tt-help-cli-ycl 1.3.24 → 1.3.26

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (60) hide show
  1. package/README.md +17 -17
  2. package/cli.js +9 -9
  3. package/package.json +47 -47
  4. package/scripts/run-explore copy.bat +68 -68
  5. package/scripts/run-explore.bat +68 -68
  6. package/scripts/run-explore.ps1 +81 -81
  7. package/scripts/run-explore.sh +73 -73
  8. package/scripts/test-captcha-lib.mjs +68 -0
  9. package/scripts/test-captcha.mjs +81 -0
  10. package/scripts/test-incognito-lib.mjs +36 -0
  11. package/scripts/test-login-state.mjs +128 -0
  12. package/scripts/test-safe-click.mjs +45 -0
  13. package/src/cli/attach.js +180 -180
  14. package/src/cli/auto.js +240 -186
  15. package/src/cli/config.js +152 -152
  16. package/src/cli/explore.js +439 -253
  17. package/src/cli/info.js +88 -88
  18. package/src/cli/open.js +102 -0
  19. package/src/cli/progress.js +111 -111
  20. package/src/cli/refresh.js +216 -216
  21. package/src/cli/scrape.js +47 -47
  22. package/src/cli/utils.js +18 -18
  23. package/src/cli/videos.js +41 -41
  24. package/src/cli/watch.js +31 -31
  25. package/src/lib/api-interceptor.js +191 -191
  26. package/src/lib/args.js +551 -517
  27. package/src/lib/browser/anti-detect.js +23 -23
  28. package/src/lib/browser/cdp.js +237 -194
  29. package/src/lib/browser/health-checker.js +93 -0
  30. package/src/lib/browser/launch.js +43 -43
  31. package/src/lib/browser/page.js +156 -156
  32. package/src/lib/constants.js +206 -199
  33. package/src/lib/delay.js +54 -54
  34. package/src/lib/explore-fetch.js +118 -118
  35. package/src/lib/fetcher.js +45 -45
  36. package/src/lib/filter.js +66 -66
  37. package/src/lib/io.js +54 -54
  38. package/src/lib/output.js +80 -80
  39. package/src/lib/page-error-detector.js +71 -71
  40. package/src/lib/parse-ssr.mjs +69 -69
  41. package/src/lib/parser.js +47 -47
  42. package/src/lib/retry.js +45 -45
  43. package/src/lib/scrape.js +89 -89
  44. package/src/lib/tiktok-scraper.mjs +194 -194
  45. package/src/lib/url.js +52 -52
  46. package/src/main.js +44 -42
  47. package/src/results/user-videos-bar.lar.lar.moeta.json +37 -0
  48. package/src/scraper/auto-core.js +203 -203
  49. package/src/scraper/core.js +211 -211
  50. package/src/scraper/explore-core.js +201 -189
  51. package/src/scraper/modules/captcha-handler.js +114 -114
  52. package/src/scraper/modules/comment-extractor.js +74 -74
  53. package/src/scraper/modules/follow-extractor.js +118 -118
  54. package/src/scraper/modules/guess-extractor.js +51 -51
  55. package/src/scraper/modules/page-helpers.js +48 -48
  56. package/src/scraper/refresh-core.js +179 -179
  57. package/src/videos/core.js +101 -101
  58. package/src/watch/data-store.js +828 -828
  59. package/src/watch/public/index.html +753 -753
  60. package/src/watch/server.js +705 -705
package/src/main.js CHANGED
@@ -1,42 +1,44 @@
1
- import { parseArgs } from './lib/args.js';
2
- import { proxy, HELP_TEXT, getConfigText } from './lib/constants.js';
3
- import { handleInfo } from './cli/info.js';
4
- import { handleExplore } from './cli/explore.js';
5
- import { handleAttach } from './cli/attach.js';
6
- import { handleWatch } from './cli/watch.js';
7
- import { handleConfig, showConfig, showUsage, version } from './cli/config.js';
8
-
9
