html-content-processor/dist/convenience-api.d.ts

A professional library for processing, cleaning, filtering, and converting HTML content to Markdown. Features advanced customization options, presets, plugin support, fluent API, and TypeScript integration for reliable content extraction.

import { HtmlProcessor } from './html-processor';
import { ConvertOptions, ProcessorOptions, FilterOptions } from './types';
import { MarkdownResult } from './types';
/**
 * Convert HTML to Markdown with optional configuration
 * @param html HTML content to convert
 * @param options Conversion options
 * @returns Markdown string
 */
export declare function htmlToMarkdown(html: string, options?: ConvertOptions): Promise<string>;
/**
 * Convert HTML to Markdown with citations
 * @param html HTML content to convert
 * @param baseUrl Base URL for resolving relative links
 * @param options Conversion options
 * @returns Markdown string with citations
 */
export declare function htmlToMarkdownWithCitations(html: string, baseUrl?: string, options?: ConvertOptions): Promise<string>;
/**
 * Convert HTML to plain text
 * @param html HTML content to convert
 * @param options Filter options
 * @returns Plain text string
 */
export declare function htmlToText(html: string, options?: FilterOptions): Promise<string>;
/**
 * Clean HTML by removing unwanted elements and content
 * @param html HTML content to clean
 * @param options Filter options
 * @returns Cleaned HTML string
 */
export declare function cleanHtml(html: string, options?: FilterOptions): Promise<string>;
/**
 * Extract main content from HTML as array of fragments
 * @param html HTML content to process
 * @param options Filter options
 * @returns Array of HTML content fragments
 */
export declare function extractContent(html: string, options?: FilterOptions): Promise<string[]>;
/**
 * Convert HTML to Markdown using article preset (optimized for long-form content)
 * @param html HTML content to convert
 * @param baseUrl Base URL for resolving relative links
 * @returns Markdown string
 */
export declare function htmlToArticleMarkdown(html: string, baseUrl?: string): Promise<string>;
/**
 * Convert HTML to Markdown using blog preset (optimized for blog posts)
 * @param html HTML content to convert
 * @param baseUrl Base URL for resolving relative links
 * @returns Markdown string
 */
export declare function htmlToBlogMarkdown(html: string, baseUrl?: string): Promise<string>;
/**
 * Convert HTML to Markdown using news preset (optimized for news articles)
 * @param html HTML content to convert
 * @param baseUrl Base URL for resolving relative links
 * @returns Markdown string
 */
export declare function htmlToNewsMarkdown(html: string, baseUrl?: string): Promise<string>;
/**
 * Quick and aggressive HTML cleaning using strict preset
 * @param html HTML content to clean
 * @returns Cleaned HTML string
 */
export declare function strictCleanHtml(html: string): Promise<string>;
/**
 * Gentle HTML cleaning using loose preset
 * @param html HTML content to clean
 * @returns Cleaned HTML string
 */
export declare function gentleCleanHtml(html: string): Promise<string>;
/**
 * Create a processor instance with custom configuration
 * @param options Processor configuration options
 * @returns Configured HtmlProcessor instance
 */
export declare function createProcessor(options?: ProcessorOptions): HtmlProcessor;
/**
 * Convert HTML to Markdown with automatic page type detection
 * @param html HTML content
 * @param url Optional URL for better detection accuracy
 * @param options Additional processing options
 * @returns Markdown result
 */
export declare function htmlToMarkdownAuto(html: string, url?: string, options?: Partial<ProcessorOptions>): Promise<MarkdownResult>;
/**
 * Clean HTML with automatic page type detection
 * @param html HTML content
 * @param url Optional URL for better detection accuracy
 * @param options Additional processing options
 * @returns Clean HTML string
 */
export declare function cleanHtmlAuto(html: string, url?: string, options?: Partial<ProcessorOptions>): Promise<string>;
/**
 * Extract content with automatic page type detection and return detailed result
 * @param html HTML content
 * @param url Optional URL for better detection accuracy
 * @param options Additional processing options
 * @returns Detailed extraction result with page type information
 */
export declare function extractContentAuto(html: string, url?: string, options?: Partial<ProcessorOptions>): Promise<{
    markdown: MarkdownResult;
    pageType: import('./page-type-detector').PageTypeResult | null;
    cleanHtml: string;
}>;