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.
TypeScript apifyautomationcrawlercrawlingheadlessheadless-chromejavascriptnodejsnpmplaywrightpuppeteerscraperscrapingtypescriptweb-crawlerweb-crawlingweb-scraping
fix: `ImpitHttpClient` respects the internal `Request` timeout (#3103)
Jindřich Bära35376d2ce0a
diff --git a/packages/impit-client/package.json b/packages/impit-client/package.jsonindex ae50255a4..8dce63ca8 100644--- a/packages/impit-client/package.json+++ b/packages/impit-client/package.json@@ -60,7 +60,7 @@},"dependencies": {"@apify/datastructures": "^2.0.3",- "impit": "^0.5.2",+ "impit": "^0.5.3","tough-cookie": "^5.1.2"},"packageManager": "[email protected]"diff --git a/packages/impit-client/src/index.ts b/packages/impit-client/src/index.tsindex 75dcb2cb9..94e4c3052 100644--- a/packages/impit-client/src/index.ts+++ b/packages/impit-client/src/index.ts@@ -127,6 +127,7 @@ export class ImpitHttpClient implements BaseHttpClient {method: request.method as HttpMethod,headers: this.intoHeaders(request.headers),body: this.intoImpitBody(request.body),+ timeout: (request.timeout as { request?: number })?.request,});if (this.followRedirects && response.status >= 300 && response.status < 400) {diff --git a/yarn.lock b/yarn.lockindex 86493c9b6..b4a30539d 100644--- a/yarn.lock+++ b/yarn.lock@@ -621,7 +621,7 @@ __metadata:dependencies:"@apify/datastructures": "npm:^2.0.3""@crawlee/core": "npm:^3.14.1"- impit: "npm:^0.5.2"+ impit: "npm:^0.5.3"tough-cookie: "npm:^5.1.2"peerDependencies:"@crawlee/core": ^3.12.1@@ -7526,7 +7526,7 @@ __metadata:languageName: nodelinkType: hard-"impit@npm:^0.5.0, impit@npm:^0.5.2":+"impit@npm:^0.5.0, impit@npm:^0.5.3":version: 0.5.3resolution: "impit@npm:0.5.3"dependencies: