@crawlee/core 4.0.0-beta.99 → 4.0.0-rc.1

package/crawlers/crawler_commons.d.ts

@@ -1,257 +0,0 @@
-import type { Dictionary, HttpRequestOptions, ISession, ProxyInfo, SendRequestOptions } from '@crawlee/types';
-import type { ReadonlyDeep, SetRequired } from 'type-fest';
-import type { Configuration } from '../configuration.js';
-import type { EnqueueLinksOptions } from '../enqueue_links/enqueue_links.js';
-import type { CrawleeLogger } from '../log.js';
-import type { Request, RequestOptions, Source } from '../request.js';
-import type { StorageIdentifier } from '../storages/storage_instance_manager.js';
-import type { Dataset } from '../storages/dataset.js';
-import { KeyValueStore, type RecordOptions } from '../storages/key_value_store.js';
-import type { RequestQueueOperationOptions } from '../storages/request_queue.js';
-/** @internal */
-export type IsAny<T> = 0 extends 1 & T ? true : false;
-/**
- * A request input (URL string, request-options object, or {@link Request}) whose `userData` is typed
- * according to its `label`, based on a router's route map.
- *
- * When the route map is open (the default `Record<string, ...>`), this is just the regular loose
- * {@link Source} input. When the map declares concrete labels, providing a `label` requires the matching
- * `userData` shape and rejects labels not present in the map; unlabeled requests keep loose `userData`.
- */
-export type LabeledSource<Routes extends Record<keyof Routes, Dictionary>> = string extends keyof Routes ? string | Source : string | Request | ({
-    requestsFromUrl?: string;
-    regex?: RegExp;
-} & ({
-    [Label in keyof Routes & string]: Omit<Partial<RequestOptions<Routes[Label]>>, 'label'> & {
-        label: Label;
-    };
-}[keyof Routes & string] | (Omit<Partial<RequestOptions>, 'label'> & {
-    label?: undefined;
-})));
-/**
- * The iterable/array of {@link LabeledSource} inputs accepted by the label-aware `addRequests`/`run`
- * methods of a crawler bound to a typed router.
- * @internal
- */
-export type TypedRequestsLike<Routes extends Record<keyof Routes, Dictionary>> = AsyncIterable<LabeledSource<Routes>> | Iterable<LabeledSource<Routes>> | LabeledSource<Routes>[];
-/**
- * The label-aware `addRequests` method signature exposed on a request handler's context when the crawler is
- * bound to a typed router. Mirrors {@link RestrictedCrawlingContext.addRequests} with typed sources.
- */
-export type TypedContextAddRequests<Routes extends Record<keyof Routes, Dictionary>> = (requestsLike: ReadonlyDeep<LabeledSource<Routes>[]>, options?: ReadonlyDeep<RequestQueueOperationOptions>) => Promise<void>;
-/**
- * An `enqueueLinks`-options object with its `label`/`userData` retyped according to a router's route map: a
- * declared `label` requires the matching `userData` shape (unknown labels are rejected), while unlabeled
- * calls keep loose `userData`. Returns the options unchanged when the route map is open (the default).
- */
-type TypedEnqueueLinksOptions<Options, Routes extends Record<keyof Routes, Dictionary>> = string extends keyof Routes ? Options : Omit<Options, 'label' | 'userData'> & ({
-    [Label in keyof Routes & string]: {
-        label: Label;
-        userData?: Routes[Label];
-    };
-}[keyof Routes & string] | {
-    label?: undefined;
-    userData?: Dictionary;
-});
-/**
- * Transforms a context's existing `enqueueLinks` method so that the `label`/`userData` in its options follow
- * the router's route map, while preserving everything else about the signature (argument optionality and
- * return type, which differ between crawler types).
- */
-export type TypedContextEnqueueLinks<EnqueueLinks, Routes extends Record<keyof Routes, Dictionary>> = EnqueueLinks extends (options?: infer Options) => infer Result ? (options?: TypedEnqueueLinksOptions<Options, Routes>) => Result : EnqueueLinks extends (options: infer Options) => infer Result ? (options: TypedEnqueueLinksOptions<Options, Routes>) => Result : EnqueueLinks;
-export type WithRequired<T, K extends keyof T> = T & {
-    [P in K]-?: T[P];
-};
-export type LoadedRequest<R extends Request> = WithRequired<R, 'id' | 'loadedUrl'>;
-/** @internal */
-export type LoadedContext<Context extends RestrictedCrawlingContext> = IsAny<Context> extends true ? Context : {
-    request: LoadedRequest<Context['request']>;
-} & Omit<Context, 'request'>;
-export interface RestrictedCrawlingContext<UserData extends Dictionary = Dictionary> {
-    id: string;
-    session: ISession;
-    /**
-     * An object with information about currently used proxy by the crawler
-     * and configured by the {@link ProxyConfiguration} class.
