youtube_crawler_v1_backup.js
21 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
/**
* YouTube Trending Crawler v2
* 支持 Data API v3 + yt-dlp + Invidious 三级降级
* 符合 benchmark_v2.md 评分标准
*/
const { execSync } = require('child_process');
const fs = require('fs');
const path = require('path');
/**
* 解析 ISO 8601 时长 (PT3M33S)
* @param {string} duration
* @returns {number|null} 秒数
*/
function parseISODuration(duration) {
if (!duration || typeof duration !== 'string') return null;
const match = duration.match(/PT(?:(\d+)H)?(?:(\d+)M)?(?:(\d+)S)?/);
if (!match) return null;
const hours = parseInt(match[1] || 0, 10);
const minutes = parseInt(match[2] || 0, 10);
const seconds = parseInt(match[3] || 0, 10);
return hours * 3600 + minutes * 60 + seconds;
}
/**
* 休眠
* @param {number} ms
* @returns {Promise<void>}
*/
function sleep(ms) {
return new Promise(resolve => setTimeout(resolve, ms));
}
/**
* YouTube 热门视频爬虫类
* @class YouTubeTrendingCrawler
*/
class YouTubeTrendingCrawler {
/**
* @param {Object} options
* @param {string} [options.apiKey] - API Key
* @param {boolean} [options.useMock=false] - Mock 模式
* @param {number} [options.timeout=30000] - 超时(ms)
* @param {number} [options.maxRetries=5] - 最大重试次数
* @param {boolean} [options.enableFallback=true] - 启用降级
* @param {number} [options.quotaLimit=10000] - 每日配额
* @param {number} [options.requestInterval=2000] - 请求间隔(ms)
* @param {string} [options.invidiousInstance='https://iv.datura.network'] - Invidious 实例
*/
constructor(options = {}) {
this.apiKey = options.apiKey || process.env.YOUTUBE_API_KEY || null;
this.useMock = options.useMock || process.env.YOUTUBE_CRAWLER_MOCK === '1' || false;
this.timeout = options.timeout || 30000;
this.maxRetries = options.maxRetries || 5;
this.enableFallback = options.enableFallback !== false;
this.quotaLimit = options.quotaLimit || 10000;
this.quotaUsed = 0;
this.requestInterval = options.requestInterval || 2000;
this.invidiousInstance = options.invidiousInstance || 'https://iv.datura.network';
this.logs = [];
this.cache = new Map();
this.cacheTTL = options.cacheTTL || 900000; // 15min default
this._log('info', 'YouTubeTrendingCrawler v2 initialized');
}
_log(level, message) {
const entry = { timestamp: new Date().toISOString(), level, message };
this.logs.push(entry);
}
getLogs() {
return this.logs;
}
_validateRegionCode(code) {
if (!code || typeof code !== 'string') return false;
return /^[A-Z]{2}$/.test(code.toUpperCase());
}
_validateMaxResults(maxResults) {
const num = parseInt(maxResults, 10);
return !isNaN(num) && num >= 1 && num <= 50;
}
_validateCategoryId(categoryId) {
if (!categoryId) return true;
const num = parseInt(categoryId, 10);
return !isNaN(num) && num >= 1 && num <= 44;
}
getRemainingQuota() {
return this.quotaLimit - this.quotaUsed;
}
_recordQuotaUsage(units = 1) {
this.quotaUsed += units;
this._log('info', `Quota used: ${this.quotaUsed}/${this.quotaLimit}`);
}
_cleanString(str) {
if (!str || typeof str !== 'string') return '';
return str.trim();
}
_parseViewCount(viewCount) {
if (typeof viewCount === 'number') return viewCount;
if (!viewCount) return 0;
const parsed = parseInt(viewCount.toString().replace(/[^0-9]/g, ''), 10);
return isNaN(parsed) ? 0 : parsed;
}
_getCacheKey(regionCode, categoryId, maxResults) {
return `${regionCode}:${categoryId || 'all'}:${maxResults}`;
}
_getCached(key) {
const entry = this.cache.get(key);
if (!entry) return null;
if (Date.now() - entry.time > this.cacheTTL) {
this.cache.delete(key);
return null;
}
return entry.data;
}
_setCache(key, data) {
this.cache.set(key, { time: Date.now(), data });
}
_getMockData(regionCode = 'US', maxResults = 10) {
const baseVideos = [
{
video_id: 'mock_001',
