a11yanalyze/dist/scanner/site-crawler.d.ts

A command-line tool for developers and QA engineers to test web pages and websites for WCAG 2.2 AA accessibility compliance

import { EventEmitter } from 'events';
import { CrawlerConfig, CrawlSession, CrawlProgress } from '../types/crawler';
import { ScanOptions, BrowserConfig, RuleEngineConfig } from '../types';
import { WCAGLevelConfig } from './wcag-level-handler';
import { ResilienceConfig } from './error-resilience';
/**
 * Site crawler for multi-page accessibility scanning
 * Provides crawling capabilities with depth limits, domain restrictions, and rate limiting
 */
export declare class SiteCrawler extends EventEmitter {
    private pageScanner;
    private session;
    private isRunning;
    private isPaused;
    private abortController;
    private activeRequests;
    private requestQueue;
    private lastRequestTime;
    private robotsCache;
    private sitemapCache;
    constructor(browserConfig?: BrowserConfig, ruleEngineConfig?: RuleEngineConfig, resilienceConfig?: Partial<ResilienceConfig>, wcagLevelConfig?: Partial<WCAGLevelConfig>);
    /**
     * Start a new crawl session
     */
    startCrawl(startUrls: string[], config?: Partial<CrawlerConfig>, scanOptions?: Partial<ScanOptions>): Promise<string>;
    /**
     * Pause the current crawl session
     */
    pauseCrawl(): Promise<void>;
    /**
     * Resume the paused crawl session
     */
    resumeCrawl(): Promise<void>;
    /**
     * Stop the current crawl session
     */
    stopCrawl(): Promise<void>;
    /**
     * Get current crawl progress
     */
    getProgress(): CrawlProgress | null;
    /**
     * Get current session information
     */
    getSession(): CrawlSession | null;
    /**
     * Main crawling process
     * @private
     */
    private crawlAsync;
    /**
     * Initialize URLs from start URLs
     * @private
     */
    private initializeUrls;
    /**
     * Main URL crawling loop
     * @private
     */
    private crawlUrls;
    /**
     * Process a single URL
     * @private
     */
    private processUrl;
    /**
     * Discover URLs from a scanned page
     * @private
     */
    private discoverUrlsFromPage;
    /**
     * Extract URLs from a page
     * @private
     */
    private extractUrlsFromPage;
    /**
     * Check if URL should be processed
     * @private
     */
    private shouldProcessUrl;
    /**
     * Check if URL should be added to crawl queue
     * @private
     */
    private shouldAddUrl;
    /**
     * Discover URLs from sitemaps
     * @private
     */
    private discoverFromSitemaps;
    /**
     * Fetch and parse sitemap
     * @private
     */
    private fetchSitemap;
    /**
     * Apply rate limiting
     * @private
     */
    private applyRateLimit;
    /**
     * Get next URL to process
     * @private
     */
    private getNextUrl;
    /**
     * Check if there's more work to do
     * @private
     */
    private hasWorkToDo;
    /**
     * Wait for all active requests to complete
     * @private
     */
    private waitForActiveRequests;
    /**
     * Validate start URLs
     * @private
     */
    private validateStartUrls;
    /**
     * Create default crawler configuration
     * @private
     */
    private createDefaultConfig;
    /**
     * Create initial statistics
     * @private
     */
    private createInitialStats;
    /**
     * Update statistics
     * @private
     */
    private updateStats;
    /**
     * Update statistics for completed URL
     * @private
     */
    private updateStatsForCompletedUrl;
    /**
     * Handle crawl errors
     * @private
     */
    private handleCrawlError;
    /**
     * Emit crawl event
     * @private
     */
    private emitEvent;
    /**
     * Get current crawl depth
     * @private
     */
    private getCurrentDepth;
    /**
     * Get current URL being processed
     * @private
     */
    private getCurrentUrl;
    /**
     * Get recent errors
     * @private
     */
    private getRecentErrors;
    /**
     * Generate session ID
     * @private
     */
    private generateSessionId;
    /**
     * Sleep for specified duration
     * @private
     */
    private sleep;
    /**
     * Cleanup resources
     * @private
     */
    private cleanup;
}
//# sourceMappingURL=site-crawler.d.ts.map