Skip to content

Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.

chore: fix build errors from `master` rebase (#3285)

Jindřich Bär52fe3d1543fe
diff --git a/packages/basic-crawler/package.json b/packages/basic-crawler/package.json
index 4cb703fcd..7469257d4 100644
--- a/packages/basic-crawler/package.json
+++ b/packages/basic-crawler/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/basic",
- "version": "3.17.0",
+ "version": "4.0.0",
"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"
@@ -43,12 +43,12 @@
"@apify/log": "^2.5.18",
"@apify/timeout": "^0.3.2",
"@apify/utilities": "^2.15.5",
- "@crawlee/core": "3.17.0",
- "@crawlee/types": "3.17.0",
- "@crawlee/utils": "3.17.0",
+ "@crawlee/core": "4.0.0",
+ "@crawlee/types": "4.0.0",
+ "@crawlee/utils": "4.0.0",
"csv-stringify": "^6.5.2",
"fs-extra": "^11.3.0",
- "got-scraping": "^4.2.1",
+ "got-scraping": "^4.1.1",
"ow": "^2.0.0",
"tldts": "^7.0.6",
"tslib": "^2.8.1",
diff --git a/packages/basic-crawler/src/index.ts b/packages/basic-crawler/src/index.ts
index df955c3f9..ab98a1004 100644
--- a/packages/basic-crawler/src/index.ts
+++ b/packages/basic-crawler/src/index.ts
@@ -1,3 +1,3 @@
export * from '@crawlee/core';
export * from './internals/basic-crawler.js';
-export { CheerioRoot, CheerioAPI, Cheerio } from '@crawlee/utils';
+export { CheerioRoot, CheerioAPI, Cheerio, Element } from '@crawlee/utils';
diff --git a/packages/browser-crawler/package.json b/packages/browser-crawler/package.json
index 7be1abfed..532776a32 100644
--- a/packages/browser-crawler/package.json
+++ b/packages/browser-crawler/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/browser",
- "version": "3.17.0",
+ "version": "4.0.0",
"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"
@@ -48,10 +48,10 @@
},
"dependencies": {
"@apify/timeout": "^0.3.2",
- "@crawlee/basic": "3.17.0",
- "@crawlee/browser-pool": "3.17.0",
- "@crawlee/types": "3.17.0",
- "@crawlee/utils": "3.17.0",
+ "@crawlee/basic": "4.0.0",
+ "@crawlee/browser-pool": "4.0.0",
+ "@crawlee/types": "4.0.0",
+ "@crawlee/utils": "4.0.0",
"ow": "^2.0.0",
"tslib": "^2.8.1",
"type-fest": "^4.41.0"
diff --git a/packages/browser-pool/package.json b/packages/browser-pool/package.json
index 902fa5fc8..c92ae0e14 100644
--- a/packages/browser-pool/package.json
+++ b/packages/browser-pool/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/browser-pool",
- "version": "3.17.0",
+ "version": "4.0.0",
"description": "Rotate multiple browsers using popular automation libraries such as Playwright or Puppeteer.",
"engines": {
"node": ">=22.0.0"
@@ -32,8 +32,8 @@
"dependencies": {
"@apify/log": "^2.5.18",
"@apify/timeout": "^0.3.2",
- "@crawlee/core": "3.17.0",
- "@crawlee/types": "3.17.0",
+ "@crawlee/core": "4.0.0",
+ "@crawlee/types": "4.0.0",
"fingerprint-generator": "^2.1.68",
"fingerprint-injector": "^2.1.68",
"lodash.merge": "^4.6.2",
diff --git a/packages/cheerio-crawler/package.json b/packages/cheerio-crawler/package.json
index 04f51b23a..8ddfdcdc3 100644
--- a/packages/cheerio-crawler/package.json
+++ b/packages/cheerio-crawler/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/cheerio",
- "version": "3.17.0",
+ "version": "4.0.0",
"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": "3.17.0",
