@crawlee/basic 4.0.0-beta.121 → 4.0.0-beta.123

package/internals/basic-crawler.d.ts

@@ -1,9 +1,10 @@
-import type { AddRequestsBatchedOptions, AddRequestsBatchedResult, ConcurrencySystemOptions, Configuration, CrawleeLogger, CrawlingContext, DatasetExportOptions, EnqueueLinksOptions, EventManager, FinalStatistics, GetUserDataFromRequest, IConcurrencySystem, IProxyConfiguration, IRequestLoader, IRequestManager, IStatistics, Request, RequestsLike, RouterHandler, RouterRoutes, SkippedRequestCallback, Source, StatisticState, StorageIdentifier, StorageWritePolicy, TaskLoopPredicates, TypedRequestsLike } from '@crawlee/core';
-import { ConcurrencySystem, ContextPipeline, Dataset, RequestQueue } from '@crawlee/core';
-import type { Awaitable, BaseHttpClient, BatchAddRequestsResult, Dictionary, ISession, ISessionPool, ProxyInfo, SetStatusMessageOptions, StorageBackend } from '@crawlee/types';
+import type { AddRequestsBatchedOptions, AddRequestsBatchedResult, ConcurrencySystemOptions, CrawleeLogger, CrawlingContext, DatasetExportOptions, EnqueueUrlsOptions, FinalStatistics, GetUserDataFromRequest, IConcurrencySystem, IProxyConfiguration, IRequestLoader, IRequestManager, IStatistics, RequestsLike, RouterHandler, RouterRoutes, SkippedRequestCallback, Source, StatisticState, StorageIdentifier, StorageWritePolicy, TaskLoopPredicates, TypedRequestsLike } from '@crawlee/core';
+import { ConcurrencySystem, Configuration, ContextPipeline, Request, Dataset, EventManager, RequestQueue } from '@crawlee/core';
+import { BaseHttpClient } from '@crawlee/http-client';
+import type { Awaitable, Dictionary, ISession, ISessionPool, ProxyInfo, SetStatusMessageOptions, StorageBackend } from '@crawlee/types';
 import { RobotsTxtFile } from '@crawlee/utils';
-import { type BasePredicate } from 'ow';
-import type { ReadonlyDeep, SetRequired } from 'type-fest';
+import type { ReadonlyDeep } from 'type-fest';
+import { z } from 'zod';
 import { TimeoutError } from '@apify/timeout';
 export interface BasicCrawlingContext<UserData extends Dictionary = Dictionary> extends CrawlingContext<UserData> {
 }
@@ -514,80 +515,93 @@ export declare class BasicCrawler<Context extends CrawlingContext = CrawlingCont
     protected readonly onSkippedRequest?: SkippedRequestCallback;
     protected readonly identity: CrawlerIdentity;
     protected static optionsShape: {
-// @ts-ignore optional peer dependency or compatibility with es2022
-        contextPipelineBuilder: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        extendContext: import("ow").Predicate<Function> & BasePredicate<Function | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        requestList: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        requestQueue: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        requestManager: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        requestHandler: import("ow").Predicate<Function> & BasePredicate<Function | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        requestHandlerTimeoutSecs: import("ow").NumberPredicate & BasePredicate<number | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        errorHandler: import("ow").Predicate<Function> & BasePredicate<Function | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        failedRequestHandler: import("ow").Predicate<Function> & BasePredicate<Function | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        maxRequestRetries: import("ow").NumberPredicate & BasePredicate<number | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        sameDomainDelaySecs: import("ow").NumberPredicate & BasePredicate<number | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        maxRequestsPerCrawl: import("ow").NumberPredicate & BasePredicate<number | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        maxCrawlDepth: import("ow").NumberPredicate & BasePredicate<number | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        taskLoopOptions: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        concurrencySystem: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        sessionPool: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        proxyConfiguration: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        statusMessageLoggingInterval: import("ow").NumberPredicate & BasePredicate<number | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        statusMessageCallback: import("ow").Predicate<Function> & BasePredicate<Function | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        additionalHttpErrorStatusCodes: import("ow").ArrayPredicate<number>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        ignoreHttpErrorStatusCodes: import("ow").ArrayPredicate<number>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        blockedStatusCodes: import("ow").ArrayPredicate<number>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        retryOnBlocked: import("ow").BooleanPredicate & BasePredicate<boolean | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        respectRobotsTxtFile: import("ow").AnyPredicate<boolean | object>;
-        transactionalStorage: BasePredicate<boolean | Partial<StorageWritePolicy> | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        onSkippedRequest: import("ow").Predicate<Function> & BasePredicate<Function | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        httpClient: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        configuration: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        storageBackend: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        eventManager: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        logger: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        minConcurrency: import("ow").NumberPredicate & BasePredicate<number | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        maxConcurrency: import("ow").NumberPredicate & BasePredicate<number | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        maxRequestsPerMinute: import("ow").NumberPredicate & BasePredicate<number | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        keepAlive: import("ow").BooleanPredicate & BasePredicate<boolean | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        statistics: import("ow").ObjectPredicate<object> & BasePredicate<object | undefined>;
-// @ts-ignore optional peer dependency or compatibility with es2022
-        id: import("ow").StringPredicate & BasePredicate<string | undefined>;
+        contextPipelineBuilder: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
+        extendContext: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
+        requestList: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        requestQueue: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        requestManager: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        requestHandler: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
+        requestHandlerTimeoutSecs: z.ZodOptional<z.ZodCustom<number, number>>;
+        errorHandler: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
+        failedRequestHandler: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
+        maxRequestRetries: z.ZodDefault<z.ZodCustom<number, number>>;
+        sameDomainDelaySecs: z.ZodDefault<z.ZodCustom<number, number>>;
+        maxRequestsPerCrawl: z.ZodOptional<z.ZodCustom<number, number>>;
+        maxCrawlDepth: z.ZodOptional<z.ZodCustom<number, number>>;
+        taskLoopOptions: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
+        concurrencySystem: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
+        sessionPool: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        proxyConfiguration: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        statusMessageLoggingInterval: z.ZodDefault<z.ZodCustom<number, number>>;
+        statusMessageCallback: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
+        additionalHttpErrorStatusCodes: z.ZodDefault<z.ZodArray<z.ZodCustom<number, number>>>;
+        ignoreHttpErrorStatusCodes: z.ZodDefault<z.ZodArray<z.ZodCustom<number, number>>>;
+        blockedStatusCodes: z.ZodOptional<z.ZodArray<z.ZodCustom<number, number>>>;
+        retryOnBlocked: z.ZodDefault<z.ZodBoolean>;
+        respectRobotsTxtFile: z.ZodDefault<z.ZodUnion<readonly [z.ZodBoolean, z.ZodCustom<Dictionary, Dictionary>]>>;
+        transactionalStorage: z.ZodOptional<z.ZodUnion<readonly [z.ZodBoolean, z.ZodObject<{
+            requestQueue: z.ZodOptional<z.ZodEnum<{
+                deferred: "deferred";
+                writeThrough: "writeThrough";
+            }>>;
+        }, z.core.$strict>]>>;
+        onSkippedRequest: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
+        httpClient: z.ZodOptional<z.ZodCustom<BaseHttpClient, BaseHttpClient>>;
+        configuration: z.ZodOptional<z.ZodCustom<Configuration, Configuration>>;
+        storageBackend: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        eventManager: z.ZodOptional<z.ZodCustom<EventManager, EventManager>>;
+        logger: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        minConcurrency: z.ZodOptional<z.ZodCustom<number, number>>;
+        maxConcurrency: z.ZodOptional<z.ZodCustom<number, number>>;
+        maxRequestsPerMinute: z.ZodOptional<z.ZodCustom<number, number>>;
+        keepAlive: z.ZodOptional<z.ZodBoolean>;
+        statistics: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
+        id: z.ZodOptional<z.ZodString>;
     };
+    protected static optionsSchema: z.ZodObject<{
+        contextPipelineBuilder: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
+        extendContext: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
+        requestList: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        requestQueue: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        requestManager: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        requestHandler: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
+        requestHandlerTimeoutSecs: z.ZodOptional<z.ZodCustom<number, number>>;
+        errorHandler: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
+        failedRequestHandler: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
+        maxRequestRetries: z.ZodDefault<z.ZodCustom<number, number>>;
+        sameDomainDelaySecs: z.ZodDefault<z.ZodCustom<number, number>>;
+        maxRequestsPerCrawl: z.ZodOptional<z.ZodCustom<number, number>>;
+        maxCrawlDepth: z.ZodOptional<z.ZodCustom<number, number>>;
+        taskLoopOptions: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
+        concurrencySystem: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
+        sessionPool: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        proxyConfiguration: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        statusMessageLoggingInterval: z.ZodDefault<z.ZodCustom<number, number>>;
+        statusMessageCallback: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
+        additionalHttpErrorStatusCodes: z.ZodDefault<z.ZodArray<z.ZodCustom<number, number>>>;
+        ignoreHttpErrorStatusCodes: z.ZodDefault<z.ZodArray<z.ZodCustom<number, number>>>;
+        blockedStatusCodes: z.ZodOptional<z.ZodArray<z.ZodCustom<number, number>>>;
+        retryOnBlocked: z.ZodDefault<z.ZodBoolean>;
+        respectRobotsTxtFile: z.ZodDefault<z.ZodUnion<readonly [z.ZodBoolean, z.ZodCustom<Dictionary, Dictionary>]>>;
+        transactionalStorage: z.ZodOptional<z.ZodUnion<readonly [z.ZodBoolean, z.ZodObject<{
+            requestQueue: z.ZodOptional<z.ZodEnum<{
+                deferred: "deferred";
+                writeThrough: "writeThrough";
+            }>>;
+        }, z.core.$strict>]>>;
+        onSkippedRequest: z.ZodOptional<z.ZodCustom<(...args: any[]) => unknown, (...args: any[]) => unknown>>;
+        httpClient: z.ZodOptional<z.ZodCustom<BaseHttpClient, BaseHttpClient>>;
+        configuration: z.ZodOptional<z.ZodCustom<Configuration, Configuration>>;
+        storageBackend: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        eventManager: z.ZodOptional<z.ZodCustom<EventManager, EventManager>>;
+        logger: z.ZodOptional<z.ZodType<Dictionary<any>, unknown, z.core.$ZodTypeInternals<Dictionary<any>, unknown>>>;
+        minConcurrency: z.ZodOptional<z.ZodCustom<number, number>>;
+        maxConcurrency: z.ZodOptional<z.ZodCustom<number, number>>;
+        maxRequestsPerMinute: z.ZodOptional<z.ZodCustom<number, number>>;
+        keepAlive: z.ZodOptional<z.ZodBoolean>;
+        statistics: z.ZodOptional<z.ZodCustom<Dictionary, Dictionary>>;
+        id: z.ZodOptional<z.ZodString>;
+    }, z.core.$strict>;
     /**
      * All `BasicCrawler` parameters are passed via an options object.
