@crawlee/core 4.0.0-beta.12 → 4.0.0-beta.121

package/enqueue_links/enqueue_links.d.ts

@@ -1,25 +1,29 @@
-import type { Awaitable, BatchAddRequestsResult, Dictionary } from '@crawlee/types';
+import type { BatchAddRequestsResult, Dictionary } from '@crawlee/types';
 import { type RobotsTxtFile } from '@crawlee/utils';
 import type { SetRequired } from 'type-fest';
-import type { RequestProvider, RequestQueueOperationOptions } from '../storages/request_provider.js';
-import type { GlobInput, PseudoUrlInput, RegExpInput, RequestTransform } from './shared.js';
-export type SkippedRequestCallback = (args: {
-    url: string;
-    reason: 'robotsTxt';
-}) => Awaitable<void>;
+import { Request } from '../request.js';
+import type { IRequestManager } from '../storages/request_manager.js';
+import type { AddRequestsBatchedOptions, AddRequestsBatchedResult, RequestQueueOperationOptions } from '../storages/request_queue.js';
+import type { RequestTransform, SkippedRequestCallback, UrlPatternInput } from './shared.js';
 export interface EnqueueLinksOptions extends RequestQueueOperationOptions {
     /** Limit the amount of actually enqueued URLs to this number. Useful for testing across the entire crawling scope. */
     limit?: number;
     /** An array of URLs to enqueue. */
     urls?: readonly string[];
-    /** A request queue to which the URLs will be enqueued. */
-    requestQueue?: RequestProvider;
+    /** A request manager to which the URLs will be enqueued. */
+    requestManager?: IRequestManager;
     /** A CSS selector matching links to be enqueued. */
     selector?: string;
     /** Sets {@link Request.userData} for newly enqueued requests. */
     userData?: Dictionary;
-    /** Sets {@link Request.label} for newly enqueued requests. */
+    /**
+     * Sets {@link Request.label} for newly enqueued requests.
+     *
+     * Can be overwritten by `transformRequestFunction`.
+     */
     label?: string;
+    /** Sets {@link Request.sessionId} for newly enqueued requests. */
+    sessionId?: string;
     /**
      * If set to `true`, tells the crawler to skip navigation and process the request directly.
      * @default false
@@ -31,67 +35,37 @@ export interface EnqueueLinksOptions extends RequestQueueOperationOptions {
      */
     baseUrl?: string;
     /**
-     * An array of glob pattern strings or plain objects
-     * containing glob pattern strings matching the URLs to be enqueued.
+     * An array of URL patterns that URLs must match to be enqueued.
      *
-     * The plain objects must include at least the `glob` property, which holds the glob pattern string.
-     * All remaining keys will be used as request options for the corresponding enqueued {@link Request} objects.
-     *
-     * The matching is always case-insensitive.
-     * If you need case-sensitive matching, use `regexps` property directly.
-     *
-     * If `globs` is an empty array or `undefined`, and `regexps` are also not defined, then the function
-     * enqueues the links with the same subdomain.
-     */
-    globs?: readonly GlobInput[];
-    /**
-     * An array of glob pattern strings, regexp patterns or plain objects
-     * containing patterns matching URLs that will **never** be enqueued.
-     *
-     * The plain objects must include either the `glob` property or the `regexp` property.
-     * All remaining keys will be used as request options for the corresponding enqueued {@link Request} objects.
+     * Accepts glob pattern strings, `{ glob: string }` objects, `RegExp` instances, or `{ regexp: RegExp }` objects.
      *
      * Glob matching is always case-insensitive.
-     * If you need case-sensitive matching, provide a regexp.
-     */
-    exclude?: readonly (GlobInput | RegExpInput)[];
-    /**
-     * An array of regular expressions or plain objects
-     * containing regular expressions matching the URLs to be enqueued.
+     * If you need case-sensitive matching, use a `RegExp`.
      *
-     * The plain objects must include at least the `regexp` property, which holds the regular expression.
