tt-help-cli-ycl 1.0.7 → 1.0.8

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "tt-help-cli-ycl",
-  "version": "1.0.7",
+  "version": "1.0.8",
   "description": "TikTok user & video data scraper - extract ttSeller, verified, locationCreated from HTML source",
   "type": "module",
   "bin": {

package/src/auto-core.cjs

@@ -38,6 +38,7 @@ async function runAuto(options) {
     collectMax = 1,
     scrapeDepth = 50,
     maxComments = 200,
+    maxGuess = 10,
     preset = null,
     switchMax = null,
     commentMax = null,
@@ -127,6 +128,7 @@ async function runAuto(options) {
       videoUrl,
       maxVideos: scrapeDepth,
       maxComments,
+      maxGuess,
       preset,
       switchMax,
       commentMax,
@@ -151,6 +153,15 @@ async function runAuto(options) {
         users.set(cu, mergeUserInfo({}, { uniqueId: cu }, 'comment'));
       }
     }
+
+    // 添加猜你喜欢作者
+    for (const ga of (scrapeOutput.guessAuthors || [])) {
+      const gaId = ga.replace(/^@/, '');
+      if (restrictedUsers.has(gaId)) continue;
+      if (!users.has(gaId)) {
+        users.set(gaId, mergeUserInfo({}, { uniqueId: gaId }, 'guess'));
+      }
+    }
   }
 
   // 构建输出
@@ -183,6 +194,7 @@ async function processUser(page, username, options, log) {
     collectMax = 1,
     scrapeDepth = 50,
     maxComments = 200,
+    maxGuess = 10,
     preset = 'fast',
     switchMax = null,
     commentMax = null,
@@ -194,6 +206,7 @@ async function processUser(page, username, options, log) {
     collectedVideos: [],
     discoveredVideoAuthors: [],
     discoveredCommentAuthors: [],
+    discoveredGuessAuthors: [],
     error: null,
   };
 
@@ -220,9 +233,10 @@ async function processUser(page, username, options, log) {
       videoUrl: v.href,
     }));
 
-    if (videoList.length > 0) {
+      if (videoList.length > 0) {
       const allVideoAuthors = new Map();
       const allCommentAuthors = new Set();
+      const allGuessAuthors = new Set();
 
       for (let i = 0; i < videoList.length; i++) {
         const video = videoList[i];
@@ -235,6 +249,7 @@ async function processUser(page, username, options, log) {
           videoUrl,
           maxVideos: scrapeDepth,
           maxComments,
+          maxGuess,
           preset,
           switchMax,
           commentMax,
@@ -262,12 +277,19 @@ async function processUser(page, username, options, log) {
             allCommentAuthors.add(cu);
           }
         }
+
+        if (scrapeOutput && scrapeOutput.guessAuthors) {
+          for (const ga of scrapeOutput.guessAuthors) {
+            allGuessAuthors.add(ga);
+          }
+        }
       }
 
       result.discoveredVideoAuthors = [...allVideoAuthors.values()];
       result.discoveredCommentAuthors = [...allCommentAuthors];
+      result.discoveredGuessAuthors = [...allGuessAuthors];
 
-      log(`  发现: ${result.discoveredVideoAuthors.length} 个视频作者, ${result.discoveredCommentAuthors.length} 个评论作者`);
+      log(`  发现: ${result.discoveredVideoAuthors.length} 个视频作者, ${result.discoveredCommentAuthors.length} 个评论作者, ${result.discoveredGuessAuthors.length} 个猜你喜欢作者`);
     } else {
       const restricted = await isPageRestricted(page);
       result.restricted = restricted;

package/src/lib/args.js

@@ -8,6 +8,7 @@ function parseScrapeArgs(args) {
   let scrapePreset = null;
   let scrapeMaxVideos = 20;
   let scrapeMaxComments = 999;
+  let scrapeMaxGuess = 10;
   let scrapeSwitchDelay = null;
   let scrapeCommentDelay = null;
   let outputFile = null;
@@ -34,9 +35,11 @@ function parseScrapeArgs(args) {
       scrapePreset = positional[1].toLowerCase();
       scrapeMaxVideos = parseInt(positional[2]) || 20;
       scrapeMaxComments = parseInt(positional[3]) || 999;
+      scrapeMaxGuess = parseInt(positional[4]) || 10;
     } else {
       scrapeMaxVideos = parseInt(positional[1]) || 20;
       scrapeMaxComments = parseInt(positional[2]) || 999;
+      scrapeMaxGuess = parseInt(positional[3]) || 10;
     }
   }
 