- async function main() {
10
- const parsed = parseArgs();
11
-
12
- switch (parsed.subcommand) {
13
- case 'explore': return handleExplore(parsed);
14
- case 'info': return handleInfo(parsed);
15
- case 'attach': return handleAttach(parsed);
16
- case 'watch': return handleWatch(parsed);
17
- }
18
-
19
- const { urls, outputFile, outputFormat, exploreCount, showConfig: showCfg, showHelp, showVersion, customProxy, configAction, configKey, configValue } = parsed;
20
-
21
- if (showVersion) {
22
- console.log(version);
23
- process.exit(0);
24
- }
25
- if (showHelp) return showUsage();
26
- if (configAction) return handleConfig(configAction, configKey, configValue);
27
- if (showCfg) return showConfig(urls, outputFile);
28
- if (urls.length === 0 && exploreCount === 0) return showUsage();
29
-
30
- // 默认行为:URL info,--explore explore
31
- if (exploreCount > 0) {
32
- return handleExplore({ ...parsed, subcommand: 'explore' });
33
- }
34
-
35
- // 有 URL 默认走 info
36
- return handleInfo(parsed);
37
- }
38
-
39
- main().catch(err => {
40
- console.error(`错误: ${err.message}`);
41
- process.exit(1);
42
- });
1
+ import { parseArgs } from './lib/args.js';
2
+ import { proxy, HELP_TEXT, getConfigText } from './lib/constants.js';
3
+ import { handleInfo } from './cli/info.js';
4
+ import { handleExplore } from './cli/explore.js';
5
+ import { handleAttach } from './cli/attach.js';
6
+ import { handleWatch } from './cli/watch.js';
7
+ import { handleConfig, showConfig, showUsage, version } from './cli/config.js';
8
+ import { handleOpen } from './cli/open.js';
9
+
10
+ async function main() {
11
+ const parsed = parseArgs();
12
+
13
+ switch (parsed.subcommand) {
14
+ case 'explore': return handleExplore(parsed);
15
+ case 'info': return handleInfo(parsed);
16
+ case 'attach': return handleAttach(parsed);
17
+ case 'watch': return handleWatch(parsed);
18
+ case 'open': return handleOpen(parsed);
19
+ }
20
+
21
+ const { urls, outputFile, outputFormat, exploreCount, showConfig: showCfg, showHelp, showVersion, customProxy, configAction, configKey, configValue } = parsed;
22
+
23
+ if (showVersion) {
24
+ console.log(version);
25
+ process.exit(0);
26
+ }
27
+ if (showHelp) return showUsage();
28
+ if (configAction) return handleConfig(configAction, configKey, configValue);
29
+ if (showCfg) return showConfig(urls, outputFile);
30
+ if (urls.length === 0 && exploreCount === 0) return showUsage();
31
+
32
+ // 默认行为:URL info,--explore explore
33
+ if (exploreCount > 0) {
34
+ return handleExplore({ ...parsed, subcommand: 'explore' });
35
+ }
36
+
37
+ // 有 URL 默认走 info
38
+ return handleInfo(parsed);
39
+ }
40
+
41
+ main().catch(err => {
42
+ console.error(`错误: ${err.message}`);
43
+ process.exit(1);
44
+ });
@@ -0,0 +1,37 @@
1
+ {
2
+ "user": {
3
+ "uniqueId": "bar.lar.lar.moeta",
4
+ "secUid": "MS4wLjABAAAA3cgKTWvKfga0JAWeakAzx3zQ-aFAC8RuQvxD4HQFraKKsc_TbOIyMo3_ofVlXofV",
5
+ "nickname": "Bar Lar Lar Moetain",
6
+ "ttSeller": false,
7
+ "verified": false,
8
+ "followerCount": 24000,
9
+ "videoCount": 749,
10
+ "followingCount": 4293,
11
+ "heartCount": 254300,
12
+ "signature": ""
13
+ },
14
+ "totalVideos": 5,
15
+ "videos": [
16
+ {
17
+ "id": "7638231799084158228",
18
+ "url": "https://www.tiktok.com/@bar.lar.lar.moeta/video/7638231799084158228"
19
+ },
20
+ {
21