-     * All remaining keys will be used as request options for the corresponding enqueued {@link Request} objects.
+     * The patterns are combined with the {@link EnqueueLinksOptions.strategy|`strategy`} using AND logic - a URL
+     * must match at least one `include` pattern **and** satisfy the strategy to be enqueued. To match URLs across
+     * hostnames, pass an explicit {@link EnqueueStrategy.All} strategy.
      *
-     * If `regexps` is an empty array or `undefined`, and `globs` are also not defined, then the function
-     * enqueues the links with the same subdomain.
+     * If `undefined`, the links are enqueued based on the {@link EnqueueLinksOptions.strategy|`strategy`} alone.
+     * Passing an empty array is not allowed.
      */
-    regexps?: readonly RegExpInput[];
+    include?: readonly UrlPatternInput[];
     /**
-     * *NOTE:* In future versions of SDK the options will be removed.
-     * Please use `globs` or `regexps` instead.
-     *
-     * An array of {@link PseudoUrl} strings or plain objects
-     * containing {@link PseudoUrl} strings matching the URLs to be enqueued.
-     *
-     * The plain objects must include at least the `purl` property, which holds the pseudo-URL string.
-     * All remaining keys will be used as request options for the corresponding enqueued {@link Request} objects.
-     *
-     * With a pseudo-URL string, the matching is always case-insensitive.
-     * If you need case-sensitive matching, use `regexps` property directly.
+     * An array of URL patterns. Matching URLs will **not** be enqueued.
      *
-     * If `pseudoUrls` is an empty array or `undefined`, then the function
-     * enqueues the links with the same subdomain.
+     * Accepts glob pattern strings, `{ glob: string }` objects, `RegExp` instances, or `{ regexp: RegExp }` objects.
      *
-     * @deprecated prefer using `globs` or `regexps` instead
+     * Glob matching is always case-insensitive.
+     * If you need case-sensitive matching, use a `RegExp`.
      */
-    pseudoUrls?: readonly PseudoUrlInput[];
+    exclude?: readonly UrlPatternInput[];
     /**
-     * Just before a new {@link Request} is constructed and enqueued to the {@link RequestQueue}, this function can be used
-     * to remove it or modify its contents such as `userData`, `payload` or, most importantly `uniqueKey`. This is useful
+     * After request options are filtered by `include`/`exclude` patterns, this function can be used
+     * to remove them or modify their contents such as `userData`, `payload` or, most importantly `uniqueKey`. This is useful
      * when you need to enqueue multiple `Requests` to the queue that share the same URL, but differ in methods or payloads,
      * or to dynamically update or create `userData`.
      *
-     * For example: by adding `keepUrlFragment: true` to the `request` object, URL fragments will not be removed
+     * For example: by adding `keepUrlFragment: true` to the request options, URL fragments will not be removed
      * when `uniqueKey` is computed.
      *
      * **Example:**
@@ -105,9 +79,13 @@ export interface EnqueueLinksOptions extends RequestQueueOperationOptions {
      * }
      * ```
      *
-     * Note that `transformRequestFunction` has a priority over request options
-     * specified in `globs`, `regexps`, or `pseudoUrls` objects,
-     * and thus some options could be over-written by `transformRequestFunction`.
+     * Note that `transformRequestFunction` has the highest priority and can overwrite
+     * the global `label` option.
+     *
+     * The function receives a {@link RequestOptions} object and can return either:
+     * - The modified {@link RequestOptions} object
+     * - `'unchanged'` to keep the original options as-is
+     * - A falsy value or `'skip'` to exclude the request from the queue
      */
     transformRequestFunction?: RequestTransform;
     /**
@@ -138,10 +116,21 @@ export interface EnqueueLinksOptions extends RequestQueueOperationOptions {
      * RobotsTxtFile instance for the current request that triggered the `enqueueLinks`.
      * If provided, disallowed URLs will be ignored.
