@crawlee/cheerio 4.0.0-beta.19 → 4.0.0-beta.190

package/README.md

@@ -1,23 +1,23 @@
 <h1 align="center">
     <a href="https://crawlee.dev">
         <picture>
-          <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/apify/crawlee/master/website/static/img/crawlee-dark.svg?sanitize=true">
-          <img alt="Crawlee" src="https://raw.githubusercontent.com/apify/crawlee/master/website/static/img/crawlee-light.svg?sanitize=true" width="500">
+          <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/apify/crawlee/master/website/static/img/crawlee-dark.svg?sanitize=true" />
+          <img alt="Crawlee" src="https://raw.githubusercontent.com/apify/crawlee/master/website/static/img/crawlee-light.svg?sanitize=true" width="500" />
         </picture>
     </a>
-    <br>
+    <br />
     <small>A web scraping and browser automation library</small>
 </h1>
 
-<p align=center>
-    <a href="https://trendshift.io/repositories/5179" target="_blank"><img src="https://trendshift.io/api/badge/repositories/5179" alt="apify%2Fcrawlee | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+<p align="center">
+    <a href="https://trendshift.io/repositories/5179" target="_blank"><img src="https://trendshift.io/api/badge/repositories/5179" alt="apify%2Fcrawlee | Trendshift" width="250" height="55"/></a>
 </p>
 
-<p align=center>
-    <a href="https://www.npmjs.com/package/@crawlee/core" rel="nofollow"><img src="https://img.shields.io/npm/v/@crawlee/core.svg" alt="NPM latest version" data-canonical-src="https://img.shields.io/npm/v/@crawlee/core/next.svg" style="max-width: 100%;"></a>
-    <a href="https://www.npmjs.com/package/@crawlee/core" rel="nofollow"><img src="https://img.shields.io/npm/dm/@crawlee/core.svg" alt="Downloads" data-canonical-src="https://img.shields.io/npm/dm/@crawlee/core.svg" style="max-width: 100%;"></a>
-    <a href="https://discord.gg/jyEM2PRvMU" rel="nofollow"><img src="https://img.shields.io/discord/801163717915574323?label=discord" alt="Chat on discord" data-canonical-src="https://img.shields.io/discord/801163717915574323?label=discord" style="max-width: 100%;"></a>
-    <a href="https://github.com/apify/crawlee/actions/workflows/test-ci.yml"><img src="https://github.com/apify/crawlee/actions/workflows/test-ci.yml/badge.svg?branch=master" alt="Build Status" style="max-width: 100%;"></a>
+<p align="center">
+    <a href="https://www.npmjs.com/package/@crawlee/core" rel="nofollow"><img src="https://img.shields.io/npm/v/@crawlee/core.svg" alt="NPM latest version" data-canonical-src="https://img.shields.io/npm/v/@crawlee/core/next.svg" /></a>
+    <a href="https://www.npmjs.com/package/@crawlee/core" rel="nofollow"><img src="https://img.shields.io/npm/dm/@crawlee/core.svg" alt="Downloads" data-canonical-src="https://img.shields.io/npm/dm/@crawlee/core.svg" /></a>
+    <a href="https://discord.gg/jyEM2PRvMU" rel="nofollow"><img src="https://img.shields.io/discord/801163717915574323?label=discord" alt="Chat on discord" data-canonical-src="https://img.shields.io/discord/801163717915574323?label=discord" /></a>
+    <a href="https://github.com/apify/crawlee/actions/workflows/test-ci.yml"><img src="https://github.com/apify/crawlee/actions/workflows/test-ci.yml/badge.svg?branch=master" alt="Build Status" /></a>
 </p>
 
 Crawlee covers your crawling and scraping end-to-end and **helps you build reliable scrapers. Fast.**
@@ -89,7 +89,7 @@ By default, Crawlee stores data to `./storage` in the current working directory.
