interface Candidate {
    score: number;
    elem: any;
}
/**
 * ### HTML-to-Main-Content Extractor #1
 * The function extracts main content with regex patterns, cleaning HTML, scoring nodes
 *  based on content indicators like paragraphs and id/class names, selecting
 *  the top candidate, extracting it, and cleaning up content around it.
 *
 *
 * 1. Define regular expressions:
 *    - Various regex patterns are defined to identify content and non-content areas.
 *
 * 2. Define helper functions:
 *    - normalizeSpaces: Normalizes whitespace in a string.
 *    - stripTags: Removes all HTML tags from a string.
 *    - getTextLength: Calculates the length of text after stripping tags.
 *    - calculateLinkDensity: Calculates the ratio of link text to total text.
 *
 * 3. Clean HTML:
 *    - Remove unlikely candidates (e.g., ads, sidebars) from the HTML.
 *
 * 4. Define scoring function:
 *    - scoreNode: Assigns a score to an HTML node based on content and attributes.
 *    - Increases score for positive indicators (e.g., article, body, content tags).
 *    - Decreases score for negative indicators (e.g., hidden, footer, sidebar tags).
 *    - Adds to score based on paragraph tags and text length.
 *
 * 5. Find and score candidate nodes:
 *    - Identify potential content nodes in the cleaned HTML.
 *    - Score each node using the scoreNode function.
 *
 * 6. Select top candidate:
 *    - Sort candidates by score and select the highest-scoring node.
 *
 * 7. Extract content:
 *    - Use regex to extract content around the top candidate node.
 *
 * 8. Clean up extracted content:
 *    - Remove script and style tags and their contents.
 *    - Process anchor tags based on content density.
 *    - Keep only specific HTML tags (a, p, img, h1-h6, ul, ol, li).
 *    - Remove excess whitespace from the final content.
 *
 * [Article Extraction Benchmark](https://trafilatura.readthedocs.io/en/latest/evaluation.html)
 *
 * @example
 * var url = "https://www.nytimes.com/2024/08/28/business/telegram-ceo-pavel-durov-charged.html"
 * const html = await (await fetch(url)).text();
 * var articleContent = extractMainContentFromHTML(html);
 * @param {Object} [options]
 * @param {number} options.minContentLength default=140 - Minimum length of content to be considered valid
 * @param {number} options.minScore default=20 - Minimum score for content to be considered valid
 * @param {number} options.minTextLength default=25 - Minimum length of text to be considered valid
 * @param {number} options.retryLength default=250 - Length to retry content extraction if initial attempt fails
 * @returns {string} Extracted HTML string of main content
 * @author [vtempest (2025)](https://github.com/vtempest)
 * Based on [Mozilla Readability (2015)](https://github.com/mozilla/readability)
 * @category Extract
 */
export declare function extractMainContentFromHTML(html: string, options?: {
    minContentLength?: number;
    minScore?: number;
    minTextLength?: number;
    retryLength?: number;
}): string;
/**
 * Calculates the link density of an element.
 * @param {Element} elem - The element to calculate link density for
 * @returns {number} The link density (ratio of link text length to total text length)
 */
export declare function getLinkDensity(elem: any): number;
/**
 * Calculates the weight of an element based on its class and id attributes.
 * @param {Element} elem - The element to calculate weight for
 * @param {RegExp} positiveRe - Regular expression for positive indicators
 * @param {RegExp} negativeRe - Regular expression for negative indicators
 * @returns {number} The calculated weight
 */
export declare function classWeight(elem: any, positiveRe: RegExp, negativeRe: RegExp): number;
/**
 * Scores a node based on its tag name and attributes.
 * @param {Element} elem - The element to score
 * @param {RegExp} positiveRe - Regular expression for positive indicators
 * @param {RegExp} negativeRe - Regular expression for negative indicators
 * @returns {Object} An object containing the score and the element
 */
export declare function scoreNode(elem: any, positiveRe: RegExp, negativeRe: RegExp): Candidate;
/**
 * Sanitizes the content by removing unwanted elements and cleaning remaining elements.
 * @param {Element} node - The node to sanitize
 * @param {Object} candidates - Object containing scored candidates
 * @param {RegExp} videoRe - Regular expression for video URLs
 * @param {RegExp} positiveRe - Regular expression for positive indicators
 * @param {RegExp} negativeRe - Regular expression for negative indicators
 * @param {number} minTextLength - Minimum text length to consider
 * @returns {Element} The sanitized node
 */
export declare function sanitize(node: any, candidates: Record<string, Candidate>, videoRe: RegExp, positiveRe: RegExp, negativeRe: RegExp, minTextLength: number): any;
export {};