import type { DocumentSource, FileInput } from './index.js';
import type { FileLoaderOptions } from './text.js';
/** An HTML page as text, with what a loader needs from its head and its links. */
export interface HtmlText {
    /** The readable text. Headings become Markdown `#` lines and list items `- ` lines. */
    text: string;
    /** The `<title>`. */
    title?: string;
    /** The `<meta name="description">`. */
    description?: string;
    /** Every `href` on an `<a>`, resolved against `baseUrl` when one is given. */
    links: string[];
}
/** Options for `htmlToText()`. */
export interface HtmlToTextOptions {
    /**
     * Keeps only `<main>`, or else `<article>`, when the page has one, dropping navigation, headers,
     * and footers. On by default.
     */
    mainContent?: boolean;
    /** Resolves relative links. */
    baseUrl?: string | URL;
}
/**
 * Turns HTML into readable text without a DOM: scripts, styles, and the head are dropped, block
 * elements become line breaks, headings become Markdown headings so `splitOnMarkdownHeadings` splits
 * a page at its sections, and entities are decoded. A heuristic, not a browser: it is built for pages
 * whose content is in the HTML, not rendered by script.
 */
export declare function htmlToText(html: string, options?: HtmlToTextOptions): HtmlText;
/** Options for `loadHtml()`. */
export interface HtmlLoaderOptions extends FileLoaderOptions, HtmlToTextOptions {
}
/** HTML files, one document each, with the page title and description in the metadata. */
export declare function loadHtml(inputs: FileInput | Iterable<FileInput>, options?: HtmlLoaderOptions): AsyncGenerator<DocumentSource>;