 We provide automated beta builds for every merged code change in Crawlee. You can find them in the npm [list of releases](https://www.npmjs.com/package/crawlee?activeTab=versions). If you want to test new features or bug fixes before we release them, feel free to install a beta build like this:
 
 ```bash
-npm install crawlee@3.12.3-beta.13
+npm install crawlee@next
 ```
 
 If you also use the [Apify SDK](https://github.com/apify/apify-sdk-js), you need to specify dependency overrides in your `package.json` file so that you don't end up with multiple versions of Crawlee installed:
@@ -98,9 +98,9 @@ If you also use the [Apify SDK](https://github.com/apify/apify-sdk-js), you need
 {
     "overrides": {
        "apify": {
-           "@crawlee/core": "3.12.3-beta.13",
-           "@crawlee/types": "3.12.3-beta.13",
-           "@crawlee/utils": "3.12.3-beta.13"
+           "@crawlee/core": "$crawlee",
+           "@crawlee/types": "$crawlee",
+           "@crawlee/utils": "$crawlee"
        }
     }
 }

package/index.d.ts

@@ -1,3 +1,3 @@
 export * from '@crawlee/http';
 export * from './internals/cheerio-crawler.js';
-//# sourceMappingURL=index.d.ts.map
+export type { CheerioParseResult } from './internals/cheerio-parser.js';

package/index.js

@@ -1,3 +1,2 @@
 export * from '@crawlee/http';
 export * from './internals/cheerio-crawler.js';
-//# sourceMappingURL=index.js.map

package/internals/cheerio-crawler.d.ts

@@ -1,58 +1,18 @@
-import type { BasicCrawlingContext, Configuration, EnqueueLinksOptions, ErrorHandler, GetUserDataFromRequest, HttpCrawlerOptions, InternalHttpCrawlingContext, InternalHttpHook, RequestHandler, RequestProvider, RouterRoutes, SkippedRequestCallback } from '@crawlee/http';
-import { HttpCrawler } from '@crawlee/http';
-import type { BatchAddRequestsResult, Dictionary } from '@crawlee/types';
-import { type CheerioRoot, type RobotsTxtFile } from '@crawlee/utils';
-import * as cheerio from 'cheerio';
+import type { CrawlingContext, DOMCrawlingContext, ErrorHandler, GetUserDataFromRequest, HttpCrawlerOptions, InternalHttpHook, RequestHandler, RouterHandler, RouterRoutes, RouteSchemas, RoutesFromSchemas } from '@crawlee/http';
+import { DOMCrawler } from '@crawlee/http';
+import type { Dictionary } from '@crawlee/types';
+import type { CheerioParseResult } from './cheerio-parser.js';
 export type CheerioErrorHandler<UserData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
-JSONData extends Dictionary = any> = ErrorHandler<CheerioCrawlingContext<UserData, JSONData>>;
+JSONData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
+ContextExtension = Dictionary<never>> = ErrorHandler<CrawlingContext, CheerioCrawlingContext<UserData, JSONData> & ContextExtension>;
 export interface CheerioCrawlerOptions<ContextExtension = Dictionary<never>, ExtendedContext extends CheerioCrawlingContext = CheerioCrawlingContext & ContextExtension, UserData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
-JSONData extends Dictionary = any> extends HttpCrawlerOptions<CheerioCrawlingContext<UserData, JSONData>, ContextExtension, ExtendedContext> {
+JSONData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
+Routes extends Record<keyof Routes, Dictionary> = Record<string, UserData>, StatisticStateExtension extends object = {}> extends HttpCrawlerOptions<CheerioCrawlingContext<UserData, JSONData>, ContextExtension, ExtendedContext, Routes, StatisticStateExtension> {
 }
 export type CheerioHook<UserData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
 JSONData extends Dictionary = any> = InternalHttpHook<CheerioCrawlingContext<UserData, JSONData>>;
 export interface CheerioCrawlingContext<UserData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
-JSONData extends Dictionary = any> extends InternalHttpCrawlingContext<UserData, JSONData> {
-    /**
-     * The raw HTML content of the web page as a string.
-     */
-    body: string;
-    /**
-     * The [Cheerio](https://cheerio.js.org/) object with parsed HTML.
-     * Cheerio is available only for HTML and XML content types.
-     */
-    $: cheerio.CheerioAPI;
-    /**
-     * Wait for an element matching the selector to appear. Timeout is ignored.
-     *
-     * **Example usage:**
-     * ```ts
-     * async requestHandler({ waitForSelector, parseWithCheerio }) {
-     *     await waitForSelector('article h1');
-     *     const $ = await parseWithCheerio();
-     *     const title = $('title').text();
-     * });
-     * ```
-     */
-    waitForSelector(selector: string, timeoutMs?: number): Promise<void>;
-    /**
-     * Returns Cheerio handle, this is here to unify the crawler API, so they all have this handy method.
-     * It has the same return type as the `$` context property, use it only if you are abstracting your workflow to
-     * support different context types in one handler.
-     * When provided with the `selector` argument, it will throw if it's not available.
-     *
-     * **Example usage:**
-     * ```ts
-     * async requestHandler({ parseWithCheerio }) {
-     *     const $ = await parseWithCheerio();
-     *     const title = $('title').text();
-     * });
-     * ```
-     */
-    parseWithCheerio(selector?: string, timeoutMs?: number): Promise<CheerioRoot>;
-    /**
-     * Helper function for extracting URLs from the parsed HTML and adding them to the request queue.
-     */
-    enqueueLinks(options?: EnqueueLinksOptions): Promise<BatchAddRequestsResult>;
+JSONData extends Dictionary = any> extends DOMCrawlingContext<CheerioParseResult, UserData, JSONData> {
 }
 export type CheerioRequestHandler<UserData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
 JSONData extends Dictionary = any> = RequestHandler<CheerioCrawlingContext<UserData, JSONData>>;
@@ -72,13 +32,15 @@ JSONData extends Dictionary = any> = RequestHandler<CheerioCrawlingContext<UserD
  * and then invokes the user-provided {@link CheerioCrawlerOptions.requestHandler} to extract page data
  * using a [jQuery](https://jquery.com/)-like interface to the parsed HTML DOM.
  *
- * The source URLs are represented using {@link Request} objects that are fed from
- * {@link RequestList} or {@link RequestQueue} instances provided by the {@link CheerioCrawlerOptions.requestList}
- * or {@link CheerioCrawlerOptions.requestQueue} constructor options, respectively.
+ * The source URLs are represented using {@link Request} objects that are fed from the
+ * {@link IRequestManager|request manager} provided via the {@link CheerioCrawlerOptions.requestManager|`requestManager`}
+ * constructor option (a {@link RequestQueue} is itself a request manager). To read from a read-only source such
+ * as a {@link RequestList} while still being able to enqueue new requests, combine it with a queue into a
+ * {@link RequestManagerTandem} via {@link IRequestLoader.toTandem|`requestLoader.toTandem()`} and pass the
+ * result as `requestManager`.