@@ -46,6 +49,7 @@ function parseScrapeArgs(args) {
     scrapePreset,
     scrapeMaxVideos,
     scrapeMaxComments,
+    scrapeMaxGuess,
     scrapeSwitchDelay,
     scrapeCommentDelay,
     outputFile,
@@ -66,6 +70,7 @@ function parseAutoArgs(args) {
   let autoCollectMax = 1;
   let autoScrapeDepth = 50;
   let autoMaxComments = 200;
+  let autoMaxGuess = 10;
   let autoPreset = 'fast';
   let autoSwitchDelay = null;
   let autoCommentDelay = null;
@@ -112,10 +117,12 @@ function parseAutoArgs(args) {
     autoCollectMax = parseInt(positional[j]) || 1; j++;
     autoScrapeDepth = parseInt(positional[j]) || 50; j++;
     autoMaxComments = parseInt(positional[j]) || 200; j++;
+    autoMaxGuess = parseInt(positional[j]) || 10; j++;
   } else if (usernames.length > 0) {
     autoCollectMax = parseInt(positional[j]) || 1; j++;
     autoScrapeDepth = parseInt(positional[j]) || 50; j++;
-    autoMaxComments = parseInt(positional[j]) || 200;
+    autoMaxComments = parseInt(positional[j]) || 200; j++;
+    autoMaxGuess = parseInt(positional[j]) || 10;
   }
 
   return {
@@ -124,6 +131,7 @@ function parseAutoArgs(args) {
     autoCollectMax,
     autoScrapeDepth,
     autoMaxComments,
+    autoMaxGuess,
     autoPreset,
     autoSwitchDelay,
     autoCommentDelay,

package/src/main.mjs

@@ -315,7 +315,7 @@ async function runScrape(urls, proxyUrl, outputFile, outputFormat, filter) {
 }
 
 async function handleScrape(options) {
-  const { scrapeUrl, scrapePreset, scrapeMaxVideos, scrapeMaxComments, scrapeSwitchDelay, scrapeCommentDelay, outputFile } = options;
+  const { scrapeUrl, scrapePreset, scrapeMaxVideos, scrapeMaxComments, scrapeMaxGuess, scrapeSwitchDelay, scrapeCommentDelay, outputFile } = options;
 
   if (!scrapeUrl) {
     console.error('用法: tt-help scrape <视频URL> [preset] [最大视频数] [最大评论数] [-o 输出路径]');
@@ -334,6 +334,7 @@ async function handleScrape(options) {
       videoUrl: scrapeUrl,
       maxVideos: scrapeMaxVideos,
       maxComments: scrapeMaxComments,
+      maxGuess: scrapeMaxGuess,
       preset: scrapePreset,
       switchMax: scrapeSwitchDelay,
       commentMax: scrapeCommentDelay,
@@ -350,7 +351,7 @@ async function handleScrape(options) {
     }
 
     const stats = output.stats;
-    console.error(`\n共 ${stats.totalVideos} 个视频, ${stats.uniqueVideoAuthors} 个视频作者, ${stats.uniqueCommentAuthors} 个评论作者`);
+    console.error(`\n共 ${stats.totalVideos} 个视频, ${stats.uniqueVideoAuthors} 个视频作者, ${stats.uniqueCommentAuthors} 个评论作者, ${stats.uniqueGuessAuthors} 个猜你喜欢作者`);
   } catch (err) {
     console.error(`浏览器抓取失败: ${err.message}`);
     process.exit(1);
@@ -386,12 +387,13 @@ async function handleWatch(options) {
 }
 
 async function handleAuto(options) {
-  const { autoUsernames, autoCollectMax, autoScrapeDepth, autoMaxComments, autoPreset, autoSwitchDelay, autoCommentDelay, outputFile, autoWatch, autoWatchPort } = options;
+  const { autoUsernames, autoCollectMax, autoScrapeDepth, autoMaxComments, autoMaxGuess, autoPreset, autoSwitchDelay, autoCommentDelay, outputFile, autoWatch, autoWatchPort } = options;
 
   const runOptions = {
     collectMax: autoCollectMax,
     scrapeDepth: autoScrapeDepth,
     maxComments: autoMaxComments,
+    maxGuess: autoMaxGuess,
     preset: autoPreset,
     switchMax: autoSwitchDelay,
     commentMax: autoCommentDelay,
@@ -526,6 +528,20 @@ async function handleAuto(options) {
         }
       }
 
