/**
 * HTML content extractor.
 *
 * Extracts clean text content from HTML pages and converts to Markdown.
 * Includes Divi-specific handling for WordPress + Divi page builder sites.
 */
import type { ExtractedPage, ExtractorOptions, PreprocessorOptions } from './types.js';
/**
 * Extended extractor options including preprocessing.
 */
export interface ExtendedExtractorOptions extends ExtractorOptions {
    /** Preprocessing options for content cleaning */
    preprocessing?: PreprocessorOptions;
    /** Enable deduplication of repeated content blocks */
    deduplicate?: boolean;
    /** Remove elements hidden via inline styles */
    removeHiddenElements?: boolean;
}
/**
 * Default extractor options (Divi-optimized).
 */
export declare const DEFAULT_EXTRACTOR_OPTIONS: ExtendedExtractorOptions;
/**
 * Extract content from HTML page and convert to Markdown.
 *
 * @param html - Raw HTML content
 * @param url - Page URL (used for title extraction and metadata)
 * @param options - Extractor options
 * @returns Extracted page with title and Markdown content
 */
export declare function extractContent(html: string, url: string, options?: Partial<ExtendedExtractorOptions>): ExtractedPage;
/**
 * Check if extracted content is meaningful (not just boilerplate or empty).
 */
export declare function isContentMeaningful(content: string): boolean;
//# sourceMappingURL=extractor.d.ts.map