- "@crawlee/types": "3.17.0",
- "@crawlee/utils": "3.17.0",
+ "@crawlee/http": "4.0.0",
+ "@crawlee/types": "4.0.0",
+ "@crawlee/utils": "4.0.0",
"cheerio": "^1.0.0",
"htmlparser2": "^10.0.0",
"tslib": "^2.8.1"
diff --git a/packages/cli/package.json b/packages/cli/package.json
index 206c6051c..39e45face 100644
--- a/packages/cli/package.json
+++ b/packages/cli/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/cli",
- "version": "3.17.0",
+ "version": "4.0.0",
"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"
@@ -45,7 +45,7 @@
"access": "public"
},
"dependencies": {
- "@crawlee/templates": "3.17.0",
+ "@crawlee/templates": "4.0.0",
"@inquirer/prompts": "^7.5.0",
"ansi-colors": "^4.1.3",
"fs-extra": "^11.3.0",
diff --git a/packages/core/package.json b/packages/core/package.json
index 5595cd772..3c7d4a074 100644
--- a/packages/core/package.json
+++ b/packages/core/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/core",
- "version": "3.17.0",
+ "version": "4.0.0",
"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"
@@ -53,9 +53,9 @@
"@apify/pseudo_url": "^2.0.59",
"@apify/timeout": "^0.3.2",
"@apify/utilities": "^2.15.5",
- "@crawlee/memory-storage": "3.17.0",
- "@crawlee/types": "3.17.0",
- "@crawlee/utils": "3.17.0",
+ "@crawlee/memory-storage": "4.0.0",
+ "@crawlee/types": "4.0.0",
+ "@crawlee/utils": "4.0.0",
"@sapphire/async-queue": "^1.5.5",
"@vladfrangu/async_event_emitter": "^2.4.6",
"csv-stringify": "^6.5.2",
diff --git a/packages/core/src/storages/request_list_adapter.ts b/packages/core/src/storages/request_list_adapter.ts
index 0e39dea17..363622955 100644
--- a/packages/core/src/storages/request_list_adapter.ts
+++ b/packages/core/src/storages/request_list_adapter.ts
@@ -1,13 +1,13 @@
import type { Dictionary } from '@crawlee/types';
-import type { Request } from '../request';
-import type { IRequestList } from './request_list';
+import type { Request } from '../request.js';
+import type { IRequestList } from './request_list.js';
import type {
AddRequestsBatchedResult,
IRequestManager,
RequestQueueOperationInfo,
RequestQueueOperationOptions,
-} from './request_provider';
+} from './request_provider.js';
/**
* Adapts the IRequestList interface to the IRequestManager interface.
diff --git a/packages/core/src/storages/request_manager_tandem.ts b/packages/core/src/storages/request_manager_tandem.ts
index cc79cf45c..0d1ad21ff 100644
--- a/packages/core/src/storages/request_manager_tandem.ts
+++ b/packages/core/src/storages/request_manager_tandem.ts
@@ -2,9 +2,9 @@ import type { Dictionary } from '@crawlee/types';
import type { Log } from '@apify/log';
-import { log } from '../log';
-import type { Request, Source } from '../request';
-import type { IRequestList } from './request_list';
+import { log } from '../log.js';
+import type { Request, Source } from '../request.js';
+import type { IRequestList } from './request_list.js';
import type {
AddRequestsBatchedOptions,
AddRequestsBatchedResult,
@@ -12,7 +12,7 @@ import type {
RequestQueueOperationInfo,
RequestQueueOperationOptions,
RequestsLike,
-} from './request_provider';
+} from './request_provider.js';
/**
* A request manager that combines a RequestList and a RequestQueue.