      */
@@ -719,6 +733,11 @@ export declare class BasicCrawler<Context extends CrawlingContext = CrawlingCont
      * the batches via `waitBetweenBatchesMillis`. If you want to wait for all batches to be added to the queue, you can use
      * the `waitForAllRequestsToBeAdded` promise you get in the response object.
      *
+     * Optionally, the requests can be filtered using `include`/`exclude` glob or regexp patterns and an
+     * enqueue `strategy` (both AND-ed together, same as {@link CrawlingContext.enqueueLinks|`enqueueLinks`}),
+     * relative to `baseUrl`. Unlike `enqueueLinks`, there is no implicit "current page" to anchor the strategy
+     * to, so `strategy` defaults to {@link EnqueueStrategy.All|`all`} here.
+     *
      * This is an alias for calling `addRequestsBatched()` on the implicit `RequestQueue` for this crawler instance.
      *
      * @param requests The requests to add
@@ -813,14 +832,6 @@ export declare class BasicCrawler<Context extends CrawlingContext = CrawlingCont
     private delayRequest;
     /** Handles a single request - runs the request handler with retries, error handling, and lifecycle management. */
     private handleRequest;
-    /**
-     * Wrapper around the crawling context's `enqueueLinks` method:
-     * - Injects `crawlDepth` to each request being added based on the crawling context request.
-     * - Provides defaults for the `enqueueLinks` options based on the crawler configuration.
-     *      - These options can be overridden by the user.
-     * @internal
-     */
-    protected enqueueLinksWithCrawlDepth(options: SetRequired<EnqueueLinksOptions, 'urls'>, request: Request<Dictionary>, requestManager: IRequestManager): Promise<BatchAddRequestsResult>;
     /**
      * Generator function that yields requests injected with the given crawl depth.
      * @internal
@@ -879,7 +890,7 @@ export interface CreateContextOptions {
     session: ISession;
     proxyInfo?: ProxyInfo;
 }
-export interface CrawlerAddRequestsOptions extends AddRequestsBatchedOptions {
+export interface CrawlerAddRequestsOptions extends AddRequestsBatchedOptions, EnqueueUrlsOptions {
 }
 export interface CrawlerAddRequestsResult extends AddRequestsBatchedResult {
 }

package/internals/basic-crawler.js

@@ -1,19 +1,20 @@
 import { mkdir, writeFile } from 'node:fs/promises';
 import { dirname } from 'node:path';
-import { AutoscaledPool, bindMethodsToServiceLocator, BLOCKED_STATUS_CODES, ConcurrencySystem, ContextPipeline, ContextPipelineCleanupError, ContextPipelineInitializationError, ContextPipelineInterruptedError, createStorageTransaction, CriticalError, currentStorageTransaction, Dataset, enqueueLinks, EnqueueStrategy, EventType, getObjectType, KeyValueStore, log, LogLevel, mergeCookies, MissingSessionError, NavigationSkippedError, NonRetryableError, OwnedOrInjected, purgeDefaultStorages, RequestHandlerError, parseRetryAfterHeader, RequestThrottledError, RequestManagerTandem, RequestQueue, RequestState, RetryRequestError, supportsDomainThrottling, Router, ServiceLocator, serviceLocator, Session, SessionError, SessionPool, Statistics, validateUserData, validators, withDirectStorageAccess, } from '@crawlee/core';
-import { FetchHttpClient } from '@crawlee/http-client';
+import { applyRequestTransform, AutoscaledPool, bindMethodsToServiceLocator, BLOCKED_STATUS_CODES, buildEnqueueStrategyPatterns, ConcurrencySystem, Configuration, constructUrlPatternObjects, ContextPipeline, ContextPipelineCleanupError, ContextPipelineInitializationError, ContextPipelineInterruptedError, createRequestOptions, createStorageTransaction, Request, CriticalError, currentStorageTransaction, Dataset, EnqueueStrategy, EventManager, EventType, filterRequestOptionsByPatterns, getObjectType, KeyValueStore, log, LogLevel, mergeCookies, MissingSessionError, NavigationSkippedError, NonRetryableError, OwnedOrInjected, parseArgument, purgeDefaultStorages, RequestHandlerError, parseRetryAfterHeader, RequestThrottledError, RequestManagerTandem, RequestQueue, RequestState, RetryRequestError, supportsDomainThrottling, Router, schemas, ServiceLocator, serviceLocator, Session, SessionError, SessionPool, Statistics, validateUserData, validators, withDirectStorageAccess, } from '@crawlee/core';
+import { BaseHttpClient, FetchHttpClient } from '@crawlee/http-client';
 import { isAsyncIterable, isIterable, ROTATE_PROXY_ERRORS } from '@crawlee/utils/internal';
 import { RobotsTxtFile } from '@crawlee/utils';
-import ow, { ArgumentError } from 'ow';
 import { getDomain } from 'tldts';
+import { z } from 'zod';
 import { LruCache } from '@apify/datastructures';
 import { addTimeoutToPromise, extendTimeout, TimeoutError } from '@apify/timeout';
 import { cryptoRandomObjectId } from '@apify/utilities';
 import { extendTimeoutKey, navigationDeadlineKey, raceWithTimeout, timeoutExpiredKey, } from './request-timeout.js';
 import { createSendRequest } from './send-request.js';
-class LazyDefaultHttpClient {
+class LazyDefaultHttpClient extends BaseHttpClient {
     #delegatePromise;
     constructor(options) {
+        super(options);
         this.#delegatePromise = import('@crawlee/impit-client')
             .then(({ ImpitHttpClient }) => new ImpitHttpClient(options))
             .catch(() => {
@@ -22,6 +23,9 @@ class LazyDefaultHttpClient {
             return new FetchHttpClient(options);
         });
     }
+    fetch() {
+        throw new Error('LazyDefaultHttpClient delegates `sendRequest` entirely; `fetch` is never called.');
+    }
     async sendRequest(...args) {
         return (await this.#delegatePromise).sendRequest(...args);
     }
@@ -39,6 +43,33 @@ const SAFE_MIGRATION_WAIT_MILLIS = 20000;
 const deferredCleanupKey = Symbol('deferredCleanup');
 // The request timeout plumbing (the window helper, the context symbols, and the race) lives in its own module.