      */
-    robotsTxtFile?: RobotsTxtFile;
+    robotsTxtFile?: Pick<RobotsTxtFile, 'isAllowed'>;
+    /**
+     * Mirrors {@link BasicCrawlerOptions.respectRobotsTxtFile}: pass `false` to disable filtering or
+     * `{ userAgent }` to evaluate rules for a specific user-agent. Defaults to `*` when
+     * {@link EnqueueLinksOptions.robotsTxtFile|`robotsTxtFile`} is provided.
+     */
+    respectRobotsTxtFile?: boolean | {
+        userAgent?: string;
+    };
     /**
      * When a request is skipped for some reason, you can use this callback to act on it.
-     * This is currently fired only for requests skipped based on robots.txt file.
+     * This is currently fired for requests skipped
+     * 1. based on robots.txt file,
+     * 2. because they don't match enqueueLinks filters,
+     * 3. or because the maxRequestsPerCrawl limit has been reached
      */
     onSkippedRequest?: SkippedRequestCallback;
 }
@@ -200,17 +189,16 @@ export declare enum EnqueueStrategy {
  * This function enqueues the urls provided to the {@link RequestQueue} provided. If you want to automatically find and enqueue links,
  * you should use the context-aware `enqueueLinks` function provided on the crawler contexts.
  *
- * 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.
+ * Optionally, the function allows you to filter the target links' URLs using an array of glob or regexp patterns.
  *
  * **Example usage**
  *
  * ```javascript
  * await enqueueLinks({
  *   urls: aListOfFoundUrls,
- *   requestQueue,
+ *   requestManager,
  *   selector: 'a.product-detail',
- *   globs: [
+ *   include: [
  *       'https://www.example.com/handbags/*',
  *       'https://www.example.com/purses/*'
  *   ],
@@ -220,7 +208,11 @@ export declare enum EnqueueStrategy {
  * @param options All `enqueueLinks()` parameters are passed via an options object.
  * @returns Promise that resolves to {@link BatchAddRequestsResult} object.
  */
-export declare function enqueueLinks(options: SetRequired<EnqueueLinksOptions, 'requestQueue' | 'urls'>): Promise<BatchAddRequestsResult>;
+export declare function enqueueLinks(options: SetRequired<Omit<EnqueueLinksOptions, 'requestManager'>, 'urls'> & {
+    requestManager: {
+        addRequestsBatched: (requests: Request<Dictionary>[], options: AddRequestsBatchedOptions) => Promise<AddRequestsBatchedResult>;
+    };
+}): Promise<BatchAddRequestsResult>;
 /**
  * @internal
  * This method helps resolve the baseUrl that will be used for filtering in {@link enqueueLinks}.
@@ -239,4 +231,3 @@ export interface ResolveBaseUrl {
     originalRequestUrl: string;
     finalRequestUrl?: string;
 }
-//# sourceMappingURL=enqueue_links.d.ts.map

package/enqueue_links/enqueue_links.js

@@ -1,7 +1,7 @@
 import ow from 'ow';
 import { getDomain } from 'tldts';
-import log from '@apify/log';
-import { constructGlobObjectsFromGlobs, constructRegExpObjectsFromPseudoUrls, constructRegExpObjectsFromRegExps, createRequestOptions, createRequests, filterRequestsByPatterns, } from './shared.js';
+import { Request } from '../request.js';
+import { applyRequestTransform, constructUrlPatternObjects, createRequestOptions, filterRequestOptionsByPatterns, } from './shared.js';
 /**
  * The different enqueueing strategies available.
  *
@@ -58,17 +58,16 @@ export var EnqueueStrategy;
  * This function enqueues the urls provided to the {@link RequestQueue} provided. If you want to automatically find and enqueue links,
  * you should use the context-aware `enqueueLinks` function provided on the crawler contexts.
  *
- * 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.
+ * Optionally, the function allows you to filter the target links' URLs using an array of glob or regexp patterns.