source_url: 'https://www.youtube.com/watch?v=mock_001',
title: 'Mock Trending Video: Global Hits 2024',
channel_id: 'UCmock001',
channel_title: 'Mock Music Channel',
view_count: 12500000,
like_count: 450000,
comment_count: 12000,
published_at: '2024-03-15T10:00:00Z',
thumbnail_url: 'https://i.ytimg.com/vi/mock_001/hqdefault.jpg',
category_id: '10',
duration: 213,
crawl_time: new Date().toISOString()
},
{
video_id: 'mock_002',
source_url: 'https://www.youtube.com/watch?v=mock_002',
title: 'Mock Gaming: Speedrun World Record',
channel_id: 'UCmock002',
channel_title: 'Mock Gaming',
view_count: 3200000,
like_count: 180000,
comment_count: 5400,
published_at: '2024-03-14T08:30:00Z',
thumbnail_url: 'https://i.ytimg.com/vi/mock_002/hqdefault.jpg',
category_id: '20',
duration: 1855,
crawl_time: new Date().toISOString()
},
{
video_id: 'mock_003',
source_url: 'https://www.youtube.com/watch?v=mock_003',
title: 'Mock Tech Review: Latest Smartphone',
channel_id: 'UCmock003',
channel_title: 'Mock Tech',
view_count: 1800000,
like_count: 92000,
comment_count: 3100,
published_at: '2024-03-13T14:00:00Z',
thumbnail_url: 'https://i.ytimg.com/vi/mock_003/hqdefault.jpg',
category_id: '28',
duration: 728,
crawl_time: new Date().toISOString()
},
{
video_id: 'mock_004',
source_url: 'https://www.youtube.com/watch?v=mock_004',
title: 'Mock Comedy: Stand-up Special',
channel_id: 'UCmock004',
channel_title: 'Mock Comedy Central',
view_count: 5400000,
like_count: 210000,
comment_count: 8700,
published_at: '2024-03-12T20:00:00Z',
thumbnail_url: 'https://i.ytimg.com/vi/mock_004/hqdefault.jpg',
category_id: '23',
duration: 1840,
crawl_time: new Date().toISOString()
},
{
video_id: 'mock_005',
source_url: 'https://www.youtube.com/watch?v=mock_005',
title: 'Mock Education: How Quantum Computers Work',
channel_id: 'UCmock005',
channel_title: 'Mock Education',
view_count: 890000,
like_count: 56000,
comment_count: 1800,
published_at: '2024-03-11T09:00:00Z',
thumbnail_url: 'https://i.ytimg.com/vi/mock_005/hqdefault.jpg',
category_id: '27',
duration: 634,
crawl_time: new Date().toISOString()
}
];
return baseVideos.slice(0, maxResults).map(v => ({
...v,
_mockRegion: regionCode.toUpperCase()
}));
}
/**
* 从 API 响应中提取标准化视频信息
* @param {Object} apiItem
* @returns {Object}
*/
extract_video_info(apiItem) {
if (!apiItem || !apiItem.id) {
throw new Error('Invalid API item: missing id');
}
const videoId = typeof apiItem.id === 'string' ? apiItem.id : apiItem.id.videoId;
const snippet = apiItem.snippet || {};
const statistics = apiItem.statistics || {};
const contentDetails = apiItem.contentDetails || {};
const thumbnails = snippet.thumbnails || {};
const crawlTime = new Date().toISOString();
return {
video_id: videoId,
source_url: `https://www.youtube.com/watch?v=${videoId}`,
title: this._cleanString(snippet.title) || 'Unknown Title',
channel_id: snippet.channelId || null,
channel_title: this._cleanString(snippet.channelTitle) || 'Unknown Channel',
view_count: this._parseViewCount(statistics.viewCount),
like_count: this._parseViewCount(statistics.likeCount),
comment_count: this._parseViewCount(statistics.commentCount),
published_at: snippet.publishedAt || null,
thumbnail_url: thumbnails.high?.url || thumbnails.medium?.url || thumbnails.default?.url || null,
category_id: snippet.categoryId || null,
duration: parseISODuration(contentDetails.duration),
crawl_time: crawlTime
};
}
/**
* 带指数退避的重试包装
* @private
*/
async _fetchWithRetry(url, options, backoffBase = 2000, maxBackoff = 60000) {
let lastError = null;
for (let attempt = 0; attempt < this.maxRetries; attempt++) {
try {
const response = await fetch(url, options);
return response;
} catch (error) {
lastError = error;
