@crawlee/cheerio 4.0.0-beta.134 → 4.0.0-beta.135

package/internals/cheerio-crawler.d.ts

@@ -1,7 +1,6 @@
-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 type { CheerioAPI } from 'cheerio';
 import * as cheerio from 'cheerio';
 export type CheerioErrorHandler<UserData extends Dictionary = any, // with default to Dictionary we cant use a typed router in untyped crawler
@@ -51,7 +50,7 @@ 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 HTML, without adding them to the request queue.
      */
@@ -147,16 +146,7 @@ export declare class CheerioCrawler<ContextExtension = Dictionary<never>, Extend
      * All `CheerioCrawler` parameters are passed via an options object.
      */
     constructor(options?: CheerioCrawlerOptions<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 body: string;
-        readonly $: CheerioAPI;
-    } & {
-        extractLinks: (options?: ExtractLinksOptions) => Promise<string[]>;
-        enqueueLinks: (options?: EnqueueLinksOptions) => Promise<AddRequestsBatchedResult>;
-        waitForSelector: (selector: string, _timeoutMs?: number) => Promise<void>;
-        parseWithCheerio: (selector?: string, timeoutMs?: number) => Promise<CheerioAPI>;
-    }>;
+    protected buildContextPipeline(): ContextPipeline<CrawlingContext, CheerioCrawlingContext>;
     private parseContent;
     private addHelpers;
 }

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/cheerio",
-    "version": "4.0.0-beta.134",
+    "version": "4.0.0-beta.135",
     "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.134",
-        "@crawlee/types": "4.0.0-beta.134",
-        "@crawlee/utils": "4.0.0-beta.134",
+        "@crawlee/http": "4.0.0-beta.135",
+        "@crawlee/types": "4.0.0-beta.135",
+        "@crawlee/utils": "4.0.0-beta.135",
         "cheerio": "^1.0.0",
         "htmlparser2": "^10.0.0",
         "tslib": "^2.8.1"
@@ -61,5 +61,5 @@
             }
         }
     },
-    "gitHead": "0f269d5b24ec2829f3d44c19a35973fa20d95999"
+    "gitHead": "ca0325880bbcc753d97506796e9bda3b35bca201"
 }