  *
- * If both {@link CheerioCrawlerOptions.requestList} and {@link CheerioCrawlerOptions.requestQueue} are used,
- * the instance first processes URLs from the {@link RequestList} and automatically enqueues all of them
- * to {@link RequestQueue} before it starts their processing. This ensures that a single URL is not crawled multiple times.
+ * > The {@link CheerioCrawlerOptions.requestList|`requestList`} and {@link CheerioCrawlerOptions.requestQueue|`requestQueue`}
+ * > options are deprecated; they are still accepted and folded into a single `requestManager` for back-compat.
  *
  * The crawler finishes when there are no more {@link Request} objects to crawl.
  *
@@ -92,18 +54,18 @@ JSONData extends Dictionary = any> = RequestHandler<CheerioCrawlingContext<UserD
  * ]
  * ```
  *
- * By default, `CheerioCrawler` only processes web pages with the `text/html`
- * and `application/xhtml+xml` MIME content types (as reported by the `Content-Type` HTTP header),
+ * By default, `CheerioCrawler` only processes web pages with the `text/html`, `application/xhtml+xml`, `text/xml`, `application/xml`,
+ * and `application/json` MIME content types (as reported by the `Content-Type` HTTP header),
  * and skips pages with other content types. If you want the crawler to process other content types,
  * use the {@link CheerioCrawlerOptions.additionalMimeTypes} constructor option.
  * Beware that the parsing behavior differs for HTML, XML, JSON and other types of content.
  * For more details, see {@link CheerioCrawlerOptions.requestHandler}.
  *
- * New requests are only dispatched when there is enough free CPU and memory available,
- * using the functionality provided by the {@link AutoscaledPool} class.
- * All {@link AutoscaledPool} configuration options can be passed to the `autoscaledPoolOptions`
- * parameter of the `CheerioCrawler` constructor. For user convenience, the `minConcurrency` and `maxConcurrency`
- * {@link AutoscaledPool} options are available directly in the `CheerioCrawler` constructor.
+ * New requests are only dispatched when there is enough free CPU and memory available, as judged by the crawler's
+ * {@link ConcurrencySystem}.
+ * Concurrency is tuned via the `minConcurrency`, `maxConcurrency` and `maxRequestsPerMinute` options of the
+ * `CheerioCrawler` constructor, or, for finer control, by injecting a pre-configured
+ * {@link ConcurrencySystem|`concurrencySystem`}.
  *
  * **Example usage:**
  *
@@ -133,32 +95,12 @@ JSONData extends Dictionary = any> = RequestHandler<CheerioCrawlingContext<UserD
  * ```
  * @category Crawlers
  */
-export declare class CheerioCrawler<ContextExtension = Dictionary<never>, ExtendedContext extends CheerioCrawlingContext = CheerioCrawlingContext & ContextExtension> extends HttpCrawler<CheerioCrawlingContext, ContextExtension, ExtendedContext> {
+export declare class CheerioCrawler<ContextExtension = Dictionary<never>, ExtendedContext extends CheerioCrawlingContext = CheerioCrawlingContext & ContextExtension, Routes extends Record<keyof Routes, Dictionary> = Record<string, GetUserDataFromRequest<CheerioCrawlingContext['request']>>, StatisticStateExtension extends object = {}> extends DOMCrawler<CheerioParseResult, ContextExtension, ExtendedContext, Routes, StatisticStateExtension> {
     /**
      * All `CheerioCrawler` parameters are passed via an options object.
      */
-    constructor(options?: CheerioCrawlerOptions<ContextExtension, ExtendedContext>, config?: Configuration);
-    private parseContent;
-    private addHelpers;
-}
-interface EnqueueLinksInternalOptions {
-    options?: EnqueueLinksOptions;
-    $: cheerio.CheerioAPI | null;
-    requestQueue: RequestProvider;
-    robotsTxtFile?: RobotsTxtFile;
-    onSkippedRequest?: SkippedRequestCallback;
-    originalRequestUrl: string;
-    finalRequestUrl?: string;
-}
-interface BoundEnqueueLinksInternalOptions {
-    enqueueLinks: BasicCrawlingContext['enqueueLinks'];
-    options?: EnqueueLinksOptions;
-    $: cheerio.CheerioAPI | null;
-    originalRequestUrl: string;
-    finalRequestUrl?: string;
+    constructor(options?: CheerioCrawlerOptions<ContextExtension, ExtendedContext, any, any, Routes, StatisticStateExtension>);
 }
-/** @internal */
-export declare function cheerioCrawlerEnqueueLinks(options: EnqueueLinksInternalOptions | BoundEnqueueLinksInternalOptions): Promise<unknown>;
 /**
  * Creates new {@link Router} instance that works based on request labels.
  * This instance can then serve as a `requestHandler` of your {@link CheerioCrawler}.