 export { navigationDeadlineKey, remainingNavigationWindowMillis } from './request-timeout.js';
+const urlPatternSchema = z.union([
+    z.string(),
+    z.instanceof(RegExp),
+    schemas.objectWithKeys(['glob']),
+    schemas.objectWithKeys(['regexp']),
+]);
+// `looseObject` (rather than `strictObject`) lets subclasses forward their own extraction-only options
+// (e.g. `selector`) straight through without having to strip them out first.
+const addRequestsOptionsSchema = z.looseObject({
+    forefront: z.boolean().optional(),
+    cache: z.boolean().optional(),
+    waitForAllRequestsToBeAdded: z.boolean().optional(),
+    batchSize: schemas.anyNumber.optional(),
+    waitBetweenBatchesMillis: schemas.anyNumber.optional(),
+    maxNewRequests: schemas.anyNumber.optional(),
+    limit: schemas.anyNumber.optional(),
+    baseUrl: z.string().optional(),
+    userData: schemas.anyObject.optional(),
+    label: z.string().optional(),
+    sessionId: z.string().optional(),
+    skipNavigation: z.boolean().optional(),
+    include: schemas.arrayOf(urlPatternSchema, 'URL patterns').min(1).optional(),
+    exclude: schemas.arrayOf(urlPatternSchema, 'URL patterns').optional(),
+    transformRequestFunction: schemas.anyFunction.optional(),
+    strategy: z.enum(EnqueueStrategy).optional(),
+    onSkippedRequest: schemas.anyFunction.optional(),
+});
 export class BasicCrawler {
     static CRAWLEE_STATE_KEY = 'CRAWLEE_STATE';
     /**
@@ -200,72 +231,77 @@ export class BasicCrawler {
     identity;
     #contextPipelineOptions;
     static optionsShape = {
-        contextPipelineBuilder: ow.optional.object,
-        extendContext: ow.optional.function,
-        requestList: ow.optional.object.validate(validators.requestList),
-        requestQueue: ow.optional.object.validate(validators.requestQueue),
-        requestManager: ow.optional.object,
+        contextPipelineBuilder: schemas.anyObject.optional(),
+        extendContext: schemas.anyFunction.optional(),
+        requestList: validators.requestList.optional(),
+        requestQueue: validators.requestQueue.optional(),
+        requestManager: validators.requestManager.optional(),
         // Subclasses override this function instead of passing it
         // in constructor, so this validation needs to apply only
         // if the user creates an instance of BasicCrawler directly.
-        requestHandler: ow.optional.function,
-        requestHandlerTimeoutSecs: ow.optional.number,
-        errorHandler: ow.optional.function,
-        failedRequestHandler: ow.optional.function,
-        maxRequestRetries: ow.optional.number,
-        sameDomainDelaySecs: ow.optional.number,
-        maxRequestsPerCrawl: ow.optional.number,
-        maxCrawlDepth: ow.optional.number,
-        taskLoopOptions: ow.optional.object,
-        concurrencySystem: ow.optional.object,
-        sessionPool: ow.optional.object.validate(validators.sessionPool),
-        proxyConfiguration: ow.optional.object.validate(validators.proxyConfiguration),
-        statusMessageLoggingInterval: ow.optional.number,
-        statusMessageCallback: ow.optional.function,
-        additionalHttpErrorStatusCodes: ow.optional.array.ofType(ow.number),
-        ignoreHttpErrorStatusCodes: ow.optional.array.ofType(ow.number),
-        blockedStatusCodes: ow.optional.array.ofType(ow.number),
-        retryOnBlocked: ow.optional.boolean,
-        respectRobotsTxtFile: ow.optional.any(ow.boolean, ow.object),
-        transactionalStorage: ow.optional.any(ow.boolean, ow.object.exactShape({
-            requestQueue: ow.optional.string.oneOf(['deferred', 'writeThrough']),
-        })),
-        onSkippedRequest: ow.optional.function,
-        httpClient: ow.optional.object,
-        configuration: ow.optional.object,
-        storageBackend: ow.optional.object,
-        eventManager: ow.optional.object,
-        logger: ow.optional.object,
+        requestHandler: schemas.anyFunction.optional(),
+        requestHandlerTimeoutSecs: schemas.anyNumber.optional(),
+        errorHandler: schemas.anyFunction.optional(),
+        failedRequestHandler: schemas.anyFunction.optional(),
+        maxRequestRetries: schemas.anyNumber.default(3),
+        sameDomainDelaySecs: schemas.anyNumber.default(0),
+        maxRequestsPerCrawl: schemas.anyNumber.optional(),
+        maxCrawlDepth: schemas.anyNumber.optional(),
+        // No zod default — subclasses provide their own fallback (e.g. HTTP-optimized pool options).