diff --git a/packages/crawlee/package.json b/packages/crawlee/package.json
index e85bac43c..0b6e99562 100644
--- a/packages/crawlee/package.json
+++ b/packages/crawlee/package.json
@@ -1,6 +1,6 @@
{
"name": "crawlee",
- "version": "3.17.0",
+ "version": "4.0.0",
"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"
@@ -48,19 +48,18 @@
"access": "public"
},
"dependencies": {
- "@crawlee/basic": "3.17.0",
- "@crawlee/browser": "3.17.0",
- "@crawlee/browser-pool": "3.17.0",
- "@crawlee/cheerio": "3.17.0",
- "@crawlee/cli": "3.17.0",
- "@crawlee/core": "3.17.0",
- "@crawlee/http": "3.17.0",
- "@crawlee/jsdom": "3.17.0",
- "@crawlee/linkedom": "3.17.0",
- "@crawlee/memory-storage": "3.17.0",
- "@crawlee/playwright": "3.17.0",
- "@crawlee/puppeteer": "3.17.0",
- "@crawlee/utils": "3.17.0",
+ "@crawlee/basic": "4.0.0",
+ "@crawlee/browser": "4.0.0",
+ "@crawlee/browser-pool": "4.0.0",
+ "@crawlee/cheerio": "4.0.0",
+ "@crawlee/cli": "4.0.0",
+ "@crawlee/core": "4.0.0",
+ "@crawlee/http": "4.0.0",
+ "@crawlee/jsdom": "4.0.0",
+ "@crawlee/linkedom": "4.0.0",
+ "@crawlee/playwright": "4.0.0",
+ "@crawlee/puppeteer": "4.0.0",
+ "@crawlee/utils": "4.0.0",
"import-local": "^3.2.0",
"tslib": "^2.8.1"
},
diff --git a/packages/http-crawler/package.json b/packages/http-crawler/package.json
index 3eaef9129..7c9873f41 100644
--- a/packages/http-crawler/package.json
+++ b/packages/http-crawler/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/http",
- "version": "3.17.0",
+ "version": "4.0.0",
"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"
@@ -49,14 +49,13 @@
"dependencies": {
"@apify/timeout": "^0.3.2",
"@apify/utilities": "^2.15.5",
- "@crawlee/basic": "3.17.0",
- "@crawlee/core": "3.17.0",
- "@crawlee/types": "3.17.0",
- "@crawlee/utils": "3.17.0",
+ "@crawlee/basic": "4.0.0",
+ "@crawlee/types": "4.0.0",
+ "@crawlee/utils": "4.0.0",
"@types/content-type": "^1.1.8",
"cheerio": "^1.0.0",
"content-type": "^1.0.5",
- "got-scraping": "^4.2.1",
+ "got-scraping": "^4.1.1",
"iconv-lite": "^0.7.0",
"mime-types": "^3.0.1",
"ow": "^2.0.0",
diff --git a/packages/http-crawler/src/internals/http-crawler.ts b/packages/http-crawler/src/internals/http-crawler.ts
index c0c606053..86b8ea88d 100644
--- a/packages/http-crawler/src/internals/http-crawler.ts
+++ b/packages/http-crawler/src/internals/http-crawler.ts
@@ -589,8 +589,8 @@ export class HttpCrawler<
this.sessionPool!['blockedStatusCodes']
: BLOCKED_STATUS_CODES;
- if (blockedStatusCodes.includes(crawlingContext.response.statusCode!)) {
- return `Blocked by status code ${crawlingContext.response.statusCode}`;
+ if (blockedStatusCodes.includes(crawlingContext.response.status!)) {
+ return `Blocked by status code ${crawlingContext.response.status}`;
}
return false;
diff --git a/packages/impit-client/package.json b/packages/impit-client/package.json
index 6ae782503..a0d4e8c69 100644
--- a/packages/impit-client/package.json
+++ b/packages/impit-client/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/impit-client",
- "version": "3.18.1",
+ "version": "4.0.0",
"description": "impit-based HTTP client implementation for Crawlee. Impersonates browser requests to avoid bot detection.",
"engines": {
"node": ">=22.0.0"
@@ -47,10 +47,10 @@
"access": "public"
},
"peerDependencies": {