+      // 发现的猜你喜欢作者
+      for (const ga of (result.discoveredGuessAuthors || [])) {
+        const gaId = ga.replace(/^@/, '');
+        store.addUser({
+          uniqueId: gaId,
+          sources: ['guess'],
+        });
+        if (!store.getUser(gaId) || !store.getUser(gaId).followerCount) {
+          if (!queue.includes(gaId)) {
+            queue.push(gaId);
+          }
+        }
+      }
+
       processedCount++;
       store.save();
       console.error(`  已保存，当前共 ${store.getAllUsers().length} 个用户`);

package/src/scraper/core.cjs

@@ -8,8 +8,9 @@ const {
   retryWithBackoff,
 } = require("./modules/page-helpers.cjs");
 const { extractCommentAuthors } = require("./modules/comment-extractor.cjs");
+const { extractGuessVideos } = require("./modules/guess-extractor.cjs");
 
-async function scrapeSingleVideo(page, maxComments, log) {
+async function scrapeSingleVideo(page, maxComments, maxGuess, log, location = 'ES') {
   const config = getDelayConfig();
 
   await page
@@ -44,9 +45,16 @@ async function scrapeSingleVideo(page, maxComments, log) {
     throw new Error("无法获取视频作者");
   }
 
-  const commentUsers = await extractCommentAuthors(page, maxComments);
-  await closeCommentPanel(page);
-  await delay(Math.round(config.commentMax * 0.3), config.commentMax);
+  let guessVideos = [];
+  let commentUsers = [];
+
+  if (userData.locationCreated === location) {
+    guessVideos = await extractGuessVideos(page, maxGuess);
+
+    commentUsers = await extractCommentAuthors(page, maxComments);
+    await closeCommentPanel(page);
+    await delay(Math.round(config.commentMax * 0.3), config.commentMax);
+  }
 
   const uniqueUsers = [...new Set(commentUsers)];
 
@@ -56,6 +64,7 @@ async function scrapeSingleVideo(page, maxComments, log) {
     nickname: userData.nickname,
     locationCreated: userData.locationCreated,
     commentUsers: uniqueUsers,
+    guessVideos,
   };
 }
 
@@ -64,6 +73,7 @@ async function runScrape(options) {
     videoUrl,
     maxVideos = 20,
     maxComments = 999,
+    maxGuess = 10,
     preset = null,
     switchMax = null,
     commentMax = null,
@@ -89,7 +99,7 @@ async function runScrape(options) {
   if (!isExternal) {
     log(`视频地址: ${videoUrl}`);
     log(
-      `视频数: ${maxVideos}, 评论数: ${maxComments}, 切换延迟: ${config.switchMax}ms, 评论延迟: ${config.commentMax}ms`,
+      `视频数: ${maxVideos}, 评论数: ${maxComments}, 猜你喜欢: ${maxGuess}, 切换延迟: ${config.switchMax}ms, 评论延迟: ${config.commentMax}ms`,
     );
   }
 
@@ -115,13 +125,15 @@ async function runScrape(options) {
   const videoAuthors = new Set();
   const commentUsers = new Set();
   const allCommentAuthorsList = [];
+  const allGuessAuthors = new Set();
+  const allGuessVideos = [];
 
   for (let i = 0; i < maxVideos; i++) {
     await delay(Math.round(config.commentMax * 0.3), config.commentMax);
 
     let result;
     try {
-      result = await scrapeSingleVideo(page, maxComments, log);
+      result = await scrapeSingleVideo(page, maxComments, maxGuess, log);
     } catch (e) {
       log(`[${i + 1}/${maxVideos}] 跳过: ${e.message}`);
       if (i < maxVideos - 1) {
@@ -140,10 +152,16 @@ async function runScrape(options) {
     videoAuthors.add(result.videoAuthor);
     result.commentUsers.forEach((u) => commentUsers.add(u));
     allCommentAuthorsList.push(...result.commentUsers);
+    if (result.guessVideos) {
+      allGuessVideos.push(...result.guessVideos);
+      result.guessVideos.forEach((v) => {
+        if (v.author) allGuessAuthors.add(v.author);
+      });
+    }
 