if (error.name === 'TimeoutError' || error.message.includes('timeout')) {
const delay = Math.min(backoffBase * Math.pow(2, attempt), maxBackoff);
this._log('warn', `Timeout, retrying in ${delay}ms (attempt ${attempt + 1})`);
await sleep(delay);
continue;
}
throw error;
}
}
throw lastError || new Error('Request failed after max retries');
}
async _fetchFromAPI(regionCode, maxResults, videoCategoryId = null, pageToken = null) {
if (!this.apiKey) {
throw new Error('API key is required');
}
const url = 'https://www.googleapis.com/youtube/v3/videos';
const params = new URLSearchParams({
part: 'snippet,statistics,contentDetails',
chart: 'mostPopular',
regionCode: regionCode.toUpperCase(),
maxResults: maxResults.toString(),
key: this.apiKey
});
if (videoCategoryId) {
params.append('videoCategoryId', videoCategoryId);
}
if (pageToken) {
params.append('pageToken', pageToken);
}
let lastError = null;
for (let attempt = 0; attempt < this.maxRetries; attempt++) {
try {
const response = await fetch(`${url}?${params}`, {
headers: { 'User-Agent': 'YouTubeTrendingCrawler/2.0' },
signal: AbortSignal.timeout(this.timeout)
});
if (!response.ok) {
const errorData = await response.json().catch(() => ({}));
const errorMessage = errorData.error?.message || response.statusText;
if (response.status === 400) {
throw new Error(`API error 400: Invalid request parameters. ${errorMessage}`);
} else if (response.status === 403) {
throw new Error(`API error 403: Invalid API key or quota exceeded. ${errorMessage}`);
} else if (response.status === 404) {
this._log('warn', `API error 404: Resource not found. ${errorMessage}`);
return { items: [], nextPageToken: null };
} else if (response.status === 429) {
const delay = Math.min(2000 * Math.pow(2, attempt), 60000);
this._log('warn', `API error 429: Rate limit exceeded. Retrying in ${delay}ms (attempt ${attempt + 1})`);
lastError = new Error(`API error 429: ${errorMessage}`);
await sleep(delay);
continue;
} else if (response.status === 500 || response.status === 502) {
if (attempt < 3) {
const delay = Math.min(2000 * Math.pow(2, attempt), 30000);
this._log('warn', `API error ${response.status}: Retrying in ${delay}ms (attempt ${attempt + 1})`);
await sleep(delay);
continue;
}
throw new Error(`API error ${response.status}: ${errorMessage}`);
} else if (response.status === 503) {
const delay = Math.min(5000 * Math.pow(2, attempt), 120000);
this._log('warn', `API error 503: Service unavailable. Retrying in ${delay}ms (attempt ${attempt + 1})`);
lastError = new Error(`API error 503: ${errorMessage}`);
await sleep(delay);
continue;
} else {
throw new Error(`API error ${response.status}: ${errorMessage}`);
}
}
const data = await response.json();
this._recordQuotaUsage(1);
return { items: data.items || [], nextPageToken: data.nextPageToken || null };
} catch (error) {
lastError = error;
if (error.message && (error.message.includes('400') || error.message.includes('403') || error.message.includes('404'))) {
throw error;
}
if (!error.message || (!error.message.includes('429') && !error.message.includes('503') && !error.message.includes('timeout'))) {
throw error;
}
}
}
throw lastError || new Error('API request failed after max retries');
}
async _fetchFromYTDLP(regionCode, maxResults) {
const url = regionCode === 'US'
? 'https://www.youtube.com/feed/trending'
: `https://www.youtube.com/feed/trending?gl=${regionCode}`;
const cmd = `yt-dlp --flat-playlist --playlist-end ${maxResults} -J "${url}" 2>/dev/null`;
try {
const output = execSync(cmd, { encoding: 'utf-8', timeout: this.timeout });
const data = JSON.parse(output);
if (!data.entries || !Array.isArray(data.entries)) {
throw new Error('Invalid yt-dlp response format');
}
const crawlTime = new Date().toISOString();