- "@crawlee/core": "^3.13.3"
+ "@crawlee/core": "4.0.0"
},
"devDependencies": {
- "@crawlee/core": "^3.18.1"
+ "@crawlee/core": "4.0.0"
},
"dependencies": {
"@apify/datastructures": "^2.0.3",
diff --git a/packages/jsdom-crawler/package.json b/packages/jsdom-crawler/package.json
index 3d3617ab1..d891d25d7 100644
--- a/packages/jsdom-crawler/package.json
+++ b/packages/jsdom-crawler/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/jsdom",
- "version": "3.17.0",
+ "version": "4.0.0",
"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": "^0.3.0",
"@apify/utilities": "^2.7.10",
- "@crawlee/http": "3.17.0",
- "@crawlee/types": "3.17.0",
- "@crawlee/utils": "3.17.0",
+ "@crawlee/http": "4.0.0",
+ "@crawlee/types": "4.0.0",
+ "@crawlee/utils": "4.0.0",
"@types/jsdom": "^21.1.7",
"cheerio": "^1.0.0",
"jsdom": "^26.1.0",
diff --git a/packages/linkedom-crawler/package.json b/packages/linkedom-crawler/package.json
index 2a7e00241..2b16f7599 100644
--- a/packages/linkedom-crawler/package.json
+++ b/packages/linkedom-crawler/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/linkedom",
- "version": "3.17.0",
+ "version": "4.0.0",
"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"
@@ -49,10 +49,8 @@
"dependencies": {
"@apify/timeout": "^0.3.2",
"@apify/utilities": "^2.15.5",
- "@crawlee/http": "3.17.0",
- "@crawlee/types": "3.17.0",
- "@crawlee/utils": "3.17.0",
- "cheerio": "^1.0.0",
+ "@crawlee/http": "4.0.0",
+ "@crawlee/types": "4.0.0",
"linkedom": "^0.18.10",
"ow": "^2.0.0",
"tslib": "^2.8.1"
diff --git a/packages/memory-storage/package.json b/packages/memory-storage/package.json
index 8f166226f..40b5ee42b 100644
--- a/packages/memory-storage/package.json
+++ b/packages/memory-storage/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/memory-storage",
- "version": "3.17.0",
+ "version": "4.0.0",
"description": "A simple in-memory storage implementation of the Apify API",
"engines": {
"node": ">=22.0.0"
@@ -43,14 +43,13 @@
},
"dependencies": {
"@apify/log": "^2.5.18",
- "@crawlee/types": "3.17.0",
+ "@crawlee/types": "4.0.0",
"@sapphire/async-queue": "^1.5.5",
"@sapphire/shapeshift": "^4.0.0",
"content-type": "^1.0.5",
"fs-extra": "^11.3.0",
"json5": "^2.2.3",
"mime-types": "^3.0.1",
- "p-limit": "^3.1.0",
"proper-lockfile": "^4.1.2",
"tslib": "^2.8.1"
}
diff --git a/packages/memory-storage/src/resource-clients/key-value-store.ts b/packages/memory-storage/src/resource-clients/key-value-store.ts
index 2339906f7..1b0343681 100644
--- a/packages/memory-storage/src/resource-clients/key-value-store.ts
+++ b/packages/memory-storage/src/resource-clients/key-value-store.ts
@@ -131,10 +131,10 @@ export class KeyValueStoreClient extends BaseClient {
): AsyncIterable<storage.KeyValueStoreItemData> & Promise<storage.KeyValueStoreClientListData> {
const { limit, exclusiveStartKey, prefix } = s
.object({
- limit: s.number().greaterThan(0).optional,
- exclusiveStartKey: s.string().optional,
- collection: s.string().optional, // This is ignored, but kept for validation consistency with API client.
- prefix: s.string().optional,
+ limit: s.number().greaterThan(0).optional(),
+ exclusiveStartKey: s.string().optional(),
+ collection: s.string().optional(), // This is ignored, but kept for validation consistency with API client.