-     */
-    proxyInfo?: ProxyInfo;
-    /**
-     * The original {@link Request} object.
-     */
-    request: Request<UserData>;
-    /**
-     * This function allows you to push data to a {@link Dataset} specified by name, or the one currently used by the crawler.
-     *
-     * Shortcut for `crawler.pushData()`.
-     *
-     * @param [data] Data to be pushed to the default dataset.
-     */
-    pushData(data: ReadonlyDeep<Parameters<Dataset['pushData']>[0]>, datasetIdentifier?: string | StorageIdentifier): Promise<void>;
-    /**
-     * This function automatically finds and enqueues links from the current page, adding them to the {@link RequestQueue}
-     * currently used by the crawler.
-     *
-     * Optionally, the function allows you to filter the target links' URLs using an array of globs or regular expressions
-     * and override settings of the enqueued {@link Request} objects.
-     *
-     * Check out the [Crawl a website with relative links](https://crawlee.dev/js/docs/examples/crawl-relative-links) example
-     * for more details regarding its usage.
-     *
-     * **Example usage**
-     *
-     * ```ts
-     * async requestHandler({ enqueueLinks }) {
-     *     await enqueueLinks({
-     *       globs: [
-     *           'https://www.example.com/handbags/*',
-     *       ],
-     *     });
-     * },
-     * ```
-     *
-     * @param [options] All `enqueueLinks()` parameters are passed via an options object.
-     */
-    enqueueLinks: (options: ReadonlyDeep<Omit<SetRequired<EnqueueLinksOptions, 'urls'>, 'requestManager' | 'robotsTxtFile'>>) => Promise<unknown>;
-    /**
-     * Add requests directly to the request queue.
-     *
-     * @param requests The requests to add
-     * @param options Options for the request queue
-     */
-    addRequests: (requestsLike: ReadonlyDeep<(string | Source)[]>, options?: ReadonlyDeep<RequestQueueOperationOptions>) => Promise<void>;
-    /**
-     * Returns the state - a piece of mutable persistent data shared across all the request handler runs.
-     */
-    useState: <State extends Dictionary = Dictionary>(defaultValue?: State) => Promise<State>;
-    /**
-     * Get a key-value store with given name or id, or the default one for the crawler.
-     */
-    getKeyValueStore: (identifier?: string | StorageIdentifier) => Promise<Pick<KeyValueStore, 'id' | 'name' | 'getValue' | 'getAutoSavedValue' | 'setValue' | 'getPublicUrl'>>;
-    /**
-     * A preconfigured logger for the request handler.
-     */
-    log: CrawleeLogger;
-}
-export interface CrawlingContext<UserData extends Dictionary = Dictionary> extends RestrictedCrawlingContext<UserData> {
-    /**
-     * This function automatically finds and enqueues links from the current page, adding them to the {@link RequestQueue}
-     * currently used by the crawler.
-     *
-     * Optionally, the function allows you to filter the target links' URLs using an array of globs or regular expressions
-     * and override settings of the enqueued {@link Request} objects.
-     *
-     * Check out the [Crawl a website with relative links](https://crawlee.dev/js/docs/examples/crawl-relative-links) example
-     * for more details regarding its usage.
-     *
-     * **Example usage**
-     *
-     * ```ts
-     * async requestHandler({ enqueueLinks }) {
-     *     await enqueueLinks({
-     *       globs: [
-     *           'https://www.example.com/handbags/*',
-     *       ],
-     *     });
-     * },
-     * ```
-     *
-     * @param [options] All `enqueueLinks()` parameters are passed via an options object.
-     * @returns Promise that resolves to {@link BatchAddRequestsResult} object.
-     */
-    enqueueLinks(options: ReadonlyDeep<Omit<SetRequired<EnqueueLinksOptions, 'urls'>, 'requestManager' | 'robotsTxtFile'>> & Pick<EnqueueLinksOptions, 'requestManager' | 'robotsTxtFile'>): Promise<unknown>;
-    /**
-     * Fires HTTP request via the internal HTTP client, allowing to override the request options on the fly.