  *
  * **Example usage**
  *
  * ```javascript
  * await enqueueLinks({
  *   urls: aListOfFoundUrls,
- *   requestQueue,
+ *   requestManager,
  *   selector: 'a.product-detail',
- *   globs: [
+ *   include: [
  *       'https://www.example.com/handbags/*',
  *       'https://www.example.com/purses/*'
  *   ],
@@ -85,52 +84,33 @@ export async function enqueueLinks(options) {
             'Check out our guide on how to use enqueueLinks() here: https://crawlee.dev/js/docs/examples/crawl-relative-links',
         ].join('\n'));
     }
+    const urlPatternValidator = ow.any(ow.string, ow.regExp, ow.object.hasKeys('glob'), ow.object.hasKeys('regexp'));
     ow(options, ow.object.exactShape({
         urls: ow.array.ofType(ow.string),
-        requestQueue: ow.object.hasKeys('fetchNextRequest', 'addRequest'),
+        requestManager: ow.object.hasKeys('addRequestsBatched'),
         robotsTxtFile: ow.optional.object.hasKeys('isAllowed'),
+        respectRobotsTxtFile: ow.optional.any(ow.boolean, ow.object.exactShape({ userAgent: ow.optional.string })),
         onSkippedRequest: ow.optional.function,
         forefront: ow.optional.boolean,
         skipNavigation: ow.optional.boolean,
+        sessionId: ow.optional.string,
         limit: ow.optional.number,
         selector: ow.optional.string,
         baseUrl: ow.optional.string,
         userData: ow.optional.object,
         label: ow.optional.string,
-        pseudoUrls: ow.optional.array.ofType(ow.any(ow.string, ow.object.hasKeys('purl'))),
-        globs: ow.optional.array.ofType(ow.any(ow.string, ow.object.hasKeys('glob'))),
-        exclude: ow.optional.array.ofType(ow.any(ow.string, ow.regExp, ow.object.hasKeys('glob'), ow.object.hasKeys('regexp'))),
-        regexps: ow.optional.array.ofType(ow.any(ow.regExp, ow.object.hasKeys('regexp'))),
+        include: ow.optional.array.minLength(1).ofType(urlPatternValidator),
+        exclude: ow.optional.array.ofType(urlPatternValidator),
         transformRequestFunction: ow.optional.function,
         strategy: ow.optional.string.oneOf(Object.values(EnqueueStrategy)),
         waitForAllRequestsToBeAdded: ow.optional.boolean,
     }));
-    const { requestQueue, limit, urls, pseudoUrls, exclude, globs, regexps, transformRequestFunction, forefront, waitForAllRequestsToBeAdded, robotsTxtFile, onSkippedRequest, } = options;
-    const urlExcludePatternObjects = [];
-    const urlPatternObjects = [];
-    if (exclude?.length) {
-        for (const excl of exclude) {
-            if (typeof excl === 'string' || 'glob' in excl) {
-                urlExcludePatternObjects.push(...constructGlobObjectsFromGlobs([excl]));
-            }
-            else if (excl instanceof RegExp || 'regexp' in excl) {
-                urlExcludePatternObjects.push(...constructRegExpObjectsFromRegExps([excl]));
-            }
-        }
-    }
-    if (pseudoUrls?.length) {
-        log.deprecated('`pseudoUrls` option is deprecated, use `globs` or `regexps` instead');
-        urlPatternObjects.push(...constructRegExpObjectsFromPseudoUrls(pseudoUrls));
-    }
-    if (globs?.length) {
-        urlPatternObjects.push(...constructGlobObjectsFromGlobs(globs));
-    }
-    if (regexps?.length) {
-        urlPatternObjects.push(...constructRegExpObjectsFromRegExps(regexps));
-    }
-    if (!urlPatternObjects.length) {
-        options.strategy ??= EnqueueStrategy.SameHostname;
-    }
+    const { requestManager, limit, urls, include, exclude, transformRequestFunction, forefront, waitForAllRequestsToBeAdded, robotsTxtFile, onSkippedRequest, } = options;
+    const urlExcludePatternObjects = exclude?.length ? constructUrlPatternObjects(exclude) : [];
+    const urlPatternObjects = include?.length ? constructUrlPatternObjects(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.
