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
Merge branch 'develop' into feature/metamorph
Marek Trunkáta2c7d547216e
diff --cc package.jsonindex aec377ac6,b18838c86..a69fbb5ca--- a/package.json+++ b/package.json@@@ -50,8 -50,8 +50,8 @@@},"dependencies": {"@apify/ps-tree": "^1.1.3",- "apify-client": "^0.5.5",+ "apify-client": "^0.5.6",- "apify-shared": "^0.1.20",+ "apify-shared": "^0.1.23","bluebird": "^3.5.3","cheerio": "^1.0.0-rc.2","content-type": "^1.0.4",diff --cc src/actor.jsindex 17f9ffccc,48a794447..7a58400a5--- a/src/actor.js+++ b/src/actor.js@@@ -4,10 -4,10 +4,10 @@@ import Promise from 'bluebird'import log from 'apify-shared/log';import { checkParamOrThrow } from 'apify-client/build/utils';import { APIFY_PROXY_VALUE_REGEX } from 'apify-shared/regexs';- import { ENV_VARS, LOCAL_ENV_VARS, ACT_JOB_TERMINAL_STATUSES, ACT_JOB_STATUSES } from 'apify-shared/consts';+ import { ENV_VARS, INTEGER_ENV_VARS, LOCAL_ENV_VARS, ACT_JOB_TERMINAL_STATUSES, ACT_JOB_STATUSES } from 'apify-shared/consts';import { EXIT_CODES } from './constants';import { initializeEvents, stopEvents } from './events';- import { apifyClient, addCharsetToContentType, sleep } from './utils';-import { apifyClient, addCharsetToContentType, snakeCaseToCamelCase } from './utils';++import { apifyClient, addCharsetToContentType, sleep, snakeCaseToCamelCase } from './utils';import { maybeStringify } from './key_value_store';import { ApifyCallError } from './errors';