     if ((i + 1) % 5 === 0 || i === 0) {
       log(
-        `[${i + 1}/${maxVideos}] ${result.videoAuthor} | 昵称: ${result.nickname || "-"} | 评论用户: ${result.commentUsers.length}`,
+        `[${i + 1}/${maxVideos}] ${result.videoAuthor} | 昵称: ${result.nickname || "-"} | 评论用户: ${result.commentUsers.length} | 猜你喜欢: ${result.guessVideos ? result.guessVideos.length : 0}`,
       );
     }
 
@@ -159,7 +177,7 @@ async function runScrape(options) {
   }
 
   log(
-    `\n结果: 视频作者 ${videoAuthors.size} | 评论用户 ${commentUsers.size} | 总评论 ${allCommentAuthorsList.length}`,
+    `\n结果: 视频作者 ${videoAuthors.size} | 评论用户 ${commentUsers.size} | 总评论 ${allCommentAuthorsList.length} | 猜你喜欢作者 ${allGuessAuthors.size} | 总猜中视频 ${allGuessVideos.length}`,
   );
 
   const videoDetails = {};
@@ -179,10 +197,14 @@ async function runScrape(options) {
     videoDetails: Object.values(videoDetails),
     commentUsers: [...commentUsers].sort(),
     allCommentAuthorsList,
+    guessVideos: allGuessVideos,
+    guessAuthors: [...allGuessAuthors].sort(),
     stats: {
       totalVideos: allResults.length,
       uniqueVideoAuthors: videoAuthors.size,
       uniqueCommentAuthors: commentUsers.size,
+      uniqueGuessAuthors: allGuessAuthors.size,
+      totalGuessVideos: allGuessVideos.length,
     },
   };
 

package/src/scraper/index.cjs

@@ -18,6 +18,7 @@ async function main() {
   let preset = null;
   let maxVideos = 20;
   let maxComments = 999;
+  let maxGuess = 10;
   let switchMax = null;
   let commentMax = null;
 
@@ -26,21 +27,23 @@ async function main() {
       preset = args[1].toLowerCase();
       maxVideos = parseInt(args[2]) || 20;
       maxComments = parseInt(args[3]) || 999;
+      maxGuess = parseInt(args[4]) || 10;
     } else {
       maxVideos = parseInt(args[1]) || 20;
       maxComments = parseInt(args[2]) || 999;
-      switchMax = parseInt(args[3]) || null;
-      commentMax = parseInt(args[4]) || null;
+      maxGuess = parseInt(args[3]) || 10;
+      switchMax = parseInt(args[4]) || null;
+      commentMax = parseInt(args[5]) || null;
     }
   }
 
   if (!videoUrl) {
     console.error("用法:");
     console.error(
-      "  预设模式: node index.cjs <视频URL> <preset> [最大视频数] [最大评论数] [-o 输出路径]",
+      "  预设模式: node index.cjs <视频URL> <preset> [最大视频数] [最大评论数] [猜你喜欢数] [-o 输出路径]",
     );
     console.error(
-      "  手动模式: node index.cjs <视频URL> [最大视频数] [最大评论数] [切换延迟ms] [评论延迟ms] [-o 输出路径]",
+      "  手动模式: node index.cjs <视频URL> [最大视频数] [最大评论数] [猜你喜欢数] [切换延迟ms] [评论延迟ms] [-o 输出路径]",
     );
     console.error(
       "预设: fast(1s/0.8s), normal(2.5s/1.5s), slow(5s/3s), stealth(8s/5s)",
@@ -57,6 +60,7 @@ async function main() {
       videoUrl,
       maxVideos,
       maxComments,
+      maxGuess,
       preset,
       switchMax,
       commentMax,