+        taskLoopOptions: schemas.anyObject.optional(),
+        concurrencySystem: schemas.anyObject.optional(),
+        sessionPool: validators.sessionPool.optional(),
+        proxyConfiguration: validators.proxyConfiguration.optional(),
+        statusMessageLoggingInterval: schemas.anyNumber.default(10),
+        statusMessageCallback: schemas.anyFunction.optional(),
+        additionalHttpErrorStatusCodes: schemas.arrayOf(schemas.anyNumber, 'numbers').default(() => []),
+        ignoreHttpErrorStatusCodes: schemas.arrayOf(schemas.anyNumber, 'numbers').default(() => []),
+        blockedStatusCodes: schemas.arrayOf(schemas.anyNumber, 'numbers').optional(),
+        retryOnBlocked: z.boolean().default(false),
+        respectRobotsTxtFile: z.union([z.boolean(), schemas.anyObject]).default(false),
+        transactionalStorage: z
+            .union([z.boolean(), z.strictObject({ requestQueue: z.enum(['deferred', 'writeThrough']).optional() })])
+            .optional(),
+        onSkippedRequest: schemas.anyFunction.optional(),
+        httpClient: schemas.httpClient.optional(),
+        configuration: z.instanceof(Configuration).optional(),
+        storageBackend: validators.storageBackend.optional(),
+        eventManager: z.instanceof(EventManager).optional(),
+        logger: validators.logger.optional(),
         // AutoscaledPool shorthands
-        minConcurrency: ow.optional.number,
-        maxConcurrency: ow.optional.number,
-        maxRequestsPerMinute: ow.optional.number.integerOrInfinite.positive.greaterThanOrEqual(1),
-        keepAlive: ow.optional.boolean,
-        statistics: ow.optional.object,
-        id: ow.optional.string,
+        minConcurrency: schemas.anyNumber.optional(),
+        maxConcurrency: schemas.anyNumber.optional(),
+        maxRequestsPerMinute: schemas.anyNumber
+            .refine((value) => Number.isInteger(value) || value === Infinity, 'Expected an integer or infinite number')
+            .refine((value) => value >= 1, 'Expected a number greater than or equal to 1')
+            .optional(),
+        keepAlive: z.boolean().optional(),
+        statistics: schemas.anyObject.optional(),
+        id: z.string().optional(),
     };
+    static optionsSchema = z.strictObject(BasicCrawler.optionsShape);
     /**
      * All `BasicCrawler` parameters are passed via an options object.
      */
     constructor(options = {}) {
-        ow(options, 'BasicCrawlerOptions', ow.object.exactShape(BasicCrawler.optionsShape));
+        const parsedOptions = parseArgument(options, BasicCrawler.optionsSchema, 'BasicCrawlerOptions');
         const { 
         // oxlint-disable-next-line typescript/no-deprecated -- still accepted and folded into `requestManager` for back-compat
         requestList, 
         // oxlint-disable-next-line typescript/no-deprecated -- still accepted and folded into `requestManager` for back-compat
-        requestQueue, requestManager, maxRequestRetries = 3, sameDomainDelaySecs = 0, maxRequestsPerCrawl, maxCrawlDepth, taskLoopOptions = {}, concurrencySystem, keepAlive, sessionPool, proxyConfiguration, additionalHttpErrorStatusCodes = [], ignoreHttpErrorStatusCodes = [], 
+        requestQueue, requestManager, maxRequestRetries, sameDomainDelaySecs, maxRequestsPerCrawl, maxCrawlDepth, taskLoopOptions = {}, concurrencySystem, keepAlive, sessionPool, proxyConfiguration, additionalHttpErrorStatusCodes, ignoreHttpErrorStatusCodes, 
         // Service locator options
         configuration, storageBackend, eventManager, logger, 
         // AutoscaledPool shorthands
-        minConcurrency, maxConcurrency, maxRequestsPerMinute, blockedStatusCodes: blockedStatusCodesInput, retryOnBlocked = false, respectRobotsTxtFile = false, transactionalStorage, onSkippedRequest, requestHandler, requestHandlerTimeoutSecs, errorHandler, failedRequestHandler, statusMessageLoggingInterval = 10, statusMessageCallback, statistics, httpClient, id, } = options;
+        minConcurrency, maxConcurrency, maxRequestsPerMinute, blockedStatusCodes: blockedStatusCodesInput, retryOnBlocked, respectRobotsTxtFile, transactionalStorage, onSkippedRequest, requestHandler, requestHandlerTimeoutSecs, errorHandler, failedRequestHandler, statusMessageLoggingInterval, statusMessageCallback, statistics, httpClient, id, } = parsedOptions;
         // All concurrency configuration lives on the `ConcurrencySystem`, so the shortcuts have nowhere to go once
         // one is supplied - and silently dropping a `maxConcurrency` the user asked for is how crawls end up
         // hammering a site.