-     *
-     * This is handy when you work with a browser crawler but want to execute some requests outside it (e.g. API requests).
-     * Check the [Skipping navigations for certain requests](https://crawlee.dev/js/docs/examples/skip-navigation) example for
-     * more detailed explanation of how to do that.
-     *
-     * ```ts
-     * async requestHandler({ sendRequest }) {
-     *     const { body } = await sendRequest({
-     *         // override headers only
-     *         headers: { ... },
-     *     });
-     * },
-     * ```
-     */
-    sendRequest: (requestOverrides?: Partial<HttpRequestOptions>, optionsOverrides?: SendRequestOptions) => Promise<Response>;
-    /**
-     * Register a function to be called at the very end of the request handling process. This is useful for resources that should be accessible to error handlers, for instance.
-     */
-    registerDeferredCleanup(cleanup: () => Promise<unknown>): void;
-    /**
-     * Gives the current request `secs` more seconds to finish, for when how long it needs is only apparent
-     * once it is already running - a listing page that turns out to have far more to scroll through than
-     * usual, say. Prefer `requestHandlerTimeoutSecs`, or a per-route override via
-     * {@link Router.addHandler|`router.addHandler`}, whenever the time needed is known up front.
-     *
-     * ```ts
-     * router.addHandler('LIST', async ({ extendTimeout, page }) => {
-     *     const pageCount = await countPages(page);
-     *     extendTimeout(pageCount * 10);
-     *     await scrapeAllPages(page);
-     * });
-     * ```
-     *
-     * Extends the request handler's own timeout and the crawler's internal one together, so the extension
-     * is not immediately undone by the latter. Calling it from a handler that has already timed out does
-     * nothing.
-     */
-    extendTimeout(secs: number): void;
-}
-/**
- * A partial implementation of {@link RestrictedCrawlingContext} that stores parameters of calls to context methods for later inspection.
- *
- * @experimental
- */
-export declare class RequestHandlerResult {
-    private configuration;
-    private crawleeStateKey;
-    private _keyValueStoreChanges;
-    private pushDataCalls;
-    private addRequestsCalls;
-    constructor(configuration: Configuration, crawleeStateKey: string);
-    /**
-     * A record of calls to {@link RestrictedCrawlingContext.pushData}, {@link RestrictedCrawlingContext.addRequests}, {@link RestrictedCrawlingContext.enqueueLinks} made by a request handler.
-     */
-    get calls(): ReadonlyDeep<{
-        pushData: Parameters<RestrictedCrawlingContext['pushData']>[];
-        addRequests: Parameters<RestrictedCrawlingContext['addRequests']>[];
-    }>;
-    /**
-     * A record of changes made to key-value stores by a request handler.
-     */
-    get keyValueStoreChanges(): ReadonlyDeep<Record<string, Record<string, {
-        changedValue: unknown;
-        options?: RecordOptions;
-    }>>>;
-    /**
-     * Items added to datasets by a request handler.
-     */
-    get datasetItems(): ReadonlyDeep<{
-        item: Dictionary;
-        datasetIdentifier?: string | StorageIdentifier;
-    }[]>;
-    /**
-     * URLs enqueued to the request queue by a request handler, either via {@link RestrictedCrawlingContext.addRequests} or {@link RestrictedCrawlingContext.enqueueLinks}
-     */
-    get enqueuedUrls(): ReadonlyDeep<{
-        url: string;
-        label?: string;
-    }[]>;
-    /**
-     * URL lists enqueued to the request queue by a request handler via {@link RestrictedCrawlingContext.addRequests} using the `requestsFromUrl` option.
-     */
-    get enqueuedUrlLists(): ReadonlyDeep<{
-        listUrl: string;
-        label?: string;
-    }[]>;
-    pushData: RestrictedCrawlingContext['pushData'];
-    addRequests: RestrictedCrawlingContext['addRequests'];
-    useState: RestrictedCrawlingContext['useState'];
-    getKeyValueStore: RestrictedCrawlingContext['getKeyValueStore'];
-    private getKeyValueStoreChangedValue;
-    private setKeyValueStoreChangedValue;
-}
-export {};

package/crawlers/crawler_commons.js

@@ -1,107 +0,0 @@
-import { KeyValueStore } from '../storages/key_value_store.js';
-/**
- * A partial implementation of {@link RestrictedCrawlingContext} that stores parameters of calls to context methods for later inspection.