package/src/scraper/modules/guess-extractor.cjs

@@ -0,0 +1,117 @@
+const { delay, getDelayConfig, closeCommentPanel } = require('./page-helpers.cjs');
+
+async function openGuessTab(page) {
+  const tabs = page.locator('[class*="tabbar-item"]');
+  const guessTab = tabs.filter({ hasText: /猜你喜欢/i }).first();
+  await guessTab.click();
+  const config = getDelayConfig();
+  await delay(Math.round(config.commentMax * 0.5), config.commentMax);
+  await page.waitForSelector('[class*="Related"]', { timeout: 5000 }).catch(() => {});
+}
+
+async function extractGuessVideos(page, maxVideos = 10) {
+  await openGuessTab(page);
+
+  const config = getDelayConfig();
+  const allVideos = [];
+  const seenIds = new Set();
+
+  let prevScrollHeight = 0;
+  let noChangeCount = 0;
+  const maxNoChange = 6;
+
+  while (allVideos.length < maxVideos) {
+    const snapshot = await page.evaluate(() => {
+      const relatedContainer = document.querySelector('[class*="Related"]');
+      if (!relatedContainer) return { items: [], scrollHeight: 0, containerFound: false };
+
+      function findScrollableAncestor(el) {
+        if (el.scrollHeight > el.clientHeight + 10) return el;
+        let current = el.parentElement;
+        while (current && current !== document.body) {
+          if (current.scrollHeight > current.clientHeight + 10) return current;
+          current = current.parentElement;
+        }
+        return el;
+      }
+
+      const scrollContainer = findScrollableAncestor(relatedContainer);
+
+      const result = [];
+      const items = relatedContainer.querySelectorAll('[class*="DivItemContainer"]');
+      items.forEach(item => {
+        const link = item.querySelector('a[href*="/video/"]');
+        if (!link || !link.href) return;
+        const videoUrl = link.href;
+
+        const m = videoUrl.match(/@([^/]+)\/video\/(\d+)/);
+        if (!m) return;
+
+        result.push({ author: '@' + m[1], videoId: m[2], url: videoUrl, title: '' });
+      });
+
+      return {
+        items: result,
+        scrollHeight: scrollContainer.scrollHeight,
+        containerFound: true,
+      };
+    });
+
+    if (!snapshot.containerFound) break;
+
+    for (const item of snapshot.items) {
+      if (allVideos.length >= maxVideos) break;
+      if (!seenIds.has(item.videoId)) {
+        seenIds.add(item.videoId);
+        allVideos.push(item);
+      }
+    }
+
+    if (allVideos.length >= maxVideos) break;
+
+    if (snapshot.scrollHeight === prevScrollHeight) {
+      noChangeCount++;
+      if (noChangeCount >= maxNoChange) break;
+    } else {
+      noChangeCount = 0;
+    }
+    prevScrollHeight = snapshot.scrollHeight;
+
+    await page.evaluate(async () => {
+      const relatedContainer = document.querySelector('[class*="Related"]');
+      if (!relatedContainer) return;
+
+      function findScrollableAncestor(el) {
+        if (el.scrollHeight > el.clientHeight + 10) return el;
+        let current = el.parentElement;
+        while (current && current !== document.body) {
+          if (current.scrollHeight > current.clientHeight + 10) return current;
+          current = current.parentElement;
+        }
+        return el;
+      }
+
+      const el = findScrollableAncestor(relatedContainer);
+      const delay = ms => new Promise(r => setTimeout(r, ms));
+
+      el.scrollTop = el.scrollHeight;
+      await delay(400 + Math.random() * 400);
+
+      el.scrollTop -= 100 + Math.random() * 100;
+      await delay(200 + Math.random() * 200);
+
+      el.scrollTop = el.scrollHeight;
+    });
+
+    await delay(2000, 4000);
+  }
+
+  await closeCommentPanel(page);
+  await delay(Math.round(config.commentMax * 0.3), config.commentMax);
+
+  return allVideos.slice(0, maxVideos);
+}
+
+module.exports = {
+  extractGuessVideos,
+};

package/src/watch/public/index.html

@@ -236,7 +236,7 @@ async function addUsers() {
     const res = await fetch('/api/users', {
       method: 'POST',
       headers: { 'Content-Type': 'application/json' },
-      body: JSON.stringify({ users: names })
+      body: JSON.stringify({ usernames: names })
     });
     const data = await res.json();
     showToast(`${data.message || `${names.length} 个用户已插入队列`}`);