         if (concurrencySystem !== undefined &&
             (minConcurrency !== undefined || maxConcurrency !== undefined || maxRequestsPerMinute !== undefined)) {
-            throw new ArgumentError('The `minConcurrency`/`maxConcurrency`/`maxRequestsPerMinute` shortcuts cannot be combined with ' +
+            throw new Error('The `minConcurrency`/`maxConcurrency`/`maxRequestsPerMinute` shortcuts cannot be combined with ' +
                 '`concurrencySystem` - they configure the default `ConcurrencySystem` that a supplied one ' +
-                'replaces. Pass them to the `ConcurrencySystem` constructor instead.', this.constructor);
+                'replaces. Pass them to the `ConcurrencySystem` constructor instead.');
         }
         // Create per-crawler service locator if custom services were provided.
         // This wraps every method on the crawler instance so that calls to the global `serviceLocator`
@@ -287,8 +323,8 @@ export class BasicCrawler {
         try {
             serviceLocatorScope.enterScope();
             this.#contextPipelineOptions = {
-                contextPipelineBuilder: options.contextPipelineBuilder,
-                extendContext: options.extendContext,
+                contextPipelineBuilder: parsedOptions.contextPipelineBuilder,
+                extendContext: parsedOptions.extendContext,
             };
             this.#log = serviceLocator.getLogger().child({ prefix: this.constructor.name });
             // Initialize the Configuration instance to avoid lazy loading in the components
@@ -589,17 +625,13 @@ export class BasicCrawler {
         return { session, proxyInfo: session?.proxyInfo };
     }
     async createContextHelpers({ request, session }) {
-        const enqueueLinksWrapper = async (options) => {
-            const requestManager = await this.getRequestManager();
-            return await this.enqueueLinksWithCrawlDepth(options, request, requestManager);
-        };
         const addRequests = async (requests, options = {}) => {
             const newCrawlDepth = request.crawlDepth + 1;
             const requestsGenerator = this.addCrawlDepthRequestGenerator(requests, newCrawlDepth);
-            await this.addRequests(requestsGenerator, options);
+            return await this.addRequests(requestsGenerator, options);
         };
         const sendRequest = createSendRequest(this.httpClient, request, session);
-        return { enqueueLinks: enqueueLinksWrapper, addRequests, sendRequest };
+        return { addRequests, sendRequest };
     }
     buildFinalContextPipeline() {
         const subclassPipeline = (this.#contextPipelineOptions.contextPipelineBuilder?.() ??
@@ -996,6 +1028,11 @@ export class BasicCrawler {
      * the batches via `waitBetweenBatchesMillis`. If you want to wait for all batches to be added to the queue, you can use
      * the `waitForAllRequestsToBeAdded` promise you get in the response object.
      *
+     * Optionally, the requests can be filtered using `include`/`exclude` glob or regexp patterns and an
+     * enqueue `strategy` (both AND-ed together, same as {@link CrawlingContext.enqueueLinks|`enqueueLinks`}),
+     * relative to `baseUrl`. Unlike `enqueueLinks`, there is no implicit "current page" to anchor the strategy
+     * to, so `strategy` defaults to {@link EnqueueStrategy.All|`all`} here.
+     *
      * This is an alias for calling `addRequestsBatched()` on the implicit `RequestQueue` for this crawler instance.
      *
      * @param requests The requests to add
@@ -1003,55 +1040,95 @@ export class BasicCrawler {
      */
     async addRequests(requests, options = {}) {
         await this.getRequestManager();
-        const requestLimit = await this.calculateEnqueuedRequestLimit();
-        const skippedBecauseOfRobots = new Set();
-        const skippedBecauseOfMaxCrawlDepth = new Set();
+        if (!isIterable(requests) && !isAsyncIterable(requests)) {
+            throw new Error(`Expected an iterable or async iterable, got ${getObjectType(requests)}`);
+        }
+        parseArgument(options, addRequestsOptionsSchema, 'EnqueueUrlsOptions');
+        // `label`/`userData` apply to every request this call produces, so a single upfront validation
+        // against the label's schema covers them all and fails the whole call fast, rather than failing
+        // lazily once the generator below is drained. Skipped when neither is set - each item still gets
+        // its own per-item validation below, and validating an absent label/userData here would spuriously
+        // check them against a registered default-route schema.
+        if (options.label !== undefined || options.userData !== undefined) {
+            await this.validateRequestUserData({ label: options.label, userData: options.userData });
+        }
+        const requestLimit = await this.calculateEnqueuedRequestLimit(options.limit);
+        const strategy = options.strategy ?? EnqueueStrategy.All;
+        const urlExcludePatternObjects = options.exclude?.length
+            ? constructUrlPatternObjects(options.exclude)
+            : [];
+        const urlPatternObjects = options.include?.length
+            ? constructUrlPatternObjects(options.include)
+            : [];
+        // The strategy always applies, even when `include` patterns are provided - the two are AND-ed together
+        // (a URL must match an `include` pattern *and* satisfy the strategy). This mirrors crawlee-python.
+        const enqueueStrategyPatterns = options.baseUrl
+            ? buildEnqueueStrategyPatterns(options.baseUrl, strategy)
+            : [];
         const isAllowedBasedOnRobotsTxtFile = this.isAllowedBasedOnRobotsTxtFile.bind(this);
         const maxCrawlDepth = this.maxCrawlDepth;
         const validateRequestUserData = this.validateRequestUserData.bind(this);
-        ow(requests, ow.object
-            .is((value) => isIterable(value) || isAsyncIterable(value))
-            .message((value) => `Expected an iterable or async iterable, got ${getObjectType(value)}`));
+        const allSkipped = [];
         async function* filteredRequests() {
             for await (const request of requests) {
-                const url = typeof request === 'string' ? request : request.url;
-                if (maxCrawlDepth !== undefined && request.crawlDepth > maxCrawlDepth) {
-                    skippedBecauseOfMaxCrawlDepth.add(url);
+                const [requestOptions] = createRequestOptions([typeof request === 'string' ? request : request], { ...options, strategy });
+                if (!requestOptions) {
+                    continue; // invalid URL, silently dropped (matches `createRequestOptions`'s own filtering)
+                }
+                if (maxCrawlDepth !== undefined && requestOptions.crawlDepth > maxCrawlDepth) {
+                    allSkipped.push({ url: requestOptions.url, reason: 'depth' });
                     continue;
                 }
-                if (await isAllowedBasedOnRobotsTxtFile(url)) {
-                    await validateRequestUserData(request);
-                    yield request;
+                if (!(await isAllowedBasedOnRobotsTxtFile(requestOptions.url))) {
+                    allSkipped.push({ url: requestOptions.url, reason: 'robotsTxt' });
+                    continue;
                 }
-                else {
-                    skippedBecauseOfRobots.add(url);
+                const onSkippedFilterUrl = (url) => allSkipped.push({ url, reason: 'filters' });
+                // Filter by user patterns first (with exclude)...
+                let filtered = filterRequestOptionsByPatterns([requestOptions], urlPatternObjects.length > 0 ? urlPatternObjects : undefined, urlExcludePatternObjects, strategy, onSkippedFilterUrl);
+                // ...then filter by the enqueue strategy (making this an AND check)
+                filtered = filterRequestOptionsByPatterns(filtered, enqueueStrategyPatterns.length > 0 ? enqueueStrategyPatterns : undefined, [], strategy, onSkippedFilterUrl);
+                if (filtered.length === 0) {
+                    continue;
+                }
+                let [finalOptions] = filtered;
+                if (options.transformRequestFunction) {
+                    const transformed = applyRequestTransform([finalOptions], options.transformRequestFunction, (r) => allSkipped.push({ url: r.url, reason: r.skippedReason ?? 'transform' }));
+                    if (transformed.length === 0) {
+                        continue;
+                    }
+                    [finalOptions] = transformed;
                 }
+                await validateRequestUserData(finalOptions);
+                yield new Request(finalOptions);
             }
         }
         const result = await this.requestManager.addRequestsBatched(filteredRequests(), {
-            ...options,
+            forefront: options.forefront,
+            waitForAllRequestsToBeAdded: options.waitForAllRequestsToBeAdded,
+            batchSize: options.batchSize,
+            waitBetweenBatchesMillis: options.waitBetweenBatchesMillis,
             maxNewRequests: requestLimit,
         });
-        // Report requests skipped due to the maxNewRequests budget (i.e. maxRequestsPerCrawl limit)
-        const skippedBecauseOfLimit = result.requestsOverLimit ?? [];
-        if (skippedBecauseOfRobots.size > 0) {
-            this.log.warning(`Some requests were skipped because they were disallowed based on the robots.txt file`, {
-                skipped: [...skippedBecauseOfRobots],
-            });
-        }
-        if (skippedBecauseOfRobots.size > 0 ||
-            skippedBecauseOfLimit.length > 0 ||
-            skippedBecauseOfMaxCrawlDepth.size > 0) {
-            await Promise.all([...skippedBecauseOfRobots]
-                .map((url) => {
-                return this.handleSkippedRequest({ url, reason: 'robotsTxt' });
-            })
-                .concat(skippedBecauseOfLimit.map((request) => {
-                const url = typeof request === 'string' ? request : request.url;
-                return this.handleSkippedRequest({ url, reason: 'limit' });
-            }), [...skippedBecauseOfMaxCrawlDepth].map((url) => {
-                return this.handleSkippedRequest({ url, reason: 'depth' });
-            })));
+        // Report requests skipped due to the maxNewRequests budget (i.e. maxRequestsPerCrawl limit, or an
+        // explicit `limit` option)
+        for (const request of result.requestsOverLimit ?? []) {
+            allSkipped.push({ url: typeof request === 'string' ? request : request.url, reason: 'limit' });
+        }
+        if (allSkipped.length > 0) {
+            const skippedRobotsUrls = allSkipped.filter((s) => s.reason === 'robotsTxt').map((s) => s.url);
+            if (skippedRobotsUrls.length > 0) {
+                this.log.warning(`Some requests were skipped because they were disallowed based on the robots.txt file`, { skipped: skippedRobotsUrls });
+            }
+            // Only log the limit message when an explicit `limit` was passed (not the internal
+            // `maxRequestsPerCrawl`-derived one), and only once per call.