+    options.strategy ??= EnqueueStrategy.SameHostname;
     const enqueueStrategyPatterns = [];
     if (options.baseUrl) {
         const url = new URL(options.baseUrl);
@@ -167,44 +147,60 @@ export async function enqueueLinks(options) {
                 break;
         }
     }
+    async function reportSkippedRequests(skippedRequests, reason) {
+        if (onSkippedRequest && skippedRequests.length > 0) {
+            await Promise.all(skippedRequests.map((request) => {
+                return onSkippedRequest({
+                    url: request.url,
+                    reason: request.skippedReason ?? reason,
+                });
+            }));
+        }
+    }
     let requestOptions = createRequestOptions(urls, options);
-    if (robotsTxtFile) {
+    if (robotsTxtFile && options.respectRobotsTxtFile !== false) {
+        const robotsUserAgent = typeof options.respectRobotsTxtFile === 'object' ? (options.respectRobotsTxtFile.userAgent ?? '*') : '*';
         const skippedRequests = [];
         requestOptions = requestOptions.filter((request) => {
-            if (robotsTxtFile.isAllowed(request.url)) {
+            if (robotsTxtFile.isAllowed(request.url, robotsUserAgent)) {
                 return true;
             }
             skippedRequests.push(request);
             return false;
         });
-        if (onSkippedRequest && skippedRequests.length > 0) {
-            await Promise.all(skippedRequests.map((request) => {
-                return onSkippedRequest({ url: request.url, reason: 'robotsTxt' });
-            }));
-        }
+        await reportSkippedRequests(skippedRequests, 'robotsTxt');
     }
-    if (transformRequestFunction) {
-        requestOptions = requestOptions
-            .map((request) => transformRequestFunction(request))
-            .filter((r) => !!r);
-    }
-    function createFilteredRequests() {
-        // No user provided patterns means we can skip an extra filtering step
+    async function createFilteredRequests() {
+        const skippedRequests = [];
+        // Step 1: Filter request options by exclude patterns, user include patterns, and strategy patterns.
+        let filteredOptions;
         if (urlPatternObjects.length === 0) {
-            return createRequests(requestOptions, enqueueStrategyPatterns, urlExcludePatternObjects, options.strategy);
+            filteredOptions = filterRequestOptionsByPatterns(requestOptions, enqueueStrategyPatterns.length > 0 ? enqueueStrategyPatterns : undefined, urlExcludePatternObjects, options.strategy, (url) => skippedRequests.push(url));
+        }
+        else {
+            // Filter by user patterns first (with exclude)
+            const afterUserPatterns = filterRequestOptionsByPatterns(requestOptions, urlPatternObjects, urlExcludePatternObjects, options.strategy, (url) => skippedRequests.push(url));
+            // ...then filter by the enqueue links strategy (making this an AND check)
+            filteredOptions = filterRequestOptionsByPatterns(afterUserPatterns, enqueueStrategyPatterns.length > 0 ? enqueueStrategyPatterns : undefined, [], options.strategy, (url) => skippedRequests.push(url));
         }
-        // Generate requests based on the user patterns first
-        const generatedRequestsFromUserFilters = createRequests(requestOptions, urlPatternObjects, urlExcludePatternObjects, options.strategy);
-        // ...then filter them by the enqueue links strategy (making this an AND check)
-        return filterRequestsByPatterns(generatedRequestsFromUserFilters, enqueueStrategyPatterns);
+        await reportSkippedRequests(skippedRequests.map((url) => ({ url })), 'filters');
+        // Step 2: Apply transformRequestFunction on request options - it has the highest priority
+        if (transformRequestFunction) {
