youtube_crawler.js 17 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
/**
 * YouTube Trending Crawler - Class-based Implementation
 * YouTube 热门视频爬虫 - 支持 API 和 yt-dlp 降级方案
 */

const { execSync } = require('child_process');
const fs = require('fs');
const path = require('path');

/**
 * YouTube 热门视频爬虫类
 * @class YouTubeTrendingCrawler
 */
class YouTubeTrendingCrawler {
  /**
   * 创建爬虫实例
   * @param {Object} options - 配置选项
   * @param {string} [options.apiKey] - YouTube Data API Key
   * @param {boolean} [options.useMock=false] - 是否使用 Mock 数据
   * @param {number} [options.timeout=30000] - 请求超时时间(毫秒)
   * @param {number} [options.maxRetries=3] - 最大重试次数
   * @param {boolean} [options.enableFallback=true] - 是否启用 yt-dlp 降级方案
   * @param {number} [options.quotaLimit=10000] - 每日 API 配额限制
   */
  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 || 3;
    this.enableFallback = options.enableFallback !== false;
    this.quotaLimit = options.quotaLimit || 10000;
    this.quotaUsed = 0;
    this.logs = [];

    this._log('info', 'YouTubeTrendingCrawler initialized');
  }

  /**
   * 内部日志记录方法
   * @private
   * @param {string} level - 日志级别 (info, warn, error)
   * @param {string} message - 日志消息
   */
  _log(level, message) {
    const entry = {
      timestamp: new Date().toISOString(),
      level,
      message
    };
    this.logs.push(entry);
  }

  /**
   * 获取所有日志
   * @returns {Array} 日志数组
   */
  getLogs() {
    return this.logs;
  }

  /**
   * 验证地区代码格式
   * @private
   * @param {string} code - 地区代码
   * @returns {boolean} 是否有效
   */
  _validateRegionCode(code) {
    if (!code || typeof code !== 'string') return false;
    return /^[A-Z]{2}$/.test(code.toUpperCase());
  }

  /**
   * 验证 maxResults 范围
   * @private
   * @param {number} maxResults - 最大结果数
   * @returns {boolean} 是否有效
   */
  _validateMaxResults(maxResults) {
    const num = parseInt(maxResults, 10);
    return !isNaN(num) && num >= 1 && num <= 50;
  }

  /**
   * 获取剩余 API 配额
   * @returns {number} 剩余配额
   */
  getRemainingQuota() {
    return this.quotaLimit - this.quotaUsed;
  }

  /**
   * 记录配额使用
   * @private
   * @param {number} units - 使用的配额单位数
   */
  _recordQuotaUsage(units = 1) {
    this.quotaUsed += units;
    this._log('info', `Quota used: ${this.quotaUsed}/${this.quotaLimit}`);
  }

  /**
   * 清理字符串
   * @private
   * @param {string} str - 输入字符串
   * @returns {string} 清理后的字符串
   */
  _cleanString(str) {
    if (!str || typeof str !== 'string') return '';
    return str.trim();
  }

  /**
   * 解析观看次数
   * @private
   * @param {string|number} viewCount - 观看次数
   * @returns {number} 解析后的数字
   */
  _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;
  }

