@crawlee/linkedom 4.0.0-beta.134 → 4.0.0-beta.136

package/internals/linkedom-crawler.d.ts

@@ -1,8 +1,7 @@
-import type { AddRequestsBatchedResult, CrawlingContext, EnqueueLinksOptions, ErrorHandler, ExtractLinksOptions, GetUserDataFromRequest, HttpCrawlerOptions, InternalHttpCrawlingContext, InternalHttpHook, RequestHandler, RouterHandler, RouterRoutes, RouteSchemas, RoutesFromSchemas } from '@crawlee/http';
+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 { Dictionary } from '@crawlee/types';
-import { type CheerioRoot } from '@crawlee/utils/internal';
-import * as cheerio from 'cheerio';
+import type { CheerioAPI } from 'cheerio';
 export type LinkeDOMErrorHandler<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, LinkeDOMCrawlingContext<UserData, JSONData> & ContextExtension>;
@@ -42,7 +41,7 @@ JSONData extends Dictionary = any> extends InternalHttpCrawlingContext<UserData,
      * });
      * ```
      */
-    parseWithCheerio(selector?: string, timeoutMs?: number): Promise<CheerioRoot>;
+    parseWithCheerio(selector?: string, timeoutMs?: number): Promise<CheerioAPI>;
     /**
      * Extracts URLs from the parsed DOM, without adding them to the request queue.
      */
@@ -129,17 +128,7 @@ 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']>>, StatisticStateExtension extends object = {}> extends HttpCrawler<LinkeDOMCrawlingContext, ContextExtension, ExtendedContext, Routes, StatisticStateExtension> {
     #private;
     constructor(options?: LinkeDOMCrawlerOptions<ContextExtension, ExtendedContext, any, any, Routes, StatisticStateExtension>);
-// @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;
-    } & {
-        extractLinks: (options?: ExtractLinksOptions) => Promise<string[]>;
-        enqueueLinks: (options?: EnqueueLinksOptions) => Promise<AddRequestsBatchedResult>;
-        waitForSelector(selector: string, timeoutMs?: number): Promise<void>;
-        parseWithCheerio(selector?: string, _timeoutMs?: number): Promise<cheerio.CheerioAPI>;
-    }>;
+    protected buildContextPipeline(): ContextPipeline<CrawlingContext, LinkeDOMCrawlingContext>;
     private parseContent;
     private addHelpers;
 }

package/internals/linkedom-crawler.js

@@ -1,5 +1,6 @@
-import { EnqueueStrategy, HttpCrawler, NavigationSkippedError, resolveBaseUrlForEnqueueLinksFiltering, Router, tryAbsoluteURL, } from '@crawlee/http';
+import { EnqueueStrategy, HttpCrawler, NavigationSkippedError, resolveBaseUrlForEnqueueLinksFiltering, Router, } from '@crawlee/http';
 import { sleep } from '@crawlee/utils';
+import { tryAbsoluteURL } from '@crawlee/utils/internal';
 import * as cheerio from 'cheerio';
 import { DOMParser } from 'linkedom/cached';
 /**

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/linkedom",
-    "version": "4.0.0-beta.134",
+    "version": "4.0.0-beta.136",
     "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.134",
-        "@crawlee/types": "4.0.0-beta.134",
-        "@crawlee/utils": "4.0.0-beta.134",
+        "@crawlee/http": "4.0.0-beta.136",
+        "@crawlee/types": "4.0.0-beta.136",
+        "@crawlee/utils": "4.0.0-beta.136",
         "cheerio": "^1.0.0",
         "linkedom": "^0.18.10",
         "tslib": "^2.8.1"
@@ -63,5 +63,5 @@
             }
         }
     },
-    "gitHead": "0f269d5b24ec2829f3d44c19a35973fa20d95999"
+    "gitHead": "d425bb9841885b4b71b84ae6fb0bafbdc4a7e978"
 }