+ "id": "7638162444698914068",
22
+ "url": "https://www.tiktok.com/@bar.lar.lar.moeta/video/7638162444698914068"
23
+ },
24
+ {
25
+ "id": "7638116251767819541",
26
+ "url": "https://www.tiktok.com/@bar.lar.lar.moeta/video/7638116251767819541"
27
+ },
28
+ {
29
+ "id": "7638069637321690388",
30
+ "url": "https://www.tiktok.com/@bar.lar.lar.moeta/video/7638069637321690388"
31
+ },
32
+ {
33
+ "id": "7637927171025112341",
34
+ "url": "https://www.tiktok.com/@bar.lar.lar.moeta/video/7637927171025112341"
35
+ }
36
+ ]
37
+ }
@@ -1,203 +1,203 @@
1
- import {
2
- delay,
3
- ensureBrowserReady,
4
- ensureTikTokPage,
5
- setDelayConfig,
6
- getDelayConfig,
7
- closeCommentPanel,
8
- retryWithBackoff,
9
- detectPageError,
10
- isLoggedIn,
11
- assertPageUrl,
12
- } from './modules/page-helpers.js';
13
- import { detectCaptcha } from './modules/captcha-handler.js';
14
- export { ensureBrowserReady };
15
- import {
16
- getUserInfo,
17
- collectVideos,
18
- } from '../videos/core.js';
19
- import { runScrape } from './core.js';
20
- import { extractFollowAndFollowers } from './modules/follow-extractor.js';
21
-
22
- function mergeUserInfo(existing, incoming, source) {
23
- const merged = { ...existing };
24
- for (const [key, value] of Object.entries(incoming)) {
25
- if (key === '_sources') continue;
26
- if (value === undefined || value === null || value === '') continue;
27
- if (typeof value === 'number' && typeof merged[key] === 'number') {
28
- merged[key] = Math.max(merged[key], value);
29
- } else if (merged[key] === undefined || merged[key] === null || merged[key] === '') {
30
- merged[key] = value;
31
- }
32
- }
33
- if (source) {
34
- if (!merged._sources) merged._sources = [];
35
- if (!merged._sources.includes(source)) merged._sources.push(source);
36
- }
37
- return merged;
38
- }
39
-
40
- async function processUser(page, username, options, log) {
41
- const {
42
- collectMax = 1,
43
- scrapeDepth = 50,
44
- maxComments = 200,
45
- maxGuess = 10,
46
- preset = 'fast',
47
- switchMax = null,
48
- commentMax = null,
49
- enableFollow = false,
50
- maxFollowing = 200,
51
- maxFollowers = 200,
52
- browser = null,
53
- } = options;
54
-
55
- const result = {
56
- userInfo: null,
57
- collectedVideos: [],
58
- discoveredVideoAuthors: [],
59
- discoveredCommentAuthors: [],
60
- discoveredGuessAuthors: [],
61
- discoveredFollowing: [],
62
- discoveredFollowers: [],
63
- error: null,
64
- };
65
-
66
- try {
67
- log(`\n[processUser] 访问 @${username}...`);
68
- await retryWithBackoff(async () => {
69
- await page.goto(`https://www.tiktok.com/@${username}`, {
70
- waitUntil: 'load', timeout: 30000,
71
- });
72
- assertPageUrl(page, `@${username}`);
73
- }, { log });
74
- await page.waitForSelector('[class*="DivVideoList"]', { timeout: 10000 }).catch(() => {});
75
- await delay(1000, 2000);
76
-
77
- const info = await getUserInfo(page);
78
- result.userInfo = info;
79
- if (!info.uniqueId) info.uniqueId = username;
80
- log(` 昵称: ${info.nickname || '-'} | 粉丝: ${info.followerCount || 0}`);
81
-
82
- if (options.enableFollow) {
83
- const loggedIn = await isLoggedIn(page);
84
- if (!loggedIn) {
85
- log(' [跳过] 提取关注/粉丝:未登录,请先登录 TikTok');
86
- result.discoveredFollowing = [];
87
- result.discoveredFollowers = [];
88
- } else {
89
- try {
90
- log(' 提取关注/粉丝列表...');
