/**
 * Content Parser — HTML → Markdown article structure
 *
 * Handles:
 * - HTML cleaning (remove scripts, fix relative URLs)
 * - HTML → Markdown conversion (Turndown)
 * - Article structure extraction (title, breadcrumb, related articles)
 * - Search snippet cleaning
 */
import * as cheerio from 'cheerio';
/**
 * Clean HTML content: remove unwanted elements, fix relative URLs.
 */
export declare function cleanHtml($: cheerio.CheerioAPI): void;
export interface ParsedArticleContent {
    title: string;
    content: string;
    breadcrumb: string[];
    relatedArticles: {
        title: string;
        url: string;
    }[];
}
/**
 * Parse HTML into article structure (title, markdown content, breadcrumb).
 */
export declare function parseArticle(html: string, displayUrl: string, options?: {
    includeRelated?: boolean;
}): ParsedArticleContent;
/**
 * Clean an HTML search snippet: strip tags, clean breadcrumb prefixes.
 */
export declare function cleanSnippet(snippet: string, title: string, product: string | null): string;
/**
 * Convert raw HTML to Markdown using the shared Turndown instance.
 */
export declare function htmlToMarkdown(html: string): string;
//# sourceMappingURL=content-parser.d.ts.map