- *
- * @experimental
- */
-export class RequestHandlerResult {
-    configuration;
-    crawleeStateKey;
-    _keyValueStoreChanges = {};
-    pushDataCalls = [];
-    addRequestsCalls = [];
-    constructor(configuration, crawleeStateKey) {
-        this.configuration = configuration;
-        this.crawleeStateKey = crawleeStateKey;
-    }
-    /**
-     * A record of calls to {@link RestrictedCrawlingContext.pushData}, {@link RestrictedCrawlingContext.addRequests}, {@link RestrictedCrawlingContext.enqueueLinks} made by a request handler.
-     */
-    get calls() {
-        return {
-            pushData: this.pushDataCalls,
-            addRequests: this.addRequestsCalls,
-        };
-    }
-    /**
-     * A record of changes made to key-value stores by a request handler.
-     */
-    get keyValueStoreChanges() {
-        return this._keyValueStoreChanges;
-    }
-    /**
-     * Items added to datasets by a request handler.
-     */
-    get datasetItems() {
-        return this.pushDataCalls.flatMap(([data, datasetIdentifier]) => (Array.isArray(data) ? data : [data]).map((item) => ({ item, datasetIdentifier })));
-    }
-    /**
-     * URLs enqueued to the request queue by a request handler, either via {@link RestrictedCrawlingContext.addRequests} or {@link RestrictedCrawlingContext.enqueueLinks}
-     */
-    get enqueuedUrls() {
-        const result = [];
-        for (const [requests] of this.addRequestsCalls) {
-            for (const request of requests) {
-                if (typeof request === 'object' &&
-                    (!('requestsFromUrl' in request) || request.requestsFromUrl !== undefined) &&
-                    request.url !== undefined) {
-                    result.push({ url: request.url, label: request.label });
-                }
-                else if (typeof request === 'string') {
-                    result.push({ url: request });
-                }
-            }
-        }
-        return result;
-    }
-    /**
-     * URL lists enqueued to the request queue by a request handler via {@link RestrictedCrawlingContext.addRequests} using the `requestsFromUrl` option.
-     */
-    get enqueuedUrlLists() {
-        const result = [];
-        for (const [requests] of this.addRequestsCalls) {
-            for (const request of requests) {
-                if (typeof request === 'object' &&
-                    'requestsFromUrl' in request &&
-                    request.requestsFromUrl !== undefined) {
-                    result.push({ listUrl: request.requestsFromUrl, label: request.label });
-                }
-            }
-        }
-        return result;
-    }
-    pushData = async (data, datasetIdOrName) => {
-        this.pushDataCalls.push([data, datasetIdOrName]);
-    };
-    addRequests = async (requests, options = {}) => {
-        this.addRequestsCalls.push([requests, options]);
-    };
-    useState = async (defaultValue) => {
-        const store = await this.getKeyValueStore(undefined);
-        return await store.getAutoSavedValue(this.crawleeStateKey, defaultValue);
-    };
-    getKeyValueStore = async (identifier) => {
-        const store = await KeyValueStore.open(identifier, { configuration: this.configuration });
-        const storeId = store.id;
-        return {
-            id: storeId ?? this.configuration.defaultKeyValueStoreId,
-            name: store.name,
-            getValue: async (key) => this.getKeyValueStoreChangedValue(storeId, key) ?? (await store.getValue(key)),
-            setValue: async (key, value, options) => {
-                this.setKeyValueStoreChangedValue(storeId, key, value, options);
-            },
-            getAutoSavedValue: store.getAutoSavedValue.bind(store),
-            getPublicUrl: store.getPublicUrl.bind(store),
-        };
-    };
-    getKeyValueStoreChangedValue = (storeKey, key) => {
-        const id = storeKey ?? this.configuration.defaultKeyValueStoreId;
-        this._keyValueStoreChanges[id] ??= {};
-        return this.keyValueStoreChanges[id][key]?.changedValue ?? null;
-    };
-    setKeyValueStoreChangedValue = (storeKey, key, changedValue, options) => {
-        const id = storeKey ?? this.configuration.defaultKeyValueStoreId;
-        this._keyValueStoreChanges[id] ??= {};
-        this._keyValueStoreChanges[id][key] = { changedValue, options };
-    };
-}

package/crawlers/error_snapshotter.d.ts

@@ -1,59 +0,0 @@
-import type { CrawlingContext } from '../crawlers/crawler_commons.js';
-import type { KeyValueStore } from '../storages/key_value_store.js';
-import type { ErrnoException } from './error_tracker.js';
-import type { SnapshottableProperties } from './internals/types.js';
-interface BrowserCrawlingContext {
-    saveSnapshot: (options: {
-        key: string;
-    }) => Promise<void>;
-}
-export interface SnapshotResult {
-    screenshotFileName?: string;
-    htmlFileName?: string;
-}
-interface ErrorSnapshot {
-    screenshotFileName?: string;
-    screenshotFileUrl?: string;
-    htmlFileName?: string;
-    htmlFileUrl?: string;
-}
-/**
- * ErrorSnapshotter class is used to capture a screenshot of the page and a snapshot of the HTML when an error occurs during web crawling.