91
- const { following, followers } = await extractFollowAndFollowers(page, {
92
- maxFollowing: options.maxFollowing || 200,
93
- maxFollowers: options.maxFollowers || 200,
94
- log,
95
- });
96
- result.discoveredFollowing = following;
97
- result.discoveredFollowers = followers;
98
- log(` 关注: ${following.length} | 粉丝: ${followers.length}`);
99
- } catch (e) {
100
- log(` 关注/粉丝提取失败: ${e.message}`);
101
- result.discoveredFollowing = [];
102
- result.discoveredFollowers = [];
103
- }
104
- }
105
- }
106
-
107
- const captcha = await detectCaptcha(page);
108
- if (captcha && captcha.visible) {
109
- log(`[验证码] @${username} 页面出现验证码`);
110
- result.captchaDetected = true;
111
- result.captchaStage = result.captchaStage || 'video-page';
112
- result.captchaMessage = result.captchaMessage || '视频页出现验证码';
113
- }
114
-
115
- const videos = await collectVideos(page, username, collectMax, log);
116
- const videoList = Array.from(videos.values()).slice(0, collectMax);
117
- result.collectedVideos = videoList.map(v => ({
118
- videoId: v.id,
119
- videoUrl: v.href,
120
- }));
121
-
122
- if (videoList.length > 0) {
123
- const allVideoAuthors = new Map();
124
- const allCommentAuthors = new Set();
125
- const allGuessAuthors = new Set();
126
-
127
- for (let i = 0; i < videoList.length; i++) {
128
- const video = videoList[i];
129
- const videoUrl = video.href.startsWith('http')
130
- ? video.href
131
- : `https://www.tiktok.com${video.href}`;
132
- log(` [${i + 1}/${videoList.length}] 开始 scrape: ${videoUrl} (深度 ${scrapeDepth})`);
133
-
134
- const scrapeResult = await runScrape({
135
- videoUrl,
136
- maxVideos: scrapeDepth,
137
- maxComments,
138
- maxGuess,
139
- preset,
140
- switchMax,
141
- commentMax,
142
- browser,
143
- page,
144
- log,
145
- });
146
-
147
- if (scrapeResult.captchaDetected) {
148
- result.captchaDetected = true;
149
- result.captchaStage = scrapeResult.captchaStage || 'scrape';
150
- result.captchaMessage = scrapeResult.captchaMessage || 'scrape阶段出现验证码';
151
- }
152
-
153
- const scrapeOutput = scrapeResult.output;
154
-
155
- if (scrapeOutput && scrapeOutput.videoDetails) {
156
- for (const vd of scrapeOutput.videoDetails) {
157
- if (!allVideoAuthors.has(vd.uniqueId)) {
158
- allVideoAuthors.set(vd.uniqueId, {
159
- uniqueId: vd.uniqueId,
160
- nickname: vd.nickname,
161
- locationCreated: vd.locationCreated,
162
- });
163
- }
164
- }
165
- }
166
-
167
- if (scrapeOutput && scrapeOutput.commentUsers) {
168
- for (const cu of scrapeOutput.commentUsers) {
169
- allCommentAuthors.add(cu);
170
- }
171
- }
172
-
173
- if (scrapeOutput && scrapeOutput.guessAuthors) {
174
- for (const ga of scrapeOutput.guessAuthors) {
175
- allGuessAuthors.add(ga);
176
- }
177
- }
178
- }
179
-
180
- result.discoveredVideoAuthors = [...allVideoAuthors.values()];
181
- result.discoveredCommentAuthors = [...allCommentAuthors];
182
- result.discoveredGuessAuthors = [...allGuessAuthors];
183
-
184
- log(` 发现: ${result.discoveredVideoAuthors.length} 个视频作者, ${result.discoveredCommentAuthors.length} 个评论作者, ${result.discoveredGuessAuthors.length} 个猜你喜欢作者`);
185
- } else {
186
- const pageError = await detectPageError(page);
187
- result.restricted = !!pageError;
188
- if (pageError) {
189
- log(` @${username} 页面受限(${pageError}),标记跳过`);
190
- } else {
191
