@xapp/arachne-utils/lib/detectDocumentLinks.d.ts

/*! Copyright (c) 2025, XAPP AI */
import type { Page } from "puppeteer-core";
/**
 * Document type enumeration
 */
export type DocumentType = "PDF" | "MS_WORD" | "MS_EXCEL" | "PPT";
/**
 * Interface representing a document link detected on a page
 */
export interface DocumentLink {
    /**
     * The absolute URL to the document
     */
    url: string;
    /**
     * The type of document
     */
    type: DocumentType;
    /**
     * Optional title/text of the link
     */
    title?: string;
}
/**
 * All supported document extensions
 */
export declare const DOCUMENT_EXTENSIONS: string[];
/**
 * Detects document links on a page
 *
 * This function identifies document links by checking file extensions in both the pathname
 * and query parameters of URLs. It detects common document formats including PDF, Word,
 * Excel, and PowerPoint files.
 *
 * **Limitations**:
 * - Only detects documents with recognizable file extensions
 * - Does not detect documents served via content-type headers without extensions
 * - Does not make HEAD requests to verify content types
 *
 * @param page - The Puppeteer page to scan for document links
 * @param allowedTypes - Optional array of document types to filter by (e.g., ['PDF', 'MS_WORD'])
 * @returns Promise resolving to an array of detected document links
 *
 * @example
 * ```typescript
 * const documentLinks = await detectDocumentLinks(page);
 * // Returns all document links
 *
 * const pdfLinks = await detectDocumentLinks(page, ['PDF']);
 * // Returns only PDF links
 * ```
 */
export declare function detectDocumentLinks(page: Page, allowedTypes?: DocumentType[]): Promise<DocumentLink[]>;