+ prefix: s.string().optional(),
})
.parse(options);
diff --git a/packages/playwright-crawler/package.json b/packages/playwright-crawler/package.json
index 5649a6d9e..791a0cd17 100644
--- a/packages/playwright-crawler/package.json
+++ b/packages/playwright-crawler/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/playwright",
- "version": "3.17.0",
+ "version": "4.0.0",
"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"
@@ -50,12 +50,12 @@
"@apify/datastructures": "^2.0.3",
"@apify/log": "^2.5.18",
"@apify/timeout": "^0.3.2",
- "@crawlee/browser": "3.17.0",
- "@crawlee/browser-pool": "3.17.0",
- "@crawlee/cheerio": "3.17.0",
- "@crawlee/core": "3.17.0",
- "@crawlee/types": "3.17.0",
- "@crawlee/utils": "3.17.0",
+ "@crawlee/browser": "4.0.0",
+ "@crawlee/browser-pool": "4.0.0",
+ "@crawlee/cheerio": "4.0.0",
+ "@crawlee/core": "4.0.0",
+ "@crawlee/types": "4.0.0",
+ "@crawlee/utils": "4.0.0",
"cheerio": "^1.0.0",
"idcac-playwright": "^0.1.3",
"jquery": "^3.7.1",
diff --git a/packages/puppeteer-crawler/package.json b/packages/puppeteer-crawler/package.json
index 9096371a7..49db82d95 100644
--- a/packages/puppeteer-crawler/package.json
+++ b/packages/puppeteer-crawler/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/puppeteer",
- "version": "3.17.0",
+ "version": "4.0.0",
"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"
@@ -49,10 +49,10 @@
"dependencies": {
"@apify/datastructures": "^2.0.3",
"@apify/log": "^2.5.18",
- "@crawlee/browser": "3.17.0",
- "@crawlee/browser-pool": "3.17.0",
- "@crawlee/types": "3.17.0",
- "@crawlee/utils": "3.17.0",
+ "@crawlee/browser": "4.0.0",
+ "@crawlee/browser-pool": "4.0.0",
+ "@crawlee/types": "4.0.0",
+ "@crawlee/utils": "4.0.0",
"cheerio": "^1.0.0",
"devtools-protocol": "*",
"idcac-playwright": "^0.2.0",
diff --git a/packages/templates/package.json b/packages/templates/package.json
index 777cecb4d..49634e294 100644
--- a/packages/templates/package.json
+++ b/packages/templates/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/templates",
- "version": "3.18.1",
+ "version": "4.0.0",
"description": "Templates for the crawlee projects",
"engines": {
"node": ">=22.0.0"
diff --git a/packages/types/package.json b/packages/types/package.json
index ed0d21b70..1cb7a652e 100644
--- a/packages/types/package.json
+++ b/packages/types/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/types",
- "version": "3.18.1",
+ "version": "4.0.0",
"description": "Shared types for the crawlee projects",
"engines": {
"node": ">=22.0.0"
diff --git a/packages/utils/package.json b/packages/utils/package.json
index 6564cb54e..3cc5ada3a 100644
--- a/packages/utils/package.json
+++ b/packages/utils/package.json
@@ -1,6 +1,6 @@
{
"name": "@crawlee/utils",
- "version": "3.17.0",
+ "version": "4.0.0",
"description": "A set of shared utilities that can be used by crawlers",
"engines": {
"node": ">=22.0.0"
@@ -43,10 +43,11 @@
"dependencies": {
"@apify/log": "^2.5.18",
"@apify/ps-tree": "^1.2.0",
- "@crawlee/types": "3.17.0",
+ "@crawlee/types": "4.0.0",
"@types/sax": "^1.2.7",
"cheerio": "^1.0.0",
- "file-type": "^21.3.1",
+ "domhandler": "^5.0.3",
+ "file-type": "^21.0.0",
"got-scraping": "^4.2.1",
"ow": "^2.0.0",
"robots-parser": "^3.0.1",
diff --git a/packages/utils/src/internals/cheerio.ts b/packages/utils/src/internals/cheerio.ts
index 522dbb37d..7cd123b29 100644
--- a/packages/utils/src/internals/cheerio.ts
+++ b/packages/utils/src/internals/cheerio.ts
@@ -6,6 +6,7 @@ import { tryAbsoluteURL } from './extract-urls.js';
export type CheerioRoot = CheerioAPI;
export type { CheerioAPI, Cheerio } from 'cheerio';
+export type { Element } from 'domhandler';
// NOTE: We are skipping 'noscript' since it's content is evaluated as text, instead of HTML elements. That damages the results.