  /**
   * 生成 Mock 数据
   * @private
   * @param {string} regionCode - 地区代码
   * @param {number} maxResults - 最大结果数
   * @returns {Array} Mock 视频数据数组
   */
  _getMockData(regionCode = 'US', maxResults = 10) {
    const baseVideos = [
      {
        videoId: 'mock_001',
        url: 'https://youtube.com/watch?v=mock_001',
        title: 'Mock Trending Video: Global Hits 2024',
        channelTitle: 'Mock Music Channel',
        viewCount: 12500000,
        publishedAt: '2024-03-15T10:00:00Z',
        thumbnails: {
          default: 'https://i.ytimg.com/vi/mock_001/default.jpg',
          medium: 'https://i.ytimg.com/vi/mock_001/mqdefault.jpg',
          high: 'https://i.ytimg.com/vi/mock_001/hqdefault.jpg'
        },
        categoryId: '10'
      },
      {
        videoId: 'mock_002',
        url: 'https://youtube.com/watch?v=mock_002',
        title: 'Mock Gaming: Speedrun World Record',
        channelTitle: 'Mock Gaming',
        viewCount: 3200000,
        publishedAt: '2024-03-14T08:30:00Z',
        thumbnails: {
          default: 'https://i.ytimg.com/vi/mock_002/default.jpg',
          medium: 'https://i.ytimg.com/vi/mock_002/mqdefault.jpg',
          high: 'https://i.ytimg.com/vi/mock_002/hqdefault.jpg'
        },
        categoryId: '20'
      },
      {
        videoId: 'mock_003',
        url: 'https://youtube.com/watch?v=mock_003',
        title: 'Mock Tech Review: Latest Smartphone',
        channelTitle: 'Mock Tech',
        viewCount: 1800000,
        publishedAt: '2024-03-13T14:00:00Z',
        thumbnails: {
          default: 'https://i.ytimg.com/vi/mock_003/default.jpg',
          medium: 'https://i.ytimg.com/vi/mock_003/mqdefault.jpg',
          high: 'https://i.ytimg.com/vi/mock_003/hqdefault.jpg'
        },
        categoryId: '28'
      },
      {
        videoId: 'mock_004',
        url: 'https://youtube.com/watch?v=mock_004',
        title: 'Mock Comedy: Stand-up Special',
        channelTitle: 'Mock Comedy Central',
        viewCount: 5400000,
        publishedAt: '2024-03-12T20:00:00Z',
        thumbnails: {
          default: 'https://i.ytimg.com/vi/mock_004/default.jpg',
          medium: 'https://i.ytimg.com/vi/mock_004/mqdefault.jpg',
          high: 'https://i.ytimg.com/vi/mock_004/hqdefault.jpg'
        },
        categoryId: '23'
      },
      {
        videoId: 'mock_005',
        url: 'https://youtube.com/watch?v=mock_005',
        title: 'Mock Education: How Quantum Computers Work',
        channelTitle: 'Mock Education',
        viewCount: 890000,
        publishedAt: '2024-03-11T09:00:00Z',
        thumbnails: {
          default: 'https://i.ytimg.com/vi/mock_005/default.jpg',
          medium: 'https://i.ytimg.com/vi/mock_005/mqdefault.jpg',
          high: 'https://i.ytimg.com/vi/mock_005/hqdefault.jpg'
        },
        categoryId: '27'
      }
    ];

    return baseVideos.slice(0, maxResults).map(v => ({
      ...v,
      _mockRegion: regionCode.toUpperCase()
    }));
  }

  /**
   * 从 API 响应中提取视频信息
   * @param {Object} apiItem - YouTube API 返回的视频项
   * @returns {Object} 标准化的视频信息对象
   */
  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 thumbnails = snippet.thumbnails || {};

    return {
      videoId: videoId,
      url: `https://youtube.com/watch?v=${videoId}`,
      title: this._cleanString(snippet.title) || 'Unknown Title',
      channelTitle: this._cleanString(snippet.channelTitle) || 'Unknown Channel',
      viewCount: this._parseViewCount(statistics.viewCount),
      publishedAt: snippet.publishedAt || null,
      thumbnails: {
        default: thumbnails.default?.url || null,
        medium: thumbnails.medium?.url || null,
        high: thumbnails.high?.url || null
      },
      categoryId: snippet.categoryId || null
    };
  }

  /**
   * 使用 YouTube Data API 获取热门视频
   * @private
   */
  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',
      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}`, {
          signal: AbortSignal.timeout(this.timeout)
        });

        if (!response.ok) {
          const errorData = await response.json().catch(() => ({}));
          const errorMessage = errorData.error?.message || response.statusText;

          if (response.status === 403) {
            throw new Error(`API error 403: Invalid API key or quota exceeded. ${errorMessage}`);
          } else if (response.status === 429) {
            this._log('warn', `API error 429: Retrying... (attempt ${attempt + 1})`);
            lastError = new Error(`API error 429: ${errorMessage}`);
            await new Promise(r => setTimeout(r, Math.pow(2, attempt) * 1000));
            continue;
          } else if (response.status === 400) {
            throw new Error(`API error 400: Invalid request parameters. ${errorMessage}`);
          } 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.name === 'TimeoutError' || error.message.includes('timeout')) {
          this._log('warn', `Request timeout, retrying... (attempt ${attempt + 1})`);
          await new Promise(r => setTimeout(r, Math.pow(2, attempt) * 1000));
        } else if (!error.message.includes('429')) {
          throw error;
        }
      }
    }

    throw lastError || new Error('API request failed after max retries');
  }

  /**
   * 使用 yt-dlp 获取热门视频 (降级方案)
   * @private
   */
  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');
      }

