@crawlee/linkedom 4.0.0-beta.120 → 4.0.0-beta.121

package/internals/linkedom-crawler.d.ts

@@ -1,6 +1,6 @@
 import type { BasicCrawlingContext, CrawlingContext, EnqueueLinksOptions, ErrorHandler, GetUserDataFromRequest, HttpCrawlerOptions, InternalHttpCrawlingContext, InternalHttpHook, IRequestManager, RequestHandler, RouterHandler, RouterRoutes, RouteSchemas, RoutesFromSchemas, SkippedRequestCallback } from '@crawlee/http';
 import { HttpCrawler } from '@crawlee/http';
-import type { Dictionary } from '@crawlee/types';
+import type { BatchAddRequestsResult, Dictionary } from '@crawlee/types';
 import { type CheerioRoot } from '@crawlee/utils/internal';
 import { type RobotsTxtFile } from '@crawlee/utils';
 import * as cheerio from 'cheerio';
@@ -46,6 +46,10 @@ JSONData extends Dictionary = any> extends InternalHttpCrawlingContext<UserData,
      * ```
      */
     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?: LinkeDOMCrawlerEnqueueLinksOptions): Promise<BatchAddRequestsResult>;
 }
 export type LinkeDOMRequestHandler<UserData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
 JSONData extends Dictionary = any> = RequestHandler<LinkeDOMCrawlingContext<UserData, JSONData>>;
@@ -123,14 +127,14 @@ JSONData extends Dictionary = any> = RequestHandler<LinkeDOMCrawlingContext<User
  */
 export declare class LinkeDOMCrawler<ContextExtension = Dictionary<never>, ExtendedContext extends LinkeDOMCrawlingContext = LinkeDOMCrawlingContext & ContextExtension, Routes extends Record<keyof Routes, Dictionary> = Record<string, GetUserDataFromRequest<LinkeDOMCrawlingContext['request']>>> extends HttpCrawler<LinkeDOMCrawlingContext, ContextExtension, ExtendedContext, Routes> {
     #private;
-    constructor(options: LinkeDOMCrawlerOptions<ContextExtension, ExtendedContext, any, any, Routes>);
+    constructor(options?: LinkeDOMCrawlerOptions<ContextExtension, ExtendedContext, any, any, Routes>);
 // @ts-ignore optional peer dependency or compatibility with es2022
     protected buildContextPipeline(): import("@crawlee/http").ContextPipeline<CrawlingContext<Dictionary>, InternalHttpCrawlingContext<any, any> & {
         readonly window: Window;
         readonly body: string;
         readonly document: Document;
     } & {
-        enqueueLinks: (enqueueOptions?: LinkeDOMCrawlerEnqueueLinksOptions) => Promise<unknown>;
+        enqueueLinks: (enqueueOptions?: LinkeDOMCrawlerEnqueueLinksOptions) => Promise<BatchAddRequestsResult>;
         waitForSelector(selector: string, timeoutMs?: number): Promise<void>;
         parseWithCheerio(selector?: string, _timeoutMs?: number): Promise<cheerio.CheerioAPI>;
     }>;

package/internals/linkedom-crawler.js

@@ -76,7 +76,7 @@ import { DOMParser } from 'linkedom/cached';
  */
 export class LinkeDOMCrawler extends HttpCrawler {
     static #parser = new DOMParser();
-    constructor(options) {
+    constructor(options = {}) {
         const { contextPipelineBuilder, ...rest } = options;
         super({
             ...rest,
@@ -126,18 +126,18 @@ export class LinkeDOMCrawler extends HttpCrawler {
     async addHelpers(crawlingContext) {
         return {
             enqueueLinks: async (enqueueOptions) => {
-                return linkedomCrawlerEnqueueLinks({
+                return (await linkedomCrawlerEnqueueLinks({
                     options: {
                         ...enqueueOptions,
                         limit: await this.calculateEnqueuedRequestLimit(enqueueOptions?.limit),
                     },
-                    window: document.defaultView,
+                    window: crawlingContext.window,
                     requestManager: await this.getRequestManager(),
                     robotsTxtFile: await this.getRobotsTxtFileForUrl(crawlingContext.request.url),
                     onSkippedRequest: this.handleSkippedRequest,
                     originalRequestUrl: crawlingContext.request.url,
                     finalRequestUrl: crawlingContext.request.loadedUrl,
-                });
+                })); // TODO make this type safe, see https://github.com/apify/crawlee/issues/4024
             },
             async waitForSelector(selector, timeoutMs = 5_000) {
                 const $ = cheerio.load(crawlingContext.body);

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/linkedom",
-    "version": "4.0.0-beta.120",
+    "version": "4.0.0-beta.121",
     "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"
@@ -49,9 +49,9 @@
     "dependencies": {
         "@apify/timeout": "^0.4.4",
         "@apify/utilities": "^2.15.5",
-        "@crawlee/http": "4.0.0-beta.120",
-        "@crawlee/types": "4.0.0-beta.120",
-        "@crawlee/utils": "4.0.0-beta.120",
+        "@crawlee/http": "4.0.0-beta.121",
+        "@crawlee/types": "4.0.0-beta.121",
+        "@crawlee/utils": "4.0.0-beta.121",
         "cheerio": "^1.0.0",
         "linkedom": "^0.18.10",
         "ow": "^2.0.0",
@@ -64,5 +64,5 @@
             }
         }
     },
-    "gitHead": "da5d427c4c1c9dcaea95b151e9c4c7310100885d"
+    "gitHead": "5027317de626f5ba6de5047ae9341a898258cc5a"
 }