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
refactored code and builded docs
Petr Patek5a28fd30872d
diff --git a/docs/api/TimeoutError.md b/docs/api/TimeoutError.mdnew file mode 100644index 000000000..be0f74b83--- /dev/null+++ b/docs/api/TimeoutError.md@@ -0,0 +1,8 @@+---+id: timeouterror+title: TimeoutError+---++<a name="TimeoutError"></a>++TimeoutError class. This error should be thrown after request timeout from `requestAsBrowser`.diff --git a/src/errors.js b/src/errors.jsindex c3a965ba6..bf956b92b 100644--- a/src/errors.js+++ b/src/errors.js@@ -21,3 +21,8 @@ export class ApifyCallError extends Error {Error.captureStackTrace(this, ApifyCallError);}}+/**+ * TimeoutError class.+ * This error should be thrown after request timeout from `requestAsBrowser`.+ */+export class TimeoutError extends Error {}diff --git a/src/utils_request.js b/src/utils_request.jsindex e8b7ebe7b..f2c064c20 100644--- a/src/utils_request.js+++ b/src/utils_request.js@@ -3,6 +3,7 @@ import * as url from 'url';import _ from 'underscore';import httpRequest from '@apify/http-request';import errors from '@apify/http-request/src/errors';+import { TimeoutError } from './errors';export const FIREFOX_MOBILE_USER_AGENT = 'Mozilla/5.0 (Android; Mobile; rv:14.0) Gecko/14.0 Firefox/14.0';export const FIREFOX_DESKTOP_USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.14; rv:68.0) Gecko/20100101 Firefox/68.0';@@ -91,10 +92,4 @@ export const requestAsBrowser = async (options) => {throw e;}-};--/**- * TimeoutError helper class- */-export class TimeoutError extends Error {}