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
Bump puppeteer and user agent to Chrome 87
Ondra Urban22c6ca0f1ed0
diff --git a/package.json b/package.jsonindex 68b84bb8e..1ffdfd006 100644--- a/package.json+++ b/package.json@@ -118,6 +118,6 @@"why-is-node-running": "^2.2.0"},"optionalDependencies": {- "puppeteer": "5.3.1"+ "puppeteer": "5.4.1"}}diff --git a/src/constants.js b/src/constants.jsindex 0abedda10..a4639b086 100644--- a/src/constants.js+++ b/src/constants.js@@ -5,7 +5,7 @@ import { ACTOR_EVENT_NAMES } from 'apify-shared/consts';* Last updated on 2020-05-22.*/// eslint-disable-next-line max-len-export const DEFAULT_USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36';+export const DEFAULT_USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.67 Safari/537.36';/*** Exit codes for the actor process.