@@ -183,7 +125,6 @@ export declare function cheerioCrawlerEnqueueLinks(options: EnqueueLinksInternal
  * await crawler.run();
  * ```
  */
-// @ts-ignore optional peer dependency or compatibility with es2022
-export declare function createCheerioRouter<Context extends CheerioCrawlingContext = CheerioCrawlingContext, UserData extends Dictionary = GetUserDataFromRequest<Context['request']>>(routes?: RouterRoutes<Context, UserData>): import("@crawlee/http").RouterHandler<Context>;
-export {};
-//# sourceMappingURL=cheerio-crawler.d.ts.map
+export declare function createCheerioRouter<Context extends CheerioCrawlingContext = CheerioCrawlingContext, Routes extends Record<keyof Routes, Dictionary> = Record<string, GetUserDataFromRequest<Context['request']>>>(routes?: RouterRoutes<Context, Routes>): RouterHandler<Context, Routes>;
+export declare function createCheerioRouter<Context extends CheerioCrawlingContext = CheerioCrawlingContext, UserData extends Dictionary = GetUserDataFromRequest<Context['request']>>(routes?: RouterRoutes<Context, Record<string, UserData>>): RouterHandler<Context, Record<string, UserData>>;
+export declare function createCheerioRouter<Context extends CheerioCrawlingContext = CheerioCrawlingContext, const Schemas extends RouteSchemas = RouteSchemas>(schemas: Schemas): RouterHandler<Context, RoutesFromSchemas<Schemas>>;

package/internals/cheerio-crawler.js

@@ -1,7 +1,5 @@
-import { enqueueLinks, HttpCrawler, resolveBaseUrlForEnqueueLinksFiltering, Router } from '@crawlee/http';
-import { extractUrlsFromCheerio } from '@crawlee/utils';
-import * as cheerio from 'cheerio';
-import { parseDocument } from 'htmlparser2';
+import { DOMCrawler, Router } from '@crawlee/http';
+import { cheerioParser } from './cheerio-parser.js';
 /**
  * Provides a framework for the parallel crawling of web pages using plain HTTP requests and
  * [cheerio](https://www.npmjs.com/package/cheerio) HTML parser.
@@ -18,13 +16,15 @@ import { parseDocument } from 'htmlparser2';
  * and then invokes the user-provided {@link CheerioCrawlerOptions.requestHandler} to extract page data
  * using a [jQuery](https://jquery.com/)-like interface to the parsed HTML DOM.
  *
- * The source URLs are represented using {@link Request} objects that are fed from
- * {@link RequestList} or {@link RequestQueue} instances provided by the {@link CheerioCrawlerOptions.requestList}
- * or {@link CheerioCrawlerOptions.requestQueue} constructor options, respectively.
+ * The source URLs are represented using {@link Request} objects that are fed from the
+ * {@link IRequestManager|request manager} provided via the {@link CheerioCrawlerOptions.requestManager|`requestManager`}
+ * constructor option (a {@link RequestQueue} is itself a request manager). To read from a read-only source such
+ * as a {@link RequestList} while still being able to enqueue new requests, combine it with a queue into a
+ * {@link RequestManagerTandem} via {@link IRequestLoader.toTandem|`requestLoader.toTandem()`} and pass the
+ * result as `requestManager`.
  *
- * If both {@link CheerioCrawlerOptions.requestList} and {@link CheerioCrawlerOptions.requestQueue} are used,
- * the instance first processes URLs from the {@link RequestList} and automatically enqueues all of them
- * to {@link RequestQueue} before it starts their processing. This ensures that a single URL is not crawled multiple times.
+ * > The {@link CheerioCrawlerOptions.requestList|`requestList`} and {@link CheerioCrawlerOptions.requestQueue|`requestQueue`}
+ * > options are deprecated; they are still accepted and folded into a single `requestManager` for back-compat.
  *
  * The crawler finishes when there are no more {@link Request} objects to crawl.
  *
@@ -38,18 +38,18 @@ import { parseDocument } from 'htmlparser2';
  * ]
  * ```
  *
- * By default, `CheerioCrawler` only processes web pages with the `text/html`
- * and `application/xhtml+xml` MIME content types (as reported by the `Content-Type` HTTP header),
+ * By default, `CheerioCrawler` only processes web pages with the `text/html`, `application/xhtml+xml`, `text/xml`, `application/xml`,
+ * and `application/json` MIME content types (as reported by the `Content-Type` HTTP header),
  * and skips pages with other content types. If you want the crawler to process other content types,
  * use the {@link CheerioCrawlerOptions.additionalMimeTypes} constructor option.
  * Beware that the parsing behavior differs for HTML, XML, JSON and other types of content.
  * For more details, see {@link CheerioCrawlerOptions.requestHandler}.
  *
- * New requests are only dispatched when there is enough free CPU and memory available,
- * using the functionality provided by the {@link AutoscaledPool} class.
- * All {@link AutoscaledPool} configuration options can be passed to the `autoscaledPoolOptions`
- * parameter of the `CheerioCrawler` constructor. For user convenience, the `minConcurrency` and `maxConcurrency`
- * {@link AutoscaledPool} options are available directly in the `CheerioCrawler` constructor.
+ * New requests are only dispatched when there is enough free CPU and memory available, as judged by the crawler's
+ * {@link ConcurrencySystem}.
+ * Concurrency is tuned via the `minConcurrency`, `maxConcurrency` and `maxRequestsPerMinute` options of the
+ * `CheerioCrawler` constructor, or, for finer control, by injecting a pre-configured
+ * {@link ConcurrencySystem|`concurrencySystem`}.
  *
  * **Example usage:**
  *
@@ -79,121 +79,14 @@ import { parseDocument } from 'htmlparser2';
  * ```
  * @category Crawlers
  */
-export class CheerioCrawler extends HttpCrawler {
+export class CheerioCrawler extends DOMCrawler {
     /**
      * All `CheerioCrawler` parameters are passed via an options object.