- log(` @${username} 没有视频,跳过 scrape`);
192
- }
193
- }
194
- } catch (e) {
195
- result.error = e.message;
196
- result.errorStack = e.stack || '';
197
- log(` [错误] ${e.message}`);
198
- }
199
-
200
- return result;
201
- }
202
-
203
- export { processUser, mergeUserInfo };
1
+ import {
2
+ delay,
3
+ ensureBrowserReady,
4
+ ensureTikTokPage,
5
+ setDelayConfig,
6
+ getDelayConfig,
7
+ closeCommentPanel,
8
+ retryWithBackoff,
9
+ detectPageError,
10
+ isLoggedIn,
11
+ assertPageUrl,
12
+ } from './modules/page-helpers.js';
13
+ import { detectCaptcha } from './modules/captcha-handler.js';
14
+ export { ensureBrowserReady };
15
+ import {
16
+ getUserInfo,
17
+ collectVideos,
18
+ } from '../videos/core.js';
19
+ import { runScrape } from './core.js';
20
+ import { extractFollowAndFollowers } from './modules/follow-extractor.js';
21
+
22
+ function mergeUserInfo(existing, incoming, source) {
23
+ const merged = { ...existing };
24
+ for (const [key, value] of Object.entries(incoming)) {
25
+ if (key === '_sources') continue;
26
+ if (value === undefined || value === null || value === '') continue;
27
+ if (typeof value === 'number' && typeof merged[key] === 'number') {
28
+ merged[key] = Math.max(merged[key], value);
29
+ } else if (merged[key] === undefined || merged[key] === null || merged[key] === '') {
30
+ merged[key] = value;
31
+ }
32
+ }
33
+ if (source) {
34
+ if (!merged._sources) merged._sources = [];
35
+ if (!merged._sources.includes(source)) merged._sources.push(source);
36
+ }
37
+ return merged;
38
+ }
39
+
40
+ async function processUser(page, username, options, log) {
41
+ const {
42
+ collectMax = 1,
43
+ scrapeDepth = 50,
44
+ maxComments = 200,
45
+ maxGuess = 10,
46
+ preset = 'fast',
47
+ switchMax = null,
48
+ commentMax = null,
49
+ enableFollow = false,
50
+ maxFollowing = 200,
51
+ maxFollowers = 200,
52
+ browser = null,
53
+ } = options;
54
+
55
+ const result = {
56
+ userInfo: null,
57
+ collectedVideos: [],
58
+ discoveredVideoAuthors: [],
59
+ discoveredCommentAuthors: [],
60
+ discoveredGuessAuthors: [],
61
+ discoveredFollowing: [],
62
+ discoveredFollowers: [],
63
+ error: null,
64
+ };
65
+
66
+ try {
67
+ log(`\n[processUser] 访问 @${username}...`);
68
+ await retryWithBackoff(async () => {
69
+ await page.goto(`https://www.tiktok.com/@${username}`, {
70
+ waitUntil: 'load', timeout: 30000,
71
+ });
72
+ assertPageUrl(page, `@${username}`);
73
+ }, { log });
74
+ await page.waitForSelector('[class*="DivVideoList"]', { timeout: 10000 }).catch(() => {});
75
+ await delay(1000, 2000);
76
+
77
+ const info = await getUserInfo(page);
78
+ result.userInfo = info;
79
+ if (!info.uniqueId) info.uniqueId = username;
80
+ log(` 昵称: ${info.nickname || '-'} | 粉丝: ${info.followerCount || 0}`);
81
+
82
+ if (options.enableFollow) {
83
+ const loggedIn = await isLoggedIn(page);
84
+ if (!loggedIn) {
85
+ log(' [跳过] 提取关注/粉丝:未登录,请先登录 TikTok');
86
+ result.discoveredFollowing = [];
87
+ result.discoveredFollowers = [];
88
+ } else {
89
+ try {
90
+ log(' 提取关注/粉丝列表...');
91
+ const { following, followers } = await extractFollowAndFollowers(page, {
92
+ maxFollowing: options.maxFollowing || 200,
93
+ maxFollowers: options.maxFollowers || 200,
94
+ log,
95
+ });
96
+ result.discoveredFollowing = following;
97
+ result.discoveredFollowers = followers;
98
+ log(` 关注: ${following.length} | 粉丝: ${followers.length}`);
99
+ } catch (e) {
100
+ log(` 关注/粉丝提取失败: ${e.message}`);
101
+ result.discoveredFollowing = [];
102
+ result.discoveredFollowers = [];
103
+ }
104
+ }
105
+ }
106
+
107
+ const captcha = await detectCaptcha(page);
108
+ if (captcha && captcha.visible) {
109
+ log(`[验证码] @${username} 页面出现验证码`);
110
+ result.captchaDetected = true;
111
+ result.captchaStage = result.captchaStage || 'video-page';
112
+ result.captchaMessage = result.captchaMessage || '视频页出现验证码';
113
+ }
114
+
115
+ const videos = await collectVideos(page, username, collectMax, log);
116
+ const videoList = Array.from(videos.values()).slice(0, collectMax);
117
+ result.collectedVideos = videoList.map(v => ({
118
+ videoId: v.id,
119
+ videoUrl: v.href,
120
+ }));
121
+
122
+ if (videoList.length > 0) {
123
+ const allVideoAuthors = new Map();
124
+ const allCommentAuthors = new Set();
125
+ const allGuessAuthors = new Set();
126
+
127
+ for (let i = 0; i < videoList.length; i++) {
128
+ const video = videoList[i];
129
+ const videoUrl = video.href.startsWith('http')
130
+ ? video.href
131
+ : `https://www.tiktok.com${video.href}`;
132
+ log(` [${i + 1}/${videoList.length}] 开始 scrape: ${videoUrl} (深度 ${scrapeDepth})`);
133
+
134
+ const scrapeResult = await runScrape({
135
+ videoUrl,
136
+ maxVideos: scrapeDepth,
137
+ maxComments,
138
+ maxGuess,
139
+ preset,
140
+ switchMax,
141
+ commentMax,
142
+ browser,
143
+ page,
144
+ log,
145
+ });
146
+
147
+ if (scrapeResult.captchaDetected) {
148
+ result.captchaDetected = true;
149
+ result.captchaStage = scrapeResult.captchaStage || 'scrape';
150
+ result.captchaMessage = scrapeResult.captchaMessage || 'scrape阶段出现验证码';
151
+ }
152
+
153
+ const scrapeOutput = scrapeResult.output;
154
+
155
+ if (scrapeOutput && scrapeOutput.videoDetails) {
156
+ for (const vd of scrapeOutput.videoDetails) {
157
+ if (!allVideoAuthors.has(vd.uniqueId)) {
158
+ allVideoAuthors.set(vd.uniqueId, {
159
+ uniqueId: vd.uniqueId,
160
+ nickname: vd.nickname,
161
+ locationCreated: vd.locationCreated,
162
+ });
163
+ }
164
+ }
165
+ }
166
+
167
+ if (scrapeOutput && scrapeOutput.commentUsers) {
168
+ for (const cu of scrapeOutput.commentUsers) {
169
+ allCommentAuthors.add(cu);
170
+ }
171
+ }
172
+
173
+ if (scrapeOutput && scrapeOutput.guessAuthors) {
174
+ for (const ga of scrapeOutput.guessAuthors) {
175
+ allGuessAuthors.add(ga);
176
+ }
177
+ }
178
+ }
179
+
180
+ result.discoveredVideoAuthors = [...allVideoAuthors.values()];
181
+ result.discoveredCommentAuthors = [...allCommentAuthors];
182
+ result.discoveredGuessAuthors = [...allGuessAuthors];
183
+
184
+ log(` 发现: ${result.discoveredVideoAuthors.length} 个视频作者, ${result.discoveredCommentAuthors.length} 个评论作者, ${result.discoveredGuessAuthors.length} 个猜你喜欢作者`);
185
+ } else {
186
+ const pageError = await detectPageError(page);
187
+ result.restricted = !!pageError;
188
+ if (pageError) {
189
+ log(` @${username} 页面受限(${pageError}),标记跳过`);
190
+ } else {
191
+ log(` @${username} 没有视频,跳过 scrape`);
192
+ }
193
+ }
194
+ } catch (e) {
195
+ result.error = e.message;
196
+ result.errorStack = e.stack || '';
197
+ log(` [错误] ${e.message}`);
198
+ }
199
+
200
+ return result;
201
+ }
202
+
203
+ export { processUser, mergeUserInfo };