batch_extract_timestamps

Instructions

Implementation Reference

• src/index.ts:159-209 (handler)

  Handler for the 'batch_extract_timestamps' tool. Parses arguments, validates URLs array, instantiates TimestampExtractor with optional config, concurrently extracts timestamps from each URL using Promise.allSettled, processes results including errors, and returns JSON-formatted array of results.

  if (name === 'batch_extract_timestamps') {
    const { urls, config } = args as {
      urls: string[];
      config?: {
        timeout?: number;
        userAgent?: string;
        followRedirects?: boolean;
        maxRedirects?: number;
        enableHeuristics?: boolean;
      };
    };
  
    if (!Array.isArray(urls) || urls.length === 0) {
      return {
        content: [
          {
            type: 'text',
            text: 'Error: URLs array is required and must not be empty',
          },
        ],
        isError: true,
      };
    }
  
    const timestampExtractor = config ? new TimestampExtractor(config) : extractor;
    const results = await Promise.allSettled(
      urls.map(url => timestampExtractor.extractTimestamps(url))
    );
  
    const processedResults = results.map((result, index) => {
      if (result.status === 'fulfilled') {
        return result.value;
      } else {
        return {
          url: urls[index],
          sources: [],
          confidence: 'low' as const,
          errors: [`Failed to extract timestamps: ${result.reason}`],
        };
      }
    });
  
    return {
      content: [
        {
          type: 'text',
          text: JSON.stringify(processedResults, null, 2),
        },
      ],
    };
  }

• src/index.ts:67-109 (registration)

  Registration of the 'batch_extract_timestamps' tool in the tools array returned by ListToolsRequestHandler, including detailed input schema for batch processing.

  {
    name: 'batch_extract_timestamps',
    description: 'Extract timestamps from multiple webpages in batch',
    inputSchema: {
      type: 'object',
      properties: {
        urls: {
          type: 'array',
          items: {
            type: 'string',
          },
          description: 'Array of URLs to extract timestamps from',
        },
        config: {
          type: 'object',
          description: 'Optional configuration for the extraction',
          properties: {
            timeout: {
              type: 'number',
              description: 'Request timeout in milliseconds (default: 10000)',
            },
            userAgent: {
              type: 'string',
              description: 'User agent string to use for requests',
            },
            followRedirects: {
              type: 'boolean',
              description: 'Whether to follow HTTP redirects (default: true)',
            },
            maxRedirects: {
              type: 'number',
              description: 'Maximum number of redirects to follow (default: 5)',
            },
            enableHeuristics: {
              type: 'boolean',
              description: 'Whether to enable heuristic timestamp detection (default: true)',
            },
          },
        },
      },
      required: ['urls'],
    },
  },

• src/index.ts:70-108 (schema)

  Input schema definition for the 'batch_extract_timestamps' tool, specifying required 'urls' array and optional 'config' object.

  inputSchema: {
    type: 'object',
    properties: {
      urls: {
        type: 'array',
        items: {
          type: 'string',
        },
        description: 'Array of URLs to extract timestamps from',
      },
      config: {
        type: 'object',
        description: 'Optional configuration for the extraction',
        properties: {
          timeout: {
            type: 'number',
            description: 'Request timeout in milliseconds (default: 10000)',
          },
          userAgent: {
            type: 'string',
            description: 'User agent string to use for requests',
          },
          followRedirects: {
            type: 'boolean',
            description: 'Whether to follow HTTP redirects (default: true)',
          },
          maxRedirects: {
            type: 'number',
            description: 'Maximum number of redirects to follow (default: 5)',
          },
          enableHeuristics: {
            type: 'boolean',
            description: 'Whether to enable heuristic timestamp detection (default: true)',
          },
        },
      },
    },
    required: ['urls'],
  },

• src/extractor.ts:19-56 (helper)

  Helper method in TimestampExtractor class that implements the core logic for extracting timestamps from a single webpage, used by both 'extract_timestamps' and 'batch_extract_timestamps' tools.

  async extractTimestamps(url: string): Promise<TimestampResult> {
    const errors: string[] = [];
    let fetchResult: FetchResult;
  
    try {
      fetchResult = await this.fetchPage(url);
    } catch (error) {
      return {
        url,
        sources: [],
        confidence: 'low',
        errors: [`Failed to fetch page: ${error instanceof Error ? error.message : String(error)}`],
      };
    }
  
    const $ = cheerio.load(fetchResult.html);
    const sources: TimestampSource[] = [];
  
    // Extract timestamps from various sources
    sources.push(...this.extractFromHtmlMeta($));
    sources.push(...this.extractFromHttpHeaders(fetchResult.headers));
    sources.push(...this.extractFromJsonLd($));
    sources.push(...this.extractFromMicrodata($));
    sources.push(...this.extractFromOpenGraph($));
    sources.push(...this.extractFromTwitterCards($));
    
    if (this.config.enableHeuristics) {
      sources.push(...this.extractFromHeuristics($));
    }
  
    const result = this.consolidateTimestamps(url, sources);
    
    if (errors.length > 0) {
      result.errors = errors;
    }
  
    return result;
  }