- *
- * This functionality is opt-in, and can be enabled via the crawler options:
- *
- * ```ts
- * const crawler = new BasicCrawler({
- *   // ...
- *   statisticsOptions: {
- *     saveErrorSnapshots: true,
- *   },
- * });
- * ```
- */
-export declare class ErrorSnapshotter {
-    static readonly MAX_ERROR_CHARACTERS = 30;
-    static readonly MAX_HASH_LENGTH = 30;
-    static readonly MAX_FILENAME_LENGTH = 250;
-    static readonly BASE_MESSAGE = "An error occurred";
-    static readonly SNAPSHOT_PREFIX = "ERROR_SNAPSHOT";
-    /**
-     * Capture a snapshot of the error context.
-     */
-    captureSnapshot(error: ErrnoException, context: CrawlingContext & SnapshottableProperties): Promise<ErrorSnapshot>;
-    /**
-     * Captures a snapshot of the current page using the context.saveSnapshot function.
-     * This function is applicable for browser contexts only.
-     * Returns an object containing the filenames of the screenshot and HTML file.
-     */
-    contextCaptureSnapshot(context: BrowserCrawlingContext, fileName: string): Promise<SnapshotResult | undefined>;
-    /**
-     * Save the HTML snapshot of the page, and return the fileName with the extension.
-     */
-    saveHTMLSnapshot(html: string, keyValueStore: Pick<KeyValueStore, 'setValue'>, fileName: string): Promise<string | undefined>;
-    /**
-     * Generate a unique fileName for each error snapshot.
-     */
-    generateFilename(error: ErrnoException): string;
-}
-export {};

package/crawlers/error_snapshotter.js

@@ -1,117 +0,0 @@
-import crypto from 'node:crypto';
-/**
- * ErrorSnapshotter class is used to capture a screenshot of the page and a snapshot of the HTML when an error occurs during web crawling.
- *
- * This functionality is opt-in, and can be enabled via the crawler options:
- *
- * ```ts
- * const crawler = new BasicCrawler({
- *   // ...
- *   statisticsOptions: {
- *     saveErrorSnapshots: true,
- *   },
- * });
- * ```
- */
-export class ErrorSnapshotter {
-    static MAX_ERROR_CHARACTERS = 30;
-    static MAX_HASH_LENGTH = 30;
-    static MAX_FILENAME_LENGTH = 250;
-    static BASE_MESSAGE = 'An error occurred';
-    static SNAPSHOT_PREFIX = 'ERROR_SNAPSHOT';
-    /**
-     * Capture a snapshot of the error context.
-     */
-    async captureSnapshot(error, context) {
-        try {
-            const page = context?.page;
-            const body = context?.body;
-            const keyValueStore = await context?.getKeyValueStore();
-            // If the key-value store is not available, or the body and page are not available, return empty filenames
-            if (!keyValueStore || (!body && !page)) {
-                return {};
-            }
-            const fileName = this.generateFilename(error);
-            let screenshotFileName;
-            let htmlFileName;
-            if (page) {
-                const capturedFiles = await this.contextCaptureSnapshot(context, fileName);
-                if (capturedFiles) {
-                    screenshotFileName = capturedFiles.screenshotFileName;
-                    htmlFileName = capturedFiles.htmlFileName;
-                }
-                // If the snapshot for browsers failed to capture the HTML, try to capture it from the page content
-                if (!htmlFileName) {
-                    const html = await page.content();
-                    htmlFileName = html ? await this.saveHTMLSnapshot(html, keyValueStore, fileName) : undefined;
-                }
-            }
-            else if (typeof body === 'string') {
-                // for non-browser contexts
-                htmlFileName = await this.saveHTMLSnapshot(body, keyValueStore, fileName);
-            }
-            return {
-                screenshotFileName,
-                screenshotFileUrl: screenshotFileName && (await keyValueStore.getPublicUrl(screenshotFileName)),
-                htmlFileName,
-                htmlFileUrl: htmlFileName && (await keyValueStore.getPublicUrl(htmlFileName)),
-            };
-        }
-        catch {
-            return {};
-        }
-    }
-    /**
-     * Captures a snapshot of the current page using the context.saveSnapshot function.
