defuddle/dist/defuddle.d.ts

Extract article content and metadata from web pages.

import { DefuddleOptions, DefuddleResponse } from './types';
export declare class Defuddle {
    private readonly doc;
    private options;
    private debug;
    /**
     * Create a new Defuddle instance
     * @param doc - The document to parse
     * @param options - Options for parsing
     */
    constructor(doc: Document, options?: DefuddleOptions);
    /**
     * Parse the document and extract its main content
     */
    parse(): DefuddleResponse;
    /**
     * Internal parse method that does the actual work
     */
    private parseInternal;
    private countWords;
    private _log;
    private _evaluateMediaQueries;
    private applyMobileStyles;
    private removeHiddenElements;
    private removeBySelector;
    private findSmallImages;
    private removeSmallImages;
    private getElementIdentifier;
    private findMainContent;
    private findTableBasedContent;
    private findContentByScoring;
    private getElementSelector;
    private getComputedStyle;
    private _extractSchemaOrgData;
    private _decodeHTMLEntities;
}