+            const skippedByTransform = [];
+            filteredOptions = applyRequestTransform(filteredOptions, transformRequestFunction, (r) => skippedByTransform.push(r));
+            await reportSkippedRequests(skippedByTransform, 'transform');
+        }
+        // Step 3: Create Request instances from the final request options
+        return filteredOptions.map((opts) => new Request(opts));
     }
-    let requests = createFilteredRequests();
-    if (limit)
-        requests = requests.slice(0, limit);
-    const { addedRequests } = await requestQueue.addRequestsBatched(requests, {
+    const { addedRequests, requestsOverLimit } = await requestManager.addRequestsBatched(await createFilteredRequests(), {
         forefront,
         waitForAllRequestsToBeAdded,
+        maxNewRequests: limit,
     });
+    if (requestsOverLimit?.length !== undefined && requestsOverLimit.length > 0) {
+        await reportSkippedRequests(requestsOverLimit.map((r) => ({ url: typeof r === 'string' ? r : r.url })), 'enqueueLimit');
+    }
     return { processedRequests: addedRequests, unprocessedRequests: [] };
 }
 /**
@@ -242,9 +238,8 @@ export function resolveBaseUrlForEnqueueLinksFiltering({ enqueueStrategy, finalR
     return originalUrlOrigin;
 }
 /**
- * Internal function that changes the enqueue globs to match both http and https
+ * Internal function that changes the enqueue glob patterns to match both http and https
  */
 function ignoreHttpSchema(pattern) {
     return pattern.replace(/^(https?):\/\//, 'http{s,}://');
 }
-//# sourceMappingURL=enqueue_links.js.map

package/enqueue_links/index.d.ts

@@ -1,3 +1,2 @@
 export * from './enqueue_links.js';
 export * from './shared.js';
-//# sourceMappingURL=index.d.ts.map

package/enqueue_links/index.js

@@ -1,3 +1,2 @@
 export * from './enqueue_links.js';
 export * from './shared.js';
-//# sourceMappingURL=index.js.map

package/enqueue_links/shared.d.ts

@@ -1,33 +1,30 @@
+import type { Awaitable } from '@crawlee/types';
 import type { RequestOptions } from '../request.js';
-import { Request } from '../request.js';
 import type { EnqueueLinksOptions } from './enqueue_links.js';
-export { tryAbsoluteURL } from '@crawlee/utils';
-export type UrlPatternObject = {
+export { tryAbsoluteURL } from '@crawlee/utils/internal';
+export interface UrlPatternObject {
     glob?: string;
     regexp?: RegExp;
-} & Pick<RequestOptions, 'method' | 'payload' | 'label' | 'userData' | 'headers'>;
-export type PseudoUrlObject = {
-    purl: string;
-} & Pick<RequestOptions, 'method' | 'payload' | 'label' | 'userData' | 'headers'>;
-export type PseudoUrlInput = string | PseudoUrlObject;
-export type GlobObject = {
+}
+export interface GlobObject {
     glob: string;
-} & Pick<RequestOptions, 'method' | 'payload' | 'label' | 'userData' | 'headers'>;
+}
 export type GlobInput = string | GlobObject;
-export type RegExpObject = {
+export interface RegExpObject {
     regexp: RegExp;
-} & Pick<RequestOptions, 'method' | 'payload' | 'label' | 'userData' | 'headers'>;
+}
 export type RegExpInput = RegExp | RegExpObject;
+/** Unified URL pattern input — accepts glob strings, glob objects, RegExp instances, or regexp objects. */
+export type UrlPatternInput = GlobInput | RegExpInput;
+export type SkippedRequestReason = 'robotsTxt' | 'limit' | 'enqueueLimit' | 'filters' | 'transform' | 'redirect' | 'depth';
+export type SkippedRequestCallback = (args: {
+    url: string;
+    reason: SkippedRequestReason;
+}) => Awaitable<void>;
 /**
  * @ignore
  */
-export declare function updateEnqueueLinksPatternCache(item: GlobInput | RegExpInput | PseudoUrlInput, pattern: RegExpObject | GlobObject): void;
-/**
- * Helper factory used in the `enqueueLinks()` and enqueueLinksByClickingElements() function
- * to construct RegExps from PseudoUrl strings.
- * @ignore
- */
-export declare function constructRegExpObjectsFromPseudoUrls(pseudoUrls: readonly PseudoUrlInput[]): RegExpObject[];
+export declare function updateEnqueueLinksPatternCache(item: GlobInput | RegExpInput, pattern: RegExpObject | GlobObject): void;
 /**
  * Helper factory used in the `enqueueLinks()` and enqueueLinksByClickingElements() function
  * to construct Glob objects from Glob pattern strings.
@@ -45,23 +42,39 @@ export declare function validateGlobPattern(glob: string): string;
  */
 export declare function constructRegExpObjectsFromRegExps(regexps: readonly RegExpInput[]): RegExpObject[];
 /**
+ * Helper factory used in the `enqueueLinks()` function to construct UrlPatternObjects
+ * from a mixed array of glob strings, glob objects, RegExp instances, and regexp objects.
  * @ignore
  */
-export declare function createRequests(requestOptions: (string | RequestOptions)[], urlPatternObjects?: UrlPatternObject[], excludePatternObjects?: UrlPatternObject[], strategy?: EnqueueLinksOptions['strategy']): Request[];
-export declare function filterRequestsByPatterns(requests: Request[], patterns?: UrlPatternObject[]): Request[];
+export declare function constructUrlPatternObjects(patterns: readonly UrlPatternInput[]): UrlPatternObject[];
 /**
+ * Filters request options by URL patterns.
+ *
+ * When `includePatterns` is empty/undefined, all options pass through (only exclude filtering applies).
  * @ignore
  */
-export declare function createRequestOptions(sources: readonly (string | Record<string, unknown>)[], options?: Pick<EnqueueLinksOptions, 'label' | 'userData' | 'baseUrl' | 'skipNavigation' | 'strategy'>): RequestOptions[];
+export declare function filterRequestOptionsByPatterns(requestOptions: RequestOptions[], includePatterns: UrlPatternObject[] | undefined, excludePatterns?: UrlPatternObject[], strategy?: EnqueueLinksOptions['strategy'], onSkippedUrl?: (url: string) => void): RequestOptions[];
 /**
- * Takes an Apify {@link RequestOptions} object and changes its attributes in a desired way. This user-function is used
- * {@link enqueueLinks} to modify requests before enqueuing them.
+ * @ignore
+ */
+export declare function createRequestOptions(sources: readonly (string | Record<string, unknown>)[], options?: Pick<EnqueueLinksOptions, 'label' | 'userData' | 'baseUrl' | 'skipNavigation' | 'sessionId' | 'strategy'>): RequestOptions[];
+/**
+ * Takes a {@link RequestOptions} object and changes its attributes in a desired way. This user-function is used
+ * by {@link enqueueLinks} to modify request options before they are converted to {@link Request} instances.
  */
 export interface RequestTransform {
     /**
      * @param original Request options to be modified.
-     * @returns The modified request options to enqueue.
+     * @returns The modified request options to enqueue, `'unchanged'` to keep the original options as-is,
+     *   or a falsy value / `'skip'` to exclude the request from the queue.
      */
-    (original: RequestOptions): RequestOptions | false | undefined | null;
+    (original: RequestOptions): RequestOptions | false | undefined | null | 'skip' | 'unchanged';
 }
-//# sourceMappingURL=shared.d.ts.map
+/**
+ * Applies a {@link RequestTransform} function to a list of request options.
+ * Options for which the transform returns a falsy value are removed from the list.
+ * @param onSkipped Called with the original request options when the transform returns a falsy value (i.e. the request is skipped).
+ * @ignore
+ * @internal
+ */
+export declare function applyRequestTransform(requestOptions: RequestOptions[], transformFn: RequestTransform, onSkipped?: (requestOptions: RequestOptions) => void): RequestOptions[];