      */
-    constructor(options, config) {
-        super({
-            ...options,
-            contextPipelineBuilder: () => this.buildContextPipeline()
-                .compose({
-                action: async (context) => await this.parseContent(context),
-            })
-                .compose({ action: async (context) => await this.addHelpers(context) }),
-        }, config);
+    constructor(options) {
+        super({ ...options, parser: cheerioParser() });
     }
-    async parseContent(crawlingContext) {
-        const isXml = crawlingContext.contentType.type.includes('xml');
-        const body = Buffer.isBuffer(crawlingContext.body)
-            ? crawlingContext.body.toString(crawlingContext.contentType.encoding)
-            : crawlingContext.body;
-        const dom = parseDocument(body, { decodeEntities: true, xmlMode: isXml });
-        const $ = cheerio.load(dom, {
-            xml: { decodeEntities: true, xmlMode: isXml },
-        });
-        return {
-            $,
-            body,
-        };
-    }
-    async addHelpers(crawlingContext) {
-        const originalEnqueueLinks = crawlingContext.enqueueLinks;
-        return {
-            enqueueLinks: async (enqueueOptions) => {
-                return (await cheerioCrawlerEnqueueLinks({
-                    options: { ...enqueueOptions, limit: this.calculateEnqueuedRequestLimit(enqueueOptions?.limit) },
-                    $: crawlingContext.$,
-                    requestQueue: await this.getRequestQueue(),
-                    robotsTxtFile: await this.getRobotsTxtFileForUrl(crawlingContext.request.url),
-                    onSkippedRequest: this.handleSkippedRequest,
-                    originalRequestUrl: crawlingContext.request.url,
-                    finalRequestUrl: crawlingContext.request.loadedUrl,
-                    enqueueLinks: originalEnqueueLinks,
-                })); // TODO make this type safe
-            },
-            waitForSelector: async (selector, _timeoutMs) => {
-                if (crawlingContext.$(selector).get().length === 0) {
-                    throw new Error(`Selector '${selector}' not found.`);
-                }
-            },
-            parseWithCheerio: async (selector, timeoutMs) => {
-                if (selector) {
-                    await crawlingContext.waitForSelector(selector, timeoutMs);
-                }
-                return crawlingContext.$;
-            },
-        };
-    }
-}
-/** @internal */
-function containsEnqueueLinks(options) {
-    return !!options.enqueueLinks;
 }
-/** @internal */
-export async function cheerioCrawlerEnqueueLinks(options) {
-    const { options: enqueueLinksOptions, $, originalRequestUrl, finalRequestUrl } = options;
-    if (!$) {
-        throw new Error('Cannot enqueue links because the DOM is not available.');
-    }
-    const baseUrl = resolveBaseUrlForEnqueueLinksFiltering({
-        enqueueStrategy: enqueueLinksOptions?.strategy,
-        finalRequestUrl,
-        originalRequestUrl,
-        userProvidedBaseUrl: enqueueLinksOptions?.baseUrl,
-    });
-    const urls = extractUrlsFromCheerio($, enqueueLinksOptions?.selector ?? 'a', enqueueLinksOptions?.baseUrl ?? finalRequestUrl ?? originalRequestUrl);
-    if (containsEnqueueLinks(options)) {
-        return options.enqueueLinks({
-            urls,
-            baseUrl,
-            ...enqueueLinksOptions,
-        });
-    }
-    return enqueueLinks({
-        requestQueue: options.requestQueue,
-        robotsTxtFile: options.robotsTxtFile,
-        onSkippedRequest: options.onSkippedRequest,
-        urls,
-        baseUrl,
-        ...enqueueLinksOptions,
-    });
-}
-/**
- * Creates new {@link Router} instance that works based on request labels.
- * This instance can then serve as a `requestHandler` of your {@link CheerioCrawler}.
- * Defaults to the {@link CheerioCrawlingContext}.
- *
- * > Serves as a shortcut for using `Router.create<CheerioCrawlingContext>()`.
- *
- * ```ts
- * import { CheerioCrawler, createCheerioRouter } from 'crawlee';
- *
- * const router = createCheerioRouter();
- * router.addHandler('label-a', async (ctx) => {
- *    ctx.log.info('...');
- * });
- * router.addDefaultHandler(async (ctx) => {
- *    ctx.log.info('...');
- * });
- *
- * const crawler = new CheerioCrawler({
- *     requestHandler: router,
- * });
- * await crawler.run();
- * ```
- */
-export function createCheerioRouter(routes) {
-    return Router.create(routes);
+export function createCheerioRouter(routesOrSchemas) {
+    return Router.create(routesOrSchemas);
 }
-//# sourceMappingURL=cheerio-crawler.js.map

package/internals/cheerio-parser.d.ts

@@ -0,0 +1,11 @@
+import type { DOMParser } from '@crawlee/http';
+import type { CheerioAPI } from 'cheerio';
+export interface CheerioParseResult {
+    $: CheerioAPI;
+    body: string;
+}
+/**
+ * A {@link DOMParser} backed by [cheerio](https://www.npmjs.com/package/cheerio). Pass it to a
+ * {@link DOMCrawler} to get the crawling context {@link CheerioCrawler} provides.
+ */
+export declare function cheerioParser(): DOMParser<CheerioParseResult>;

package/internals/cheerio-parser.js

@@ -0,0 +1,27 @@
+import { extractUrlsFromCheerio } from '@crawlee/utils/internal';
+// slim uses faster htmlparser2 parser and doesn't load extra libs like undici
+import * as cheerio from 'cheerio/slim';
+import { parseDocument } from 'htmlparser2';
+/**
+ * A {@link DOMParser} backed by [cheerio](https://www.npmjs.com/package/cheerio). Pass it to a
+ * {@link DOMCrawler} to get the crawling context {@link CheerioCrawler} provides.
