@crawlee/utils/internals/sitemap.d.ts

A set of shared utilities that can be used by crawlers

// @ts-ignore optional peer dependency or compatibility with es2022
import type { Delays } from 'got-scraping';
interface SitemapUrlData {
    loc: string;
    lastmod?: Date;
    changefreq?: 'always' | 'hourly' | 'daily' | 'weekly' | 'monthly' | 'yearly' | 'never';
    priority?: number;
}
export type SitemapUrl = SitemapUrlData & {
    originSitemapUrl: string;
};
interface NestedSitemap {
    loc: string;
    originSitemapUrl: null;
}
type SitemapSource = ({
    type: 'url';
    url: string;
} | {
    type: 'raw';
    content: string;
}) & {
    depth?: number;
};
export interface ParseSitemapOptions {
    /**
     * If set to `true`, elements referring to other sitemaps will be emitted as special objects with `originSitemapUrl` set to `null`.
     */
    emitNestedSitemaps?: true | false;
    /**
     * Maximum depth of nested sitemaps to follow.
     */
    maxDepth?: number;
    /**
     * Number of retries for fetching sitemaps. The counter resets for each nested sitemap.
     */
    sitemapRetries?: number;
    /**
     * Network timeouts for sitemap fetching. See [Got documentation](https://github.com/sindresorhus/got/blob/main/documentation/6-timeout.md) for more details.
     */
    networkTimeouts?: Delays;
    /**
     * If true, the parser will log a warning if it fails to fetch a sitemap due to a network error
     * @default true
     */
    reportNetworkErrors?: boolean;
}
export declare function parseSitemap<T extends ParseSitemapOptions>(initialSources: SitemapSource[], proxyUrl?: string, options?: T): AsyncIterable<T['emitNestedSitemaps'] extends true ? SitemapUrl | NestedSitemap : SitemapUrl>;
/**
 * Loads one or more sitemaps from given URLs, following references in sitemap index files, and exposes the contained URLs.
 *
 * **Example usage:**
 * ```javascript
 * // Load a sitemap
 * const sitemap = await Sitemap.load(['https://example.com/sitemap.xml', 'https://example.com/sitemap_2.xml.gz']);
 *
 * // Enqueue all the contained URLs (including those from sub-sitemaps from sitemap indexes)
 * await crawler.addRequests(sitemap.urls);
 * ```
 */
export declare class Sitemap {
    readonly urls: string[];
    constructor(urls: string[]);
    /**
     * Try to load sitemap from the most common locations - `/sitemap.xml` and `/sitemap.txt`.
     * For loading based on `Sitemap` entries in `robots.txt`, the {@link RobotsTxtFile} class should be used.
     * @param url The domain URL to fetch the sitemap for.
     * @param proxyUrl A proxy to be used for fetching the sitemap file.
     */
    static tryCommonNames(url: string, proxyUrl?: string): Promise<Sitemap>;
    /**
     * Fetch sitemap content from given URL or URLs and return URLs of referenced pages.
     * @param urls sitemap URL(s)
     * @param proxyUrl URL of a proxy to be used for fetching sitemap contents
     */
    static load(urls: string | string[], proxyUrl?: string, parseSitemapOptions?: ParseSitemapOptions): Promise<Sitemap>;
    /**
     * Parse XML sitemap content from a string and return URLs of referenced pages. If the sitemap references other sitemaps, they will be loaded via HTTP.
     * @param content XML sitemap content
     * @param proxyUrl URL of a proxy to be used for fetching sitemap contents
     */
    static fromXmlString(content: string, proxyUrl?: string): Promise<Sitemap>;
    protected static parse(sources: SitemapSource[], proxyUrl?: string, parseSitemapOptions?: ParseSitemapOptions): Promise<Sitemap>;
}
export {};
//# sourceMappingURL=sitemap.d.ts.map