return data.entries.map(entry => ({
video_id: entry.id,
source_url: entry.webpage_url || `https://www.youtube.com/watch?v=${entry.id}`,
title: entry.title || 'Unknown Title',
channel_id: entry.channel_id || null,
channel_title: entry.uploader || entry.channel || 'Unknown Channel',
view_count: entry.view_count || 0,
like_count: entry.like_count || 0,
comment_count: entry.comment_count || 0,
published_at: entry.upload_date
? `${entry.upload_date.slice(0, 4)}-${entry.upload_date.slice(4, 6)}-${entry.upload_date.slice(6, 8)}T00:00:00Z`
: null,
thumbnail_url: entry.thumbnail ? entry.thumbnail.replace(/hqdefault/, 'hqdefault') : null,
category_id: null,
duration: entry.duration || null,
crawl_time: crawlTime
}));
} catch (error) {
throw new Error(`yt-dlp failed: ${error.message}`);
}
}
async _fetchFromInvidious(regionCode, maxResults) {
const url = `${this.invidiousInstance}/api/v1/trending?region=${regionCode.toUpperCase()}`;
try {
const response = await fetch(url, {
headers: { 'User-Agent': 'YouTubeTrendingCrawler/2.0' },
signal: AbortSignal.timeout(this.timeout)
});
if (!response.ok) {
throw new Error(`Invidious error ${response.status}: ${response.statusText}`);
}
const data = await response.json();
const items = Array.isArray(data) ? data : [];
const crawlTime = new Date().toISOString();
return items.slice(0, maxResults).map(entry => ({
video_id: entry.videoId,
source_url: `https://www.youtube.com/watch?v=${entry.videoId}`,
title: entry.title || 'Unknown Title',
channel_id: entry.authorId || null,
channel_title: entry.author || 'Unknown Channel',
view_count: entry.viewCount || 0,
like_count: entry.likeCount || 0,
comment_count: entry.commentCount || 0,
published_at: entry.publishedText ? null : null, // Textual only from Invidious basic
thumbnail_url: entry.videoThumbnails ? entry.videoThumbnails.find(t => t.quality === 'maxresdefault')?.url || entry.videoThumbnails[0]?.url : null,
category_id: null,
duration: entry.lengthSeconds || null,
crawl_time: crawlTime
}));
} catch (error) {
throw new Error(`Invidious failed: ${error.message}`);
}
}
async get_trending(regionCode = 'US', maxResults = 10, videoCategoryId = null) {
if (!this._validateRegionCode(regionCode)) {
throw new Error(`Invalid regionCode: ${regionCode}. Must be 2-letter ISO code.`);
}
if (!this._validateMaxResults(maxResults)) {
throw new Error(`Invalid maxResults: ${maxResults}. Must be between 1 and 50.`);
}
if (!this._validateCategoryId(videoCategoryId)) {
throw new Error(`Invalid videoCategoryId: ${videoCategoryId}.`);
}
const normalizedRegion = regionCode.toUpperCase();
// 缓存检查
const cacheKey = this._getCacheKey(normalizedRegion, videoCategoryId, maxResults);
const cached = this._getCached(cacheKey);
if (cached) {
this._log('info', `Cache hit for ${cacheKey}`);
return cached;
}
// Mock 模式
if (this.useMock) {
const data = this._getMockData(normalizedRegion, maxResults);
this._setCache(cacheKey, data);
return data;
}
// API
if (this.apiKey && this.getRemainingQuota() > 0) {
try {
const result = await this._fetchFromAPI(normalizedRegion, maxResults, videoCategoryId);
const videos = result.items.map(item => this.extract_video_info(item));
this._log('info', `API fetched ${videos.length} videos for ${normalizedRegion}`);
this._setCache(cacheKey, videos);
return videos;
} catch (error) {
this._log('warn', `API failed: ${error.message}`);
if (!this.enableFallback) throw error;
this._log('info', 'Falling back to yt-dlp...');
}
}
// yt-dlp
if (this.enableFallback) {
try {
const videos = await this._fetchFromYTDLP(normalizedRegion, maxResults);
this._log('info', `yt-dlp fetched ${videos.length} videos for ${normalizedRegion}`);
this._setCache(cacheKey, videos);