+ */
+export function cheerioParser() {
+    return {
+        placeholderMembers: { $: true, body: true },
+        parse(context) {
+            const isXml = context.contentType.type.includes('xml');
+            const body = Buffer.isBuffer(context.body)
+                ? context.body.toString(context.contentType.encoding)
+                : context.body;
+            const dom = parseDocument(body, { decodeEntities: true, xmlMode: isXml });
+            const $ = cheerio.load(dom, {
+                xml: { decodeEntities: true, xmlMode: isXml },
+            });
+            return { $, body };
+        },
+        extractLinks: ({ $ }, selector, baseUrl) => extractUrlsFromCheerio($, selector, baseUrl),
+        select: ({ $ }, selector) => $(selector).get(),
+        toCheerio: ({ $ }) => $,
+    };
+}

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/cheerio",
-    "version": "4.0.0-beta.19",
+    "version": "4.0.0-beta.190",
     "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"
@@ -38,7 +38,7 @@
     },
     "homepage": "https://crawlee.dev",
     "scripts": {
-        "build": "yarn clean && yarn compile && yarn copy",
+        "build": "pnpm clean && pnpm compile && pnpm copy",
         "clean": "rimraf ./dist",
         "compile": "tsc -p tsconfig.build.json",
         "copy": "tsx ../../scripts/copy.ts"
@@ -47,9 +47,9 @@
         "access": "public"
     },
     "dependencies": {
-        "@crawlee/http": "4.0.0-beta.19",
-        "@crawlee/types": "4.0.0-beta.19",
-        "@crawlee/utils": "4.0.0-beta.19",
+        "@crawlee/http": "4.0.0-beta.190",
+        "@crawlee/types": "4.0.0-beta.190",
+        "@crawlee/utils": "4.0.0-beta.190",
         "cheerio": "^1.0.0",
         "htmlparser2": "^10.0.0",
         "tslib": "^2.8.1"
@@ -61,5 +61,5 @@
             }
         }
     },
-    "gitHead": "690af03140bea34c9a8871d370607cd52339caa0"
+    "gitHead": "0a6af5ff4704225ddb009a7dd58bdeaad48ebb14"
 }

package/index.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,cAAc,eAAe,CAAC;AAC9B,cAAc,gCAAgC,CAAC"}

package/index.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,cAAc,eAAe,CAAC;AAC9B,cAAc,gCAAgC,CAAC"}

package/internals/cheerio-crawler.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"cheerio-crawler.d.ts","sourceRoot":"","sources":["../../src/internals/cheerio-crawler.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACR,oBAAoB,EACpB,aAAa,EACb,mBAAmB,EACnB,YAAY,EACZ,sBAAsB,EACtB,kBAAkB,EAClB,2BAA2B,EAC3B,gBAAgB,EAChB,cAAc,EACd,eAAe,EACf,YAAY,EACZ,sBAAsB,EACzB,MAAM,eAAe,CAAC;AACvB,OAAO,EAAgB,WAAW,EAAkD,MAAM,eAAe,CAAC;AAC1G,OAAO,KAAK,EAAE,sBAAsB,EAAE,UAAU,EAAE,MAAM,gBAAgB,CAAC;AACzE,OAAO,EAAE,KAAK,WAAW,EAA0B,KAAK,aAAa,EAAE,MAAM,gBAAgB,CAAC;AAE9F,OAAO,KAAK,OAAO,MAAM,SAAS,CAAC;AAGnC,MAAM,MAAM,mBAAmB,CAC3B,QAAQ,SAAS,UAAU,GAAG,GAAG,EAAE,2EAA2E;AAC9G,QAAQ,SAAS,UAAU,GAAG,GAAG,IACjC,YAAY,CAAC,sBAAsB,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAC,CAAC;AAE7D,MAAM,WAAW,qBAAqB,CAClC,gBAAgB,GAAG,UAAU,CAAC,KAAK,CAAC,EACpC,eAAe,SAAS,sBAAsB,GAAG,sBAAsB,GAAG,gBAAgB,EAC1F,QAAQ,SAAS,UAAU,GAAG,GAAG,EAAE,2EAA2E;AAC9G,QAAQ,SAAS,UAAU,GAAG,GAAG,CACnC,SAAQ,kBAAkB,CAAC,sBAAsB,CAAC,QAAQ,EAAE,QAAQ,CAAC,EAAE,gBAAgB,EAAE,eAAe,CAAC;CAAG;AAE9G,MAAM,MAAM,WAAW,CACnB,QAAQ,SAAS,UAAU,GAAG,GAAG,EAAE,2EAA2E;AAC9G,QAAQ,SAAS,UAAU,GAAG,GAAG,IACjC,gBAAgB,CAAC,sBAAsB,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAC,CAAC;AAEjE,MAAM,WAAW,sBAAsB,CACnC,QAAQ,SAAS,UAAU,GAAG,GAAG,EAAE,2EAA2E;AAC9G,QAAQ,SAAS,UAAU,GAAG,GAAG,CACnC,SAAQ,2BAA2B,CAAC,QAAQ,EAAE,QAAQ,CAAC;IACrD;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IAEb;;;OAGG;IACH,CAAC,EAAE,OAAO,CAAC,UAAU,CAAC;IAEtB;;;;;;;;;;;OAWG;IACH,eAAe,CAAC,QAAQ,EAAE,MAAM,EAAE,SAAS,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC;IAErE;;;;;;;;;;;;;OAaG;IACH,gBAAgB,CAAC,QAAQ,CAAC,EAAE,MAAM,EAAE,SAAS,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,WAAW,CAAC,CAAC;IAE9E;;OAEG;IACH,YAAY,CAAC,OAAO,CAAC,EAAE,mBAAmB,GAAG,OAAO,CAAC,sBAAsB,CAAC,CAAC;CAChF;AAED,MAAM,MAAM,qBAAqB,CAC7B,QAAQ,SAAS,UAAU,GAAG,GAAG,EAAE,2EAA2E;AAC9G,QAAQ,SAAS,UAAU,GAAG,GAAG,IACjC,cAAc,CAAC,sBAAsB,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAC,CAAC;AAE/D;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4EG;AACH,qBAAa,cAAc,CACvB,gBAAgB,GAAG,UAAU,CAAC,KAAK,CAAC,EACpC,eAAe,SAAS,sBAAsB,GAAG,sBAAsB,GAAG,gBAAgB,CAC5F,SAAQ,WAAW,CAAC,sBAAsB,EAAE,gBAAgB,EAAE,eAAe,CAAC;IAC5E;;OAEG;gBACS,OAAO,CAAC,EAAE,qBAAqB,CAAC,gBAAgB,EAAE,eAAe,CAAC,EAAE,MAAM,CAAC,EAAE,aAAa;YAexF,YAAY;YAgBZ,UAAU;CA8B3B;AAED,UAAU,2BAA2B;IACjC,OAAO,CAAC,EAAE,mBAAmB,CAAC;IAC9B,CAAC,EAAE,OAAO,CAAC,UAAU,GAAG,IAAI,CAAC;IAC7B,YAAY,EAAE,eAAe,CAAC;IAC9B,aAAa,CAAC,EAAE,aAAa,CAAC;IAC9B,gBAAgB,CAAC,EAAE,sBAAsB,CAAC;IAC1C,kBAAkB,EAAE,MAAM,CAAC;IAC3B,eAAe,CAAC,EAAE,MAAM,CAAC;CAC5B;AAED,UAAU,gCAAgC;IACtC,YAAY,EAAE,oBAAoB,CAAC,cAAc,CAAC,CAAC;IACnD,OAAO,CAAC,EAAE,mBAAmB,CAAC;IAC9B,CAAC,EAAE,OAAO,CAAC,UAAU,GAAG,IAAI,CAAC;IAC7B,kBAAkB,EAAE,MAAM,CAAC;IAC3B,eAAe,CAAC,EAAE,MAAM,CAAC;CAC5B;AASD,gBAAgB;AAChB,wBAAsB,0BAA0B,CAC5C,OAAO,EAAE,2BAA2B,GAAG,gCAAgC,oBAmC1E;AAED;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AACH,wBAAgB,mBAAmB,CAC/B,OAAO,SAAS,sBAAsB,GAAG,sBAAsB,EAC/D,QAAQ,SAAS,UAAU,GAAG,sBAAsB,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC,EAC1E,MAAM,CAAC,EAAE,YAAY,CAAC,OAAO,EAAE,QAAQ,CAAC,kDAEzC"}

package/internals/cheerio-crawler.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"cheerio-crawler.js","sourceRoot":"","sources":["../../src/internals/cheerio-crawler.ts"],"names":[],"mappings":"AAcA,OAAO,EAAE,YAAY,EAAE,WAAW,EAAE,sCAAsC,EAAE,MAAM,EAAE,MAAM,eAAe,CAAC;AAE1G,OAAO,EAAoB,sBAAsB,EAAsB,MAAM,gBAAgB,CAAC;AAE9F,OAAO,KAAK,OAAO,MAAM,SAAS,CAAC;AACnC,OAAO,EAAE,aAAa,EAAE,MAAM,aAAa,CAAC;AA2E5C;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4EG;AACH,MAAM,OAAO,cAGX,SAAQ,WAAsE;IAC5E;;OAEG;IACH,YAAY,OAAkE,EAAE,MAAsB;QAClG,KAAK,CACD;YACI,GAAG,OAAO;YACV,sBAAsB,EAAE,GAAG,EAAE,CACzB,IAAI,CAAC,oBAAoB,EAAE;iBACtB,OAAO,CAAC;gBACL,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,CAAC,MAAM,IAAI,CAAC,YAAY,CAAC,OAAO,CAAC;aAC9D,CAAC;iBACD,OAAO,CAAC,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,CAAC,MAAM,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,EAAE,CAAC;SAClF,EACD,MAAM,CACT,CAAC;IACN,CAAC;IAEO,KAAK,CAAC,YAAY,CAAC,eAA4C;QACnE,MAAM,KAAK,GAAG,eAAe,CAAC,WAAW,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC;QAC/D,MAAM,IAAI,GAAG,MAAM,CAAC,QAAQ,CAAC,eAAe,CAAC,IAAI,CAAC;YAC9C,CAAC,CAAC,eAAe,CAAC,IAAI,CAAC,QAAQ,CAAC,eAAe,CAAC,WAAW,CAAC,QAAQ,CAAC;YACrE,CAAC,CAAC,eAAe,CAAC,IAAI,CAAC;QAC3B,MAAM,GAAG,GAAG,aAAa,CAAC,IAAI,EAAE,EAAE,cAAc,EAAE,IAAI,EAAE,OAAO,EAAE,KAAK,EAAE,CAAC,CAAC;QAC1E,MAAM,CAAC,GAAG,OAAO,CAAC,IAAI,CAAC,GAAG,EAAE;YACxB,GAAG,EAAE,EAAE,cAAc,EAAE,IAAI,EAAE,OAAO,EAAE,KAAK,EAAE;SAC9B,CAAC,CAAC;QAErB,OAAO;YACH,CAAC;YACD,IAAI;SACP,CAAC;IACN,CAAC;IAEO,KAAK,CAAC,UAAU,CAAC,eAAgE;QACrF,MAAM,oBAAoB,GAAG,eAAe,CAAC,YAAY,CAAC;QAE1D,OAAO;YACH,YAAY,EAAE,KAAK,EAAE,cAAoC,EAAE,EAAE;gBACzD,OAAO,CAAC,MAAM,0BAA0B,CAAC;oBACrC,OAAO,EAAE,EAAE,GAAG,cAAc,EAAE,KAAK,EAAE,IAAI,CAAC,6BAA6B,CAAC,cAAc,EAAE,KAAK,CAAC,EAAE;oBAChG,CAAC,EAAE,eAAe,CAAC,CAAC;oBACpB,YAAY,EAAE,MAAM,IAAI,CAAC,eAAe,EAAE;oBAC1C,aAAa,EAAE,MAAM,IAAI,CAAC,sBAAsB,CAAC,eAAe,CAAC,OAAO,CAAC,GAAG,CAAC;oBAC7E,gBAAgB,EAAE,IAAI,CAAC,oBAAoB;oBAC3C,kBAAkB,EAAE,eAAe,CAAC,OAAO,CAAC,GAAG;oBAC/C,eAAe,EAAE,eAAe,CAAC,OAAO,CAAC,SAAS;oBAClD,YAAY,EAAE,oBAAoB;iBACrC,CAAC,CAA2B,CAAC,CAAC,2BAA2B;YAC9D,CAAC;YACD,eAAe,EAAE,KAAK,EAAE,QAAgB,EAAE,UAAmB,EAAE,EAAE;gBAC7D,IAAI,eAAe,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,GAAG,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;oBACjD,MAAM,IAAI,KAAK,CAAC,aAAa,QAAQ,cAAc,CAAC,CAAC;gBACzD,CAAC;YACL,CAAC;YACD,gBAAgB,EAAE,KAAK,EAAE,QAAiB,EAAE,SAAkB,EAAE,EAAE;gBAC9D,IAAI,QAAQ,EAAE,CAAC;oBACX,MAAM,eAAe,CAAC,eAAe,CAAC,QAAQ,EAAE,SAAS,CAAC,CAAC;gBAC/D,CAAC;gBAED,OAAO,eAAe,CAAC,CAAC,CAAC;YAC7B,CAAC;SACJ,CAAC;IACN,CAAC;CACJ;AAoBD,gBAAgB;AAChB,SAAS,oBAAoB,CACzB,OAAuE;IAEvE,OAAO,CAAC,CAAE,OAA4C,CAAC,YAAY,CAAC;AACxE,CAAC;AAED,gBAAgB;AAChB,MAAM,CAAC,KAAK,UAAU,0BAA0B,CAC5C,OAAuE;IAEvE,MAAM,EAAE,OAAO,EAAE,mBAAmB,EAAE,CAAC,EAAE,kBAAkB,EAAE,eAAe,EAAE,GAAG,OAAO,CAAC;IACzF,IAAI,CAAC,CAAC,EAAE,CAAC;QACL,MAAM,IAAI,KAAK,CAAC,wDAAwD,CAAC,CAAC;IAC9E,CAAC;IAED,MAAM,OAAO,GAAG,sCAAsC,CAAC;QACnD,eAAe,EAAE,mBAAmB,EAAE,QAAQ;QAC9C,eAAe;QACf,kBAAkB;QAClB,mBAAmB,EAAE,mBAAmB,EAAE,OAAO;KACpD,CAAC,CAAC;IAEH,MAAM,IAAI,GAAG,sBAAsB,CAC/B,CAAC,EACD,mBAAmB,EAAE,QAAQ,IAAI,GAAG,EACpC,mBAAmB,EAAE,OAAO,IAAI,eAAe,IAAI,kBAAkB,CACxE,CAAC;IAEF,IAAI,oBAAoB,CAAC,OAAO,CAAC,EAAE,CAAC;QAChC,OAAO,OAAO,CAAC,YAAY,CAAC;YACxB,IAAI;YACJ,OAAO;YACP,GAAG,mBAAmB;SACzB,CAAC,CAAC;IACP,CAAC;IACD,OAAO,YAAY,CAAC;QAChB,YAAY,EAAE,OAAO,CAAC,YAAY;QAClC,aAAa,EAAE,OAAO,CAAC,aAAa;QACpC,gBAAgB,EAAE,OAAO,CAAC,gBAAgB;QAC1C,IAAI;QACJ,OAAO;QACP,GAAG,mBAAmB;KACzB,CAAC,CAAC;AACP,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AACH,MAAM,UAAU,mBAAmB,CAGjC,MAAwC;IACtC,OAAO,MAAM,CAAC,MAAM,CAAU,MAAM,CAAC,CAAC;AAC1C,CAAC"}