-     * This function is applicable for browser contexts only.
-     * Returns an object containing the filenames of the screenshot and HTML file.
-     */
-    async contextCaptureSnapshot(context, fileName) {
-        try {
-            await context.saveSnapshot({ key: fileName });
-            return {
-                screenshotFileName: `${fileName}.jpg`,
-                htmlFileName: `${fileName}.html`,
-            };
-        }
-        catch {
-            return undefined;
-        }
-    }
-    /**
-     * Save the HTML snapshot of the page, and return the fileName with the extension.
-     */
-    async saveHTMLSnapshot(html, keyValueStore, fileName) {
-        try {
-            await keyValueStore.setValue(fileName, html, { contentType: 'text/html' });
-            return `${fileName}.html`;
-        }
-        catch {
-            return undefined;
-        }
-    }
-    /**
-     * Generate a unique fileName for each error snapshot.
-     */
-    generateFilename(error) {
-        const { SNAPSHOT_PREFIX, BASE_MESSAGE, MAX_HASH_LENGTH, MAX_ERROR_CHARACTERS, MAX_FILENAME_LENGTH } = ErrorSnapshotter;
-        // Create a hash of the error stack trace
-        const errorStackHash = crypto
-            .createHash('sha1')
-            .update(error.stack || error.message || '')
-            .digest('hex')
-            .slice(0, MAX_HASH_LENGTH);
-        const errorMessagePrefix = (error.message || BASE_MESSAGE).slice(0, MAX_ERROR_CHARACTERS).trim();
-        /**
-         * Remove non-word characters from the start and end of a string.
-         */
-        const sanitizeString = (str) => {
-            return str.replace(/^\W+|\W+$/g, '');
-        };
-        // Generate fileName and remove disallowed characters
-        const fileName = `${SNAPSHOT_PREFIX}_${sanitizeString(errorStackHash)}_${sanitizeString(errorMessagePrefix)}`
-            .replace(/\W+/g, '-') // Replace non-word characters with a dash
-            .slice(0, MAX_FILENAME_LENGTH);
-        return fileName;
-    }
-}

package/crawlers/error_tracker.d.ts

@@ -1,54 +0,0 @@
-import type { CrawlingContext } from '../crawlers/crawler_commons.js';
-import { ErrorSnapshotter } from './error_snapshotter.js';
-import type { SnapshottableProperties } from './internals/types.js';
-/**
- * Node.js Error interface
- */
-export interface ErrnoException extends Error {
-    errno?: number;
-    code?: string | number;
-    path?: string;
-    syscall?: string;
-    cause?: any;
-}
-export interface ErrorTrackerOptions {
-    showErrorCode: boolean;
-    showErrorName: boolean;
-    showStackTrace: boolean;
-    showFullStack: boolean;
-    showErrorMessage: boolean;
-    showFullMessage: boolean;
-    saveErrorSnapshots: boolean;
-}
-/**
- * This class tracks errors and computes a summary of information like:
- * - where the errors happened
- * - what the error names are
- * - what the error codes are
- * - what is the general error message
- *
- * This is extremely useful when there are dynamic error messages, such as argument validation.
- *
- * Since the structure of the `tracker.result` object differs when using different options,
- * it's typed as `Record<string, unknown>`. The most deep object has a `count` property, which is a number.
- *
- * It's possible to get the total amount of errors via the `tracker.total` property.
- */
-export declare class ErrorTracker {
-    #private;
-    result: Record<string, unknown>;
-    total: number;
-    errorSnapshotter?: ErrorSnapshotter;
-    constructor(options?: Partial<ErrorTrackerOptions>);
-    private updateGroup;
-    add(error: ErrnoException): void;
-    /**
-     * This method is async, because it captures a snapshot of the error context.
-     * We added this new method to avoid breaking changes.
-     */
-    addAsync(error: ErrnoException, context?: CrawlingContext): Promise<void>;
-    getUniqueErrorCount(): number;
-    getMostPopularErrors(count: number): [number, string[]][];
-    captureSnapshot(storage: Record<string, unknown>, error: ErrnoException, context: CrawlingContext & SnapshottableProperties): Promise<void>;
-    reset(): void;
-}