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
added defaults.
Petr Patek6b3c9a1fa135
diff --git a/src/crawlers/puppeteer_crawler.js b/src/crawlers/puppeteer_crawler.jsindex 46740c581..1303109e6 100644--- a/src/crawlers/puppeteer_crawler.js+++ b/src/crawlers/puppeteer_crawler.js@@ -4,7 +4,7 @@ import _ from 'underscore';import BasicCrawler from './basic_crawler';import PuppeteerPool from '../puppeteer_pool';import { addTimeoutToPromise } from '../utils';-import { BASIC_CRAWLER_TIMEOUT_MULTIPLIER, BROWSER_SESSION_ID_KEY_NAME } from '../constants';+import { BASIC_CRAWLER_TIMEOUT_MULTIPLIER } from '../constants';import { gotoExtended } from '../puppeteer_utils';import { openSessionPool } from '../session_pool/session_pool';@@ -199,9 +199,9 @@ class PuppeteerCrawler {launchPuppeteerFunction,launchPuppeteerOptions,- sessionPoolOptions,- persistCookiesPerSession,- useSessionPool,+ sessionPoolOptions = {},+ persistCookiesPerSession = false,+ useSessionPool = false,} = options;checkParamOrThrow(handlePageFunction, 'options.handlePageFunction', 'Function');