@crawlee/cheerio 4.0.0-beta.167 → 4.0.0-beta.169

package/index.d.ts

@@ -1,2 +1,3 @@
 export * from '@crawlee/http';
 export * from './internals/cheerio-crawler.js';
+export type { CheerioParseResult } from './internals/cheerio-parser.js';

package/internals/cheerio-crawler.d.ts

@@ -1,8 +1,7 @@
-import type { AddRequestsBatchedResult, ContextPipeline, CrawlingContext, EnqueueLinksOptions, ErrorHandler, ExtractLinksOptions, GetUserDataFromRequest, HttpCrawlerOptions, InternalHttpCrawlingContext, InternalHttpHook, RequestHandler, RouterHandler, RouterRoutes, RouteSchemas, RoutesFromSchemas } from '@crawlee/http';
-import { HttpCrawler } from '@crawlee/http';
+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 { CheerioAPI } from 'cheerio';
-import * as cheerio from 'cheerio';
+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, // with default to Dictionary we cant use a typed router in untyped crawler
 ContextExtension = Dictionary<never>> = ErrorHandler<CrawlingContext, CheerioCrawlingContext<UserData, JSONData> & ContextExtension>;
@@ -13,52 +12,7 @@ Routes extends Record<keyof Routes, Dictionary> = Record<string, UserData>, Stat
 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<CheerioAPI>;
-    /**
-     * Extracts URLs from the parsed HTML, without adding them to the request queue.
-     */
-    extractLinks(options?: ExtractLinksOptions): Promise<string[]>;
-    /**
-     * Helper function for extracting URLs from the parsed HTML and adding them to the request queue.
-     */
-    enqueueLinks(options?: EnqueueLinksOptions): Promise<AddRequestsBatchedResult>;
+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>>;
@@ -141,14 +95,11 @@ JSONData extends Dictionary = any> = RequestHandler<CheerioCrawlingContext<UserD
  * ```
  * @category Crawlers
  */
-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 HttpCrawler<CheerioCrawlingContext, ContextExtension, ExtendedContext, Routes, StatisticStateExtension> {
+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, any, any, Routes, StatisticStateExtension>);
-    protected buildContextPipeline(): ContextPipeline<CrawlingContext, CheerioCrawlingContext>;
-    private parseContent;
-    private addHelpers;
 }
 /**
  * Creates new {@link Router} instance that works based on request labels.

package/internals/cheerio-crawler.js

@@ -1,7 +1,5 @@
-import { EnqueueStrategy, HttpCrawler, NavigationSkippedError, resolveBaseUrlForEnqueueLinksFiltering, Router, } from '@crawlee/http';
-import { extractUrlsFromCheerio } from '@crawlee/utils/internal';
-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.
@@ -81,90 +79,12 @@ 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) {
-        const { contextPipelineBuilder, ...rest } = options ?? {};
-        super({
-            ...rest,
-            contextPipelineBuilder: contextPipelineBuilder ?? (() => this.buildContextPipeline()),
-        });
-    }
-    buildContextPipeline() {
-        return super
-            .buildContextPipeline()
-            .compose({
-            action: async (context) => await this.parseContent(context),
-        })
-            .compose({ action: async (context) => await this.addHelpers(context) });
-    }
-    async parseContent(crawlingContext) {
-        try {
-            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,
-            };
-        }
-        catch (err) {
-            if (err instanceof NavigationSkippedError) {
-                return {
-                    get body() {
-                        throw new NavigationSkippedError('The `body` property is not available - `skipNavigation` was used', { cause: err });
-                    },
-                    get $() {
-                        throw new NavigationSkippedError('The `$` property is not available - `skipNavigation` was used', { cause: err });
-                    },
-                };
-            }
-            throw err;
-        }
-    }
-    async addHelpers(crawlingContext) {
-        const addRequests = crawlingContext.addRequests;
-        const extractLinks = async (options) => {
-            if (!crawlingContext.$) {
-                throw new Error('Cannot extract links because the DOM is not available.');
-            }
-            return extractUrlsFromCheerio(crawlingContext.$, options?.selector ?? 'a', options?.baseUrl ?? crawlingContext.request.loadedUrl ?? crawlingContext.request.url);
-        };
-        return {
-            extractLinks,
-            enqueueLinks: async (options = {}) => {
-                const baseUrl = resolveBaseUrlForEnqueueLinksFiltering({
-                    enqueueStrategy: options.strategy,
-                    finalRequestUrl: crawlingContext.request.loadedUrl,
-                    originalRequestUrl: crawlingContext.request.url,
-                    userProvidedBaseUrl: options.baseUrl,
-                });
-                const urls = await extractLinks(options);
-                return addRequests(urls, {
-                    ...options,
-                    baseUrl,
-                    strategy: options.strategy ?? EnqueueStrategy.SameHostname,
-                });
-            },
-            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.$;
-            },
-        };
+        super({ ...options, parser: cheerioParser() });
     }
 }
 export function createCheerioRouter(routesOrSchemas) {

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 +1,26 @@
+import { extractUrlsFromCheerio } from '@crawlee/utils/internal';
+import * as cheerio from 'cheerio';
+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.167",
+    "version": "4.0.0-beta.169",
     "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"
@@ -47,9 +47,9 @@
         "access": "public"
     },
     "dependencies": {
-        "@crawlee/http": "4.0.0-beta.167",
-        "@crawlee/types": "4.0.0-beta.167",
-        "@crawlee/utils": "4.0.0-beta.167",
+        "@crawlee/http": "4.0.0-beta.169",
+        "@crawlee/types": "4.0.0-beta.169",
+        "@crawlee/utils": "4.0.0-beta.169",
         "cheerio": "^1.0.0",
         "htmlparser2": "^10.0.0",
         "tslib": "^2.8.1"
@@ -61,5 +61,5 @@
             }
         }
     },
-    "gitHead": "8b26080bf07dc602aa0970e12fb66e7e9cba509b"
+    "gitHead": "a42dc93fa0ef68180d83ab12af362082690f73e2"
 }