+            if (options.limit !== undefined && allSkipped.some((s) => s.reason === 'limit')) {
+                this.log.info(`Skipping requests in this call due to the enqueueLinks limit of ${options.limit}.`);
+            }
+            await Promise.all(allSkipped.map(async ({ url, reason }) => {
+                await this.handleSkippedRequest({ url, reason });
+                await options.onSkippedRequest?.({ url, reason });
+            }));
         }
         return result;
     }
@@ -1450,52 +1527,6 @@ export class BasicCrawler {
             }
         }
     }
-    /**
-     * Wrapper around the crawling context's `enqueueLinks` method:
-     * - Injects `crawlDepth` to each request being added based on the crawling context request.
-     * - Provides defaults for the `enqueueLinks` options based on the crawler configuration.
-     *      - These options can be overridden by the user.
-     * @internal
-     */
-    async enqueueLinksWithCrawlDepth(options, request, requestManager) {
-        const transformRequestFunctionWrapper = (requestOptions) => {
-            requestOptions.crawlDepth = request.crawlDepth + 1;
-            if (this.maxCrawlDepth !== undefined && requestOptions.crawlDepth > this.maxCrawlDepth) {
-                // Setting `skippedReason` before returning `false` ensures that `reportSkippedRequests`
-                // reports `'depth'` as the reason (via `request.skippedReason ?? reason` fallback),
-                // rather than the generic `'transform'` reason.
-                requestOptions.skippedReason = 'depth';
-                return false;
-            }
-            // After injecting the crawlDepth, we call the user-provided transform function, if there is one.
-            return options.transformRequestFunction?.(requestOptions) ?? requestOptions;
-        };
-        // Create a request-scoped callback that logs enqueueLimit once per request handler call
-        // Only log if an explicit limit was passed to enqueueLinks (not the internal maxRequestsPerCrawl-derived limit)
-        let loggedEnqueueLimitForThisRequest = false;
-        const onSkippedRequest = async (skippedOptions) => {
-            if (skippedOptions.reason === 'enqueueLimit') {
-                if (!loggedEnqueueLimitForThisRequest && options.limit !== undefined) {
-                    this.log.info(`Skipping URLs in the handler for ${request.url} due to the enqueueLinks limit of ${options.limit}.`);
-                    loggedEnqueueLimitForThisRequest = true;
-                }
-            }
-            await this.handleSkippedRequest(skippedOptions);
-        };
-        // `enqueueLinks` applies `options.label`/`options.userData` to every newly enqueued request, so a single
-        // validation against the label's schema covers them all (a no-op unless the router declares a schema).
-        await this.validateRequestUserData({ label: options.label, userData: options.userData });
-        return await enqueueLinks({
-            requestManager,
-            robotsTxtFile: await this.getRobotsTxtFileForUrl(request.url),
-            respectRobotsTxtFile: this.#respectRobotsTxtFile,
-            onSkippedRequest,
-            limit: await this.calculateEnqueuedRequestLimit(options.limit),
-            // Allow user options to override defaults set above ⤴
-            ...options,
-            transformRequestFunction: transformRequestFunctionWrapper,
-        });
-    }
     /**
      * Generator function that yields requests injected with the given crawl depth.
      * @internal

package/internals/send-request.d.ts

@@ -1,5 +1,6 @@
 import type { Request as CrawleeRequest } from '@crawlee/core';
-import type { BaseHttpClient, HttpRequestOptions, ISession, SendRequestOptions } from '@crawlee/types';
+import type { BaseHttpClient } from '@crawlee/http-client';
+import type { HttpRequestOptions, ISession, SendRequestOptions } from '@crawlee/types';
 /**
  * Prepares a function to be used as the `sendRequest` context helper.
  *

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/basic",
-    "version": "4.0.0-beta.121",
+    "version": "4.0.0-beta.123",
     "description": "The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.",
     "engines": {
         "node": ">=22.0.0"
@@ -42,18 +42,18 @@
         "@apify/datastructures": "^2.0.0",
         "@apify/timeout": "^0.4.4",
         "@apify/utilities": "^2.15.5",
-        "@crawlee/core": "4.0.0-beta.121",
-        "@crawlee/http-client": "4.0.0-beta.121",
-        "@crawlee/types": "4.0.0-beta.121",
-        "@crawlee/utils": "4.0.0-beta.121",
+        "@crawlee/core": "4.0.0-beta.123",
+        "@crawlee/http-client": "4.0.0-beta.123",
+        "@crawlee/types": "4.0.0-beta.123",
+        "@crawlee/utils": "4.0.0-beta.123",
         "csv-stringify": "^6.5.2",
-        "ow": "^2.0.0",
         "tldts": "^7.0.6",
         "tslib": "^2.8.1",
-        "type-fest": "^4.41.0"
+        "type-fest": "^4.41.0",
+        "zod": "^4.4.3"
     },
     "optionalDependencies": {
-        "@crawlee/impit-client": "^4.0.0-beta.121"
+        "@crawlee/impit-client": "^4.0.0-beta.123"
     },
     "lerna": {
         "command": {
@@ -62,5 +62,5 @@
             }
         }
     },
-    "gitHead": "5027317de626f5ba6de5047ae9341a898258cc5a"
+    "gitHead": "f77648095c6a3f5ed8815c7620ea765db430ae44"
 }