const SKIP_TAGS_REGEX = /^(script|style|canvas|svg|noscript)$/i;
diff --git a/test/core/autoscaling/snapshotter.test.ts b/test/core/autoscaling/snapshotter.test.ts
index cdac93eb6..fb2fade41 100644
--- a/test/core/autoscaling/snapshotter.test.ts
+++ b/test/core/autoscaling/snapshotter.test.ts
@@ -2,6 +2,7 @@ import os from 'node:os';
import { Configuration, EventType, LocalEventManager, Snapshotter } from '@crawlee/core';
import type { MemoryInfo } from '@crawlee/utils';
+import * as utils from '@crawlee/utils';
import { sleep } from '@crawlee/utils';
import log from '@apify/log';
@@ -215,7 +216,7 @@ describe('Snapshotter', () => {
mainProcessBytes: toBytes(1000),
childProcessesBytes: toBytes(1000),
} as MemoryInfo;
- vitest.spyOn(LocalEventManager.prototype as any, 'getMemoryInfo').mockResolvedValue(memoryData);
+ vitest.spyOn(utils, 'getMemoryInfo').mockResolvedValue(memoryData);
const config = new Configuration({ availableMemoryRatio: 1 });
const snapshotter = new Snapshotter({ config, maxUsedMemoryRatio: 0.5 });
// do not initialize the event intervals as we will fire them manually
@@ -246,19 +247,7 @@ describe('Snapshotter', () => {
});
test('correctly logs critical memory overload', async () => {
- const initialMemory = toBytes(10000);
- const usageRatio1 = 0.75; // below warning usage
- const usageRatio2 = 0.76; // above warning usage
- const memoryData: MemoryInfo = {
- totalBytes: initialMemory,
- freeBytes: initialMemory * (1 - usageRatio1),
- usedBytes: initialMemory * usageRatio1,
- mainProcessBytes: initialMemory * usageRatio1,
- childProcessesBytes: 0,
- };
-
- // Mock memory info to be able to inject custom memory measurement data.
- vitest.spyOn(LocalEventManager.prototype as any, 'getMemoryInfo').mockResolvedValue(memoryData);
+ vitest.spyOn(utils, 'getMemoryInfo').mockResolvedValueOnce({ totalBytes: toBytes(10000) } as MemoryInfo);
const config = new Configuration({ availableMemoryRatio: 1 });
const snapshotter = new Snapshotter({ config, maxUsedMemoryRatio: 0.5 });
diff --git a/test/core/recoverable_state.test.ts b/test/core/recoverable_state.test.ts
index b8a95798b..2a7b76e75 100644
--- a/test/core/recoverable_state.test.ts
+++ b/test/core/recoverable_state.test.ts
@@ -1,7 +1,7 @@
import { afterEach, beforeEach, describe, expect, test, vi } from 'vitest';
-import { RecoverableState } from '../../packages/core/src/recoverable_state';
-import { MemoryStorageEmulator } from '../shared/MemoryStorageEmulator';
+import { RecoverableState } from '../../packages/core/src/recoverable_state.js';
+import { MemoryStorageEmulator } from '../shared/MemoryStorageEmulator.js';
interface TestState {
counter: number;
diff --git a/test/core/request_manager_tandem.test.ts b/test/core/request_manager_tandem.test.ts
index 1117de5c6..0be32ee1d 100644
--- a/test/core/request_manager_tandem.test.ts
+++ b/test/core/request_manager_tandem.test.ts
@@ -1,7 +1,7 @@
import { log, Request, RequestList, RequestManagerTandem, RequestQueue } from '@crawlee/core';
import { afterAll, beforeAll, beforeEach, describe, expect, test, vi } from 'vitest';
-import { MemoryStorageEmulator } from '../shared/MemoryStorageEmulator';
+import { MemoryStorageEmulator } from '../shared/MemoryStorageEmulator.js';
describe('RequestManagerTandem', () => {
let logLevel: number;