: v.href.startsWith('http') ? v.href : `https://www.tiktok.com${v.href}`,
+    })),
+  };
+
+  return { output, browser };
+}
+
+export { getUserInfo, collectVideos, runGetUserVideos };