      return data.entries.map(entry => ({
        videoId: entry.id,
        url: entry.webpage_url || `https://youtube.com/watch?v=${entry.id}`,
        title: entry.title || 'Unknown Title',
        channelTitle: entry.uploader || entry.channel || 'Unknown Channel',
        viewCount: entry.view_count || 0,
        publishedAt: entry.upload_date
          ? `${entry.upload_date.slice(0, 4)}-${entry.upload_date.slice(4, 6)}-${entry.upload_date.slice(6, 8)}T00:00:00Z`
          : null,
        thumbnails: {
          default: entry.thumbnail ? entry.thumbnail.replace(/hqdefault/, 'default') : null,
          medium: entry.thumbnail ? entry.thumbnail.replace(/hqdefault/, 'mqdefault') : null,
          high: entry.thumbnail || null
        },
        categoryId: null
      }));
    } catch (error) {
      throw new Error(`yt-dlp failed: ${error.message}`);
    }
  }

  /**
   * 获取单地区热门视频
   * @param {string} regionCode - 地区代码 (如 'US', 'JP')
   * @param {number} [maxResults=10] - 最大结果数 (1-50)
   * @param {string|null} [videoCategoryId=null] - 视频分类 ID
   * @returns {Promise<Array>} 视频数据数组
   */
  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.`);
    }

    const normalizedRegion = regionCode.toUpperCase();
    this._log('info', `Fetching trending videos for region: ${normalizedRegion}`);

    // Mock 模式
    if (this.useMock) {
      return this._getMockData(normalizedRegion, maxResults);
    }

    // 优先尝试 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', `Successfully fetched ${videos.length} videos from API`);
        return videos;
      } catch (error) {
        this._log('warn', `API failed: ${error.message}`);
        if (!this.enableFallback) {
          throw error;
        }
        this._log('info', 'Falling back to yt-dlp...');
      }
    }

    // 降级到 yt-dlp
    if (this.enableFallback) {
      try {
        const videos = await this._fetchFromYTDLP(normalizedRegion, maxResults);
        this._log('info', `Successfully fetched ${videos.length} videos from yt-dlp`);
        return videos;
      } catch (error) {
        this._log('error', `yt-dlp also failed: ${error.message}`);
        throw error;
      }
    }

    throw new Error('No available data source');
  }

  /**
   * 获取多地区热门视频
   * @param {Array<string>} regionCodes - 地区代码数组
   * @param {number} [maxResultsPerRegion=10] - 每个地区的最大结果数
   * @param {string|null} [videoCategoryId=null] - 视频分类 ID
   * @returns {Promise<Object>} 以地区代码为键的结果对象
   */
  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 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}`);

        if (uniqueRegions.length > 1) {
          await new Promise(r => setTimeout(r, 100));
        }
      } catch (error) {
        this._log('error', `Failed to fetch for ${region}: ${error.message}`);
        results[region] = [];
      }
    }

    return results;
  }

  /**
   * 保存数据为 JSON 文件
   * @param {Array} data - 视频数据数组
   * @param {string} filepath - 文件路径
   * @returns {string} 保存的文件路径
   */
  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;
  }

  /**
   * 保存数据为 CSV 文件
   * @param {Array} data - 视频数据数组
   * @param {string} filepath - 文件路径
   * @returns {string} 保存的文件路径
   */
  save_to_csv(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 });
    }

    const columns = ['videoId', 'url', 'title', 'channelTitle', 'viewCount', 'thumbnails', 'publishedAt', 'categoryId'];

    const header = columns.join(',');
    const rows = data.map(video => {
      return columns.map(col => {
        let value = video[col];
        if (col === 'thumbnails' && typeof value === 'object') {
          value = JSON.stringify(value);
        }
        if (typeof value === 'string' && (value.includes(',') || value.includes('"') || value.includes('\n'))) {
          value = `"${value.replace(/"/g, '""')}"`;
        }
        return value === null || value === undefined ? '' : value;
      }).join(',');
    });

    const content = [header, ...rows].join('\n');
    fs.writeFileSync(filepath, '\ufeff' + content, 'utf-8');
    this._log('info', `Saved ${data.length} records to ${filepath}`);
    return filepath;
  }
}

/**
 * 获取 Mock 视频数据(独立函数)
 * @param {Object} options - 选项
 * @param {string} [options.regionCode='US'] - 地区代码
 * @param {number} [options.maxResults=10] - 返回数量
 * @returns {Array} Mock 视频数据
 */
function getMockTrendingVideos(options = {}) {
  const { regionCode = 'US', maxResults = 10 } = options;
  const crawler = new YouTubeTrendingCrawler({ useMock: true });
  return crawler._getMockData(regionCode, maxResults);
}

module.exports = {
  YouTubeTrendingCrawler,
  getMockTrendingVideos
};