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
FROM node:24 AS builder
COPY /packages ./packages
COPY /package*.json ./
RUN rm -rf node_modules package-lock.json
RUN npm --quiet set progress=false \
&& npm install --only=prod --no-audit \
&& npm update
FROM apify/actor-node-playwright-chrome:24-1.58.2-beta
# The browser base images ship a preinstalled node_modules - wipe it so the
# builder tree (with file: symlinks) can be copied over cleanly.
RUN rm -rf node_modules
COPY --from=builder /node_modules ./node_modules
COPY --from=builder /packages ./packages
COPY --from=builder /package*.json ./
COPY /.actor ./.actor
COPY /main.js ./
RUN echo "Installed NPM packages:" \
&& (npm list --only=prod --all || true) \
&& echo "Node.js version:" \
&& node --version \
&& echo "NPM version:" \
&& npm --version