return videos;
} catch (error) {
this._log('warn', `yt-dlp failed: ${error.message}`);
if (!this.enableFallback) throw error;
this._log('info', 'Falling back to Invidious...');
}
}
// Invidious
try {
const videos = await this._fetchFromInvidious(normalizedRegion, maxResults);
this._log('info', `Invidious fetched ${videos.length} videos for ${normalizedRegion}`);
this._setCache(cacheKey, videos);
return videos;
} catch (error) {
this._log('error', `Invidious also failed: ${error.message}`);
throw new Error(`All data sources failed: ${error.message}`);
}
}
async get_multi_region_trending(regionCodes, maxResultsPerRegion = 10, videoCategoryId = null) {
if (!Array.isArray(regionCodes) || regionCodes.length === 0) {
throw new Error('regionCodes must be a non-empty array');
}
const uniqueRegions = [...new Set(regionCodes.map(r => r.toUpperCase()))];
const primaryRegions = ['US', 'JP', 'KR', 'GB', 'DE', 'FR', 'IN', 'BR', 'RU'];
const extendedRegions = [
'US', 'JP', 'KR', 'GB', 'DE', 'FR', 'IN', 'BR', 'RU',
'CA', 'AU', 'IT', 'ES', 'MX', 'NL', 'SE', 'NO', 'FI', 'DK',
'PL', 'TR', 'ID', 'TH', 'VN', 'PH', 'TW', 'HK', 'SG', 'MY',
'AR', 'CL', 'CO', 'ZA', 'EG', 'SA', 'AE', 'IL'
];
const estimatedQuota = uniqueRegions.length;
if (this.apiKey && this.getRemainingQuota() < estimatedQuota) {
this._log('warn', `Quota may be insufficient. Required: ${estimatedQuota}, Remaining: ${this.getRemainingQuota()}`);
}
this._log('info', `Fetching trending videos for ${uniqueRegions.length} regions`);
const results = {};
for (const region of uniqueRegions) {
try {
const videos = await this.get_trending(region, maxResultsPerRegion, videoCategoryId);
results[region] = videos;
this._log('info', `Fetched ${videos.length} videos for ${region}`);
} catch (error) {
this._log('error', `Failed to fetch for ${region}: ${error.message}`);
results[region] = [];
}
if (uniqueRegions.length > 1) {
await sleep(this.requestInterval);
}
}
return results;
}
save_to_json(data, filepath) {
if (!Array.isArray(data)) throw new Error('data must be an array');
const dir = path.dirname(filepath);
if (!fs.existsSync(dir)) fs.mkdirSync(dir, { recursive: true });
fs.writeFileSync(filepath, JSON.stringify(data, null, 2), 'utf-8');
this._log('info', `Saved ${data.length} records to ${filepath}`);
return filepath;
}
save_to_csv(data, filepath, delimiter = ',') {
if (!Array.isArray(data)) throw new Error('data must be an array');
const dir = path.dirname(filepath);
if (!fs.existsSync(dir)) fs.mkdirSync(dir, { recursive: true });
const columns = [
'video_id', 'source_url', 'title', 'channel_id', 'channel_title',
'view_count', 'like_count', 'comment_count', 'published_at',
'thumbnail_url', 'category_id', 'duration', 'crawl_time'
];
const header = columns.join(delimiter);
const rows = data.map(video => {
return columns.map(col => {
let value = video[col];
if (col === 'duration' && typeof value === 'number') value = value.toString();
if (typeof value === 'string' && (value.includes(delimiter) || value.includes('"') || value.includes('\n'))) {
value = `"${value.replace(/"/g, '""')}"`;
}
return value === null || value === undefined ? '' : value;
}).join(delimiter);
});
const content = [header, ...rows].join('\n');
fs.writeFileSync(filepath, '\ufeff' + content, 'utf-8');
this._log('info', `Saved ${data.length} records to ${filepath}`);
return filepath;
}
}
/**
* @param {Object} options
* @returns {Array}
*/
function getMockTrendingVideos(options = {}) {
const { regionCode = 'US', maxResults = 10 } = options;
const crawler = new YouTubeTrendingCrawler({ useMock: true });
return crawler._getMockData(regionCode, maxResults);
}
module.exports = { YouTubeTrendingCrawler, getMockTrendingVideos, parseISODuration };