/**
 * Core web clipper for converting web pages to markdown.
 *
 * @file Implements multiple extraction strategies for different types of web content
 *
 * @category Core
 */
/**
 * Extraction strategies for different types of content.
 *
 * @category Core
 */
export type ExtractionStrategy = "auto" | "readability" | "manual" | "full" | "structured" | "headless";
/**
 * Image handling strategies.
 *
 * @category Core
 */
type ImageStrategy = "skip" | "link-only" | "download" | "base64";
/**
 * Options for web clipping operations.
 *
 * @category Core
 */
export interface WebClipperOptions {
    /** Extraction strategy to use */
    strategy?: ExtractionStrategy;
    /** How to handle images */
    imageStrategy?: ImageStrategy;
    /** Directory to save downloaded images */
    imageDir?: string;
    /** Custom CSS selectors for manual extraction */
    selectors?: string[];
    /** Include metadata in frontmatter */
    includeFrontmatter?: boolean;
    /** Request timeout in milliseconds */
    timeout?: number;
    /** Custom User-Agent string */
    userAgent?: string;
    /** Custom HTTP headers */
    headers?: Record<string, string>;
    /** Path to cookies file */
    cookiesFile?: string;
    /** Follow redirects */
    followRedirects?: boolean;
    /** Maximum redirects to follow */
    maxRedirects?: number;
    /** Show detailed output */
    verbose?: boolean;
    /** Show what would be done without doing it */
    dryRun?: boolean;
}
/**
 * Result of a web clipping operation.
 *
 * @category Core
 */
export interface ClipResult {
    /** Generated markdown content */
    markdown: string;
    /** Extracted title */
    title?: string;
    /** Extracted author */
    author?: string;
    /** Published date */
    publishedDate?: string;
    /** Description/excerpt */
    description?: string;
    /** Source URL */
    sourceUrl: string;
    /** Extraction strategy used */
    strategy: ExtractionStrategy;
    /** Images found and processed */
    images: {
        originalUrl: string;
        localPath?: string;
        alt: string | undefined;
        processed: boolean;
    }[];
    /** Links found in content */
    links: {
        url: string;
        text: string;
        type: "internal" | "external";
    }[];
    /** Structured data found */
    structuredData?: Record<string, unknown>;
}
/**
 * Core web clipper class with multiple extraction strategies.
 *
 * Provides comprehensive web page to markdown conversion with support for different content types,
 * extraction strategies, and output formats.
 *
 * @category Core
 *
 * @example
 *   Basic usage
 *   ```typescript
 *   const clipper = new WebClipper({
 *   strategy: 'readability',
 *   imageStrategy: 'download'
 *   });
 *
 *   const result = await clipper.clip('https://example.com/article');
 *   console.log(result.markdown);
 *   ```
 *
 * @example
 *   Custom extraction
 *   ```typescript
 *   const clipper = new WebClipper({
 *   strategy: 'manual',
 *   selectors: ['article', '.content', 'main']
 *   });
 *
 *   const result = await clipper.clip('https://docs.example.com');
 *   ```
 */
export declare class WebClipper {
    private options;
    private turndown;
    constructor(options?: WebClipperOptions);
    /**
     * Clip a web page to markdown.
     *
     * @param url - URL to clip
     *
     * @returns Promise resolving to clip result
     */
    clip(url: string): Promise<ClipResult>;
    /**
     * Fetch HTML content from a URL.
     *
     * @private
     */
    private fetchHtml;
    /**
     * Determine the best extraction strategy for content.
     *
     * @private
     */
    private determineStrategy;
    /**
     * Extract content using the specified strategy.
     *
     * @private
     */
    private extractContent;
    /**
     * Extract content using Mozilla Readability.
     *
     * @private
     */
    private extractWithReadability;
    /**
     * Extract content using custom selectors.
     *
     * @private
     */
    private extractWithSelectors;
    /**
     * Extract full page content.
     *
     * @private
     */
    private extractFullPage;
    /**
     * Extract content using structured data.
     *
     * @private
     */
    private extractStructured;
    /**
     * Extract title from HTML.
     *
     * @private
     */
    private extractTitle;
    /**
     * Extract author from HTML.
     *
     * @private
     */
    private extractAuthor;
    /**
     * Extract published date from HTML.
     *
     * @private
     */
    private extractPublishedDate;
    /**
     * Extract description from HTML.
     *
     * @private
     */
    private extractDescription;
    /**
     * Extract images from content.
     *
     * @private
     */
    private extractImages;
    /**
     * Extract links from content.
     *
     * @private
     */
    private extractLinks;
    /**
     * Process images according to the image strategy.
     *
     * @private
     */
    private processImages;
    /**
     * Generate final markdown content.
     *
     * @private
     */
    private generateMarkdown;
    /**
     * Generate frontmatter for the markdown file.
     *
     * @private
     */
    private generateFrontmatter;
    /**
     * Configure Turndown service for HTML to Markdown conversion.
     *
     * @private
     */
    private configureTurndown;
    /**
     * Resolve a URL relative to a base URL.
     *
     * @private
     */
    private resolveUrl;
    /**
     * Check if a URL is internal to the base domain.
     *
     * @private
     */
    private isInternalLink;
}
export {};
//# sourceMappingURL=web-clipper.d.ts.map